Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Hello_World 860ca1b3a9 | 8 months ago | |
---|---|---|
third_party | 1 year ago | |
.clang-format | 1 year ago | |
.gitmodules | 1 year ago | |
CMakeLists.txt | 1 year ago | |
README.md | 1 year ago | |
fc_relu.cu | 1 year ago | |
first_attempt.cu | 1 year ago | |
gemm.cu | 1 year ago | |
gemm_final.cu | 1 year ago | |
gemm_hide_smem_latency.cu | 1 year ago | |
gemm_naive.cu | 1 year ago | |
gemm_transpose_smem.cu | 1 year ago | |
gemm_use_128.cu | 1 year ago | |
gemm_use_smem.cu | 1 year ago | |
gemm_use_tile.cu | 8 months ago | |
util.cuh | 1 year ago |
Examples for beginners to write your own high-performance AI operators. We introduced optimizations tricks like using shared memory and pipeline rearrangement to maximize the throughput. We also provided an example for using CUTLASS to implement an FC + ReLU fused operator.
apt install libeigen3-dev
, or download fromapt install libgomp-dev
or apt install libomp-dev
for GCC or Clang separately.apt install libgflags-dev
, or download fromOnce you have installed the dependencies, you can use the following instruction to compile the project:
git clone git@github.com:openmlsys/openmlsys-cuda.git
cd openmlsys-cuda
git submodule init && git submodule sync
mkdir build && cd build
cmake ..
make -j4
first_attempt
: The naive implementationgemm
: Collection of implementations using different optimization tricksfc_relu
: Example for fusing FC and ReLU by using CUTLASSNo Description
Cuda Text
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》