├── .gitignore ├── LICENSE ├── Makefile ├── README.md ├── data ├── data.sh ├── myplot.m ├── res_0.txt ├── res_1.txt ├── res_10.txt ├── res_11.txt ├── res_2.txt ├── res_3.txt ├── res_4.txt ├── res_5.txt ├── res_6.txt ├── res_7.txt ├── res_8.txt └── res_9.txt ├── figures ├── Kernel1.png ├── Kernel10.png ├── Kernel11.png ├── Kernel2.png ├── Kernel3.png ├── Kernel4.png ├── Kernel5.png ├── Kernel6.png ├── Kernel7.png ├── Kernel8.png └── Kernel9.png ├── include ├── kernel1.cuh ├── kernel10.cuh ├── kernel11.cuh ├── kernel2.cuh ├── kernel3.cuh ├── kernel4.cuh ├── kernel5.cuh ├── kernel6.cuh ├── kernel7.cuh ├── kernel8.cuh └── kernel9.cuh ├── kernels.cuh ├── run.sh ├── test.cu ├── utils.cu └── utils.cuh /.gitignore: -------------------------------------------------------------------------------- 1 | sgemm_gpu -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/LICENSE -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/README.md -------------------------------------------------------------------------------- /data/data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/data.sh -------------------------------------------------------------------------------- /data/myplot.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/myplot.m -------------------------------------------------------------------------------- /data/res_0.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_0.txt -------------------------------------------------------------------------------- /data/res_1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_1.txt -------------------------------------------------------------------------------- /data/res_10.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_10.txt -------------------------------------------------------------------------------- /data/res_11.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_11.txt -------------------------------------------------------------------------------- /data/res_2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_2.txt -------------------------------------------------------------------------------- /data/res_3.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_3.txt -------------------------------------------------------------------------------- /data/res_4.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_4.txt -------------------------------------------------------------------------------- /data/res_5.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_5.txt -------------------------------------------------------------------------------- /data/res_6.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_6.txt -------------------------------------------------------------------------------- /data/res_7.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_7.txt -------------------------------------------------------------------------------- /data/res_8.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_8.txt -------------------------------------------------------------------------------- /data/res_9.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/data/res_9.txt -------------------------------------------------------------------------------- /figures/Kernel1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/figures/Kernel1.png -------------------------------------------------------------------------------- /figures/Kernel10.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/figures/Kernel10.png -------------------------------------------------------------------------------- /figures/Kernel11.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/figures/Kernel11.png -------------------------------------------------------------------------------- /figures/Kernel2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/figures/Kernel2.png -------------------------------------------------------------------------------- /figures/Kernel3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/figures/Kernel3.png -------------------------------------------------------------------------------- /figures/Kernel4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/figures/Kernel4.png -------------------------------------------------------------------------------- /figures/Kernel5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/figures/Kernel5.png -------------------------------------------------------------------------------- /figures/Kernel6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/figures/Kernel6.png -------------------------------------------------------------------------------- /figures/Kernel7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/figures/Kernel7.png -------------------------------------------------------------------------------- /figures/Kernel8.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/figures/Kernel8.png -------------------------------------------------------------------------------- /figures/Kernel9.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/figures/Kernel9.png -------------------------------------------------------------------------------- /include/kernel1.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/include/kernel1.cuh -------------------------------------------------------------------------------- /include/kernel10.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/include/kernel10.cuh -------------------------------------------------------------------------------- /include/kernel11.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/include/kernel11.cuh -------------------------------------------------------------------------------- /include/kernel2.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/include/kernel2.cuh -------------------------------------------------------------------------------- /include/kernel3.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/include/kernel3.cuh -------------------------------------------------------------------------------- /include/kernel4.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/include/kernel4.cuh -------------------------------------------------------------------------------- /include/kernel5.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/include/kernel5.cuh -------------------------------------------------------------------------------- /include/kernel6.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/include/kernel6.cuh -------------------------------------------------------------------------------- /include/kernel7.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/include/kernel7.cuh -------------------------------------------------------------------------------- /include/kernel8.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/include/kernel8.cuh -------------------------------------------------------------------------------- /include/kernel9.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/include/kernel9.cuh -------------------------------------------------------------------------------- /kernels.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/kernels.cuh -------------------------------------------------------------------------------- /run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/run.sh -------------------------------------------------------------------------------- /test.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/test.cu -------------------------------------------------------------------------------- /utils.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/utils.cu -------------------------------------------------------------------------------- /utils.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs/HEAD/utils.cuh --------------------------------------------------------------------------------