├── .gitignore ├── CMakeLists.txt ├── README.md ├── images ├── describe_kernel_1.png ├── describe_kernel_2.png ├── describe_kernel_3_1.png ├── describe_kernel_3_2.png ├── describe_kernel_4.png ├── describe_kernel_5.png ├── describe_kernel_6.png ├── describe_kernel_7.png ├── head.png ├── head.psd ├── 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_culas_vs_1.png └── kernel_culas_vs_7.png ├── plot.py ├── run.sh ├── sgemm ├── sgemm.cu ├── src ├── kernel.cuh ├── kernel │ ├── kernel_1.cuh │ ├── kernel_2.cuh │ ├── kernel_3.cuh │ ├── kernel_4.cuh │ ├── kernel_5.cuh │ ├── kernel_6.cuh │ └── kernel_7.cuh ├── utils.cu └── utils.cuh └── test ├── test_kernel_0.txt ├── test_kernel_1.txt ├── test_kernel_2.txt ├── test_kernel_3.txt ├── test_kernel_4.txt ├── test_kernel_5.txt ├── test_kernel_6.txt └── test_kernel_7.txt /.gitignore: -------------------------------------------------------------------------------- 1 | build/ -------------------------------------------------------------------------------- /CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/CMakeLists.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/README.md -------------------------------------------------------------------------------- /images/describe_kernel_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/describe_kernel_1.png -------------------------------------------------------------------------------- /images/describe_kernel_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/describe_kernel_2.png -------------------------------------------------------------------------------- /images/describe_kernel_3_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/describe_kernel_3_1.png -------------------------------------------------------------------------------- /images/describe_kernel_3_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/describe_kernel_3_2.png -------------------------------------------------------------------------------- /images/describe_kernel_4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/describe_kernel_4.png -------------------------------------------------------------------------------- /images/describe_kernel_5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/describe_kernel_5.png -------------------------------------------------------------------------------- /images/describe_kernel_6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/describe_kernel_6.png -------------------------------------------------------------------------------- /images/describe_kernel_7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/describe_kernel_7.png -------------------------------------------------------------------------------- /images/head.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/head.png -------------------------------------------------------------------------------- /images/head.psd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/head.psd -------------------------------------------------------------------------------- /images/kernel_1_vs_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/kernel_1_vs_2.png -------------------------------------------------------------------------------- /images/kernel_2_vs_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/kernel_2_vs_3.png -------------------------------------------------------------------------------- /images/kernel_3_vs_4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/kernel_3_vs_4.png -------------------------------------------------------------------------------- /images/kernel_4_vs_5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/kernel_4_vs_5.png -------------------------------------------------------------------------------- /images/kernel_5_vs_6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/kernel_5_vs_6.png -------------------------------------------------------------------------------- /images/kernel_6_vs_7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/kernel_6_vs_7.png -------------------------------------------------------------------------------- /images/kernel_culas_vs_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/kernel_culas_vs_1.png -------------------------------------------------------------------------------- /images/kernel_culas_vs_7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/images/kernel_culas_vs_7.png -------------------------------------------------------------------------------- /plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/plot.py -------------------------------------------------------------------------------- /run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/run.sh -------------------------------------------------------------------------------- /sgemm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/sgemm -------------------------------------------------------------------------------- /sgemm.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/sgemm.cu -------------------------------------------------------------------------------- /src/kernel.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/src/kernel.cuh -------------------------------------------------------------------------------- /src/kernel/kernel_1.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/src/kernel/kernel_1.cuh -------------------------------------------------------------------------------- /src/kernel/kernel_2.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/src/kernel/kernel_2.cuh -------------------------------------------------------------------------------- /src/kernel/kernel_3.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/src/kernel/kernel_3.cuh -------------------------------------------------------------------------------- /src/kernel/kernel_4.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/src/kernel/kernel_4.cuh -------------------------------------------------------------------------------- /src/kernel/kernel_5.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/src/kernel/kernel_5.cuh -------------------------------------------------------------------------------- /src/kernel/kernel_6.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/src/kernel/kernel_6.cuh -------------------------------------------------------------------------------- /src/kernel/kernel_7.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/src/kernel/kernel_7.cuh -------------------------------------------------------------------------------- /src/utils.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/src/utils.cu -------------------------------------------------------------------------------- /src/utils.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/src/utils.cuh -------------------------------------------------------------------------------- /test/test_kernel_0.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/test/test_kernel_0.txt -------------------------------------------------------------------------------- /test/test_kernel_1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/test/test_kernel_1.txt -------------------------------------------------------------------------------- /test/test_kernel_2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/test/test_kernel_2.txt -------------------------------------------------------------------------------- /test/test_kernel_3.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/test/test_kernel_3.txt -------------------------------------------------------------------------------- /test/test_kernel_4.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/test/test_kernel_4.txt -------------------------------------------------------------------------------- /test/test_kernel_5.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/test/test_kernel_5.txt -------------------------------------------------------------------------------- /test/test_kernel_6.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/test/test_kernel_6.txt -------------------------------------------------------------------------------- /test/test_kernel_7.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangzyon/NVIDIA_SGEMM_PRACTICE/HEAD/test/test_kernel_7.txt --------------------------------------------------------------------------------