Use faster device op config for example '1xHxW_fp16'

cc8aee3b · Po-Yen, Chen · c1f605b9 · cc8aee3b
Commit cc8aee3b authored Sep 13, 2022 by Po-Yen, Chen
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

example/37_permute/permute_1xHxW_fp16.cpp example/37_permute/permute_1xHxW_fp16.cpp +1 -1

No files found.
--- a/example/37_permute/permute_1xHxW_fp16.cpp
+++ b/example/37_permute/permute_1xHxW_fp16.cpp
@@ -12,7 +12,7 @@ using DevicePermuteInstance = ck::tensor_operation::device::DevicePermute
 // ######|      Type|      Type|   Operation|       |  Size| Block| Block| Block| LdsExtraW| ThreadClusterLengths| ThreadClusterArrangeOrder| VectorDim| VectorDim| ScalarPerVector| ScalarPerVector|
 // ######|          |          |            |       |      |      |      |      |          |                     |                          |          |          |                |                |
 // ######|          |          |            |       |      |      |      |      |          |                     |                          |          |          |                |                |
-         < ADataType, BDataType, PassThrough,      3,   256,    16,    32,    32,         0,         S<1, 16, 16>,                S<0, 1, 2>,         2,         1,               1,               1>;
+         < ADataType, BDataType, PassThrough,      3,   256,     1,    32,    32,         3,         S<1, 32,  8>,                S<0, 1, 2>,         2,         1,               2,               1>;
 // clang-format on
 #include "run_permute_example.inc"