├── .gitattributes ├── .github └── workflows │ ├── PR_Notification.yml │ ├── ci.yml │ ├── commit-message-check.yml │ ├── header_check.yml │ ├── jira_check.yml │ └── zendnnl_pr.yml ├── .gitignore ├── CMakeLists.txt ├── CMakeLists.txt.org ├── CODEOWNERS ├── Doxyfile ├── LICENSE ├── Makefile ├── README.md ├── SECURITY.md ├── THIRD-PARTY-PROGRAMS ├── _clang-format ├── cmake ├── ACL.cmake ├── Doxygen.cmake ├── Doxyrest.cmake ├── FindACL.cmake ├── FindBLAS.cmake ├── FindDoxyrest.cmake ├── FindLevelZero.cmake ├── FindOpenCL.cmake ├── FindPI_CUDA.cmake ├── FindSphinx.cmake ├── FindcuBLAS.cmake ├── FindcuDNN.cmake ├── OpenCL.cmake ├── OpenMP.cmake ├── SDL.cmake ├── SYCL.cmake ├── Sphinx.cmake ├── TBB.cmake ├── Threading.cmake ├── Threadpool.cmake ├── blas.cmake ├── build_types.cmake ├── config.cmake.in ├── configuring_primitive_list.cmake ├── coverage.cmake ├── doc.cmake ├── dpcpp_driver_check.cmake ├── gen_gpu_kernel.cmake ├── gen_gpu_kernel_list.cmake ├── host_compiler.cmake ├── lnx │ └── TBBConfig.cmake ├── mac │ └── TBBConfig.cmake ├── options.cmake ├── platform.cmake ├── run_with_env.bat.in ├── template.vcxproj.user ├── testing.cmake ├── utils.cmake ├── version.cmake ├── version.rc.in ├── win │ └── TBBConfig.cmake └── zendnn_compat.cmake ├── cmake2025 ├── FindAMDBLIS.cmake ├── FindFBGEMM.cmake ├── README.md ├── download_amdblis.cmake └── download_fbgemm.cmake ├── doc └── README_doxygen.txt ├── inc ├── zendnn.h ├── zendnn.hpp ├── zendnnLogLevel.hpp ├── zendnn_config.h ├── zendnn_config.h.in ├── zendnn_debug.h ├── zendnn_helper.hpp ├── zendnn_logging.hpp ├── zendnn_ocl.h ├── zendnn_ocl.hpp ├── zendnn_ocl_types.h ├── zendnn_perf.hpp ├── zendnn_sycl.h ├── zendnn_sycl.hpp ├── zendnn_sycl_types.h ├── zendnn_threadpool.h ├── zendnn_threadpool.hpp ├── zendnn_threadpool_iface.hpp ├── zendnn_tpp.hpp ├── zendnn_types.h ├── zendnn_version.h └── zendnn_version.h.in ├── scripts ├── gather_hw_os_kernel_bios_info.sh ├── runApiTest.sh ├── run_matmul_int8_generic_test.sh ├── zendnn_ONNXRT_env_setup.sh ├── zendnn_ONNXRT_env_setup_win.bat ├── zendnn_aocc_env_setup.sh ├── zendnn_build.sh ├── zendnn_env_setup_win.bat └── zendnn_gcc_env_setup.sh ├── src ├── CMakeLists.txt ├── common │ ├── CMakeLists.txt │ ├── attention.cpp │ ├── attention_pd.hpp │ ├── batch_normalization.cpp │ ├── batch_normalization_pd.hpp │ ├── bfloat16.cpp │ ├── bfloat16.hpp │ ├── binary.cpp │ ├── binary_pd.hpp │ ├── bit_cast.hpp │ ├── blis_wrapper.cpp │ ├── blis_wrapper.hpp │ ├── broadcast_strategy.cpp │ ├── broadcast_strategy.hpp │ ├── c_types_map.hpp │ ├── cache_blob.hpp │ ├── cache_blob_id.cpp │ ├── cache_blob_id.hpp │ ├── cblas_with_blis_api.hpp │ ├── compiler_workarounds.hpp │ ├── concat.cpp │ ├── concat_pd.hpp │ ├── convolution.cpp │ ├── convolution_pd.cpp │ ├── convolution_pd.hpp │ ├── counting_barrier.hpp │ ├── cpp_compat.hpp │ ├── deconvolution.cpp │ ├── deconvolution_pd.hpp │ ├── eltwise.cpp │ ├── eltwise_pd.hpp │ ├── embedding_bag.cpp │ ├── embedding_bag_pd.hpp │ ├── engine.cpp │ ├── engine.hpp │ ├── engine_id.hpp │ ├── experimental.cpp │ ├── experimental.hpp │ ├── float16.hpp │ ├── fpmath_mode.cpp │ ├── gemm.cpp │ ├── gemm_pd.hpp │ ├── gemm_types.hpp │ ├── gemm_utils.hpp │ ├── guard_manager.hpp │ ├── impl_list_item.hpp │ ├── impl_registration.hpp │ ├── inner_product.cpp │ ├── inner_product_pd.hpp │ ├── int4.hpp │ ├── internal_defs.hpp │ ├── internal_desc_types.hpp │ ├── ittnotify.cpp │ ├── ittnotify.hpp │ ├── ittnotify │ │ ├── LICENSE.BSD │ │ ├── README.md │ │ ├── _clang-format │ │ ├── disable_warnings.h │ │ ├── ittnotify.h │ │ ├── ittnotify_config.h │ │ ├── ittnotify_static.c │ │ ├── ittnotify_static.h │ │ ├── ittnotify_types.h │ │ ├── ittptmark64.S │ │ ├── ittptmark64.asm │ │ ├── jitprofiling.c │ │ ├── jitprofiling.h │ │ └── legacy │ │ │ └── ittnotify.h │ ├── layer_normalization.cpp │ ├── layer_normalization_pd.hpp │ ├── lrn.cpp │ ├── lrn_pd.hpp │ ├── math_utils.hpp │ ├── matmul.cpp │ ├── matmul_pd.hpp │ ├── memory.cpp │ ├── memory.hpp │ ├── memory_debug.cpp │ ├── memory_debug.hpp │ ├── memory_desc_wrapper.cpp │ ├── memory_desc_wrapper.hpp │ ├── memory_storage.cpp │ ├── memory_storage.hpp │ ├── memory_tracking.cpp │ ├── memory_tracking.hpp │ ├── memory_zero_pad.cpp │ ├── nstl.hpp │ ├── optional.hpp │ ├── pooling.cpp │ ├── pooling_pd.hpp │ ├── prelu.cpp │ ├── prelu_pd.hpp │ ├── primitive.cpp │ ├── primitive.hpp │ ├── primitive_attr.cpp │ ├── primitive_attr.hpp │ ├── primitive_cache.cpp │ ├── primitive_cache.hpp │ ├── primitive_desc.cpp │ ├── primitive_desc.hpp │ ├── primitive_exec_types.cpp │ ├── primitive_exec_types.hpp │ ├── primitive_hashing.cpp │ ├── primitive_hashing.hpp │ ├── primitive_iterator.cpp │ ├── primitive_iterator.hpp │ ├── query.cpp │ ├── reduction.cpp │ ├── reduction_pd.hpp │ ├── reorder.cpp │ ├── reorder.hpp │ ├── reorder_pd.hpp │ ├── resampling.cpp │ ├── resampling_pd.hpp │ ├── rnn.cpp │ ├── rnn.hpp │ ├── rnn_pd.hpp │ ├── rw_mutex.cpp │ ├── rw_mutex.hpp │ ├── scratchpad.cpp │ ├── scratchpad.hpp │ ├── scratchpad_debug.cpp │ ├── scratchpad_debug.hpp │ ├── serialization.cpp │ ├── serialization.hpp │ ├── serialization_stream.hpp │ ├── shuffle.cpp │ ├── shuffle_pd.hpp │ ├── softmax.cpp │ ├── softmax_pd.hpp │ ├── stack_checker.hpp │ ├── stream.cpp │ ├── stream.hpp │ ├── stream_threadpool.cpp │ ├── sum.cpp │ ├── sum_pd.hpp │ ├── tag_traits.hpp │ ├── thread_local_storage.hpp │ ├── type_helpers.hpp │ ├── utils.cpp │ ├── utils.hpp │ ├── verbose.cpp │ ├── verbose.hpp │ ├── z_magic.hpp │ ├── zendnn_avg_pool.cpp │ ├── zendnn_avg_pool_ref.cpp │ ├── zendnn_batch_norm.cpp │ ├── zendnn_batch_norm_ref.cpp │ ├── zendnn_blocked_layout.cpp │ ├── zendnn_convolution_direct.cpp │ ├── zendnn_convolution_gemm.cpp │ ├── zendnn_convolution_ref.cpp │ ├── zendnn_convolution_winograd.cpp │ ├── zendnn_convolution_winograd.hpp │ ├── zendnn_create_aocl_post_ops.cpp │ ├── zendnn_debug.cpp │ ├── zendnn_debug_autogenerated.cpp │ ├── zendnn_grp_ebag_matmul.cpp │ ├── zendnn_hw_os_kernel_bios_info.cpp │ ├── zendnn_hw_os_kernel_bios_info.hpp │ ├── zendnn_lru_cache.cpp │ ├── zendnn_lru_cache.hpp │ ├── zendnn_matmul_auto_tuner.cpp │ ├── zendnn_matmul_bf16.cpp │ ├── zendnn_matmul_gemm.cpp │ ├── zendnn_matmul_int8.cpp │ ├── zendnn_matmul_ref.cpp │ ├── zendnn_matmul_woq.cpp │ ├── zendnn_max_pool.cpp │ ├── zendnn_max_pool_ref.cpp │ ├── zendnn_postops.cpp │ ├── zendnn_private.hpp │ ├── zendnn_profiler.hpp │ ├── zendnn_reorder_cache.cpp │ ├── zendnn_reorder_cache.hpp │ ├── zendnn_reorder_custom_op.cpp │ ├── zendnn_thread.cpp │ ├── zendnn_thread.hpp │ ├── zendnn_traits.hpp │ ├── zendnn_utils.cpp │ └── zendnn_utils.hpp └── cpu │ ├── CMakeLists.txt │ ├── README.md │ ├── avx2_embedding_bag.cpp │ ├── avx2_embedding_bag.hpp │ ├── avx512_embedding_bag.cpp │ ├── avx512_embedding_bag.hpp │ ├── avx512_embedding_bag_utils.hpp │ ├── bfloat16.cpp │ ├── binary_injector_utils.cpp │ ├── binary_injector_utils.hpp │ ├── cpu_attention_list.cpp │ ├── cpu_attention_pd.hpp │ ├── cpu_batch_normalization_list.cpp │ ├── cpu_batch_normalization_pd.hpp │ ├── cpu_batch_normalization_utils.cpp │ ├── cpu_batch_normalization_utils.hpp │ ├── cpu_binary_list.cpp │ ├── cpu_binary_pd.hpp │ ├── cpu_concat.cpp │ ├── cpu_concat_pd.hpp │ ├── cpu_convolution_list.cpp │ ├── cpu_convolution_pd.hpp │ ├── cpu_deconvolution_list.cpp │ ├── cpu_deconvolution_pd.hpp │ ├── cpu_eltwise_list.cpp │ ├── cpu_eltwise_pd.hpp │ ├── cpu_embedding_bag_list.cpp │ ├── cpu_embedding_bag_pd.hpp │ ├── cpu_engine.cpp │ ├── cpu_engine.hpp │ ├── cpu_inner_product_list.cpp │ ├── cpu_inner_product_pd.hpp │ ├── cpu_layer_normalization_list.cpp │ ├── cpu_layer_normalization_pd.hpp │ ├── cpu_lrn_list.cpp │ ├── cpu_lrn_pd.hpp │ ├── cpu_memory_storage.hpp │ ├── cpu_pooling_list.cpp │ ├── cpu_pooling_pd.hpp │ ├── cpu_prelu_list.cpp │ ├── cpu_prelu_pd.hpp │ ├── cpu_primitive.hpp │ ├── cpu_reduction_list.cpp │ ├── cpu_reduction_pd.hpp │ ├── cpu_resampling_list.cpp │ ├── cpu_resampling_pd.hpp │ ├── cpu_rnn_list.cpp │ ├── cpu_shuffle_list.cpp │ ├── cpu_shuffle_pd.hpp │ ├── cpu_softmax_list.cpp │ ├── cpu_softmax_pd.hpp │ ├── cpu_stream.hpp │ ├── cpu_sum.cpp │ ├── cpu_sum_pd.hpp │ ├── dw_convolution_utils.hpp │ ├── gemm │ ├── f32 │ │ ├── gemm_utils_f32.cpp │ │ ├── gemm_utils_f32.hpp │ │ ├── ref_gemm_f32.cpp │ │ └── ref_gemm_f32.hpp │ ├── gemm.cpp │ ├── gemm.hpp │ ├── gemm_msan_unpoison.hpp │ ├── gemm_pack.cpp │ ├── gemm_pack.hpp │ ├── os_blas.hpp │ └── s8x8s32 │ │ ├── ref_gemm_s8x8s32.cpp │ │ ├── ref_gemm_s8x8s32.hpp │ │ ├── simple_gemm_s8s8s32.cpp │ │ └── simple_gemm_s8s8s32.hpp │ ├── gemm_convolution.cpp │ ├── gemm_convolution.hpp │ ├── gemm_convolution_utils.cpp │ ├── gemm_convolution_utils.hpp │ ├── gemm_inner_product.cpp │ ├── gemm_inner_product.hpp │ ├── gemm_inner_product_utils.cpp │ ├── gemm_inner_product_utils.hpp │ ├── gemm_x8s8s32x_conv_zp_src_pad_comp.cpp │ ├── gemm_x8s8s32x_conv_zp_src_pad_comp.hpp │ ├── gemm_x8s8s32x_convolution.cpp │ ├── gemm_x8s8s32x_convolution.hpp │ ├── gemm_x8s8s32x_convolution_utils.cpp │ ├── gemm_x8s8s32x_convolution_utils.hpp │ ├── gemm_x8s8s32x_inner_product.cpp │ ├── gemm_x8s8s32x_inner_product.hpp │ ├── matmul │ ├── cpu_matmul_list.cpp │ ├── cpu_matmul_pd.hpp │ ├── gemm_based_common.hpp │ ├── gemm_bf16_matmul.cpp │ ├── gemm_bf16_matmul.hpp │ ├── gemm_f32_matmul.cpp │ ├── gemm_f32_matmul.hpp │ ├── gemm_x8s8s32x_matmul.cpp │ ├── gemm_x8s8s32x_matmul.hpp │ ├── matmul_utils.hpp │ ├── ref_matmul.cpp │ ├── ref_matmul.hpp │ ├── ref_matmul_int8.cpp │ ├── ref_matmul_int8.hpp │ ├── zendnn_bf16_matmul.cpp │ ├── zendnn_bf16_matmul.hpp │ ├── zendnn_f32_matmul.cpp │ ├── zendnn_f32_matmul.hpp │ ├── zendnn_x8s8s32x_matmul.cpp │ └── zendnn_x8s8s32x_matmul.hpp │ ├── nchw_pooling.cpp │ ├── nchw_pooling.hpp │ ├── ncsp_batch_normalization.cpp │ ├── ncsp_batch_normalization.hpp │ ├── nhwc_pooling.cpp │ ├── nhwc_pooling.hpp │ ├── nspc_batch_normalization.cpp │ ├── nspc_batch_normalization.hpp │ ├── platform.cpp │ ├── platform.hpp │ ├── primitive_attr_postops.cpp │ ├── primitive_attr_postops.hpp │ ├── ref_attention.hpp │ ├── ref_batch_normalization.cpp │ ├── ref_batch_normalization.hpp │ ├── ref_binary.cpp │ ├── ref_binary.hpp │ ├── ref_concat.hpp │ ├── ref_convolution.cpp │ ├── ref_convolution.hpp │ ├── ref_convolution_int8.cpp │ ├── ref_convolution_int8.hpp │ ├── ref_convolution_utils.hpp │ ├── ref_deconvolution.cpp │ ├── ref_deconvolution.hpp │ ├── ref_eltwise.cpp │ ├── ref_eltwise.hpp │ ├── ref_embedding_bag.hpp │ ├── ref_fused_convolution.hpp │ ├── ref_inner_product.cpp │ ├── ref_inner_product.hpp │ ├── ref_inner_product_int8.cpp │ ├── ref_inner_product_int8.hpp │ ├── ref_inner_product_utils.hpp │ ├── ref_io_helper.hpp │ ├── ref_layer_normalization.cpp │ ├── ref_layer_normalization.hpp │ ├── ref_lrn.cpp │ ├── ref_lrn.hpp │ ├── ref_pooling.cpp │ ├── ref_pooling.hpp │ ├── ref_prelu.cpp │ ├── ref_prelu.hpp │ ├── ref_reduction.cpp │ ├── ref_reduction.hpp │ ├── ref_resampling.cpp │ ├── ref_resampling.hpp │ ├── ref_shuffle.cpp │ ├── ref_shuffle.hpp │ ├── ref_softmax.cpp │ ├── ref_softmax.hpp │ ├── ref_sum.hpp │ ├── reorder │ ├── cpu_reorder.cpp │ ├── cpu_reorder.hpp │ ├── cpu_reorder_comp_bf16_s8.cpp │ ├── cpu_reorder_comp_f32_s8.cpp │ ├── cpu_reorder_comp_s8_s8.cpp │ ├── cpu_reorder_pd.hpp │ ├── cpu_reorder_regular_bf16.cpp │ ├── cpu_reorder_regular_f16.cpp │ ├── cpu_reorder_regular_f32_bf16.cpp │ ├── cpu_reorder_regular_f32_f16.cpp │ ├── cpu_reorder_regular_f32_f32.cpp │ ├── cpu_reorder_regular_f32_s32.cpp │ ├── cpu_reorder_regular_f32_s8.cpp │ ├── cpu_reorder_regular_f32_u8.cpp │ ├── cpu_reorder_regular_s32.cpp │ ├── cpu_reorder_regular_s8.cpp │ ├── cpu_reorder_regular_u8.cpp │ └── simple_reorder.hpp │ ├── resampling_utils.hpp │ ├── rnn │ ├── brgemm_cell_common.cpp │ ├── cell_common.cpp │ ├── cell_gru.cpp │ ├── cell_gru_lbr.cpp │ ├── cpu_rnn_pd.hpp │ ├── postgemm_dispatcher.hpp │ ├── ref_postgemm_gru.cpp │ ├── ref_postgemm_gru_lbr.cpp │ ├── ref_postgemm_lstm.cpp │ ├── ref_postgemm_lstm_projection.cpp │ ├── ref_postgemm_rnn.cpp │ ├── ref_rnn.cpp │ ├── ref_rnn.hpp │ ├── rnn_reorders.hpp │ ├── rnn_utils.cpp │ └── rnn_utils.hpp │ ├── simple_concat.cpp │ ├── simple_concat.hpp │ ├── simple_layer_normalization.cpp │ ├── simple_layer_normalization.hpp │ ├── simple_layer_normalization_kernels.cpp │ ├── simple_layer_normalization_kernels.hpp │ ├── simple_q10n.hpp │ ├── simple_resampling.cpp │ ├── simple_resampling.hpp │ ├── simple_sum.cpp │ ├── simple_sum.hpp │ ├── x64 │ ├── CMakeLists.txt │ ├── amx_tile_configure.cpp │ ├── amx_tile_configure.hpp │ ├── brgemm │ │ ├── brgemm.cpp │ │ ├── brgemm.hpp │ │ ├── brgemm_types.hpp │ │ ├── jit_brdgmm_kernel.cpp │ │ ├── jit_brdgmm_kernel.hpp │ │ ├── jit_brgemm_amx_uker.cpp │ │ └── jit_brgemm_kernel.cpp │ ├── ck_conv_kernel_f32.cpp │ ├── ck_conv_kernel_f32.hpp │ ├── ck_convolution.cpp │ ├── ck_convolution.hpp │ ├── cpu_barrier.cpp │ ├── cpu_barrier.hpp │ ├── cpu_isa_traits.cpp │ ├── cpu_isa_traits.hpp │ ├── cpu_reducer.cpp │ ├── cpu_reducer.hpp │ ├── gemm │ │ ├── amx │ │ │ ├── jit_avx512_core_amx_copy_kern.cpp │ │ │ ├── jit_avx512_core_amx_copy_kern.hpp │ │ │ ├── jit_avx512_core_amx_gemm_kern.cpp │ │ │ └── jit_avx512_core_amx_gemm_kern.hpp │ │ ├── bf16 │ │ │ ├── common_s16.hpp │ │ │ ├── jit_avx512_core_gemm_bf16bf16f32_kern.cpp │ │ │ ├── jit_avx512_core_gemm_bf16bf16f32_kern.hpp │ │ │ ├── jit_avx512_core_gemv_bf16bf16f32_kern.cpp │ │ │ ├── jit_avx512_core_gemv_bf16bf16f32_kern.hpp │ │ │ ├── jit_avx512_core_s16_24x8_copy_an_kern_autogen.cpp │ │ │ ├── jit_avx512_core_s16_24x8_copy_at_kern_autogen.cpp │ │ │ ├── jit_avx512_core_s16_24x8_copy_bn_kern_autogen.cpp │ │ │ ├── jit_avx512_core_s16_24x8_copy_bt_kern_autogen.cpp │ │ │ ├── jit_avx512_core_s16_48x8_copy_an_kern_autogen.cpp │ │ │ ├── jit_avx512_core_s16_48x8_copy_at_kern_autogen.cpp │ │ │ ├── jit_avx512_core_s16_48x8_copy_bn_kern_autogen.cpp │ │ │ └── jit_avx512_core_s16_48x8_copy_bt_kern_autogen.cpp │ │ ├── f32 │ │ │ ├── common_f32.hpp │ │ │ ├── jit_avx2_f32_copy_an_kern_autogen.cpp │ │ │ ├── jit_avx2_f32_copy_at_kern_autogen.cpp │ │ │ ├── jit_avx2_f32_copy_bn_kern_autogen.cpp │ │ │ ├── jit_avx2_f32_copy_bt_kern_autogen.cpp │ │ │ ├── jit_avx2_kernel_sgemm_kern.cpp │ │ │ ├── jit_avx2_kernel_sgemm_kern.hpp │ │ │ ├── jit_avx512_common_gemm_f32.cpp │ │ │ ├── jit_avx512_common_gemm_f32.hpp │ │ │ ├── jit_avx512_core_f32_copy_an_kern_autogen.cpp │ │ │ ├── jit_avx512_core_f32_copy_at_kern_autogen.hpp │ │ │ ├── jit_avx512_core_f32_copy_at_kern_part1_autogen.cpp │ │ │ ├── jit_avx512_core_f32_copy_at_kern_part2_autogen.cpp │ │ │ ├── jit_avx512_core_f32_copy_bn_kern_autogen.cpp │ │ │ ├── jit_avx512_core_f32_copy_bt_kern_autogen.cpp │ │ │ ├── jit_avx512_core_gemm_smalln_tn_f32_kern.cpp │ │ │ ├── jit_avx512_core_gemm_smalln_tn_f32_kern.hpp │ │ │ ├── jit_avx_f32_copy_an_kern_autogen.cpp │ │ │ ├── jit_avx_f32_copy_at_kern_autogen.cpp │ │ │ ├── jit_avx_f32_copy_bn_kern_autogen.cpp │ │ │ ├── jit_avx_f32_copy_bt_kern_autogen.cpp │ │ │ ├── jit_avx_gemm_f32.cpp │ │ │ ├── jit_avx_gemm_f32.hpp │ │ │ ├── jit_avx_gemv_t_f32_kern.cpp │ │ │ ├── jit_avx_gemv_t_f32_kern.hpp │ │ │ ├── jit_avx_kernel_b0_sgemm_kern_autogen.hpp │ │ │ ├── jit_avx_kernel_b0_sgemm_kern_part1_autogen.cpp │ │ │ ├── jit_avx_kernel_b0_sgemm_kern_part2_autogen.cpp │ │ │ ├── jit_avx_kernel_sgemm_kern_autogen.hpp │ │ │ ├── jit_avx_kernel_sgemm_kern_part1_autogen.cpp │ │ │ ├── jit_avx_kernel_sgemm_kern_part2_autogen.cpp │ │ │ ├── jit_sse41_f32_copy_an_kern_autogen.cpp │ │ │ ├── jit_sse41_f32_copy_at_kern_autogen.cpp │ │ │ ├── jit_sse41_f32_copy_bn_kern_autogen.cpp │ │ │ ├── jit_sse41_f32_copy_bt_kern_autogen.cpp │ │ │ ├── jit_sse41_gemv_n_f32_kern.cpp │ │ │ ├── jit_sse41_gemv_n_f32_kern.hpp │ │ │ ├── jit_sse41_gemv_t_f32_kern.cpp │ │ │ ├── jit_sse41_gemv_t_f32_kern.hpp │ │ │ ├── jit_sse41_kernel_b0_sgemm_kern_autogen.cpp │ │ │ └── jit_sse41_kernel_sgemm_kern_autogen.cpp │ │ ├── gemm_driver.cpp │ │ ├── gemm_driver.hpp │ │ ├── gemm_info.cpp │ │ ├── gemm_info.hpp │ │ ├── gemm_pack.cpp │ │ ├── gemm_pack.hpp │ │ ├── gemm_pack_storage.hpp │ │ ├── gemm_partition.hpp │ │ ├── gemm_threading.hpp │ │ ├── gemm_utils.hpp │ │ ├── gemv_driver.cpp │ │ ├── gemv_driver.hpp │ │ └── s8x8s32 │ │ │ ├── common_u8.hpp │ │ │ ├── jit_avx2_gemm_s8u8s32_kern.cpp │ │ │ ├── jit_avx2_gemm_s8u8s32_kern.hpp │ │ │ ├── jit_avx2_u8_copy_an_kern_autogen.cpp │ │ │ ├── jit_avx2_u8_copy_at_kern_autogen.cpp │ │ │ ├── jit_avx2_u8_copy_bn_kern_autogen.cpp │ │ │ ├── jit_avx2_u8_copy_bt_kern_autogen.cpp │ │ │ ├── jit_avx2_u8_copy_sum_an_kern_autogen.cpp │ │ │ ├── jit_avx2_u8_copy_sum_at_kern_autogen.cpp │ │ │ ├── jit_avx2_u8_copy_sum_bn_kern_autogen.cpp │ │ │ ├── jit_avx2_u8_copy_sum_bt_kern_autogen.cpp │ │ │ ├── jit_avx2_vnni_u8_copy_an_kern_autogen.cpp │ │ │ ├── jit_avx2_vnni_u8_copy_at_kern_autogen.cpp │ │ │ ├── jit_avx2_vnni_u8_copy_bn_kern_autogen.cpp │ │ │ ├── jit_avx2_vnni_u8_copy_bt_kern_autogen.cpp │ │ │ ├── jit_avx2_vnni_u8_copy_sum_an_kern_autogen.cpp │ │ │ ├── jit_avx2_vnni_u8_copy_sum_at_kern_autogen.cpp │ │ │ ├── jit_avx2_vnni_u8_copy_sum_bn_kern_autogen.cpp │ │ │ ├── jit_avx2_vnni_u8_copy_sum_bt_kern_autogen.cpp │ │ │ ├── jit_avx512_core_gemm_s8u8s32_kern.cpp │ │ │ ├── jit_avx512_core_gemm_s8u8s32_kern.hpp │ │ │ ├── jit_avx512_core_gemv_s8x8s32.cpp │ │ │ ├── jit_avx512_core_gemv_s8x8s32.hpp │ │ │ ├── jit_avx512_core_kernel_gemv_s8x8s32_kern.cpp │ │ │ ├── jit_avx512_core_kernel_gemv_s8x8s32_kern.hpp │ │ │ ├── jit_avx512_core_u8_copy_an_kern_autogen.cpp │ │ │ ├── jit_avx512_core_u8_copy_at_kern_autogen.cpp │ │ │ ├── jit_avx512_core_u8_copy_bn_kern_autogen.cpp │ │ │ ├── jit_avx512_core_u8_copy_bt_kern_autogen.cpp │ │ │ ├── jit_avx512_core_u8_copy_sum_an_kern_autogen.cpp │ │ │ ├── jit_avx512_core_u8_copy_sum_at_kern_autogen.cpp │ │ │ ├── jit_avx512_core_u8_copy_sum_bn_kern_autogen.cpp │ │ │ ├── jit_avx512_core_u8_copy_sum_bt_kern_autogen.cpp │ │ │ ├── jit_avx_kernel_b0_b_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_avx_kernel_b0_c_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_avx_kernel_b0_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_avx_kernel_b0_r_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_avx_kernel_b_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_avx_kernel_c_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_avx_kernel_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_avx_kernel_r_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_avx_u8_copy_an_kern_autogen.cpp │ │ │ ├── jit_avx_u8_copy_at_kern_autogen.cpp │ │ │ ├── jit_avx_u8_copy_bn_kern_autogen.cpp │ │ │ ├── jit_avx_u8_copy_bt_kern_autogen.cpp │ │ │ ├── jit_avx_u8_copy_sum_an_kern_autogen.cpp │ │ │ ├── jit_avx_u8_copy_sum_at_kern_autogen.cpp │ │ │ ├── jit_avx_u8_copy_sum_bn_kern_autogen.cpp │ │ │ ├── jit_avx_u8_copy_sum_bt_kern_autogen.cpp │ │ │ ├── jit_sse41_kernel_b0_b_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_sse41_kernel_b0_c_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_sse41_kernel_b0_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_sse41_kernel_b0_r_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_sse41_kernel_b_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_sse41_kernel_c_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_sse41_kernel_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_sse41_kernel_r_gemm_s8u8s32_kern_autogen.cpp │ │ │ ├── jit_sse41_u8_copy_an_kern_autogen.cpp │ │ │ ├── jit_sse41_u8_copy_at_kern_autogen.cpp │ │ │ ├── jit_sse41_u8_copy_bn_kern_autogen.cpp │ │ │ ├── jit_sse41_u8_copy_bt_kern_autogen.cpp │ │ │ ├── jit_sse41_u8_copy_sum_an_kern_autogen.cpp │ │ │ ├── jit_sse41_u8_copy_sum_at_kern_autogen.cpp │ │ │ ├── jit_sse41_u8_copy_sum_bn_kern_autogen.cpp │ │ │ └── jit_sse41_u8_copy_sum_bt_kern_autogen.cpp │ ├── gemm_bf16_convolution.cpp │ ├── gemm_bf16_convolution.hpp │ ├── gemm_bf16_inner_product.cpp │ ├── gemm_bf16_inner_product.hpp │ ├── injectors │ │ ├── injector_utils.cpp │ │ ├── injector_utils.hpp │ │ ├── jit_uni_binary_injector.cpp │ │ ├── jit_uni_binary_injector.hpp │ │ ├── jit_uni_eltwise_injector.cpp │ │ ├── jit_uni_eltwise_injector.hpp │ │ ├── jit_uni_postops_injector.cpp │ │ └── jit_uni_postops_injector.hpp │ ├── ip_convolution.cpp │ ├── ip_convolution.hpp │ ├── jit_avx2_1x1_conv_kernel_f32.cpp │ ├── jit_avx2_1x1_conv_kernel_f32.hpp │ ├── jit_avx2_1x1_convolution.cpp │ ├── jit_avx2_1x1_convolution.hpp │ ├── jit_avx2_conv_kernel_f32.cpp │ ├── jit_avx2_conv_kernel_f32.hpp │ ├── jit_avx2_convolution.cpp │ ├── jit_avx2_convolution.hpp │ ├── jit_avx512_common_1x1_conv_kernel.cpp │ ├── jit_avx512_common_1x1_conv_kernel.hpp │ ├── jit_avx512_common_1x1_convolution.cpp │ ├── jit_avx512_common_1x1_convolution.hpp │ ├── jit_avx512_common_conv_kernel.cpp │ ├── jit_avx512_common_conv_kernel.hpp │ ├── jit_avx512_common_convolution.cpp │ ├── jit_avx512_common_convolution.hpp │ ├── jit_avx512_common_resampling.cpp │ ├── jit_avx512_common_resampling.hpp │ ├── jit_avx512_core_amx_1x1_conv_kernel.cpp │ ├── jit_avx512_core_amx_1x1_conv_kernel.hpp │ ├── jit_avx512_core_amx_1x1_convolution.cpp │ ├── jit_avx512_core_amx_1x1_convolution.hpp │ ├── jit_avx512_core_amx_conv_kernel.cpp │ ├── jit_avx512_core_amx_conv_kernel.hpp │ ├── jit_avx512_core_amx_conv_utils.hpp │ ├── jit_avx512_core_amx_convolution.cpp │ ├── jit_avx512_core_amx_convolution.hpp │ ├── jit_avx512_core_amx_deconvolution.cpp │ ├── jit_avx512_core_amx_deconvolution.hpp │ ├── jit_avx512_core_bf16_1x1_conv_kernel.cpp │ ├── jit_avx512_core_bf16_1x1_conv_kernel.hpp │ ├── jit_avx512_core_bf16_1x1_convolution.cpp │ ├── jit_avx512_core_bf16_1x1_convolution.hpp │ ├── jit_avx512_core_bf16_conv_kernel.cpp │ ├── jit_avx512_core_bf16_conv_kernel.hpp │ ├── jit_avx512_core_bf16_convolution.cpp │ ├── jit_avx512_core_bf16_convolution.hpp │ ├── jit_avx512_core_bf16_dw_conv_kernel.cpp │ ├── jit_avx512_core_bf16_dw_conv_kernel.hpp │ ├── jit_avx512_core_bf16_sum.cpp │ ├── jit_avx512_core_bf16_sum.hpp │ ├── jit_avx512_core_bf16cvt.cpp │ ├── jit_avx512_core_bf16cvt.hpp │ ├── jit_avx512_core_f32_wino_conv_2x3.cpp │ ├── jit_avx512_core_f32_wino_conv_2x3.hpp │ ├── jit_avx512_core_f32_wino_conv_4x3.cpp │ ├── jit_avx512_core_f32_wino_conv_4x3.hpp │ ├── jit_avx512_core_f32_wino_conv_4x3_kernel.cpp │ ├── jit_avx512_core_f32_wino_conv_4x3_kernel.hpp │ ├── jit_avx512_core_u8s8s32x_wino_convolution.cpp │ ├── jit_avx512_core_u8s8s32x_wino_convolution.hpp │ ├── jit_avx512_core_x8s8s32x_1x1_conv_kernel.cpp │ ├── jit_avx512_core_x8s8s32x_1x1_conv_kernel.hpp │ ├── jit_avx512_core_x8s8s32x_1x1_convolution.cpp │ ├── jit_avx512_core_x8s8s32x_1x1_convolution.hpp │ ├── jit_avx512_core_x8s8s32x_1x1_deconvolution.hpp │ ├── jit_avx512_core_x8s8s32x_conv_kernel.cpp │ ├── jit_avx512_core_x8s8s32x_conv_kernel.hpp │ ├── jit_avx512_core_x8s8s32x_convolution.cpp │ ├── jit_avx512_core_x8s8s32x_convolution.hpp │ ├── jit_avx512_core_x8s8s32x_deconvolution.cpp │ ├── jit_avx512_core_x8s8s32x_deconvolution.hpp │ ├── jit_brdgmm_dw_conv.cpp │ ├── jit_brdgmm_dw_conv.hpp │ ├── jit_brgemm_1x1_conv.cpp │ ├── jit_brgemm_1x1_conv.hpp │ ├── jit_brgemm_conv.cpp │ ├── jit_brgemm_conv.hpp │ ├── jit_brgemm_conv_comp_pad_kernel.cpp │ ├── jit_brgemm_conv_comp_pad_kernel.hpp │ ├── jit_brgemm_conv_trans_kernel.cpp │ ├── jit_brgemm_conv_trans_kernel.hpp │ ├── jit_brgemm_conv_utils.cpp │ ├── jit_brgemm_conv_utils.hpp │ ├── jit_brgemm_inner_product.cpp │ ├── jit_brgemm_inner_product.hpp │ ├── jit_brgemm_inner_product_utils.cpp │ ├── jit_brgemm_inner_product_utils.hpp │ ├── jit_brgemm_post_ops.hpp │ ├── jit_brgemm_primitive_conf.hpp │ ├── jit_brgemm_transpose_utils.cpp │ ├── jit_brgemm_transpose_utils.hpp │ ├── jit_gemm_inner_product_utils.cpp │ ├── jit_gemm_inner_product_utils.hpp │ ├── jit_gemm_x8s8s32x_conv_zp_src_pad_comp.cpp │ ├── jit_gemm_x8s8s32x_conv_zp_src_pad_comp.hpp │ ├── jit_gemm_x8s8s32x_convolution_utils.cpp │ ├── jit_gemm_x8s8s32x_convolution_utils.hpp │ ├── jit_generator.hpp │ ├── jit_primitive_conf.hpp │ ├── jit_sse41_1x1_conv_kernel_f32.cpp │ ├── jit_sse41_1x1_conv_kernel_f32.hpp │ ├── jit_sse41_1x1_convolution.cpp │ ├── jit_sse41_1x1_convolution.hpp │ ├── jit_sse41_conv_kernel_f32.cpp │ ├── jit_sse41_conv_kernel_f32.hpp │ ├── jit_sse41_convolution.cpp │ ├── jit_sse41_convolution.hpp │ ├── jit_transpose_utils.cpp │ ├── jit_transpose_utils.hpp │ ├── jit_uni_1x1_conv_utils.hpp │ ├── jit_uni_batch_normalization.cpp │ ├── jit_uni_batch_normalization.hpp │ ├── jit_uni_batch_normalization_s8.cpp │ ├── jit_uni_batch_normalization_s8.hpp │ ├── jit_uni_binary.cpp │ ├── jit_uni_binary.hpp │ ├── jit_uni_binary_kernel.cpp │ ├── jit_uni_binary_kernel.hpp │ ├── jit_uni_deconv_zp_pad_str_kernel.cpp │ ├── jit_uni_deconv_zp_pad_str_kernel.hpp │ ├── jit_uni_dw_conv_kernel_f32.cpp │ ├── jit_uni_dw_conv_kernel_f32.hpp │ ├── jit_uni_dw_conv_kernel_utils.cpp │ ├── jit_uni_dw_conv_kernel_utils.hpp │ ├── jit_uni_dw_convolution.cpp │ ├── jit_uni_dw_convolution.hpp │ ├── jit_uni_eltwise.cpp │ ├── jit_uni_eltwise.hpp │ ├── jit_uni_eltwise_int.cpp │ ├── jit_uni_eltwise_int.hpp │ ├── jit_uni_i8i8_pooling.cpp │ ├── jit_uni_i8i8_pooling.hpp │ ├── jit_uni_layer_normalization_kernels.cpp │ ├── jit_uni_layer_normalization_kernels.hpp │ ├── jit_uni_pool_kernel.cpp │ ├── jit_uni_pool_kernel.hpp │ ├── jit_uni_pooling.cpp │ ├── jit_uni_pooling.hpp │ ├── jit_uni_reduction.cpp │ ├── jit_uni_reduction.hpp │ ├── jit_uni_reduction_kernel.cpp │ ├── jit_uni_reduction_kernel.hpp │ ├── jit_uni_reorder.cpp │ ├── jit_uni_reorder.hpp │ ├── jit_uni_reorder_utils.cpp │ ├── jit_uni_resampling.cpp │ ├── jit_uni_resampling.hpp │ ├── jit_uni_resampling_kernel.cpp │ ├── jit_uni_resampling_kernel.hpp │ ├── jit_uni_softmax.cpp │ ├── jit_uni_softmax.hpp │ ├── jit_uni_tbb_batch_normalization.cpp │ ├── jit_uni_tbb_batch_normalization.hpp │ ├── jit_uni_x8s8s32x_1x1_conv_kernel.cpp │ ├── jit_uni_x8s8s32x_1x1_conv_kernel.hpp │ ├── jit_uni_x8s8s32x_1x1_convolution.cpp │ ├── jit_uni_x8s8s32x_1x1_convolution.hpp │ ├── jit_uni_x8s8s32x_1x1_deconvolution.hpp │ ├── jit_uni_x8s8s32x_conv_kernel.cpp │ ├── jit_uni_x8s8s32x_conv_kernel.hpp │ ├── jit_uni_x8s8s32x_convolution.cpp │ ├── jit_uni_x8s8s32x_convolution.hpp │ ├── jit_uni_x8s8s32x_deconvolution.cpp │ ├── jit_uni_x8s8s32x_deconvolution.hpp │ ├── lrn │ │ ├── jit_avx512_common_lrn.cpp │ │ ├── jit_avx512_common_lrn.hpp │ │ ├── jit_avx512_common_lrn_bwd_base.cpp │ │ ├── jit_avx512_common_lrn_bwd_base.hpp │ │ ├── jit_avx512_common_lrn_bwd_blocked.cpp │ │ ├── jit_avx512_common_lrn_bwd_blocked.hpp │ │ ├── jit_avx512_common_lrn_bwd_nhwc.cpp │ │ ├── jit_avx512_common_lrn_bwd_nhwc.hpp │ │ ├── jit_avx512_common_lrn_fwd_base.cpp │ │ ├── jit_avx512_common_lrn_fwd_base.hpp │ │ ├── jit_avx512_common_lrn_fwd_blocked.cpp │ │ ├── jit_avx512_common_lrn_fwd_blocked.hpp │ │ ├── jit_avx512_common_lrn_fwd_nhwc.cpp │ │ ├── jit_avx512_common_lrn_fwd_nhwc.hpp │ │ ├── jit_avx512_common_lrn_utils.hpp │ │ ├── jit_uni_lrn.cpp │ │ ├── jit_uni_lrn.hpp │ │ ├── jit_uni_lrn_kernel.cpp │ │ ├── jit_uni_lrn_kernel.hpp │ │ ├── lrn_avx512_blocked_executor.hpp │ │ ├── lrn_avx512_nhwc_executor.hpp │ │ ├── lrn_executor.hpp │ │ └── lrn_executor_factory.hpp │ ├── matmul │ │ ├── brgemm_matmul.cpp │ │ ├── brgemm_matmul.hpp │ │ ├── brgemm_matmul_copy_utils.cpp │ │ ├── brgemm_matmul_copy_utils.hpp │ │ ├── brgemm_matmul_utils.cpp │ │ └── brgemm_matmul_utils.hpp │ ├── prelu │ │ ├── jit_prelu_backward.cpp │ │ ├── jit_prelu_backward.hpp │ │ ├── jit_prelu_base_kernel.cpp │ │ ├── jit_prelu_base_kernel.hpp │ │ ├── jit_prelu_forward.cpp │ │ ├── jit_prelu_forward.hpp │ │ ├── jit_prelu_reduction_kernel.cpp │ │ ├── jit_prelu_reduction_kernel.hpp │ │ ├── jit_prelu_utils.cpp │ │ ├── jit_prelu_utils.hpp │ │ ├── jit_uni_prelu_backward_kernel.cpp │ │ ├── jit_uni_prelu_backward_kernel.hpp │ │ ├── jit_uni_prelu_forward_kernel.cpp │ │ └── jit_uni_prelu_forward_kernel.hpp │ ├── rnn │ │ ├── brgemm_cell_common_bwd.cpp │ │ ├── brgemm_cell_common_bwd.hpp │ │ ├── brgemm_cell_common_fwd.cpp │ │ ├── brgemm_cell_common_fwd.hpp │ │ ├── brgemm_cell_common_reorders.cpp │ │ ├── brgemm_cell_common_reorders.hpp │ │ ├── brgemm_cell_common_utils.cpp │ │ ├── brgemm_cell_common_utils.hpp │ │ ├── jit_brgemm_transpose_single_row.cpp │ │ ├── jit_brgemm_transpose_single_row.hpp │ │ ├── jit_diff_weights_peephole.cpp │ │ ├── jit_diff_weights_peephole.hpp │ │ ├── jit_gates_reduction.cpp │ │ ├── jit_gates_reduction.hpp │ │ ├── jit_uni_gru_cell_postgemm_1_bwd.hpp │ │ ├── jit_uni_gru_cell_postgemm_1_fwd.hpp │ │ ├── jit_uni_gru_cell_postgemm_2_bwd.hpp │ │ ├── jit_uni_gru_cell_postgemm_2_fwd.hpp │ │ ├── jit_uni_gru_lbr_cell_postgemm_bwd.hpp │ │ ├── jit_uni_gru_lbr_cell_postgemm_fwd.hpp │ │ ├── jit_uni_lstm_cell_postgemm.hpp │ │ ├── jit_uni_lstm_cell_postgemm_bwd.hpp │ │ ├── jit_uni_lstm_cell_postgemm_fwd.hpp │ │ ├── jit_uni_lstm_cell_projection_postgemm_fwd.hpp │ │ ├── jit_uni_rnn_cell_postgemm_bwd.hpp │ │ ├── jit_uni_rnn_cell_postgemm_fwd.hpp │ │ ├── jit_uni_rnn_common_postgemm.hpp │ │ ├── rnn_brgemm_utils.cpp │ │ └── rnn_brgemm_utils.hpp │ ├── shuffle │ │ ├── jit_uni_shuffle.cpp │ │ ├── jit_uni_shuffle.hpp │ │ ├── jit_uni_shuffle_kernel.cpp │ │ └── jit_uni_shuffle_kernel.hpp │ ├── utils │ │ ├── jit_io_helper.cpp │ │ └── jit_io_helper.hpp │ ├── wino_reorder.hpp │ ├── xbyak │ │ ├── COPYRIGHT │ │ ├── _clang-format │ │ ├── xbyak.h │ │ ├── xbyak_bin2hex.h │ │ ├── xbyak_mnemonic.h │ │ └── xbyak_util.h │ ├── zendnn_conv_kernel_f32.cpp │ ├── zendnn_conv_kernel_f32.hpp │ ├── zendnn_convolution.cpp │ ├── zendnn_convolution.hpp │ ├── zendnn_inner_product.cpp │ ├── zendnn_inner_product.hpp │ ├── zendnn_lpgemm_auto_tuner.cpp │ ├── zendnn_lpgemm_convolution.cpp │ ├── zendnn_lpgemm_convolution.hpp │ ├── zendnn_lpgemm_utils.hpp │ ├── zendnn_pool_kernel.cpp │ ├── zendnn_pool_kernel.hpp │ ├── zendnn_pooling.cpp │ └── zendnn_pooling.hpp │ ├── zen_avx2_utils.hpp │ ├── zen_avx512_utils.hpp │ ├── zendnn_embedding_ops.cpp │ ├── zendnn_matmul_direct.cpp │ ├── zendnn_matmul_direct.hpp │ ├── zendnn_matmul_direct_register_tile_fp32.cpp │ ├── zendnn_matmul_direct_register_tile_fp32_batch.cpp │ ├── zendnn_matmul_direct_register_tile_ref.cpp │ ├── zendnn_matmul_direct_utils.cpp │ ├── zendnn_matmul_direct_utils.hpp │ ├── zendnn_quantize_dequantize.cpp │ ├── zendnn_quantize_dequantize.hpp │ ├── zendnn_sdpa_attention.cpp │ ├── zero_point_utils.cpp │ └── zero_point_utils.hpp └── tests ├── .gitignore ├── CMakeLists.txt ├── CMakeLists.txt.org └── api_tests ├── CMakeLists.txt ├── cmd_parser.hpp ├── other_utils.hpp ├── quant_utils.hpp ├── ref_avx_conv_param.cpp ├── sha_out_NCHW ├── ref_avx_conv_maxpool_output.sha1 ├── ref_avx_conv_output.sha1 ├── ref_avx_conv_param_output.sha1 └── ref_conv_output.sha1 ├── sha_out_NHWC ├── ref_avx_conv_maxpool_output.sha1 ├── ref_avx_conv_output.sha1 ├── ref_avx_conv_param_output.sha1 ├── ref_conv_output.sha1 ├── zendnn_avx_conv_maxpool_output.sha1 ├── zendnn_avx_conv_output.sha1 ├── zendnn_avx_conv_param_output.sha1 └── zendnn_conv_output.sha1 ├── test_utils.hpp ├── zendnn_avx_conv.cpp ├── zendnn_avx_conv_maxpool.cpp ├── zendnn_avx_conv_param.cpp ├── zendnn_avx_conv_param_direct.cpp ├── zendnn_avx_conv_param_direct_u8s8s32os8.cpp ├── zendnn_avx_conv_param_fusion.cpp ├── zendnn_avx_conv_primitive_cache_test.cpp ├── zendnn_avx_maxpool_blocked.cpp ├── zendnn_block_size.cpp ├── zendnn_conv_test.cpp ├── zendnn_embedding_bag_benchmark.cpp ├── zendnn_embedding_bag_test.cpp ├── zendnn_grp_embedding_bag_test.cpp ├── zendnn_grp_embedding_bag_test_int4.cpp ├── zendnn_grp_embedding_mlp_test.cpp ├── zendnn_grp_matmul_test.cpp ├── zendnn_inference_f32.cpp ├── zendnn_lpgemm_layerwise.cpp ├── zendnn_lpgemm_layerwise_bf16.cpp ├── zendnn_lpgemm_layerwise_s32.cpp ├── zendnn_lpgemm_layerwise_s8s8s16os.cpp ├── zendnn_lpgemm_layerwise_s8s8s32_accuracy.cpp ├── zendnn_lpgemm_layerwise_s8s8s32os.cpp ├── zendnn_lpgemm_layerwise_u8s8s16ou8.cpp ├── zendnn_lpgemm_layerwise_u8s8s16ou8_accuracy.cpp ├── zendnn_lpgemm_layerwise_u8s8s32_accuracy.cpp ├── zendnn_lpgemm_network.cpp ├── zendnn_lpgemm_network_bf16.cpp ├── zendnn_lpgemm_network_s32.cpp ├── zendnn_lpgemm_network_s8s8s16os.cpp ├── zendnn_lpgemm_network_s8s8s32os.cpp ├── zendnn_matmulFusions_test.cpp ├── zendnn_matmul_bf16_test.cpp ├── zendnn_matmul_direct_test.cpp ├── zendnn_matmul_gelu_test.cpp ├── zendnn_matmul_generic_int8_test.cpp ├── zendnn_matmul_inplace_custom_op_test.cpp ├── zendnn_matmul_int4_test.cpp ├── zendnn_matmul_int8_test.cpp ├── zendnn_matmul_test.cpp ├── zendnn_matmul_weight_cache_test.cpp ├── zendnn_multihead_attention_bf16.cpp ├── zendnn_multihead_attention_f32.cpp ├── zendnn_quantize_dequantize_test.cpp ├── zendnn_sdpa_test.cpp └── zendnn_training_f32.cpp /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/.gitattributes -------------------------------------------------------------------------------- /.github/workflows/PR_Notification.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/.github/workflows/PR_Notification.yml -------------------------------------------------------------------------------- /.github/workflows/ci.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/.github/workflows/ci.yml -------------------------------------------------------------------------------- /.github/workflows/commit-message-check.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/.github/workflows/commit-message-check.yml -------------------------------------------------------------------------------- /.github/workflows/header_check.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/.github/workflows/header_check.yml -------------------------------------------------------------------------------- /.github/workflows/jira_check.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/.github/workflows/jira_check.yml -------------------------------------------------------------------------------- /.github/workflows/zendnnl_pr.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/.github/workflows/zendnnl_pr.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/.gitignore -------------------------------------------------------------------------------- /CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/CMakeLists.txt -------------------------------------------------------------------------------- /CMakeLists.txt.org: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/CMakeLists.txt.org -------------------------------------------------------------------------------- /CODEOWNERS: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/CODEOWNERS -------------------------------------------------------------------------------- /Doxyfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/Doxyfile -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/LICENSE -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/README.md -------------------------------------------------------------------------------- /SECURITY.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/SECURITY.md -------------------------------------------------------------------------------- /THIRD-PARTY-PROGRAMS: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/THIRD-PARTY-PROGRAMS -------------------------------------------------------------------------------- /_clang-format: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/_clang-format -------------------------------------------------------------------------------- /cmake/ACL.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/ACL.cmake -------------------------------------------------------------------------------- /cmake/Doxygen.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/Doxygen.cmake -------------------------------------------------------------------------------- /cmake/Doxyrest.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/Doxyrest.cmake -------------------------------------------------------------------------------- /cmake/FindACL.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/FindACL.cmake -------------------------------------------------------------------------------- /cmake/FindBLAS.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/FindBLAS.cmake -------------------------------------------------------------------------------- /cmake/FindDoxyrest.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/FindDoxyrest.cmake -------------------------------------------------------------------------------- /cmake/FindLevelZero.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/FindLevelZero.cmake -------------------------------------------------------------------------------- /cmake/FindOpenCL.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/FindOpenCL.cmake -------------------------------------------------------------------------------- /cmake/FindPI_CUDA.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/FindPI_CUDA.cmake -------------------------------------------------------------------------------- /cmake/FindSphinx.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/FindSphinx.cmake -------------------------------------------------------------------------------- /cmake/FindcuBLAS.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/FindcuBLAS.cmake -------------------------------------------------------------------------------- /cmake/FindcuDNN.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/FindcuDNN.cmake -------------------------------------------------------------------------------- /cmake/OpenCL.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/OpenCL.cmake -------------------------------------------------------------------------------- /cmake/OpenMP.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/OpenMP.cmake -------------------------------------------------------------------------------- /cmake/SDL.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/SDL.cmake -------------------------------------------------------------------------------- /cmake/SYCL.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/SYCL.cmake -------------------------------------------------------------------------------- /cmake/Sphinx.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/Sphinx.cmake -------------------------------------------------------------------------------- /cmake/TBB.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/TBB.cmake -------------------------------------------------------------------------------- /cmake/Threading.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/Threading.cmake -------------------------------------------------------------------------------- /cmake/Threadpool.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/Threadpool.cmake -------------------------------------------------------------------------------- /cmake/blas.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/blas.cmake -------------------------------------------------------------------------------- /cmake/build_types.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/build_types.cmake -------------------------------------------------------------------------------- /cmake/config.cmake.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/config.cmake.in -------------------------------------------------------------------------------- /cmake/configuring_primitive_list.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/configuring_primitive_list.cmake -------------------------------------------------------------------------------- /cmake/coverage.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/coverage.cmake -------------------------------------------------------------------------------- /cmake/doc.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/doc.cmake -------------------------------------------------------------------------------- /cmake/dpcpp_driver_check.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/dpcpp_driver_check.cmake -------------------------------------------------------------------------------- /cmake/gen_gpu_kernel.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/gen_gpu_kernel.cmake -------------------------------------------------------------------------------- /cmake/gen_gpu_kernel_list.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/gen_gpu_kernel_list.cmake -------------------------------------------------------------------------------- /cmake/host_compiler.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/host_compiler.cmake -------------------------------------------------------------------------------- /cmake/lnx/TBBConfig.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/lnx/TBBConfig.cmake -------------------------------------------------------------------------------- /cmake/mac/TBBConfig.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/mac/TBBConfig.cmake -------------------------------------------------------------------------------- /cmake/options.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/options.cmake -------------------------------------------------------------------------------- /cmake/platform.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/platform.cmake -------------------------------------------------------------------------------- /cmake/run_with_env.bat.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/run_with_env.bat.in -------------------------------------------------------------------------------- /cmake/template.vcxproj.user: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/template.vcxproj.user -------------------------------------------------------------------------------- /cmake/testing.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/testing.cmake -------------------------------------------------------------------------------- /cmake/utils.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/utils.cmake -------------------------------------------------------------------------------- /cmake/version.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/version.cmake -------------------------------------------------------------------------------- /cmake/version.rc.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/version.rc.in -------------------------------------------------------------------------------- /cmake/win/TBBConfig.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/win/TBBConfig.cmake -------------------------------------------------------------------------------- /cmake/zendnn_compat.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake/zendnn_compat.cmake -------------------------------------------------------------------------------- /cmake2025/FindAMDBLIS.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake2025/FindAMDBLIS.cmake -------------------------------------------------------------------------------- /cmake2025/FindFBGEMM.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake2025/FindFBGEMM.cmake -------------------------------------------------------------------------------- /cmake2025/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake2025/README.md -------------------------------------------------------------------------------- /cmake2025/download_amdblis.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake2025/download_amdblis.cmake -------------------------------------------------------------------------------- /cmake2025/download_fbgemm.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/cmake2025/download_fbgemm.cmake -------------------------------------------------------------------------------- /doc/README_doxygen.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/doc/README_doxygen.txt -------------------------------------------------------------------------------- /inc/zendnn.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn.h -------------------------------------------------------------------------------- /inc/zendnn.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn.hpp -------------------------------------------------------------------------------- /inc/zendnnLogLevel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnnLogLevel.hpp -------------------------------------------------------------------------------- /inc/zendnn_config.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_config.h -------------------------------------------------------------------------------- /inc/zendnn_config.h.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_config.h.in -------------------------------------------------------------------------------- /inc/zendnn_debug.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_debug.h -------------------------------------------------------------------------------- /inc/zendnn_helper.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_helper.hpp -------------------------------------------------------------------------------- /inc/zendnn_logging.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_logging.hpp -------------------------------------------------------------------------------- /inc/zendnn_ocl.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_ocl.h -------------------------------------------------------------------------------- /inc/zendnn_ocl.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_ocl.hpp -------------------------------------------------------------------------------- /inc/zendnn_ocl_types.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_ocl_types.h -------------------------------------------------------------------------------- /inc/zendnn_perf.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_perf.hpp -------------------------------------------------------------------------------- /inc/zendnn_sycl.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_sycl.h -------------------------------------------------------------------------------- /inc/zendnn_sycl.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_sycl.hpp -------------------------------------------------------------------------------- /inc/zendnn_sycl_types.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_sycl_types.h -------------------------------------------------------------------------------- /inc/zendnn_threadpool.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_threadpool.h -------------------------------------------------------------------------------- /inc/zendnn_threadpool.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_threadpool.hpp -------------------------------------------------------------------------------- /inc/zendnn_threadpool_iface.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_threadpool_iface.hpp -------------------------------------------------------------------------------- /inc/zendnn_tpp.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_tpp.hpp -------------------------------------------------------------------------------- /inc/zendnn_types.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_types.h -------------------------------------------------------------------------------- /inc/zendnn_version.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_version.h -------------------------------------------------------------------------------- /inc/zendnn_version.h.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/inc/zendnn_version.h.in -------------------------------------------------------------------------------- /scripts/gather_hw_os_kernel_bios_info.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/scripts/gather_hw_os_kernel_bios_info.sh -------------------------------------------------------------------------------- /scripts/runApiTest.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/scripts/runApiTest.sh -------------------------------------------------------------------------------- /scripts/run_matmul_int8_generic_test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/scripts/run_matmul_int8_generic_test.sh -------------------------------------------------------------------------------- /scripts/zendnn_ONNXRT_env_setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/scripts/zendnn_ONNXRT_env_setup.sh -------------------------------------------------------------------------------- /scripts/zendnn_ONNXRT_env_setup_win.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/scripts/zendnn_ONNXRT_env_setup_win.bat -------------------------------------------------------------------------------- /scripts/zendnn_aocc_env_setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/scripts/zendnn_aocc_env_setup.sh -------------------------------------------------------------------------------- /scripts/zendnn_build.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/scripts/zendnn_build.sh -------------------------------------------------------------------------------- /scripts/zendnn_env_setup_win.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/scripts/zendnn_env_setup_win.bat -------------------------------------------------------------------------------- /scripts/zendnn_gcc_env_setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/scripts/zendnn_gcc_env_setup.sh -------------------------------------------------------------------------------- /src/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/CMakeLists.txt -------------------------------------------------------------------------------- /src/common/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/CMakeLists.txt -------------------------------------------------------------------------------- /src/common/attention.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/attention.cpp -------------------------------------------------------------------------------- /src/common/attention_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/attention_pd.hpp -------------------------------------------------------------------------------- /src/common/batch_normalization.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/batch_normalization.cpp -------------------------------------------------------------------------------- /src/common/batch_normalization_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/batch_normalization_pd.hpp -------------------------------------------------------------------------------- /src/common/bfloat16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/bfloat16.cpp -------------------------------------------------------------------------------- /src/common/bfloat16.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/bfloat16.hpp -------------------------------------------------------------------------------- /src/common/binary.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/binary.cpp -------------------------------------------------------------------------------- /src/common/binary_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/binary_pd.hpp -------------------------------------------------------------------------------- /src/common/bit_cast.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/bit_cast.hpp -------------------------------------------------------------------------------- /src/common/blis_wrapper.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/blis_wrapper.cpp -------------------------------------------------------------------------------- /src/common/blis_wrapper.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/blis_wrapper.hpp -------------------------------------------------------------------------------- /src/common/broadcast_strategy.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/broadcast_strategy.cpp -------------------------------------------------------------------------------- /src/common/broadcast_strategy.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/broadcast_strategy.hpp -------------------------------------------------------------------------------- /src/common/c_types_map.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/c_types_map.hpp -------------------------------------------------------------------------------- /src/common/cache_blob.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/cache_blob.hpp -------------------------------------------------------------------------------- /src/common/cache_blob_id.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/cache_blob_id.cpp -------------------------------------------------------------------------------- /src/common/cache_blob_id.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/cache_blob_id.hpp -------------------------------------------------------------------------------- /src/common/cblas_with_blis_api.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/cblas_with_blis_api.hpp -------------------------------------------------------------------------------- /src/common/compiler_workarounds.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/compiler_workarounds.hpp -------------------------------------------------------------------------------- /src/common/concat.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/concat.cpp -------------------------------------------------------------------------------- /src/common/concat_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/concat_pd.hpp -------------------------------------------------------------------------------- /src/common/convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/convolution.cpp -------------------------------------------------------------------------------- /src/common/convolution_pd.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/convolution_pd.cpp -------------------------------------------------------------------------------- /src/common/convolution_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/convolution_pd.hpp -------------------------------------------------------------------------------- /src/common/counting_barrier.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/counting_barrier.hpp -------------------------------------------------------------------------------- /src/common/cpp_compat.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/cpp_compat.hpp -------------------------------------------------------------------------------- /src/common/deconvolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/deconvolution.cpp -------------------------------------------------------------------------------- /src/common/deconvolution_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/deconvolution_pd.hpp -------------------------------------------------------------------------------- /src/common/eltwise.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/eltwise.cpp -------------------------------------------------------------------------------- /src/common/eltwise_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/eltwise_pd.hpp -------------------------------------------------------------------------------- /src/common/embedding_bag.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/embedding_bag.cpp -------------------------------------------------------------------------------- /src/common/embedding_bag_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/embedding_bag_pd.hpp -------------------------------------------------------------------------------- /src/common/engine.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/engine.cpp -------------------------------------------------------------------------------- /src/common/engine.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/engine.hpp -------------------------------------------------------------------------------- /src/common/engine_id.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/engine_id.hpp -------------------------------------------------------------------------------- /src/common/experimental.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/experimental.cpp -------------------------------------------------------------------------------- /src/common/experimental.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/experimental.hpp -------------------------------------------------------------------------------- /src/common/float16.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/float16.hpp -------------------------------------------------------------------------------- /src/common/fpmath_mode.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/fpmath_mode.cpp -------------------------------------------------------------------------------- /src/common/gemm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/gemm.cpp -------------------------------------------------------------------------------- /src/common/gemm_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/gemm_pd.hpp -------------------------------------------------------------------------------- /src/common/gemm_types.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/gemm_types.hpp -------------------------------------------------------------------------------- /src/common/gemm_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/gemm_utils.hpp -------------------------------------------------------------------------------- /src/common/guard_manager.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/guard_manager.hpp -------------------------------------------------------------------------------- /src/common/impl_list_item.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/impl_list_item.hpp -------------------------------------------------------------------------------- /src/common/impl_registration.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/impl_registration.hpp -------------------------------------------------------------------------------- /src/common/inner_product.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/inner_product.cpp -------------------------------------------------------------------------------- /src/common/inner_product_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/inner_product_pd.hpp -------------------------------------------------------------------------------- /src/common/int4.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/int4.hpp -------------------------------------------------------------------------------- /src/common/internal_defs.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/internal_defs.hpp -------------------------------------------------------------------------------- /src/common/internal_desc_types.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/internal_desc_types.hpp -------------------------------------------------------------------------------- /src/common/ittnotify.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify.cpp -------------------------------------------------------------------------------- /src/common/ittnotify.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify.hpp -------------------------------------------------------------------------------- /src/common/ittnotify/LICENSE.BSD: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/LICENSE.BSD -------------------------------------------------------------------------------- /src/common/ittnotify/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/README.md -------------------------------------------------------------------------------- /src/common/ittnotify/_clang-format: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/_clang-format -------------------------------------------------------------------------------- /src/common/ittnotify/disable_warnings.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/disable_warnings.h -------------------------------------------------------------------------------- /src/common/ittnotify/ittnotify.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/ittnotify.h -------------------------------------------------------------------------------- /src/common/ittnotify/ittnotify_config.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/ittnotify_config.h -------------------------------------------------------------------------------- /src/common/ittnotify/ittnotify_static.c: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/ittnotify_static.c -------------------------------------------------------------------------------- /src/common/ittnotify/ittnotify_static.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/ittnotify_static.h -------------------------------------------------------------------------------- /src/common/ittnotify/ittnotify_types.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/ittnotify_types.h -------------------------------------------------------------------------------- /src/common/ittnotify/ittptmark64.S: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/ittptmark64.S -------------------------------------------------------------------------------- /src/common/ittnotify/ittptmark64.asm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/ittptmark64.asm -------------------------------------------------------------------------------- /src/common/ittnotify/jitprofiling.c: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/jitprofiling.c -------------------------------------------------------------------------------- /src/common/ittnotify/jitprofiling.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/jitprofiling.h -------------------------------------------------------------------------------- /src/common/ittnotify/legacy/ittnotify.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/ittnotify/legacy/ittnotify.h -------------------------------------------------------------------------------- /src/common/layer_normalization.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/layer_normalization.cpp -------------------------------------------------------------------------------- /src/common/layer_normalization_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/layer_normalization_pd.hpp -------------------------------------------------------------------------------- /src/common/lrn.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/lrn.cpp -------------------------------------------------------------------------------- /src/common/lrn_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/lrn_pd.hpp -------------------------------------------------------------------------------- /src/common/math_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/math_utils.hpp -------------------------------------------------------------------------------- /src/common/matmul.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/matmul.cpp -------------------------------------------------------------------------------- /src/common/matmul_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/matmul_pd.hpp -------------------------------------------------------------------------------- /src/common/memory.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/memory.cpp -------------------------------------------------------------------------------- /src/common/memory.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/memory.hpp -------------------------------------------------------------------------------- /src/common/memory_debug.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/memory_debug.cpp -------------------------------------------------------------------------------- /src/common/memory_debug.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/memory_debug.hpp -------------------------------------------------------------------------------- /src/common/memory_desc_wrapper.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/memory_desc_wrapper.cpp -------------------------------------------------------------------------------- /src/common/memory_desc_wrapper.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/memory_desc_wrapper.hpp -------------------------------------------------------------------------------- /src/common/memory_storage.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/memory_storage.cpp -------------------------------------------------------------------------------- /src/common/memory_storage.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/memory_storage.hpp -------------------------------------------------------------------------------- /src/common/memory_tracking.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/memory_tracking.cpp -------------------------------------------------------------------------------- /src/common/memory_tracking.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/memory_tracking.hpp -------------------------------------------------------------------------------- /src/common/memory_zero_pad.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/memory_zero_pad.cpp -------------------------------------------------------------------------------- /src/common/nstl.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/nstl.hpp -------------------------------------------------------------------------------- /src/common/optional.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/optional.hpp -------------------------------------------------------------------------------- /src/common/pooling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/pooling.cpp -------------------------------------------------------------------------------- /src/common/pooling_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/pooling_pd.hpp -------------------------------------------------------------------------------- /src/common/prelu.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/prelu.cpp -------------------------------------------------------------------------------- /src/common/prelu_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/prelu_pd.hpp -------------------------------------------------------------------------------- /src/common/primitive.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive.cpp -------------------------------------------------------------------------------- /src/common/primitive.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive.hpp -------------------------------------------------------------------------------- /src/common/primitive_attr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_attr.cpp -------------------------------------------------------------------------------- /src/common/primitive_attr.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_attr.hpp -------------------------------------------------------------------------------- /src/common/primitive_cache.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_cache.cpp -------------------------------------------------------------------------------- /src/common/primitive_cache.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_cache.hpp -------------------------------------------------------------------------------- /src/common/primitive_desc.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_desc.cpp -------------------------------------------------------------------------------- /src/common/primitive_desc.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_desc.hpp -------------------------------------------------------------------------------- /src/common/primitive_exec_types.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_exec_types.cpp -------------------------------------------------------------------------------- /src/common/primitive_exec_types.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_exec_types.hpp -------------------------------------------------------------------------------- /src/common/primitive_hashing.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_hashing.cpp -------------------------------------------------------------------------------- /src/common/primitive_hashing.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_hashing.hpp -------------------------------------------------------------------------------- /src/common/primitive_iterator.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_iterator.cpp -------------------------------------------------------------------------------- /src/common/primitive_iterator.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/primitive_iterator.hpp -------------------------------------------------------------------------------- /src/common/query.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/query.cpp -------------------------------------------------------------------------------- /src/common/reduction.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/reduction.cpp -------------------------------------------------------------------------------- /src/common/reduction_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/reduction_pd.hpp -------------------------------------------------------------------------------- /src/common/reorder.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/reorder.cpp -------------------------------------------------------------------------------- /src/common/reorder.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/reorder.hpp -------------------------------------------------------------------------------- /src/common/reorder_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/reorder_pd.hpp -------------------------------------------------------------------------------- /src/common/resampling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/resampling.cpp -------------------------------------------------------------------------------- /src/common/resampling_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/resampling_pd.hpp -------------------------------------------------------------------------------- /src/common/rnn.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/rnn.cpp -------------------------------------------------------------------------------- /src/common/rnn.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/rnn.hpp -------------------------------------------------------------------------------- /src/common/rnn_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/rnn_pd.hpp -------------------------------------------------------------------------------- /src/common/rw_mutex.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/rw_mutex.cpp -------------------------------------------------------------------------------- /src/common/rw_mutex.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/rw_mutex.hpp -------------------------------------------------------------------------------- /src/common/scratchpad.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/scratchpad.cpp -------------------------------------------------------------------------------- /src/common/scratchpad.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/scratchpad.hpp -------------------------------------------------------------------------------- /src/common/scratchpad_debug.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/scratchpad_debug.cpp -------------------------------------------------------------------------------- /src/common/scratchpad_debug.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/scratchpad_debug.hpp -------------------------------------------------------------------------------- /src/common/serialization.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/serialization.cpp -------------------------------------------------------------------------------- /src/common/serialization.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/serialization.hpp -------------------------------------------------------------------------------- /src/common/serialization_stream.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/serialization_stream.hpp -------------------------------------------------------------------------------- /src/common/shuffle.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/shuffle.cpp -------------------------------------------------------------------------------- /src/common/shuffle_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/shuffle_pd.hpp -------------------------------------------------------------------------------- /src/common/softmax.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/softmax.cpp -------------------------------------------------------------------------------- /src/common/softmax_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/softmax_pd.hpp -------------------------------------------------------------------------------- /src/common/stack_checker.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/stack_checker.hpp -------------------------------------------------------------------------------- /src/common/stream.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/stream.cpp -------------------------------------------------------------------------------- /src/common/stream.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/stream.hpp -------------------------------------------------------------------------------- /src/common/stream_threadpool.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/stream_threadpool.cpp -------------------------------------------------------------------------------- /src/common/sum.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/sum.cpp -------------------------------------------------------------------------------- /src/common/sum_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/sum_pd.hpp -------------------------------------------------------------------------------- /src/common/tag_traits.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/tag_traits.hpp -------------------------------------------------------------------------------- /src/common/thread_local_storage.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/thread_local_storage.hpp -------------------------------------------------------------------------------- /src/common/type_helpers.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/type_helpers.hpp -------------------------------------------------------------------------------- /src/common/utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/utils.cpp -------------------------------------------------------------------------------- /src/common/utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/utils.hpp -------------------------------------------------------------------------------- /src/common/verbose.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/verbose.cpp -------------------------------------------------------------------------------- /src/common/verbose.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/verbose.hpp -------------------------------------------------------------------------------- /src/common/z_magic.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/z_magic.hpp -------------------------------------------------------------------------------- /src/common/zendnn_avg_pool.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_avg_pool.cpp -------------------------------------------------------------------------------- /src/common/zendnn_avg_pool_ref.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_avg_pool_ref.cpp -------------------------------------------------------------------------------- /src/common/zendnn_batch_norm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_batch_norm.cpp -------------------------------------------------------------------------------- /src/common/zendnn_batch_norm_ref.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_batch_norm_ref.cpp -------------------------------------------------------------------------------- /src/common/zendnn_blocked_layout.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_blocked_layout.cpp -------------------------------------------------------------------------------- /src/common/zendnn_convolution_direct.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_convolution_direct.cpp -------------------------------------------------------------------------------- /src/common/zendnn_convolution_gemm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_convolution_gemm.cpp -------------------------------------------------------------------------------- /src/common/zendnn_convolution_ref.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_convolution_ref.cpp -------------------------------------------------------------------------------- /src/common/zendnn_convolution_winograd.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_convolution_winograd.cpp -------------------------------------------------------------------------------- /src/common/zendnn_convolution_winograd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_convolution_winograd.hpp -------------------------------------------------------------------------------- /src/common/zendnn_create_aocl_post_ops.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_create_aocl_post_ops.cpp -------------------------------------------------------------------------------- /src/common/zendnn_debug.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_debug.cpp -------------------------------------------------------------------------------- /src/common/zendnn_debug_autogenerated.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_debug_autogenerated.cpp -------------------------------------------------------------------------------- /src/common/zendnn_grp_ebag_matmul.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_grp_ebag_matmul.cpp -------------------------------------------------------------------------------- /src/common/zendnn_hw_os_kernel_bios_info.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_hw_os_kernel_bios_info.cpp -------------------------------------------------------------------------------- /src/common/zendnn_hw_os_kernel_bios_info.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_hw_os_kernel_bios_info.hpp -------------------------------------------------------------------------------- /src/common/zendnn_lru_cache.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_lru_cache.cpp -------------------------------------------------------------------------------- /src/common/zendnn_lru_cache.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_lru_cache.hpp -------------------------------------------------------------------------------- /src/common/zendnn_matmul_auto_tuner.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_matmul_auto_tuner.cpp -------------------------------------------------------------------------------- /src/common/zendnn_matmul_bf16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_matmul_bf16.cpp -------------------------------------------------------------------------------- /src/common/zendnn_matmul_gemm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_matmul_gemm.cpp -------------------------------------------------------------------------------- /src/common/zendnn_matmul_int8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_matmul_int8.cpp -------------------------------------------------------------------------------- /src/common/zendnn_matmul_ref.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_matmul_ref.cpp -------------------------------------------------------------------------------- /src/common/zendnn_matmul_woq.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_matmul_woq.cpp -------------------------------------------------------------------------------- /src/common/zendnn_max_pool.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_max_pool.cpp -------------------------------------------------------------------------------- /src/common/zendnn_max_pool_ref.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_max_pool_ref.cpp -------------------------------------------------------------------------------- /src/common/zendnn_postops.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_postops.cpp -------------------------------------------------------------------------------- /src/common/zendnn_private.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_private.hpp -------------------------------------------------------------------------------- /src/common/zendnn_profiler.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_profiler.hpp -------------------------------------------------------------------------------- /src/common/zendnn_reorder_cache.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_reorder_cache.cpp -------------------------------------------------------------------------------- /src/common/zendnn_reorder_cache.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_reorder_cache.hpp -------------------------------------------------------------------------------- /src/common/zendnn_reorder_custom_op.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_reorder_custom_op.cpp -------------------------------------------------------------------------------- /src/common/zendnn_thread.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_thread.cpp -------------------------------------------------------------------------------- /src/common/zendnn_thread.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_thread.hpp -------------------------------------------------------------------------------- /src/common/zendnn_traits.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_traits.hpp -------------------------------------------------------------------------------- /src/common/zendnn_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_utils.cpp -------------------------------------------------------------------------------- /src/common/zendnn_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/common/zendnn_utils.hpp -------------------------------------------------------------------------------- /src/cpu/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/CMakeLists.txt -------------------------------------------------------------------------------- /src/cpu/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/README.md -------------------------------------------------------------------------------- /src/cpu/avx2_embedding_bag.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/avx2_embedding_bag.cpp -------------------------------------------------------------------------------- /src/cpu/avx2_embedding_bag.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/avx2_embedding_bag.hpp -------------------------------------------------------------------------------- /src/cpu/avx512_embedding_bag.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/avx512_embedding_bag.cpp -------------------------------------------------------------------------------- /src/cpu/avx512_embedding_bag.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/avx512_embedding_bag.hpp -------------------------------------------------------------------------------- /src/cpu/avx512_embedding_bag_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/avx512_embedding_bag_utils.hpp -------------------------------------------------------------------------------- /src/cpu/bfloat16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/bfloat16.cpp -------------------------------------------------------------------------------- /src/cpu/binary_injector_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/binary_injector_utils.cpp -------------------------------------------------------------------------------- /src/cpu/binary_injector_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/binary_injector_utils.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_attention_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_attention_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_attention_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_attention_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_batch_normalization_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_batch_normalization_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_batch_normalization_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_batch_normalization_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_batch_normalization_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_batch_normalization_utils.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_batch_normalization_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_batch_normalization_utils.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_binary_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_binary_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_binary_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_binary_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_concat.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_concat.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_concat_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_concat_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_convolution_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_convolution_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_convolution_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_convolution_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_deconvolution_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_deconvolution_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_deconvolution_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_deconvolution_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_eltwise_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_eltwise_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_eltwise_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_eltwise_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_embedding_bag_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_embedding_bag_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_embedding_bag_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_embedding_bag_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_engine.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_engine.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_engine.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_engine.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_inner_product_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_inner_product_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_inner_product_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_inner_product_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_layer_normalization_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_layer_normalization_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_layer_normalization_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_layer_normalization_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_lrn_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_lrn_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_lrn_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_lrn_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_memory_storage.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_memory_storage.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_pooling_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_pooling_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_pooling_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_pooling_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_prelu_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_prelu_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_prelu_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_prelu_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_primitive.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_primitive.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_reduction_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_reduction_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_reduction_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_reduction_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_resampling_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_resampling_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_resampling_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_resampling_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_rnn_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_rnn_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_shuffle_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_shuffle_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_shuffle_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_shuffle_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_softmax_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_softmax_list.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_softmax_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_softmax_pd.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_stream.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_stream.hpp -------------------------------------------------------------------------------- /src/cpu/cpu_sum.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_sum.cpp -------------------------------------------------------------------------------- /src/cpu/cpu_sum_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/cpu_sum_pd.hpp -------------------------------------------------------------------------------- /src/cpu/dw_convolution_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/dw_convolution_utils.hpp -------------------------------------------------------------------------------- /src/cpu/gemm/f32/gemm_utils_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/f32/gemm_utils_f32.cpp -------------------------------------------------------------------------------- /src/cpu/gemm/f32/gemm_utils_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/f32/gemm_utils_f32.hpp -------------------------------------------------------------------------------- /src/cpu/gemm/f32/ref_gemm_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/f32/ref_gemm_f32.cpp -------------------------------------------------------------------------------- /src/cpu/gemm/f32/ref_gemm_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/f32/ref_gemm_f32.hpp -------------------------------------------------------------------------------- /src/cpu/gemm/gemm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/gemm.cpp -------------------------------------------------------------------------------- /src/cpu/gemm/gemm.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/gemm.hpp -------------------------------------------------------------------------------- /src/cpu/gemm/gemm_msan_unpoison.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/gemm_msan_unpoison.hpp -------------------------------------------------------------------------------- /src/cpu/gemm/gemm_pack.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/gemm_pack.cpp -------------------------------------------------------------------------------- /src/cpu/gemm/gemm_pack.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/gemm_pack.hpp -------------------------------------------------------------------------------- /src/cpu/gemm/os_blas.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/os_blas.hpp -------------------------------------------------------------------------------- /src/cpu/gemm/s8x8s32/ref_gemm_s8x8s32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/s8x8s32/ref_gemm_s8x8s32.cpp -------------------------------------------------------------------------------- /src/cpu/gemm/s8x8s32/ref_gemm_s8x8s32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/s8x8s32/ref_gemm_s8x8s32.hpp -------------------------------------------------------------------------------- /src/cpu/gemm/s8x8s32/simple_gemm_s8s8s32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/s8x8s32/simple_gemm_s8s8s32.cpp -------------------------------------------------------------------------------- /src/cpu/gemm/s8x8s32/simple_gemm_s8s8s32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm/s8x8s32/simple_gemm_s8s8s32.hpp -------------------------------------------------------------------------------- /src/cpu/gemm_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/gemm_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/gemm_convolution_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_convolution_utils.cpp -------------------------------------------------------------------------------- /src/cpu/gemm_convolution_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_convolution_utils.hpp -------------------------------------------------------------------------------- /src/cpu/gemm_inner_product.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_inner_product.cpp -------------------------------------------------------------------------------- /src/cpu/gemm_inner_product.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_inner_product.hpp -------------------------------------------------------------------------------- /src/cpu/gemm_inner_product_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_inner_product_utils.cpp -------------------------------------------------------------------------------- /src/cpu/gemm_inner_product_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_inner_product_utils.hpp -------------------------------------------------------------------------------- /src/cpu/gemm_x8s8s32x_conv_zp_src_pad_comp.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_x8s8s32x_conv_zp_src_pad_comp.cpp -------------------------------------------------------------------------------- /src/cpu/gemm_x8s8s32x_conv_zp_src_pad_comp.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_x8s8s32x_conv_zp_src_pad_comp.hpp -------------------------------------------------------------------------------- /src/cpu/gemm_x8s8s32x_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_x8s8s32x_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/gemm_x8s8s32x_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_x8s8s32x_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/gemm_x8s8s32x_convolution_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_x8s8s32x_convolution_utils.cpp -------------------------------------------------------------------------------- /src/cpu/gemm_x8s8s32x_convolution_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_x8s8s32x_convolution_utils.hpp -------------------------------------------------------------------------------- /src/cpu/gemm_x8s8s32x_inner_product.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_x8s8s32x_inner_product.cpp -------------------------------------------------------------------------------- /src/cpu/gemm_x8s8s32x_inner_product.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/gemm_x8s8s32x_inner_product.hpp -------------------------------------------------------------------------------- /src/cpu/matmul/cpu_matmul_list.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/cpu_matmul_list.cpp -------------------------------------------------------------------------------- /src/cpu/matmul/cpu_matmul_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/cpu_matmul_pd.hpp -------------------------------------------------------------------------------- /src/cpu/matmul/gemm_based_common.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/gemm_based_common.hpp -------------------------------------------------------------------------------- /src/cpu/matmul/gemm_bf16_matmul.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/gemm_bf16_matmul.cpp -------------------------------------------------------------------------------- /src/cpu/matmul/gemm_bf16_matmul.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/gemm_bf16_matmul.hpp -------------------------------------------------------------------------------- /src/cpu/matmul/gemm_f32_matmul.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/gemm_f32_matmul.cpp -------------------------------------------------------------------------------- /src/cpu/matmul/gemm_f32_matmul.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/gemm_f32_matmul.hpp -------------------------------------------------------------------------------- /src/cpu/matmul/gemm_x8s8s32x_matmul.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/gemm_x8s8s32x_matmul.cpp -------------------------------------------------------------------------------- /src/cpu/matmul/gemm_x8s8s32x_matmul.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/gemm_x8s8s32x_matmul.hpp -------------------------------------------------------------------------------- /src/cpu/matmul/matmul_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/matmul_utils.hpp -------------------------------------------------------------------------------- /src/cpu/matmul/ref_matmul.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/ref_matmul.cpp -------------------------------------------------------------------------------- /src/cpu/matmul/ref_matmul.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/ref_matmul.hpp -------------------------------------------------------------------------------- /src/cpu/matmul/ref_matmul_int8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/ref_matmul_int8.cpp -------------------------------------------------------------------------------- /src/cpu/matmul/ref_matmul_int8.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/ref_matmul_int8.hpp -------------------------------------------------------------------------------- /src/cpu/matmul/zendnn_bf16_matmul.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/zendnn_bf16_matmul.cpp -------------------------------------------------------------------------------- /src/cpu/matmul/zendnn_bf16_matmul.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/zendnn_bf16_matmul.hpp -------------------------------------------------------------------------------- /src/cpu/matmul/zendnn_f32_matmul.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/zendnn_f32_matmul.cpp -------------------------------------------------------------------------------- /src/cpu/matmul/zendnn_f32_matmul.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/zendnn_f32_matmul.hpp -------------------------------------------------------------------------------- /src/cpu/matmul/zendnn_x8s8s32x_matmul.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/zendnn_x8s8s32x_matmul.cpp -------------------------------------------------------------------------------- /src/cpu/matmul/zendnn_x8s8s32x_matmul.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/matmul/zendnn_x8s8s32x_matmul.hpp -------------------------------------------------------------------------------- /src/cpu/nchw_pooling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/nchw_pooling.cpp -------------------------------------------------------------------------------- /src/cpu/nchw_pooling.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/nchw_pooling.hpp -------------------------------------------------------------------------------- /src/cpu/ncsp_batch_normalization.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ncsp_batch_normalization.cpp -------------------------------------------------------------------------------- /src/cpu/ncsp_batch_normalization.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ncsp_batch_normalization.hpp -------------------------------------------------------------------------------- /src/cpu/nhwc_pooling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/nhwc_pooling.cpp -------------------------------------------------------------------------------- /src/cpu/nhwc_pooling.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/nhwc_pooling.hpp -------------------------------------------------------------------------------- /src/cpu/nspc_batch_normalization.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/nspc_batch_normalization.cpp -------------------------------------------------------------------------------- /src/cpu/nspc_batch_normalization.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/nspc_batch_normalization.hpp -------------------------------------------------------------------------------- /src/cpu/platform.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/platform.cpp -------------------------------------------------------------------------------- /src/cpu/platform.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/platform.hpp -------------------------------------------------------------------------------- /src/cpu/primitive_attr_postops.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/primitive_attr_postops.cpp -------------------------------------------------------------------------------- /src/cpu/primitive_attr_postops.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/primitive_attr_postops.hpp -------------------------------------------------------------------------------- /src/cpu/ref_attention.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_attention.hpp -------------------------------------------------------------------------------- /src/cpu/ref_batch_normalization.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_batch_normalization.cpp -------------------------------------------------------------------------------- /src/cpu/ref_batch_normalization.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_batch_normalization.hpp -------------------------------------------------------------------------------- /src/cpu/ref_binary.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_binary.cpp -------------------------------------------------------------------------------- /src/cpu/ref_binary.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_binary.hpp -------------------------------------------------------------------------------- /src/cpu/ref_concat.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_concat.hpp -------------------------------------------------------------------------------- /src/cpu/ref_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/ref_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/ref_convolution_int8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_convolution_int8.cpp -------------------------------------------------------------------------------- /src/cpu/ref_convolution_int8.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_convolution_int8.hpp -------------------------------------------------------------------------------- /src/cpu/ref_convolution_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_convolution_utils.hpp -------------------------------------------------------------------------------- /src/cpu/ref_deconvolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_deconvolution.cpp -------------------------------------------------------------------------------- /src/cpu/ref_deconvolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_deconvolution.hpp -------------------------------------------------------------------------------- /src/cpu/ref_eltwise.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_eltwise.cpp -------------------------------------------------------------------------------- /src/cpu/ref_eltwise.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_eltwise.hpp -------------------------------------------------------------------------------- /src/cpu/ref_embedding_bag.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_embedding_bag.hpp -------------------------------------------------------------------------------- /src/cpu/ref_fused_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_fused_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/ref_inner_product.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_inner_product.cpp -------------------------------------------------------------------------------- /src/cpu/ref_inner_product.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_inner_product.hpp -------------------------------------------------------------------------------- /src/cpu/ref_inner_product_int8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_inner_product_int8.cpp -------------------------------------------------------------------------------- /src/cpu/ref_inner_product_int8.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_inner_product_int8.hpp -------------------------------------------------------------------------------- /src/cpu/ref_inner_product_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_inner_product_utils.hpp -------------------------------------------------------------------------------- /src/cpu/ref_io_helper.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_io_helper.hpp -------------------------------------------------------------------------------- /src/cpu/ref_layer_normalization.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_layer_normalization.cpp -------------------------------------------------------------------------------- /src/cpu/ref_layer_normalization.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_layer_normalization.hpp -------------------------------------------------------------------------------- /src/cpu/ref_lrn.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_lrn.cpp -------------------------------------------------------------------------------- /src/cpu/ref_lrn.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_lrn.hpp -------------------------------------------------------------------------------- /src/cpu/ref_pooling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_pooling.cpp -------------------------------------------------------------------------------- /src/cpu/ref_pooling.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_pooling.hpp -------------------------------------------------------------------------------- /src/cpu/ref_prelu.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_prelu.cpp -------------------------------------------------------------------------------- /src/cpu/ref_prelu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_prelu.hpp -------------------------------------------------------------------------------- /src/cpu/ref_reduction.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_reduction.cpp -------------------------------------------------------------------------------- /src/cpu/ref_reduction.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_reduction.hpp -------------------------------------------------------------------------------- /src/cpu/ref_resampling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_resampling.cpp -------------------------------------------------------------------------------- /src/cpu/ref_resampling.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_resampling.hpp -------------------------------------------------------------------------------- /src/cpu/ref_shuffle.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_shuffle.cpp -------------------------------------------------------------------------------- /src/cpu/ref_shuffle.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_shuffle.hpp -------------------------------------------------------------------------------- /src/cpu/ref_softmax.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_softmax.cpp -------------------------------------------------------------------------------- /src/cpu/ref_softmax.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_softmax.hpp -------------------------------------------------------------------------------- /src/cpu/ref_sum.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/ref_sum.hpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder.hpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_comp_bf16_s8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_comp_bf16_s8.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_comp_f32_s8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_comp_f32_s8.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_comp_s8_s8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_comp_s8_s8.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_pd.hpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_regular_bf16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_regular_bf16.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_regular_f16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_regular_f16.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_regular_f32_bf16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_regular_f32_bf16.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_regular_f32_f16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_regular_f32_f16.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_regular_f32_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_regular_f32_f32.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_regular_f32_s32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_regular_f32_s32.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_regular_f32_s8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_regular_f32_s8.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_regular_f32_u8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_regular_f32_u8.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_regular_s32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_regular_s32.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_regular_s8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_regular_s8.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/cpu_reorder_regular_u8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/cpu_reorder_regular_u8.cpp -------------------------------------------------------------------------------- /src/cpu/reorder/simple_reorder.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/reorder/simple_reorder.hpp -------------------------------------------------------------------------------- /src/cpu/resampling_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/resampling_utils.hpp -------------------------------------------------------------------------------- /src/cpu/rnn/brgemm_cell_common.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/brgemm_cell_common.cpp -------------------------------------------------------------------------------- /src/cpu/rnn/cell_common.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/cell_common.cpp -------------------------------------------------------------------------------- /src/cpu/rnn/cell_gru.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/cell_gru.cpp -------------------------------------------------------------------------------- /src/cpu/rnn/cell_gru_lbr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/cell_gru_lbr.cpp -------------------------------------------------------------------------------- /src/cpu/rnn/cpu_rnn_pd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/cpu_rnn_pd.hpp -------------------------------------------------------------------------------- /src/cpu/rnn/postgemm_dispatcher.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/postgemm_dispatcher.hpp -------------------------------------------------------------------------------- /src/cpu/rnn/ref_postgemm_gru.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/ref_postgemm_gru.cpp -------------------------------------------------------------------------------- /src/cpu/rnn/ref_postgemm_gru_lbr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/ref_postgemm_gru_lbr.cpp -------------------------------------------------------------------------------- /src/cpu/rnn/ref_postgemm_lstm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/ref_postgemm_lstm.cpp -------------------------------------------------------------------------------- /src/cpu/rnn/ref_postgemm_lstm_projection.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/ref_postgemm_lstm_projection.cpp -------------------------------------------------------------------------------- /src/cpu/rnn/ref_postgemm_rnn.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/ref_postgemm_rnn.cpp -------------------------------------------------------------------------------- /src/cpu/rnn/ref_rnn.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/ref_rnn.cpp -------------------------------------------------------------------------------- /src/cpu/rnn/ref_rnn.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/ref_rnn.hpp -------------------------------------------------------------------------------- /src/cpu/rnn/rnn_reorders.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/rnn_reorders.hpp -------------------------------------------------------------------------------- /src/cpu/rnn/rnn_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/rnn_utils.cpp -------------------------------------------------------------------------------- /src/cpu/rnn/rnn_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/rnn/rnn_utils.hpp -------------------------------------------------------------------------------- /src/cpu/simple_concat.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/simple_concat.cpp -------------------------------------------------------------------------------- /src/cpu/simple_concat.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/simple_concat.hpp -------------------------------------------------------------------------------- /src/cpu/simple_layer_normalization.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/simple_layer_normalization.cpp -------------------------------------------------------------------------------- /src/cpu/simple_layer_normalization.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/simple_layer_normalization.hpp -------------------------------------------------------------------------------- /src/cpu/simple_layer_normalization_kernels.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/simple_layer_normalization_kernels.cpp -------------------------------------------------------------------------------- /src/cpu/simple_layer_normalization_kernels.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/simple_layer_normalization_kernels.hpp -------------------------------------------------------------------------------- /src/cpu/simple_q10n.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/simple_q10n.hpp -------------------------------------------------------------------------------- /src/cpu/simple_resampling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/simple_resampling.cpp -------------------------------------------------------------------------------- /src/cpu/simple_resampling.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/simple_resampling.hpp -------------------------------------------------------------------------------- /src/cpu/simple_sum.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/simple_sum.cpp -------------------------------------------------------------------------------- /src/cpu/simple_sum.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/simple_sum.hpp -------------------------------------------------------------------------------- /src/cpu/x64/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/CMakeLists.txt -------------------------------------------------------------------------------- /src/cpu/x64/amx_tile_configure.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/amx_tile_configure.cpp -------------------------------------------------------------------------------- /src/cpu/x64/amx_tile_configure.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/amx_tile_configure.hpp -------------------------------------------------------------------------------- /src/cpu/x64/brgemm/brgemm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/brgemm/brgemm.cpp -------------------------------------------------------------------------------- /src/cpu/x64/brgemm/brgemm.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/brgemm/brgemm.hpp -------------------------------------------------------------------------------- /src/cpu/x64/brgemm/brgemm_types.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/brgemm/brgemm_types.hpp -------------------------------------------------------------------------------- /src/cpu/x64/brgemm/jit_brdgmm_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/brgemm/jit_brdgmm_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/brgemm/jit_brdgmm_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/brgemm/jit_brdgmm_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/brgemm/jit_brgemm_amx_uker.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/brgemm/jit_brgemm_amx_uker.cpp -------------------------------------------------------------------------------- /src/cpu/x64/brgemm/jit_brgemm_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/brgemm/jit_brgemm_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/ck_conv_kernel_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/ck_conv_kernel_f32.cpp -------------------------------------------------------------------------------- /src/cpu/x64/ck_conv_kernel_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/ck_conv_kernel_f32.hpp -------------------------------------------------------------------------------- /src/cpu/x64/ck_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/ck_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/ck_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/ck_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/cpu_barrier.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/cpu_barrier.cpp -------------------------------------------------------------------------------- /src/cpu/x64/cpu_barrier.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/cpu_barrier.hpp -------------------------------------------------------------------------------- /src/cpu/x64/cpu_isa_traits.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/cpu_isa_traits.cpp -------------------------------------------------------------------------------- /src/cpu/x64/cpu_isa_traits.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/cpu_isa_traits.hpp -------------------------------------------------------------------------------- /src/cpu/x64/cpu_reducer.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/cpu_reducer.cpp -------------------------------------------------------------------------------- /src/cpu/x64/cpu_reducer.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/cpu_reducer.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/amx/jit_avx512_core_amx_copy_kern.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/amx/jit_avx512_core_amx_copy_kern.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/amx/jit_avx512_core_amx_copy_kern.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/amx/jit_avx512_core_amx_copy_kern.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/amx/jit_avx512_core_amx_gemm_kern.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/amx/jit_avx512_core_amx_gemm_kern.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/amx/jit_avx512_core_amx_gemm_kern.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/amx/jit_avx512_core_amx_gemm_kern.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/bf16/common_s16.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/bf16/common_s16.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/common_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/common_f32.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_avx2_kernel_sgemm_kern.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_avx2_kernel_sgemm_kern.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_avx2_kernel_sgemm_kern.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_avx2_kernel_sgemm_kern.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_avx512_common_gemm_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_avx512_common_gemm_f32.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_avx512_common_gemm_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_avx512_common_gemm_f32.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_avx_gemm_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_avx_gemm_f32.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_avx_gemm_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_avx_gemm_f32.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_avx_gemv_t_f32_kern.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_avx_gemv_t_f32_kern.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_avx_gemv_t_f32_kern.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_avx_gemv_t_f32_kern.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_sse41_gemv_n_f32_kern.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_sse41_gemv_n_f32_kern.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_sse41_gemv_n_f32_kern.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_sse41_gemv_n_f32_kern.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_sse41_gemv_t_f32_kern.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_sse41_gemv_t_f32_kern.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/f32/jit_sse41_gemv_t_f32_kern.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/f32/jit_sse41_gemv_t_f32_kern.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemm_driver.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemm_driver.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemm_driver.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemm_driver.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemm_info.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemm_info.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemm_info.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemm_info.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemm_pack.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemm_pack.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemm_pack.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemm_pack.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemm_pack_storage.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemm_pack_storage.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemm_partition.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemm_partition.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemm_threading.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemm_threading.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemm_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemm_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemv_driver.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemv_driver.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/gemv_driver.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/gemv_driver.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/s8x8s32/common_u8.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/s8x8s32/common_u8.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/s8x8s32/jit_avx2_gemm_s8u8s32_kern.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/s8x8s32/jit_avx2_gemm_s8u8s32_kern.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm/s8x8s32/jit_avx2_gemm_s8u8s32_kern.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm/s8x8s32/jit_avx2_gemm_s8u8s32_kern.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm_bf16_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm_bf16_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm_bf16_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm_bf16_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm_bf16_inner_product.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm_bf16_inner_product.cpp -------------------------------------------------------------------------------- /src/cpu/x64/gemm_bf16_inner_product.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/gemm_bf16_inner_product.hpp -------------------------------------------------------------------------------- /src/cpu/x64/injectors/injector_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/injectors/injector_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/injectors/injector_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/injectors/injector_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/injectors/jit_uni_binary_injector.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/injectors/jit_uni_binary_injector.cpp -------------------------------------------------------------------------------- /src/cpu/x64/injectors/jit_uni_binary_injector.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/injectors/jit_uni_binary_injector.hpp -------------------------------------------------------------------------------- /src/cpu/x64/injectors/jit_uni_eltwise_injector.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/injectors/jit_uni_eltwise_injector.cpp -------------------------------------------------------------------------------- /src/cpu/x64/injectors/jit_uni_eltwise_injector.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/injectors/jit_uni_eltwise_injector.hpp -------------------------------------------------------------------------------- /src/cpu/x64/injectors/jit_uni_postops_injector.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/injectors/jit_uni_postops_injector.cpp -------------------------------------------------------------------------------- /src/cpu/x64/injectors/jit_uni_postops_injector.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/injectors/jit_uni_postops_injector.hpp -------------------------------------------------------------------------------- /src/cpu/x64/ip_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/ip_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/ip_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/ip_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx2_1x1_conv_kernel_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx2_1x1_conv_kernel_f32.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx2_1x1_conv_kernel_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx2_1x1_conv_kernel_f32.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx2_1x1_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx2_1x1_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx2_1x1_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx2_1x1_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx2_conv_kernel_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx2_conv_kernel_f32.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx2_conv_kernel_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx2_conv_kernel_f32.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx2_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx2_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx2_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx2_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_common_1x1_conv_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_common_1x1_conv_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_common_1x1_conv_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_common_1x1_conv_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_common_1x1_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_common_1x1_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_common_1x1_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_common_1x1_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_common_conv_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_common_conv_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_common_conv_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_common_conv_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_common_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_common_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_common_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_common_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_common_resampling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_common_resampling.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_common_resampling.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_common_resampling.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_amx_1x1_conv_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_amx_1x1_conv_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_amx_1x1_conv_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_amx_1x1_conv_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_amx_1x1_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_amx_1x1_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_amx_1x1_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_amx_1x1_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_amx_conv_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_amx_conv_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_amx_conv_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_amx_conv_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_amx_conv_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_amx_conv_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_amx_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_amx_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_amx_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_amx_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_amx_deconvolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_amx_deconvolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_amx_deconvolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_amx_deconvolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_1x1_conv_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_1x1_conv_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_1x1_conv_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_1x1_conv_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_1x1_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_1x1_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_1x1_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_1x1_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_conv_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_conv_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_conv_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_conv_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_dw_conv_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_dw_conv_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_dw_conv_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_dw_conv_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_sum.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_sum.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16_sum.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16_sum.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16cvt.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16cvt.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_bf16cvt.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_bf16cvt.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_f32_wino_conv_2x3.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_f32_wino_conv_2x3.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_f32_wino_conv_2x3.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_f32_wino_conv_2x3.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_f32_wino_conv_4x3.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_f32_wino_conv_4x3.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_f32_wino_conv_4x3.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_f32_wino_conv_4x3.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_f32_wino_conv_4x3_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_f32_wino_conv_4x3_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_f32_wino_conv_4x3_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_f32_wino_conv_4x3_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_x8s8s32x_1x1_conv_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_x8s8s32x_1x1_conv_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_x8s8s32x_1x1_conv_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_x8s8s32x_1x1_conv_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_x8s8s32x_1x1_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_x8s8s32x_1x1_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_x8s8s32x_1x1_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_x8s8s32x_1x1_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_x8s8s32x_conv_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_x8s8s32x_conv_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_x8s8s32x_conv_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_x8s8s32x_conv_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_x8s8s32x_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_x8s8s32x_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_x8s8s32x_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_x8s8s32x_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_avx512_core_x8s8s32x_deconvolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_avx512_core_x8s8s32x_deconvolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brdgmm_dw_conv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brdgmm_dw_conv.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brdgmm_dw_conv.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brdgmm_dw_conv.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_1x1_conv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_1x1_conv.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_1x1_conv.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_1x1_conv.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_conv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_conv.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_conv.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_conv.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_conv_comp_pad_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_conv_comp_pad_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_conv_comp_pad_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_conv_comp_pad_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_conv_trans_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_conv_trans_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_conv_trans_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_conv_trans_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_conv_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_conv_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_conv_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_conv_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_inner_product.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_inner_product.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_inner_product.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_inner_product.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_inner_product_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_inner_product_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_inner_product_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_inner_product_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_post_ops.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_post_ops.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_primitive_conf.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_primitive_conf.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_transpose_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_transpose_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_brgemm_transpose_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_brgemm_transpose_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_gemm_inner_product_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_gemm_inner_product_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_gemm_inner_product_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_gemm_inner_product_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_gemm_x8s8s32x_convolution_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_gemm_x8s8s32x_convolution_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_gemm_x8s8s32x_convolution_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_gemm_x8s8s32x_convolution_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_generator.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_generator.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_primitive_conf.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_primitive_conf.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_sse41_1x1_conv_kernel_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_sse41_1x1_conv_kernel_f32.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_sse41_1x1_conv_kernel_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_sse41_1x1_conv_kernel_f32.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_sse41_1x1_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_sse41_1x1_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_sse41_1x1_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_sse41_1x1_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_sse41_conv_kernel_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_sse41_conv_kernel_f32.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_sse41_conv_kernel_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_sse41_conv_kernel_f32.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_sse41_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_sse41_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_sse41_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_sse41_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_transpose_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_transpose_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_transpose_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_transpose_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_1x1_conv_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_1x1_conv_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_batch_normalization.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_batch_normalization.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_batch_normalization.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_batch_normalization.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_batch_normalization_s8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_batch_normalization_s8.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_batch_normalization_s8.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_batch_normalization_s8.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_binary.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_binary.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_binary.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_binary.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_binary_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_binary_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_binary_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_binary_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_deconv_zp_pad_str_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_deconv_zp_pad_str_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_deconv_zp_pad_str_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_deconv_zp_pad_str_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_dw_conv_kernel_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_dw_conv_kernel_f32.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_dw_conv_kernel_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_dw_conv_kernel_f32.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_dw_conv_kernel_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_dw_conv_kernel_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_dw_conv_kernel_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_dw_conv_kernel_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_dw_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_dw_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_dw_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_dw_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_eltwise.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_eltwise.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_eltwise.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_eltwise.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_eltwise_int.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_eltwise_int.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_eltwise_int.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_eltwise_int.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_i8i8_pooling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_i8i8_pooling.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_i8i8_pooling.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_i8i8_pooling.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_layer_normalization_kernels.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_layer_normalization_kernels.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_layer_normalization_kernels.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_layer_normalization_kernels.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_pool_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_pool_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_pool_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_pool_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_pooling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_pooling.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_pooling.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_pooling.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_reduction.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_reduction.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_reduction.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_reduction.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_reduction_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_reduction_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_reduction_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_reduction_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_reorder.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_reorder.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_reorder.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_reorder.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_reorder_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_reorder_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_resampling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_resampling.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_resampling.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_resampling.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_resampling_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_resampling_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_resampling_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_resampling_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_softmax.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_softmax.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_softmax.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_softmax.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_tbb_batch_normalization.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_tbb_batch_normalization.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_tbb_batch_normalization.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_tbb_batch_normalization.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_x8s8s32x_1x1_conv_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_x8s8s32x_1x1_conv_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_x8s8s32x_1x1_conv_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_x8s8s32x_1x1_conv_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_x8s8s32x_1x1_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_x8s8s32x_1x1_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_x8s8s32x_1x1_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_x8s8s32x_1x1_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_x8s8s32x_1x1_deconvolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_x8s8s32x_1x1_deconvolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_x8s8s32x_conv_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_x8s8s32x_conv_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_x8s8s32x_conv_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_x8s8s32x_conv_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_x8s8s32x_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_x8s8s32x_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_x8s8s32x_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_x8s8s32x_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_x8s8s32x_deconvolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_x8s8s32x_deconvolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/jit_uni_x8s8s32x_deconvolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/jit_uni_x8s8s32x_deconvolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn.cpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_base.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_base.cpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_base.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_base.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_blocked.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_blocked.cpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_blocked.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_blocked.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_nhwc.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_nhwc.cpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_nhwc.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_bwd_nhwc.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_base.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_base.cpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_base.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_base.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_blocked.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_blocked.cpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_blocked.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_blocked.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_nhwc.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_nhwc.cpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_nhwc.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_fwd_nhwc.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_avx512_common_lrn_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_avx512_common_lrn_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_uni_lrn.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_uni_lrn.cpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_uni_lrn.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_uni_lrn.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_uni_lrn_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_uni_lrn_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/jit_uni_lrn_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/jit_uni_lrn_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/lrn_avx512_blocked_executor.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/lrn_avx512_blocked_executor.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/lrn_avx512_nhwc_executor.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/lrn_avx512_nhwc_executor.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/lrn_executor.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/lrn_executor.hpp -------------------------------------------------------------------------------- /src/cpu/x64/lrn/lrn_executor_factory.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/lrn/lrn_executor_factory.hpp -------------------------------------------------------------------------------- /src/cpu/x64/matmul/brgemm_matmul.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/matmul/brgemm_matmul.cpp -------------------------------------------------------------------------------- /src/cpu/x64/matmul/brgemm_matmul.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/matmul/brgemm_matmul.hpp -------------------------------------------------------------------------------- /src/cpu/x64/matmul/brgemm_matmul_copy_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/matmul/brgemm_matmul_copy_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/matmul/brgemm_matmul_copy_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/matmul/brgemm_matmul_copy_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/matmul/brgemm_matmul_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/matmul/brgemm_matmul_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/matmul/brgemm_matmul_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/matmul/brgemm_matmul_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_prelu_backward.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_prelu_backward.cpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_prelu_backward.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_prelu_backward.hpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_prelu_base_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_prelu_base_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_prelu_base_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_prelu_base_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_prelu_forward.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_prelu_forward.cpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_prelu_forward.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_prelu_forward.hpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_prelu_reduction_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_prelu_reduction_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_prelu_reduction_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_prelu_reduction_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_prelu_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_prelu_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_prelu_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_prelu_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_uni_prelu_backward_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_uni_prelu_backward_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_uni_prelu_backward_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_uni_prelu_backward_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_uni_prelu_forward_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_uni_prelu_forward_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/prelu/jit_uni_prelu_forward_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/prelu/jit_uni_prelu_forward_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/brgemm_cell_common_bwd.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/brgemm_cell_common_bwd.cpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/brgemm_cell_common_bwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/brgemm_cell_common_bwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/brgemm_cell_common_fwd.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/brgemm_cell_common_fwd.cpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/brgemm_cell_common_fwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/brgemm_cell_common_fwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/brgemm_cell_common_reorders.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/brgemm_cell_common_reorders.cpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/brgemm_cell_common_reorders.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/brgemm_cell_common_reorders.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/brgemm_cell_common_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/brgemm_cell_common_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/brgemm_cell_common_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/brgemm_cell_common_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_brgemm_transpose_single_row.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_brgemm_transpose_single_row.cpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_brgemm_transpose_single_row.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_brgemm_transpose_single_row.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_diff_weights_peephole.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_diff_weights_peephole.cpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_diff_weights_peephole.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_diff_weights_peephole.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_gates_reduction.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_gates_reduction.cpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_gates_reduction.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_gates_reduction.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_gru_cell_postgemm_1_bwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_gru_cell_postgemm_1_bwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_gru_cell_postgemm_1_fwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_gru_cell_postgemm_1_fwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_gru_cell_postgemm_2_bwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_gru_cell_postgemm_2_bwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_gru_cell_postgemm_2_fwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_gru_cell_postgemm_2_fwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_gru_lbr_cell_postgemm_bwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_gru_lbr_cell_postgemm_bwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_gru_lbr_cell_postgemm_fwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_gru_lbr_cell_postgemm_fwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_lstm_cell_postgemm.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_lstm_cell_postgemm.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_lstm_cell_postgemm_bwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_lstm_cell_postgemm_bwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_lstm_cell_postgemm_fwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_lstm_cell_postgemm_fwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_rnn_cell_postgemm_bwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_rnn_cell_postgemm_bwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_rnn_cell_postgemm_fwd.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_rnn_cell_postgemm_fwd.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/jit_uni_rnn_common_postgemm.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/jit_uni_rnn_common_postgemm.hpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/rnn_brgemm_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/rnn_brgemm_utils.cpp -------------------------------------------------------------------------------- /src/cpu/x64/rnn/rnn_brgemm_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/rnn/rnn_brgemm_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/shuffle/jit_uni_shuffle.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/shuffle/jit_uni_shuffle.cpp -------------------------------------------------------------------------------- /src/cpu/x64/shuffle/jit_uni_shuffle.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/shuffle/jit_uni_shuffle.hpp -------------------------------------------------------------------------------- /src/cpu/x64/shuffle/jit_uni_shuffle_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/shuffle/jit_uni_shuffle_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/shuffle/jit_uni_shuffle_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/shuffle/jit_uni_shuffle_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/utils/jit_io_helper.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/utils/jit_io_helper.cpp -------------------------------------------------------------------------------- /src/cpu/x64/utils/jit_io_helper.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/utils/jit_io_helper.hpp -------------------------------------------------------------------------------- /src/cpu/x64/wino_reorder.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/wino_reorder.hpp -------------------------------------------------------------------------------- /src/cpu/x64/xbyak/COPYRIGHT: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/xbyak/COPYRIGHT -------------------------------------------------------------------------------- /src/cpu/x64/xbyak/_clang-format: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/xbyak/_clang-format -------------------------------------------------------------------------------- /src/cpu/x64/xbyak/xbyak.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/xbyak/xbyak.h -------------------------------------------------------------------------------- /src/cpu/x64/xbyak/xbyak_bin2hex.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/xbyak/xbyak_bin2hex.h -------------------------------------------------------------------------------- /src/cpu/x64/xbyak/xbyak_mnemonic.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/xbyak/xbyak_mnemonic.h -------------------------------------------------------------------------------- /src/cpu/x64/xbyak/xbyak_util.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/xbyak/xbyak_util.h -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_conv_kernel_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_conv_kernel_f32.cpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_conv_kernel_f32.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_conv_kernel_f32.hpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_inner_product.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_inner_product.cpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_inner_product.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_inner_product.hpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_lpgemm_auto_tuner.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_lpgemm_auto_tuner.cpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_lpgemm_convolution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_lpgemm_convolution.cpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_lpgemm_convolution.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_lpgemm_convolution.hpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_lpgemm_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_lpgemm_utils.hpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_pool_kernel.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_pool_kernel.cpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_pool_kernel.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_pool_kernel.hpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_pooling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_pooling.cpp -------------------------------------------------------------------------------- /src/cpu/x64/zendnn_pooling.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/x64/zendnn_pooling.hpp -------------------------------------------------------------------------------- /src/cpu/zen_avx2_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zen_avx2_utils.hpp -------------------------------------------------------------------------------- /src/cpu/zen_avx512_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zen_avx512_utils.hpp -------------------------------------------------------------------------------- /src/cpu/zendnn_embedding_ops.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zendnn_embedding_ops.cpp -------------------------------------------------------------------------------- /src/cpu/zendnn_matmul_direct.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zendnn_matmul_direct.cpp -------------------------------------------------------------------------------- /src/cpu/zendnn_matmul_direct.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zendnn_matmul_direct.hpp -------------------------------------------------------------------------------- /src/cpu/zendnn_matmul_direct_register_tile_fp32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zendnn_matmul_direct_register_tile_fp32.cpp -------------------------------------------------------------------------------- /src/cpu/zendnn_matmul_direct_register_tile_ref.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zendnn_matmul_direct_register_tile_ref.cpp -------------------------------------------------------------------------------- /src/cpu/zendnn_matmul_direct_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zendnn_matmul_direct_utils.cpp -------------------------------------------------------------------------------- /src/cpu/zendnn_matmul_direct_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zendnn_matmul_direct_utils.hpp -------------------------------------------------------------------------------- /src/cpu/zendnn_quantize_dequantize.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zendnn_quantize_dequantize.cpp -------------------------------------------------------------------------------- /src/cpu/zendnn_quantize_dequantize.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zendnn_quantize_dequantize.hpp -------------------------------------------------------------------------------- /src/cpu/zendnn_sdpa_attention.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zendnn_sdpa_attention.cpp -------------------------------------------------------------------------------- /src/cpu/zero_point_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zero_point_utils.cpp -------------------------------------------------------------------------------- /src/cpu/zero_point_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/src/cpu/zero_point_utils.hpp -------------------------------------------------------------------------------- /tests/.gitignore: -------------------------------------------------------------------------------- 1 | *.so 2 | *.o 3 | -------------------------------------------------------------------------------- /tests/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/CMakeLists.txt -------------------------------------------------------------------------------- /tests/CMakeLists.txt.org: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/CMakeLists.txt.org -------------------------------------------------------------------------------- /tests/api_tests/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/CMakeLists.txt -------------------------------------------------------------------------------- /tests/api_tests/cmd_parser.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/cmd_parser.hpp -------------------------------------------------------------------------------- /tests/api_tests/other_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/other_utils.hpp -------------------------------------------------------------------------------- /tests/api_tests/quant_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/quant_utils.hpp -------------------------------------------------------------------------------- /tests/api_tests/ref_avx_conv_param.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/ref_avx_conv_param.cpp -------------------------------------------------------------------------------- /tests/api_tests/sha_out_NCHW/ref_avx_conv_output.sha1: -------------------------------------------------------------------------------- 1 | b296e74557000389fe619b0b8cae29995d71a439 ref_avx_conv_output 2 | -------------------------------------------------------------------------------- /tests/api_tests/sha_out_NCHW/ref_avx_conv_param_output.sha1: -------------------------------------------------------------------------------- 1 | 3e93585a4d1596d6aa4401eb244bfd5304c7f704 ref_avx_conv_fun_output 2 | -------------------------------------------------------------------------------- /tests/api_tests/sha_out_NCHW/ref_conv_output.sha1: -------------------------------------------------------------------------------- 1 | 0fc360f053e317aae82c3dded450c9b47d430a44 ref_conv_output 2 | -------------------------------------------------------------------------------- /tests/api_tests/sha_out_NHWC/ref_avx_conv_output.sha1: -------------------------------------------------------------------------------- 1 | ae26f3a8a1bde1f19be12eab97dfd6752ae81839 ref_avx_conv_output 2 | -------------------------------------------------------------------------------- /tests/api_tests/sha_out_NHWC/ref_avx_conv_param_output.sha1: -------------------------------------------------------------------------------- 1 | 4fe8c322792abb4bd0cdfd9f984f5fe81a01783d ref_avx_conv_param_output 2 | -------------------------------------------------------------------------------- /tests/api_tests/sha_out_NHWC/ref_conv_output.sha1: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/sha_out_NHWC/ref_conv_output.sha1 -------------------------------------------------------------------------------- /tests/api_tests/sha_out_NHWC/zendnn_avx_conv_output.sha1: -------------------------------------------------------------------------------- 1 | ae26f3a8a1bde1f19be12eab97dfd6752ae81839 zendnn_avx_conv_output 2 | -------------------------------------------------------------------------------- /tests/api_tests/sha_out_NHWC/zendnn_avx_conv_param_output.sha1: -------------------------------------------------------------------------------- 1 | 4fe8c322792abb4bd0cdfd9f984f5fe81a01783d zendnn_avx_conv_param_output 2 | -------------------------------------------------------------------------------- /tests/api_tests/sha_out_NHWC/zendnn_conv_output.sha1: -------------------------------------------------------------------------------- 1 | 76c21fa5d692c59f2d2560002a3945e2d0f47438 zendnn_conv_output 2 | -------------------------------------------------------------------------------- /tests/api_tests/test_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/test_utils.hpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_avx_conv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_avx_conv.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_avx_conv_maxpool.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_avx_conv_maxpool.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_avx_conv_param.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_avx_conv_param.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_avx_conv_param_direct.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_avx_conv_param_direct.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_avx_conv_param_fusion.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_avx_conv_param_fusion.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_avx_maxpool_blocked.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_avx_maxpool_blocked.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_block_size.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_block_size.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_conv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_conv_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_embedding_bag_benchmark.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_embedding_bag_benchmark.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_embedding_bag_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_embedding_bag_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_grp_embedding_bag_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_grp_embedding_bag_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_grp_embedding_mlp_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_grp_embedding_mlp_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_grp_matmul_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_grp_matmul_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_inference_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_inference_f32.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_lpgemm_layerwise.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_lpgemm_layerwise.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_lpgemm_layerwise_bf16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_lpgemm_layerwise_bf16.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_lpgemm_layerwise_s32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_lpgemm_layerwise_s32.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_lpgemm_layerwise_s8s8s16os.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_lpgemm_layerwise_s8s8s16os.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_lpgemm_layerwise_s8s8s32os.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_lpgemm_layerwise_s8s8s32os.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_lpgemm_network.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_lpgemm_network.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_lpgemm_network_bf16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_lpgemm_network_bf16.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_lpgemm_network_s32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_lpgemm_network_s32.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_lpgemm_network_s8s8s16os.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_lpgemm_network_s8s8s16os.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_lpgemm_network_s8s8s32os.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_lpgemm_network_s8s8s32os.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_matmulFusions_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_matmulFusions_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_matmul_bf16_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_matmul_bf16_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_matmul_direct_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_matmul_direct_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_matmul_gelu_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_matmul_gelu_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_matmul_generic_int8_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_matmul_generic_int8_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_matmul_int4_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_matmul_int4_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_matmul_int8_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_matmul_int8_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_matmul_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_matmul_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_matmul_weight_cache_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_matmul_weight_cache_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_multihead_attention_bf16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_multihead_attention_bf16.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_multihead_attention_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_multihead_attention_f32.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_quantize_dequantize_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_quantize_dequantize_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_sdpa_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_sdpa_test.cpp -------------------------------------------------------------------------------- /tests/api_tests/zendnn_training_f32.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amd/ZenDNN/HEAD/tests/api_tests/zendnn_training_f32.cpp --------------------------------------------------------------------------------