dylanyunlong/project_6_layerwiseSplit_without_dp
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

under test, not sure no errors

Browse Source
This commit is contained in:
root
2026-09-02 07:03:56 +00:00
commit 43c43b491c
4211 changed files with 1013777 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
upstream_ref/sgemm_cuda/kernels.cuh Normal file
View File

@@ -0,0 +1,14 @@
#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"