├── .gitignore ├── LICENSE ├── README.md ├── elementwise ├── README.md └── add.cu ├── example ├── cublas_example │ ├── CMakeLists.txt │ ├── README.md │ └── cublas_exmple.cu ├── cuda_info │ ├── README.md │ └── main.cu ├── hello_cuda │ ├── CMakeLists.txt │ ├── README.md │ └── hello_cuda.cu └── matrix_copy │ ├── CMakeLists.txt │ ├── README.md │ └── matrix_copy.cu ├── gemv ├── README.md └── sgemv_k32.cu ├── reduce ├── max │ ├── CMakeLists.txt │ ├── README.md │ ├── include │ │ └── utils.cuh │ ├── max.cu │ └── src │ │ └── utils.cu ├── softmax │ ├── CMakeLists.txt │ ├── README.md │ ├── include │ │ └── utils.cuh │ ├── softmax.cu │ └── src │ │ └── utils.cu ├── softmax_matrix │ ├── CMakeLists.txt │ ├── README.md │ ├── include │ │ └── utils.cuh │ ├── softmax_matrix.cu │ └── src │ │ └── utils.cu └── sum │ ├── CMakeLists.txt │ ├── README.md │ ├── include │ └── utils.cuh │ ├── src │ └── utils.cu │ └── sum.cu ├── sgemm ├── CMakeLists.txt ├── README.md ├── images │ ├── CUDA_draw.drawio │ ├── describe_kernel_2.png │ ├── double-buffer.png │ ├── image-1.png │ ├── image-3.png │ ├── image-4.png │ ├── image.png │ ├── image6-1.png │ ├── image6-2.png │ ├── image6-3.png │ ├── image7-1.png │ ├── image7-2.png │ ├── image7-3.png │ ├── image7-4.png │ ├── image7-5.png │ ├── kernel_1_vs_2.png │ ├── kernel_2_vs_3.png │ ├── kernel_3_vs_4.png │ ├── kernel_4_vs_5.png │ ├── kernel_5_vs_6.png │ ├── kernel_6_vs_7.png │ ├── kernel_cublas_vs_1.png │ ├── kernel_cublas_vs_2.png │ ├── kernel_cublas_vs_3.png │ ├── kernel_cublas_vs_4.png │ ├── kernel_cublas_vs_5.png │ ├── kernel_cublas_vs_6.png │ └── kernel_cublas_vs_7.png ├── include │ ├── kernel.cuh │ ├── kernel1.cuh │ ├── kernel2.cuh │ ├── kernel3.cuh │ ├── kernel4.cuh │ ├── kernel5.cuh │ ├── kernel6.cuh │ ├── kernel7.cuh │ └── utils.cuh ├── main.cu ├── src │ ├── kernel1.cu │ ├── kernel2.cu │ ├── kernel3.cu │ ├── kernel4.cu │ ├── kernel5.cu │ ├── kernel6.cu │ ├── kernel7.cu │ └── utils.cu ├── test │ ├── test_kernel_0.log │ ├── test_kernel_1.log │ ├── test_kernel_2.log │ ├── test_kernel_3.log │ ├── test_kernel_4.log │ ├── test_kernel_5.log │ ├── test_kernel_6.log │ └── test_kernel_7.log └── tools │ ├── plot.py │ └── test.sh └── transpose ├── CMakeLists.txt ├── README.md ├── assets └── sharedMem.png ├── include └── utils.cuh ├── src └── utils.cu └── transpose.cu /.gitignore: -------------------------------------------------------------------------------- 1 | # ide 2 | .*/ 3 | 4 | # cmake 5 | *build*/ -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/README.md -------------------------------------------------------------------------------- /elementwise/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/elementwise/README.md -------------------------------------------------------------------------------- /elementwise/add.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/elementwise/add.cu -------------------------------------------------------------------------------- /example/cublas_example/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/example/cublas_example/CMakeLists.txt -------------------------------------------------------------------------------- /example/cublas_example/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/example/cublas_example/README.md -------------------------------------------------------------------------------- /example/cublas_example/cublas_exmple.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/example/cublas_example/cublas_exmple.cu -------------------------------------------------------------------------------- /example/cuda_info/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/example/cuda_info/README.md -------------------------------------------------------------------------------- /example/cuda_info/main.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/example/cuda_info/main.cu -------------------------------------------------------------------------------- /example/hello_cuda/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/example/hello_cuda/CMakeLists.txt -------------------------------------------------------------------------------- /example/hello_cuda/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/example/hello_cuda/README.md -------------------------------------------------------------------------------- /example/hello_cuda/hello_cuda.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/example/hello_cuda/hello_cuda.cu -------------------------------------------------------------------------------- /example/matrix_copy/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/example/matrix_copy/CMakeLists.txt -------------------------------------------------------------------------------- /example/matrix_copy/README.md: -------------------------------------------------------------------------------- 1 | ref:cuda编程基础与实践 (樊哲勇) -------------------------------------------------------------------------------- /example/matrix_copy/matrix_copy.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/example/matrix_copy/matrix_copy.cu -------------------------------------------------------------------------------- /gemv/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/gemv/README.md -------------------------------------------------------------------------------- /gemv/sgemv_k32.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/gemv/sgemv_k32.cu -------------------------------------------------------------------------------- /reduce/max/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/max/CMakeLists.txt -------------------------------------------------------------------------------- /reduce/max/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/max/README.md -------------------------------------------------------------------------------- /reduce/max/include/utils.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/max/include/utils.cuh -------------------------------------------------------------------------------- /reduce/max/max.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/max/max.cu -------------------------------------------------------------------------------- /reduce/max/src/utils.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/max/src/utils.cu -------------------------------------------------------------------------------- /reduce/softmax/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/softmax/CMakeLists.txt -------------------------------------------------------------------------------- /reduce/softmax/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/softmax/README.md -------------------------------------------------------------------------------- /reduce/softmax/include/utils.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/softmax/include/utils.cuh -------------------------------------------------------------------------------- /reduce/softmax/softmax.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/softmax/softmax.cu -------------------------------------------------------------------------------- /reduce/softmax/src/utils.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/softmax/src/utils.cu -------------------------------------------------------------------------------- /reduce/softmax_matrix/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/softmax_matrix/CMakeLists.txt -------------------------------------------------------------------------------- /reduce/softmax_matrix/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/softmax_matrix/README.md -------------------------------------------------------------------------------- /reduce/softmax_matrix/include/utils.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/softmax_matrix/include/utils.cuh -------------------------------------------------------------------------------- /reduce/softmax_matrix/softmax_matrix.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/softmax_matrix/softmax_matrix.cu -------------------------------------------------------------------------------- /reduce/softmax_matrix/src/utils.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/softmax_matrix/src/utils.cu -------------------------------------------------------------------------------- /reduce/sum/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/sum/CMakeLists.txt -------------------------------------------------------------------------------- /reduce/sum/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/sum/README.md -------------------------------------------------------------------------------- /reduce/sum/include/utils.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/sum/include/utils.cuh -------------------------------------------------------------------------------- /reduce/sum/src/utils.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/sum/src/utils.cu -------------------------------------------------------------------------------- /reduce/sum/sum.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/reduce/sum/sum.cu -------------------------------------------------------------------------------- /sgemm/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/CMakeLists.txt -------------------------------------------------------------------------------- /sgemm/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/README.md -------------------------------------------------------------------------------- /sgemm/images/CUDA_draw.drawio: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/CUDA_draw.drawio -------------------------------------------------------------------------------- /sgemm/images/describe_kernel_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/describe_kernel_2.png -------------------------------------------------------------------------------- /sgemm/images/double-buffer.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/double-buffer.png -------------------------------------------------------------------------------- /sgemm/images/image-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image-1.png -------------------------------------------------------------------------------- /sgemm/images/image-3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image-3.png -------------------------------------------------------------------------------- /sgemm/images/image-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image-4.png -------------------------------------------------------------------------------- /sgemm/images/image.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image.png -------------------------------------------------------------------------------- /sgemm/images/image6-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image6-1.png -------------------------------------------------------------------------------- /sgemm/images/image6-2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image6-2.png -------------------------------------------------------------------------------- /sgemm/images/image6-3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image6-3.png -------------------------------------------------------------------------------- /sgemm/images/image7-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image7-1.png -------------------------------------------------------------------------------- /sgemm/images/image7-2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image7-2.png -------------------------------------------------------------------------------- /sgemm/images/image7-3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image7-3.png -------------------------------------------------------------------------------- /sgemm/images/image7-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image7-4.png -------------------------------------------------------------------------------- /sgemm/images/image7-5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/image7-5.png -------------------------------------------------------------------------------- /sgemm/images/kernel_1_vs_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_1_vs_2.png -------------------------------------------------------------------------------- /sgemm/images/kernel_2_vs_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_2_vs_3.png -------------------------------------------------------------------------------- /sgemm/images/kernel_3_vs_4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_3_vs_4.png -------------------------------------------------------------------------------- /sgemm/images/kernel_4_vs_5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_4_vs_5.png -------------------------------------------------------------------------------- /sgemm/images/kernel_5_vs_6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_5_vs_6.png -------------------------------------------------------------------------------- /sgemm/images/kernel_6_vs_7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_6_vs_7.png -------------------------------------------------------------------------------- /sgemm/images/kernel_cublas_vs_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_cublas_vs_1.png -------------------------------------------------------------------------------- /sgemm/images/kernel_cublas_vs_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_cublas_vs_2.png -------------------------------------------------------------------------------- /sgemm/images/kernel_cublas_vs_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_cublas_vs_3.png -------------------------------------------------------------------------------- /sgemm/images/kernel_cublas_vs_4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_cublas_vs_4.png -------------------------------------------------------------------------------- /sgemm/images/kernel_cublas_vs_5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_cublas_vs_5.png -------------------------------------------------------------------------------- /sgemm/images/kernel_cublas_vs_6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_cublas_vs_6.png -------------------------------------------------------------------------------- /sgemm/images/kernel_cublas_vs_7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/images/kernel_cublas_vs_7.png -------------------------------------------------------------------------------- /sgemm/include/kernel.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/include/kernel.cuh -------------------------------------------------------------------------------- /sgemm/include/kernel1.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/include/kernel1.cuh -------------------------------------------------------------------------------- /sgemm/include/kernel2.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/include/kernel2.cuh -------------------------------------------------------------------------------- /sgemm/include/kernel3.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/include/kernel3.cuh -------------------------------------------------------------------------------- /sgemm/include/kernel4.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/include/kernel4.cuh -------------------------------------------------------------------------------- /sgemm/include/kernel5.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/include/kernel5.cuh -------------------------------------------------------------------------------- /sgemm/include/kernel6.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/include/kernel6.cuh -------------------------------------------------------------------------------- /sgemm/include/kernel7.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/include/kernel7.cuh -------------------------------------------------------------------------------- /sgemm/include/utils.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/include/utils.cuh -------------------------------------------------------------------------------- /sgemm/main.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/main.cu -------------------------------------------------------------------------------- /sgemm/src/kernel1.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/src/kernel1.cu -------------------------------------------------------------------------------- /sgemm/src/kernel2.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/src/kernel2.cu -------------------------------------------------------------------------------- /sgemm/src/kernel3.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/src/kernel3.cu -------------------------------------------------------------------------------- /sgemm/src/kernel4.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/src/kernel4.cu -------------------------------------------------------------------------------- /sgemm/src/kernel5.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/src/kernel5.cu -------------------------------------------------------------------------------- /sgemm/src/kernel6.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/src/kernel6.cu -------------------------------------------------------------------------------- /sgemm/src/kernel7.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/src/kernel7.cu -------------------------------------------------------------------------------- /sgemm/src/utils.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/src/utils.cu -------------------------------------------------------------------------------- /sgemm/test/test_kernel_0.log: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/test/test_kernel_0.log -------------------------------------------------------------------------------- /sgemm/test/test_kernel_1.log: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/test/test_kernel_1.log -------------------------------------------------------------------------------- /sgemm/test/test_kernel_2.log: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/test/test_kernel_2.log -------------------------------------------------------------------------------- /sgemm/test/test_kernel_3.log: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/test/test_kernel_3.log -------------------------------------------------------------------------------- /sgemm/test/test_kernel_4.log: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/test/test_kernel_4.log -------------------------------------------------------------------------------- /sgemm/test/test_kernel_5.log: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/test/test_kernel_5.log -------------------------------------------------------------------------------- /sgemm/test/test_kernel_6.log: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/test/test_kernel_6.log -------------------------------------------------------------------------------- /sgemm/test/test_kernel_7.log: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/test/test_kernel_7.log -------------------------------------------------------------------------------- /sgemm/tools/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/tools/plot.py -------------------------------------------------------------------------------- /sgemm/tools/test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/sgemm/tools/test.sh -------------------------------------------------------------------------------- /transpose/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/transpose/CMakeLists.txt -------------------------------------------------------------------------------- /transpose/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/transpose/README.md -------------------------------------------------------------------------------- /transpose/assets/sharedMem.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/transpose/assets/sharedMem.png -------------------------------------------------------------------------------- /transpose/include/utils.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/transpose/include/utils.cuh -------------------------------------------------------------------------------- /transpose/src/utils.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/transpose/src/utils.cu -------------------------------------------------------------------------------- /transpose/transpose.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Tongkaio/CUDA_Kernel_Samples/HEAD/transpose/transpose.cu --------------------------------------------------------------------------------