Skip to content

GitLab

Commit 5b5a42a3 authored by wangshaojie6's avatar wangshaojie6
Browse files

reuse 256x256 in example

parent 099c470e
Hide whitespace changes
Inline Side-by-side
Showing with 8 additions and 8 deletions
example/11_conv2d_bwd_weight/conv2d_bwd_weight_xdl.cpp
View file @ 5b5a42a3
......@@ -44,22 +44,22 @@ using DeviceConvBwdWeightInstance = ck::tensor_operation::device::
WeiElementOp, // WeiElementwiseOperation
OutElementOp, // OutElementwiseOperation
256, // BlockSize
64, // MPerBlock
128, // NPerBlock
8, // K0PerBlock
256, // MPerBlock
256, // NPerBlock
4, // K0PerBlock
8, // K1
32, // MPerXdl
32, // NPerXdl
1, // MXdlPerWave
2, // NXdlPerWave
S<1, 8, 8, 4>, // ABlockTransferThreadClusterLengths_K0_M_K1
4, // MXdlPerWave
4, // NXdlPerWave
S<1, 4, 32, 2>, // ABlockTransferThreadClusterLengths_K0_M_K1
S<0, 3, 1, 2>, // ABlockTransferThreadClusterArrangeOrder
S<0, 2, 1, 3>, // ABlockTransferSrcAccessOrder
2, // ABlockTransferSrcVectorDim
8, // ABlockTransferSrcScalarPerVector
2, // ABlockTransferDstScalarPerVector_K1
4, // ABlockTransferDstScalarPerVector_K1
true, // ABlockLdsAddExtraM
S<1, 8, 16, 2>, // BBlockTransferThreadClusterLengths_K0_N_K1
S<1, 4, 32, 2>, // BBlockTransferThreadClusterLengths_K0_N_K1
S<0, 3, 1, 2>, // BBlockTransferThreadClusterArrangeOrder
S<0, 2, 1, 3>, // BBlockTransferSrcAccessOrder
2, // BBlockTransferSrcVectorDim
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment