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
14 lines
572 B
Plaintext
14 lines
572 B
Plaintext
#pragma once
|
|
|
|
#include "kernels/10_kernel_warptiling.cuh"
|
|
#include "kernels/11_kernel_double_buffering.cuh"
|
|
#include "kernels/12_kernel_double_buffering.cuh"
|
|
#include "kernels/1_naive.cuh"
|
|
#include "kernels/2_kernel_global_mem_coalesce.cuh"
|
|
#include "kernels/3_kernel_shared_mem_blocking.cuh"
|
|
#include "kernels/4_kernel_1D_blocktiling.cuh"
|
|
#include "kernels/5_kernel_2D_blocktiling.cuh"
|
|
#include "kernels/6_kernel_vectorize.cuh"
|
|
#include "kernels/7_kernel_resolve_bank_conflicts.cuh"
|
|
#include "kernels/8_kernel_bank_extra_col.cuh"
|
|
#include "kernels/9_kernel_autotuned.cuh" |