mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-20 12:59:49 +00:00
Clean up conv example, Instances, profiler and test (#324)
* convnd_fwd fp16 example
* update example
* update example
* update instance
* updating refernce conv
* update reference conv
* update conv fwd profiler
* update conv 1d and 3d instance
* update include path
* clean
* update profiler for conv bwd data and weight
* update conv bwd weight
* clean
* update conv example
* update profiler for conv bwd weight
* update ckprofiler for conv bwd data
* fix reference conv bwd data bug; update conv bwd data test
* update examples
* fix initialization issue
* update test for conv fwd
* clean
* clean
* remove test case too sensitive to error threshhold
* fix test
* clean
* fix build
* adding conv multiple d
* adding conv multiple D
* add matrix padder
* add gemm padding to convnd
* adding group conv
* update gemm multi-d
* refactor
* refactor
* refactor
* clean
* clean
* refactor
* refactor
* reorg
* add ds
* add bias
* clean
* add G
* adding group
* adding group
* adding group
* update Tensor
* clean
* update example
* update DeviceGemmMultipleD_Xdl_CShuffle
* update conv bwd-data and bwd-weight
* upate contraction example
* update gemm and batch gemm with e permute
* fix example build
* instance for grouped conv1d
* update example
* adding group conv instance
* update gemm bilinear instance
* update gemm+add+add+fastgelu instance
* update profiler
* update profiler
* update test
* update test and client example
* clean
* add grouped conv into profiler
* update profiler
* clean
* add test grouped conv, update all conv test to gtest
* update test
[ROCm/composable_kernel commit: 500fa99512]
This commit is contained in:
@@ -24,9 +24,9 @@ int profile_batched_gemm_reduce(int argc, char* argv[])
|
||||
F16_F16_F16_F32_F32, // 1
|
||||
};
|
||||
|
||||
if(!(argc == 15 || argc == 16))
|
||||
if(argc != 15)
|
||||
{
|
||||
printf("arg1: tensor operation (batched_gemm: BatchedGEMM+Reduce)\n");
|
||||
printf("arg1: tensor operation (batched_gemm_reduce: BatchedGEMM+Reduce)\n");
|
||||
printf("arg2: data type (0: fp32; 1: fp16)\n");
|
||||
printf("arg3: matrix layout (0: A[m, k] * B[k, n] = C[m, n];\n");
|
||||
printf(" 1: A[m, k] * B[n, k] = C[m, n];\n");
|
||||
@@ -37,7 +37,6 @@ int profile_batched_gemm_reduce(int argc, char* argv[])
|
||||
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);
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user