adding implicit gemm v4 (nchw, kcyx)

This commit is contained in:
Chao Liu
2019-05-30 00:07:39 -05:00
parent 8c385cf5cf
commit 0a2657312e
16 changed files with 747 additions and 27 deletions

View File

@@ -14,6 +14,7 @@
#include "device_convolution_implicit_gemm_v1_nchw_cyxk_nkhw.hpp"
#include "device_convolution_implicit_gemm_v2_chwn_cyxk_khwn.hpp"
#include "device_convolution_implicit_gemm_v3_nchw_cyxk_nkhw.hpp"
#include "device_convolution_implicit_gemm_v4_nchw_kcyx_nkhw.hpp"
struct GeneratorTensor_1
{
@@ -629,6 +630,8 @@ int main(int argc, char* argv[])
device_convolution_implicit_gemm_v2_chwn_cyxk_khwn
#elif 1
device_convolution_implicit_gemm_v3_nchw_cyxk_nkhw
#elif 1
device_convolution_implicit_gemm_v4_nchw_kcyx_nkhw
#endif
(in_nchw_desc, in_nchw, wei_kcyx_desc, wei_kcyx, out_nkhw_desc, out_nkhw_device, nrepeat);