Skip to content

GitLab

Unverified Commit fc661f7d authored by Yifan Xiong's avatar Yifan Xiong Committed by GitHub
Browse files

Support GEMM benchmark on Hopper GPUs (#456) 

Support GEMM benchmark on Hopper GPUs.
parent 616e7a5a
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
superbench/benchmarks/micro_benchmarks/cuda_gemm_flops_performance.py
View file @ fc661f7d
...@@ -47,6 +47,8 @@ def __init__(self, name, parameters=''): ...@@ -47,6 +47,8 @@ def __init__(self, name, parameters=''):
# Skip FP64 for RTX Turing/Ampere and Tesla T4/GA10x due to very limited FP64 TFLOP rate # Skip FP64 for RTX Turing/Ampere and Tesla T4/GA10x due to very limited FP64 TFLOP rate
self.__kernel_map[7.5] = {k: self.__kernel_map[7.0][k] for k in self.__kernel_map[7.0] if 'fp64' not in k} self.__kernel_map[7.5] = {k: self.__kernel_map[7.0][k] for k in self.__kernel_map[7.0] if 'fp64' not in k}
self.__kernel_map[8.6] = {k: self.__kernel_map[8.0][k] for k in self.__kernel_map[8.0] if 'fp64' not in k} self.__kernel_map[8.6] = {k: self.__kernel_map[8.0][k] for k in self.__kernel_map[8.0] if 'fp64' not in k}
# Skip INT4 for Hopper due to no native CUDA/Tensor Cores
self.__kernel_map[9.0] = {k: self.__kernel_map[8.0][k] for k in self.__kernel_map[8.0] if 'int4_tc' not in k}
self.__parse_logline = [ self.__parse_logline = [
'gemm,cutlass_simt_dgemm_128x128_8x2', 'gemm,cutlass_simt_sgemm_128x128_8x2', 'gemm,cutlass_simt_dgemm_128x128_8x2', 'gemm,cutlass_simt_sgemm_128x128_8x2',
'gemm,cutlass_simt_hgemm_256x128_8x2', 'gemm,cutlass_tensorop_d884gemm_128x128_16x3', 'gemm,cutlass_simt_hgemm_256x128_8x2', 'gemm,cutlass_tensorop_d884gemm_128x128_16x3',
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment