youngkingdom/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

address comments

Browse Source
This commit is contained in:
Masahiro Masuda
2022-03-17 16:13:29 +09:00
parent 247e3f2d22
commit 1550963c20
4 changed files with 3 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/30_wgrad_split_k/30_wgrad_split_k.cu
View File

@ -68,7 +68,6 @@ using ElementC = ElementOutput;
using ElementCompute = ElementComputeEpilogue;
using LayoutInputA = cutlass::layout::TensorNHWC;
using LayoutInputB = cutlass::layout::TensorNHWC;
using LayoutInputScaleBias = cutlass::layout::RowMajor;
using LayoutOutput = cutlass::layout::TensorNHWC;
// This code section describes whether you want to use tensor cores or regular SIMT cores on GPU SM
@ -113,7 +112,7 @@ using EpilogueOpGEMM = cutlass::epilogue::thread::LinearCombination<
// The epilogue functor for reduction. This is the one that is actually used.
using EpilogueOpReduction = cutlass::epilogue::thread::LinearCombination<
ElementOutput, // Data type of output matrix.
128 / cutlass::sizeof_bits<ElementOutput>::value, // The number of elements per vectorized.
128 / cutlass::sizeof_bits<ElementAccumulator>::value, // The number of elements per vectorized.
// memory access. This becomes the vector width of
// math instructions in the epilogue too.
ElementAccumulator, // Data type of accumulator

2
examples/30_wgrad_split_k/CMakeLists.txt
View File

@ -1,4 +1,4 @@
# Copyright (c) 2017-2021, NVIDIA CORPORATION. All rights reserved.
# Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without modification, are permitted
# provided that the following conditions are met:

1
examples/31_transposed_conv2d/31_transposed_conv2d.cu
View File

@ -68,7 +68,6 @@ using ElementC = ElementOutput;
using ElementCompute = ElementComputeEpilogue;
using LayoutInputA = TensorNHWC;
using LayoutInputB = TensorNHWC;
using LayoutInputScaleBias = cutlass::layout::RowMajor;
using LayoutOutput = TensorNHWC;
// This code section describes whether you want to use tensor cores or regular SIMT cores on GPU SM

2
examples/31_transposed_conv2d/CMakeLists.txt
View File

@ -1,4 +1,4 @@
# Copyright (c) 2017-2021, NVIDIA CORPORATION. All rights reserved.
# Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without modification, are permitted
# provided that the following conditions are met: