284804ac53
Sources: siboehm/SGEMM_CUDA → upstream_ref/sgemm_siboehm/ (25 files) wangzyon/NVIDIA_SGEMM_PRACTICE → upstream_ref/nvidia_sgemm_practice/ (23 files, filled gaps) edtallison/sgemm-cuda → upstream_ref/sgemm_edtallison/ (41 files) All files cat'd one by one from git clone (no --depth). These are the 3 public SGEMM repos that can compile on CUDA 10.2 + CoreX ivcore10. Key files for BI-V100 porting: kernel 10 (warp tiling) — already proven on device with WARPSIZE=64 kernel 11/12 (double buffering) — next optimization target sgemm.cu + runner.cu — complete build+benchmark harness CMakeLists.txt — build system reference
16 lines
335 B
Bash
16 lines
335 B
Bash
#!/bin/bash
|
|
|
|
# 全部kernel运行
|
|
rm ./test/test_kernel*
|
|
echo -n "test_kernel:"
|
|
for((i=0;i<=7;i++))
|
|
do
|
|
echo -n "${i}..."
|
|
file_name="./test/test_kernel_${i}.txt"
|
|
./sgemm ${i} >> ${file_name}
|
|
done
|
|
|
|
# 单个kernel运行
|
|
# kernel_num=$1
|
|
# file_name="test_kernel_${kernel_num}.txt"
|
|
# ./sgemm ${kernel_num} | tee ./test/${file_name} |