Skip to content

GitLab

Commit 5afba5aa authored by Adam Osewski's avatar Adam Osewski
Browse files

Fix typo.

parent 1f6787d1
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle_tile_loop.hpp
View file @ 5afba5aa
...@@ -375,7 +375,7 @@ struct DeviceGroupedGemmXdlSplitKCShuffle : public DeviceGroupedGemmSplitK<ALayo ...@@ -375,7 +375,7 @@ struct DeviceGroupedGemmXdlSplitKCShuffle : public DeviceGroupedGemmSplitK<ALayo
static constexpr int BLOCK_SUBSCRIPTION_FACTOR = 1; static constexpr int BLOCK_SUBSCRIPTION_FACTOR = 1;
static constexpr int BLOCK_WAVES = BlockSize / get_warp_size(); static constexpr int BLOCK_WAVES = BlockSize / get_warp_size();
// assume we want to have at most 2 waves per SIMD // assume we want to have at most 2 waves per SIMD
static constexpr int CU_BLOCKS = math::intiger_divide_floor(8, BLOCK_WAVES); static constexpr int CU_BLOCKS = math::integer_divide_floor(8, BLOCK_WAVES);
float Run(const Argument& arg, const StreamConfig& stream_config = StreamConfig{}) float Run(const Argument& arg, const StreamConfig& stream_config = StreamConfig{})
{ {
......
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