mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-17 03:19:48 +00:00
Add MoE & FP8 Blockscale WP Kernels for GFX950 (#2297)
* [fix] align v3 gufusion pipeline
* fix device kernel selection.
* Add .co direct asm support by CK_USE_ASM_MOE_STAGE2_BLOCKSCALE
* experimental optimization for scale load in blkscale gemm
* Add asm for no-loop v3_128x128x128
* fix bugs
* tune fp8 example
* Update v1_128x128x128 to 2x2 instead of 4x1
* wip
* add warmup to asm launch
* wip2
* 16x16 function merged to moe
* temp save, a performant version.
* wip3
* Update .co binary to 16x16
* 16x16x128 correct; 64x64x128 failed
* update
* use mem_op::set when topk=1
* add mx fp8 b_preshuffle support, function not yet tested.
* Spilt the fp4 target. Fix the known bugs. 128x128x128 sanity checked; remove prints
* some fixes
* fix update
* remove some unnecessary hacky; enable 256x256x256 tilesize
* update for function debug
* Add pipeline v3. Have some runtime issue and register spill
* Fix pipe v3 correctness issue
* remove unnecessary hacky
* clang format
* fix a bug
* fix the bug, functional test passed
* tempsave; buggy at passed 4 e8m0 to scaled mfma
* added fp4_bpreshuffle example, build failures
* fixed some bugs
* implement shuffled scale mxfp4gemm, blocker: opsel not effect
* hotfix
* fix bugs, build passed
* (M, N, K)=(128, 128, 128) function failed.
* temp save for gemm1. Function not ready
* fix compile error. Gemm2 pass. Gemm1 WIP
* fix bug for a lds read
* update moe
* Compile pass. Gemm1 function WIP
* update moe
* fix fp8; fix even/odd
* tempsave
* update moe
* Revert "update"
This reverts commit c7d79dcb672616d9bc0fd9958f714fc80e7c84fd.
* Revert "use mem_op::set when topk=1"
This reverts commit 8c7772860735001a51421e7b6d0a28f6676d6c40.
* Add v3 128x128x128_4x4_16x16.co for gfx950
* temp cmake flag suppression for aiter test
* add code for mxfp4 gemm, blockscale not supported yet
* gemm1 up-only pass. GU WIP
* function pass with inline asm hacky
* revert unexpected file change
* updated and build passed
* update CE elementOP
* added code for debug
* Gemm1 GUFusion function pass. Perf WIP
* Fix fp8/bf8; remove duplicated code
* disable the scheduler in v3; bring it back when compiler feature ready.
* update moe v1 pipeline
* Add gemm1 v1 32x128x128
* remove schedule barrier
* updated
* Fix fp8/bf8 B-row
* mfma using asm, device result correct, host result need to check
* gemm1 v3 64x128x128 debug
* fix cpu ref
* a/b thread_desc stride fix
* Use random scale for init1
* 16x16x128 input size blockscale function passed
* fix blockscale gemm bug
* tempsave. Almost all instances passed.
* v1 fix for mi350.
* temp save
* debug save
* update debug
* fix the bug, 128x128x256 tile function passed
* v3
* rename moe block selector and pipeline
* Add gemm1 v1
* Add gemm1 v1 to selector
* added mx moe block v3 support, function passed
* compile error fix
* Improve the pipeline
* Pack e8m0 as int32_t
* v1 compile pass. Function not ready
* debug synchronize issue over different GPU/ROCm
* minor fix
* Add profiler filter
* Add f4 ckProfiler
* Fix example compile error
* Add f4 profiler examples
* tempsave
* v1 function pass.
* v3 function pass
* align file and function name
* mx_moe_fp4 ready for aiter with clang-format.
* modify the way we represent fp4
* generalize the pipeline scheduling.
* init moe mx f4 scale shuffle
* Cmakelist diable compiler-bound flags
* mx_fp4 default parameter change
* Moe blockscale gemm1&gemm2 asm support for aiter. Suppression cmkae flag til new compler.
* update code
* tempsave; modify the way we represent fp4
* generalize the pipeline scheduling.
* Add gemm1 gfx942 .co support
* updated code, build passed.
* Update gemm2 asm with latest compiler flag
* Fix mx f4 ckProfiler
* Fix blockwise gemm mx v1
* lds conflict free + buffer load lds
* Add gemm2 v3 64x128x128
* fix a, b scale loading bugs, a, b scale loading now correctly
* Add gemm2 v3 64x128x128
* commit with debug info
* fix fp4 profiler
* Add mx fp4 pileline v1 instances
* Fix v2 topk_weight cal. Add silu asm.
* v2 tok_weight WIP
* init mx fp4 B no preshuffle version
* tempsave. compile pass, function wrong
* enable fp4 moe no weigth preshuffle, function pass
* update the TFlops calculation in the example
* Add gemm2 64x128x128 asm. Fix BF16 ref.
* fix 2 typos in fp4_preshuffle
* Better kernel selection in device classes
* correct preShuffleBuffer
we should used packed k to do shuffle.
* lds conflict free + buffer load lds
* optimize offset math in dma
* Fix fp4 ckProfiler
* Fix MX MFMA tests
* fix f4 pipeline issues
* gemm1 func pass
* update mx moe gemm1_bns tile size to 64x128x256
* update mx moe gemm1 gemm2 TF and BW calculation
* fix typo
* temp save
* Fix example_gemm_mx build
* rename the block pipeline
* correct a typo in tail
* Add rotating to mx examples
* fix the correctness issue
* Fix v1; use M padding
* Add NT flag to B/BScale buffer
* Merge gemm_mx_common.hpp
* temp save, 4.4~4.5
* Fix 'Merge gemm_mx_common.hpp'
* refactor the pipeline
* Pad the M for scale buffer unconditionaly
* update MX moe GEMM1 hotloopscheduling
* change the gemm1 tile from 64x128x128 to 128x64x128
* Unconditional Ascale padding
* Pad shuffled a scale only
* pad ascale
* add vmcnt guard for async copy
* Profiler add f4 wp
* Merge preshuffle device
* Add more fp4 wp instances
* Fix do_weight in gemm1. Fix cshuffle_datatype. Clang-format
* Clang-format after 2 merges
* Remove rocm6.3 workaround flags and macro
* Fix fp8 config
* Fix bf8 config
* flag and barrier fix for copmiler branch MainOpSelV3
* Add fp8 profiler instances
* Remove debug infos; Enable flags for blockscale f8
* No asm ver. for merging moe blocksale fp8 into mainline
* update the flag name for f8blockscale
* recover example
* fix performance bug of bpreshuffle f8 gemm
* clang format, remove single rate mfma restriction for f8
* remove single rate mfma restriction for f8 blockscale gemm
* Fix moe blockscale gemm1 barrier 0x800 for new compiler
* add pipeline v1 for MOE Gemm2
* Use v1 pipeline for example_moe_gemm2_xdl_mx_fp4_bns
* Fix OOB; add MB96 instances
* remove unnecessary files
* fix the cmake issue
* Enable splitk for mxfp4; clang format;
* Generate random tensor values with multiple threads
* Use packed_size_v for A/BPackedSize
* Fix warning
* Fix target_compile_options for disabled target on gfx942
* fix moe pki4 on gfx950
* doc the kGroup definition
* Fix ThreadwiseTensorSliceTransfer_v4::Run (Fuse scale)
* Refactor thread_copy_lds_direct_load; fix gfx942 direct lds load example; fix f16_pki4 example
* Fix unknown compiler flag
* fix two failed examples.
* fix some failure tile size in gfx950 universal gemm. fix test_gemm_fp16
* workaround fix for test_gemm_f32; * We have very limited support for lds direct load if input matrix is not K major
* fix test_gemm_splitk;
* Fix compile for mx_mfma_op
* add mfma selection logic for multipled_v3
* Clean up
* Fix device gemm mx link error
* improve the global atomic pattern
* Revert unnecessary copyright updates
* restore minimum_occupancy logic
* Avoid data race in moe gemm2 ref
* Build fp8 gemm_multiply_multiply and moe only on gfx94/95
* update the instance in device_mx_gemm
* Resolve comments
* Copyright 2025
* Remove unused code
* fix library linking issue
---------
Co-authored-by: OscarXu <huaiguxu@amd.com>
Co-authored-by: lalala-sh <Jiaxing.Wen@amd.com>
Co-authored-by: mtgu0705 <mtgu@amd.com>
Co-authored-by: aska-0096 <haocwang@amd.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: valarLip <340077269@qq.com>
Co-authored-by: feifei14119 <feiw@amd.com>
Co-authored-by: Lin, Qun <qlin@amd.com>
Co-authored-by: Andriy Roshchenko <andriy.roshchenko@amd.com>
Co-authored-by: joye <joye@amd.com>
Co-authored-by: asleepzzz <hanwen.chang@amd.com>
[ROCm/composable_kernel commit: 37554c31e8]
This commit is contained in:
Yi DING
@@ -0,0 +1,16 @@
|
||||
# ONLY XDL_KERNELS
|
||||
set(GEMM_BLOCKSCALE_WP_INSTANCES)
|
||||
|
||||
list(APPEND GEMM_BLOCKSCALE_WP_INSTANCES
|
||||
device_gemm_blockscale_wp_xdl_f8_f8_bf16/device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128_comp_default_instance.cpp
|
||||
device_gemm_blockscale_wp_xdl_f8_f8_bf16/device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128_comp_kpadding_instance.cpp
|
||||
device_gemm_blockscale_wp_xdl_f8_f8_bf16/device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128_mem_v1_default_instance.cpp
|
||||
device_gemm_blockscale_wp_xdl_f8_f8_bf16/device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128_mem_v1_kpadding_instance.cpp
|
||||
)
|
||||
|
||||
set_source_files_properties(device_gemm_blockscale_wp_xdl_f8_f8_bf16/device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1;-mllvm;--slp-threshold=-32;-mllvm;--misched-bottomup=1")
|
||||
set_source_files_properties(device_gemm_blockscale_wp_xdl_f8_f8_bf16/device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1;-mllvm;--slp-threshold=-32;-mllvm;--misched-bottomup=1")
|
||||
set_source_files_properties(device_gemm_blockscale_wp_xdl_f8_f8_bf16/device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128_mem_v1_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1;-mllvm;--slp-threshold=-32;-mllvm;--misched-bottomup=1")
|
||||
set_source_files_properties(device_gemm_blockscale_wp_xdl_f8_f8_bf16/device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128_mem_v1_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1;-mllvm;--slp-threshold=-32;-mllvm;--misched-bottomup=1")
|
||||
|
||||
add_instance_library(device_gemm_blockscale_wp_instance ${GEMM_BLOCKSCALE_WP_INSTANCES})
|
||||
@@ -0,0 +1,89 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
|
||||
#include "ck/ck.hpp"
|
||||
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
|
||||
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
|
||||
#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle_v3_blockscale_bpreshuffle.hpp"
|
||||
|
||||
#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
|
||||
|
||||
namespace ck {
|
||||
namespace tensor_operation {
|
||||
namespace device {
|
||||
namespace instance {
|
||||
|
||||
using F8 = f8_t;
|
||||
using BF16 = bhalf_t;
|
||||
using F32 = float;
|
||||
|
||||
using Row = tensor_layout::gemm::RowMajor;
|
||||
using Col = tensor_layout::gemm::ColumnMajor;
|
||||
|
||||
template <index_t... Is>
|
||||
using S = Sequence<Is...>;
|
||||
|
||||
using PassThrough = element_wise::PassThrough;
|
||||
using PassThrough = element_wise::PassThrough;
|
||||
|
||||
static constexpr auto GemmDefault = GemmSpecialization::Default;
|
||||
static constexpr auto GemmKPadding = GemmSpecialization::KPadding;
|
||||
static constexpr auto GemmMNPadding = GemmSpecialization::MNPadding;
|
||||
static constexpr auto GemmMNKPadding = GemmSpecialization::MNKPadding;
|
||||
|
||||
static constexpr auto Intrawave = BlockGemmPipelineScheduler::Intrawave;
|
||||
|
||||
template <GemmSpecialization GemmSpec>
|
||||
using device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_1_128_128_comp_instances = std::tuple<
|
||||
// clang-format off
|
||||
//################################################| ALayout| BLayout| DsLayout| ELayout| AData| BData| DsData| EData| AccData| Cshuffle| A| B| C| GEMM| Block| Scale| Scale| Scale| MPer| NPer| KPer| AK1| BK1|MPer| NPer| MXdl| NXdl| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| Block-wiseGemm| Block-wiseGemm|
|
||||
//################################################| | | | | Type| Type| Type| Type| Type| Type| Elementwise| Elementwise| Elementwise|Specialization| Size| Block| Block| Block| Block| Block| Block| | | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector| Pipeline| Pipeline|
|
||||
//################################################| | | | | | | | | | | Operation| Operation| Operation| | | M| N| K| | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl| _NWaveNPerXdl| Scheduler| Verision|
|
||||
//################################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
||||
|
||||
// Compute friendly
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8, F32, F8, F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 128, 128, 128, 16, 16, 16, 16, 8, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8, F32, F8, F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 64, 128, 128, 16, 16, 16, 16, 4, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8, F32, F8, F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 64, 64, 128, 16, 16, 16, 16, 4, 1, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v3, F8>
|
||||
// clang-format on
|
||||
>;
|
||||
|
||||
template <BlockGemmPipelineScheduler BlkGemmPipeSched, GemmSpecialization GemmSpec>
|
||||
using device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_1_128_128_mem_instances = std::tuple<
|
||||
// clang-format off
|
||||
//#######################################################| ALayout| BLayout| DsLayout| ELayout|AData | BData| DsData| EData| AccData| Cshuffle| A| B| C| GEMM| Block| Scale| Scale| Scale| MPer| NPer| KPer| AK1| BK1|MPer| NPer| MXdl| NXdl| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| Block-wiseGemm| Block-wiseGemm|
|
||||
//#######################################################| | | | | Type | Type| Type| Type| Type| Type| Elementwise| Elementwise| Elementwise|Specialization| Size| Block| Block| Block| Block| Block| Block| | | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector| Pipeline| Pipeline|
|
||||
//#######################################################| | | | | | | | | | | Operation| Operation| Operation| | | M| N| K| | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl| _NWaveNPerXdl| Scheduler| Verision|
|
||||
//#######################################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
||||
|
||||
// Memory friendly
|
||||
// 16x
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 16, 256, 128, 8, 16, 16, 16, 1, 4, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 1, 2, S<1, 16, 1, 16>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 16, 128, 128, 8, 16, 16, 16, 1, 2, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 1, 2, S<1, 16, 1, 16>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 16, 64, 128, 8, 16, 16, 16, 1, 1, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 1, 1, S<1, 16, 1, 16>, S<4>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 16, 128, 256, 16, 16, 16, 16, 1, 2, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 1, 2, S<1, 16, 1, 16>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 16, 64, 256, 16, 16, 16, 16, 1, 1, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 1, 1, S<1, 16, 1, 16>, S<4>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
//32x
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 32, 256, 128, 16, 16, 16, 16, 2, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 32, 128, 128, 16, 16, 16, 16, 2, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 32, 64, 128, 16, 16, 16, 16, 2, 1, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 32, 128, 256, 16, 16, 16, 16, 2, 2, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 32, 64, 256, 16, 16, 16, 16, 2, 1, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
//48x
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 48, 256, 128, 8, 16, 16, 16, 3, 4, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 1, 2, S<1, 16, 1, 16>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 48, 128, 128, 8, 16, 16, 16, 3, 2, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 1, 2, S<1, 16, 1, 16>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 48, 64, 128, 8, 16, 16, 16, 3, 1, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 1, 1, S<1, 16, 1, 16>, S<4>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 48, 128, 256, 16, 16, 16, 16, 3, 2, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 1, 2, S<1, 16, 1, 16>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 48, 64, 256, 16, 16, 16, 16, 3, 1, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 1, 1, S<1, 16, 1, 16>, S<4>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
//64x
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 64, 256, 128, 16, 16, 16, 16, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 64, 128, 128, 16, 16, 16, 16, 4, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 64, 64, 128, 16, 16, 16, 16, 4, 1, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 64, 128, 256, 16, 16, 16, 16, 4, 2, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>,
|
||||
DeviceGemmMultiD_BlockScale_Xdl_CShuffle_V3_BPreshuffle< Row, Col, Tuple<>, Row, F8,F32, F8,F32, Tuple<>, BF16, F32, F32, PassThrough, PassThrough, PassThrough, GemmSpec, 256, 1, 128, 128, 64, 64, 256, 16, 16, 16, 16, 4, 1, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<16, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 2, 1, S<1, 32, 1, 8>, S<8>, BlkGemmPipeSched, BlockGemmPipelineVersion::v1, F8>
|
||||
// clang-format on
|
||||
>;
|
||||
} // namespace instance
|
||||
} // namespace device
|
||||
} // namespace tensor_operation
|
||||
} // namespace ck
|
||||
@@ -0,0 +1,38 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
|
||||
#include "device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128.hpp"
|
||||
|
||||
namespace ck {
|
||||
namespace tensor_operation {
|
||||
namespace device {
|
||||
namespace instance {
|
||||
|
||||
void add_device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_1_128_128_comp_default_instances(
|
||||
std::vector<std::unique_ptr<DeviceGemmMultipleD_BlockScale_BPreshuffle<Row,
|
||||
Col,
|
||||
Tuple<>,
|
||||
Row,
|
||||
F8,
|
||||
F32,
|
||||
F8,
|
||||
F32,
|
||||
Tuple<>,
|
||||
BF16,
|
||||
1,
|
||||
128,
|
||||
128,
|
||||
PassThrough,
|
||||
PassThrough,
|
||||
PassThrough>>>&
|
||||
instances)
|
||||
{
|
||||
add_device_operation_instances(
|
||||
instances,
|
||||
device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_1_128_128_comp_instances<GemmDefault>{});
|
||||
}
|
||||
|
||||
} // namespace instance
|
||||
} // namespace device
|
||||
} // namespace tensor_operation
|
||||
} // namespace ck
|
||||
@@ -0,0 +1,38 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
|
||||
#include "device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128.hpp"
|
||||
|
||||
namespace ck {
|
||||
namespace tensor_operation {
|
||||
namespace device {
|
||||
namespace instance {
|
||||
|
||||
void add_device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_1_128_128_comp_kpadding_instances(
|
||||
std::vector<std::unique_ptr<DeviceGemmMultipleD_BlockScale_BPreshuffle<Row,
|
||||
Col,
|
||||
Tuple<>,
|
||||
Row,
|
||||
F8,
|
||||
F32,
|
||||
F8,
|
||||
F32,
|
||||
Tuple<>,
|
||||
BF16,
|
||||
1,
|
||||
128,
|
||||
128,
|
||||
PassThrough,
|
||||
PassThrough,
|
||||
PassThrough>>>&
|
||||
instances)
|
||||
{
|
||||
add_device_operation_instances(
|
||||
instances,
|
||||
device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_1_128_128_comp_instances<GemmKPadding>{});
|
||||
}
|
||||
|
||||
} // namespace instance
|
||||
} // namespace device
|
||||
} // namespace tensor_operation
|
||||
} // namespace ck
|
||||
@@ -0,0 +1,39 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
|
||||
#include "device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128.hpp"
|
||||
|
||||
namespace ck {
|
||||
namespace tensor_operation {
|
||||
namespace device {
|
||||
namespace instance {
|
||||
|
||||
void add_device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_1_128_128_mem_v1_default_instances(
|
||||
std::vector<std::unique_ptr<DeviceGemmMultipleD_BlockScale_BPreshuffle<Row,
|
||||
Col,
|
||||
Tuple<>,
|
||||
Row,
|
||||
F8,
|
||||
F32,
|
||||
F8,
|
||||
F32,
|
||||
Tuple<>,
|
||||
BF16,
|
||||
1,
|
||||
128,
|
||||
128,
|
||||
PassThrough,
|
||||
PassThrough,
|
||||
PassThrough>>>&
|
||||
instances)
|
||||
{
|
||||
add_device_operation_instances(
|
||||
instances,
|
||||
device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_1_128_128_mem_instances<Intrawave,
|
||||
GemmDefault>{});
|
||||
}
|
||||
|
||||
} // namespace instance
|
||||
} // namespace device
|
||||
} // namespace tensor_operation
|
||||
} // namespace ck
|
||||
@@ -0,0 +1,39 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
|
||||
#include "device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_128_128_128.hpp"
|
||||
|
||||
namespace ck {
|
||||
namespace tensor_operation {
|
||||
namespace device {
|
||||
namespace instance {
|
||||
|
||||
void add_device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_1_128_128_mem_v1_kpadding_instances(
|
||||
std::vector<std::unique_ptr<DeviceGemmMultipleD_BlockScale_BPreshuffle<Row,
|
||||
Col,
|
||||
Tuple<>,
|
||||
Row,
|
||||
F8,
|
||||
F32,
|
||||
F8,
|
||||
F32,
|
||||
Tuple<>,
|
||||
BF16,
|
||||
1,
|
||||
128,
|
||||
128,
|
||||
PassThrough,
|
||||
PassThrough,
|
||||
PassThrough>>>&
|
||||
instances)
|
||||
{
|
||||
add_device_operation_instances(
|
||||
instances,
|
||||
device_gemm_blockscale_wp_xdl_f8_f8_bf16_mk_nk_mn_1_128_128_mem_instances<Intrawave,
|
||||
GemmKPadding>{});
|
||||
}
|
||||
|
||||
} // namespace instance
|
||||
} // namespace device
|
||||
} // namespace tensor_operation
|
||||
} // namespace ck
|
||||
@@ -46,25 +46,26 @@ using device_gemm_mx_xdl_f4_f4_f16_mk_mfma_mn_instances = std::tuple<
|
||||
//#####################| | | | Type| Data| Type| Data| Type| Type| Type| Elementwise| Elementwise| Elementwise|Specialization| Size| Size| Block| Block| Block| | | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector| Pipeline| Pipeline|
|
||||
//#####################| | | | | Type| | Type| | | | Operation| Operation| Operation| | | | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl| _NWaveNPerXdl| Scheduler| Verision|
|
||||
//#####################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
||||
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 128, 128, 16, 16, 16, 16, 2, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 256, 128, 16, 16, 16, 16, 2, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 384, 128, 16, 16, 16, 16, 2, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 512, 128, 16, 16, 16, 16, 2, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 128, 128, 16, 16, 16, 16, 2, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 16>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 256, 128, 16, 16, 16, 16, 2, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 4, S<1, 8, 1, 32>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 384, 128, 16, 16, 16, 16, 2, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 16>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 512, 128, 16, 16, 16, 16, 2, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 4, S<1, 8, 1, 32>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 128, 128, 16, 16, 16, 16, 4, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 256, 128, 16, 16, 16, 16, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 384, 128, 16, 16, 16, 16, 4, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 512, 128, 16, 16, 16, 16, 4, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 128, 128, 16, 16, 16, 16, 4, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 16>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 256, 128, 16, 16, 16, 16, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 4, S<1, 8, 1, 32>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 384, 128, 16, 16, 16, 16, 4, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 16>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 512, 128, 16, 16, 16, 16, 4, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 4, S<1, 8, 1, 32>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 128, 128, 16, 16, 16, 16, 6, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 256, 128, 16, 16, 16, 16, 6, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 384, 128, 16, 16, 16, 16, 6, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 512, 128, 16, 16, 16, 16, 6, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 128, 128, 16, 16, 16, 16, 6, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 16>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 256, 128, 16, 16, 16, 16, 6, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 4, S<1, 8, 1, 32>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 384, 128, 16, 16, 16, 16, 6, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 16>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 512, 128, 16, 16, 16, 16, 6, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 4, S<1, 8, 1, 32>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 128, 128, 16, 16, 16, 16, 8, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 256, 128, 16, 16, 16, 16, 8, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 384, 128, 16, 16, 16, 16, 8, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 512, 128, 16, 16, 16, 16, 8, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 128, 128, 16, 16, 16, 16, 8, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 16>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 256, 128, 16, 16, 16, 16, 8, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 4, S<1, 8, 1, 32>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 384, 128, 16, 16, 16, 16, 8, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 16>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 512, 128, 16, 16, 16, 16, 8, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 4, S<1, 8, 1, 32>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
std::nullptr_t
|
||||
// clang-format on
|
||||
>;
|
||||
} // namespace instance
|
||||
|
||||
@@ -56,7 +56,8 @@ using device_gemm_mx_xdl_f4_f4_f16_mk_nk_mn_instances = std::tuple<
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 256, 128, 16, 16, 16, 16, 4, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 256, 128, 128, 16, 16, 16, 16, 8, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 128, 128, 16, 16, 16, 16, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 64, 32, 32, 128, 16, 16, 16, 16, 2, 2, S<8, 8, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 8, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 4>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 64, 32, 32, 128, 16, 16, 16, 16, 2, 2, S<8, 8, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 8, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 4>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
std::nullptr_t
|
||||
// clang-format on
|
||||
>;
|
||||
} // namespace instance
|
||||
|
||||
@@ -49,7 +49,8 @@ using device_gemm_mx_xdl_f8_f8_bf16_mk_nk_mn_instances = std::tuple<
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F8, E8M0PK, F8, E8M0PK, BF16, F32, BF16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 64, 256, 16, 16, 16, 16, 4, 2, S<16,16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<16,16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F8, E8M0PK, F8, E8M0PK, BF16, F32, BF16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 128, 256, 16, 16, 16, 16, 2, 4, S<16,16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<16,16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F8, E8M0PK, F8, E8M0PK, BF16, F32, BF16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 128, 128, 32, 256, 16, 16, 16, 16, 4, 2, S<16, 8, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<16, 8, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 4>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F8, E8M0PK, F8, E8M0PK, BF16, F32, BF16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 64, 32, 32, 256, 16, 16, 16, 16, 2, 2, S<16, 4, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<16, 4, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 4>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F8, E8M0PK, F8, E8M0PK, BF16, F32, BF16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 64, 32, 32, 256, 16, 16, 16, 16, 2, 2, S<16, 4, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<16, 4, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 4>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
std::nullptr_t
|
||||
// clang-format on
|
||||
>;
|
||||
|
||||
|
||||
@@ -49,7 +49,8 @@ using device_gemm_mx_xdl_f8_f8_f16_mk_nk_mn_instances = std::tuple<
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F8, E8M0PK, F8, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 64, 256, 16, 16, 16, 16, 4, 2, S<16,16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<16,16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F8, E8M0PK, F8, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 128, 256, 16, 16, 16, 16, 2, 4, S<16,16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<16,16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F8, E8M0PK, F8, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 128, 128, 32, 256, 16, 16, 16, 16, 4, 2, S<16, 8, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<16, 8, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 4>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F8, E8M0PK, F8, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 64, 32, 32, 256, 16, 16, 16, 16, 2, 2, S<16, 4, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<16, 4, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 4>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>
|
||||
DeviceGemmMX_Xdl_CShuffleV3< Row, Col, Row, F8, E8M0PK, F8, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 64, 32, 32, 256, 16, 16, 16, 16, 2, 2, S<16, 4, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<16, 4, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 16, 1, 4>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
|
||||
std::nullptr_t
|
||||
// clang-format on
|
||||
>;
|
||||
|
||||
|
||||
Reference in New Issue
Block a user