mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 21:21:22 +00:00
Fix grouped_gemm_splitk kernels on MI300. (#694)
* replace amd_buffer_atomic_add with hip_atomic_add * fix grouped_gemm_splitk kernels on mi300 * fix syntax * revert experimental atomic_add changes --------- Co-authored-by: Jing Zhang <jizhan@amd.com>
This commit is contained in:
@@ -34,7 +34,8 @@ __global__ void
|
||||
kernel_grouped_gemm_xdl_splitk(const void CK_CONSTANT_ADDRESS_SPACE* gemm_descs_const,
|
||||
const index_t group_count)
|
||||
{
|
||||
#if(!defined(__HIP_DEVICE_COMPILE__) || defined(__gfx908__) || defined(__gfx90a__))
|
||||
#if(!defined(__HIP_DEVICE_COMPILE__) || defined(__gfx908__) || defined(__gfx90a__) || \
|
||||
defined(__gfx940__))
|
||||
constexpr index_t shared_size = GridwiseGemm::GetSharedMemoryNumberOfByte();
|
||||
__shared__ uint8_t p_shared[shared_size];
|
||||
|
||||
|
||||
Reference in New Issue
Block a user