7cfa87b5ac
siboehm/SGEMM_CUDA (19 files):
siboehm_sgemm.cu, siboehm_runner.cu, siboehm_runner.cuh, siboehm_kernels.cuh
siboehm_cuBLAS_sgemm.cu, siboehm_simplest_kernel.cu, siboehm_CMakeLists.txt
siboehm_{1_naive..12_kernel_double_buffering}.cuh
wangzyon/NVIDIA_SGEMM_PRACTICE (12 files):
wangzyon_sgemm.cu, wangzyon_utils.cu, wangzyon_utils.cuh, wangzyon_kernel.cuh
wangzyon_CMakeLists.txt, wangzyon_kernel_{1..7}.cuh
edtallison/sgemm-cuda (19 files):
edtallison_sgemm.cu, edtallison_runner.cu, edtallison_runner.cuh
edtallison_kernels.cuh, edtallison_cuBLAS_sgemm.cu, edtallison_simplest_kernel.cu
edtallison_CMakeLists.txt, edtallison_{01_naive..12_kernel_double_buffering}.cuh
cat_files/ total: 25 → 75 files
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" |