Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "01ff2e14db1716e6dde9308d7fe87a9011b9178e"
Commit 84f162f9 authored by danyao12's avatar danyao12
Browse files

set occupancy to 1 to solve scratchdata and agpr issues

parent 95524dd8
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 2 deletions
include/ck/tensor_operation/gpu/device/impl/device_batched_multihead_attention_backward_xdl_cshuffle_v2.hpp
View file @ 84f162f9
......@@ -15,7 +15,7 @@
#include "ck/tensor_operation/gpu/device/masking_specialization.hpp"
#include "ck/tensor_operation/gpu/device/matrix_padder.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/grid/gridwise_batched_multihead_attention_backward_xdl_cshuffle_v3.hpp"
#include "ck/tensor_operation/gpu/grid/gridwise_batched_multihead_attention_backward_xdl_cshuffle_v2.hpp"
#include "ck/tensor_operation/operator_transform/transform_contraction_to_gemm.hpp"
#include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp"
......@@ -47,7 +47,8 @@ template <typename GridwiseGemm,
bool HasMainKBlockLoop>
__global__ void
#if CK_USE_LAUNCH_BOUNDS
__launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
// __launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
__launch_bounds__(CK_MAX_THREAD_PER_BLOCK, 1)
#endif
kernel_batched_gemm_softmax_gemm_xdl_cshuffle_v2(
const DataType* __restrict__ p_a_grid,
......
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