ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 06:49:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Revert "[CK-Tile] Add the API to load SGPR (#2878)" (#2904)

Browse Source 
This reverts commit 2cbbf5dcb3.
This commit is contained in:
asleepzzz
2025-09-24 05:33:51 +08:00
committed by GitHub
parent 959df2a155
commit f161b5b738
40 changed files with 167 additions and 273 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
include/ck_tile/ops/batched_transpose/kernel/batched_transpose_kernel.hpp
View File

@@ -84,9 +84,9 @@ struct BatchedTransposeKernel
static constexpr ck_tile::index_t VectorSizeOutput = Problem::VectorSizeOutput;
static constexpr ck_tile::index_t VectorStrideOutput = 1;
const auto iM = amd_wave_read_first_lane(blockIdx.x * kMPerBlock);
const auto iN = amd_wave_read_first_lane(blockIdx.y * kNPerBlock);
const auto offset = amd_wave_read_first_lane(blockIdx.z * kargs.height * kargs.width);
const auto iM = __builtin_amdgcn_readfirstlane(blockIdx.x * kMPerBlock);
const auto iN = __builtin_amdgcn_readfirstlane(blockIdx.y * kNPerBlock);
const auto offset = __builtin_amdgcn_readfirstlane(blockIdx.z * kargs.height * kargs.width);
const auto x_m_n = [&]() {
const auto x_dram_naive = make_naive_tensor_view<address_space_enum::global>(