adding implicit gemm

[ROCm/composable_kernel commit: 84d9802d30]
This commit is contained in:
Chao Liu
2019-01-15 00:11:30 -06:00
parent 50256bbcfe
commit aa885b185d
15 changed files with 268 additions and 169 deletions

View File

@@ -1,5 +1,5 @@
#pragma once
#include "constant_tensor_descriptor.cuh"
#include "ConstantTensorDescriptor.cuh"
// optimized for scenario if p_in, p_wei, p_out are in register
template <class Float, class InDesc, class WeiDesc, class OutDesc>