ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-24 14:54:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add host API (#220)

Browse Source 
* Add host API

* manually rebase on develop

* clean

* manually rebase on develop

* exclude tests from all target

* address review comments

* update client app name

* fix missing lib name

* clang-format update

* refactor

* refactor

* refactor

* refactor

* refactor

* fix test issue

* refactor

* refactor

* refactor

* upate cmake and readme

Co-authored-by: Chao Liu <chao.liu2@amd.com>
This commit is contained in:
JD
2022-05-12 09:21:01 -05:00
committed by GitHub
parent 0f912e205e
commit cec69bc3bc
131 changed files with 1666 additions and 1089 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
profiler/src/profile_batched_gemm_reduce.cpp
View File

@@ -33,8 +33,8 @@ int profile_batched_gemm_reduce(int argc, char* argv[])
printf(" 3: A[k, m] * B[n, k] = C[m, n])\n");
printf("arg4: verification (0: no; 1: yes)\n");
printf("arg5: initialization (0: no init; 1: integer value; 2: decimal value)\n");
printf("arg8: print tensor value (0: no; 1: yes)\n");
printf("arg7: run kernel # of times (>1)\n");
printf("arg6: print tensor value (0: no; 1: yes)\n");
printf("arg7: time kernel (0=n0, 1=yes)\n");
printf("arg8 to 14: M, N, K, StrideA, StrideB, StrideC, BatchCount\n");
printf("arg15: split k into mulitiple batch\n");
exit(1);
@@ -45,7 +45,7 @@ int profile_batched_gemm_reduce(int argc, char* argv[])
const bool do_verification = std::stoi(argv[4]);
const int init_method = std::stoi(argv[5]);
const bool do_log = std::stoi(argv[6]);
const int nrepeat = std::stoi(argv[7]);
const bool time_kernel = std::stoi(argv[7]);
const int M = std::stoi(argv[8]);
const int N = std::stoi(argv[9]);
@@ -69,7 +69,7 @@ int profile_batched_gemm_reduce(int argc, char* argv[])
do_verification,
init_method,
do_log,
nrepeat,
time_kernel,
M,
N,
K,
@@ -91,7 +91,7 @@ int profile_batched_gemm_reduce(int argc, char* argv[])
do_verification,
init_method,
do_log,
nrepeat,
time_kernel,
M,
N,
K,
@@ -113,7 +113,7 @@ int profile_batched_gemm_reduce(int argc, char* argv[])
do_verification,
init_method,
do_log,
nrepeat,
time_kernel,
M,
N,
K,
@@ -135,7 +135,7 @@ int profile_batched_gemm_reduce(int argc, char* argv[])
do_verification,
init_method,
do_log,
nrepeat,
time_kernel,
M,
N,
K,