ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-21 21:39:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix flash attn mask bug (#733)

Browse Source 
* add check input parameter

* add instance for vector load = 1

* move gerneral instance to first pos

* fix read bias code

* regular code for bias load

---------

Co-authored-by: zjing14 <zhangjing14@gmail.com>

[ROCm/composable_kernel commit: 0ede66de54]
This commit is contained in:
ltqin
2023-06-12 21:35:31 +08:00
committed by GitHub
parent 9499f4b51b
commit 8c5f5f1293
7 changed files with 86 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
View File

@@ -41,10 +41,11 @@ template <index_t NumDimG,
using device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instances =
std::tuple<
// clang-format off
// #############################################| NumDimG| NumDimM| NumDimN| NumDimK| NumDimO| AData| B0Data| B1Data| CData| Acc0BiasData| Acc1BiasData| AccData| CShuffle| A| B0| Acc0| B1| C| GEMM| ATensorSpec| B0TensorSpec| B1TensorSpec| CTensorSpec| NumGemmK| Block| Gemm01| Gemm0| Gemm0| Gemm1| Gemm1| AK1| BK1| B1K1| MPer| NPer| Gemm0| Gemm0| Gemm1| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockLds| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| MaskingSpec|
// #############################################| | | | | | Type| Type| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Elementwise| Elementwise| Specialization| | | | | Prefetch| Size| MPer| NPer| KPer| NPer| KPer| | | | XDL| XDL| MXdl| NXdl| NXdl| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector| |
// #############################################| | | | | | | | | | | | | | Operation| Operation| Operation| Operation| Operation| | | | | | Stage| | Block| Block| Block| Block| Block| | | | | | Per| Per| Per| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl| |
// #############################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | | |
// #############################################| NumDimG| NumDimM| NumDimN| NumDimK| NumDimO| AData| B0Data| B1Data| CData| Acc0BiasData| Acc1BiasData| AccData| CShuffle| A| B0| Acc0| B1| C| GEMM| ATensorSpec| B0TensorSpec| B1TensorSpec| CTensorSpec| NumGemmK| Block| Gemm01| Gemm0| Gemm0| Gemm1| Gemm1| AK1| BK1| B1K1| MPer| NPer| Gemm0| Gemm0| Gemm1| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockLds| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| MaskingSpec| D0s Bias|
// #############################################| | | | | | Type| Type| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Elementwise| Elementwise| Specialization| | | | | Prefetch| Size| MPer| NPer| KPer| NPer| KPer| | | | XDL| XDL| MXdl| NXdl| NXdl| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector| | SrcScalar|
// #############################################| | | | | | | | | | | | | | Operation| Operation| Operation| Operation| Operation| | | | | | Stage| | Block| Block| Block| Block| Block| | | | | | Per| Per| Per| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl| | PerVector|
// #############################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<BF16>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 64, 32, 128, 32, 8, 8, 2, 32, 32, 1, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec, 1>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<BF16>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 256, 128, 32, 64, 32, 8, 8, 2, 32, 32, 2, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<BF16>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 256, 128, 32, 128, 32, 8, 8, 2, 32, 32, 2, 4, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<BF16>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 256, 32, 64, 32, 8, 8, 2, 32, 32, 1, 8, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
@@ -58,8 +59,9 @@ using device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<BF16>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 64, 256, 64, 128, 32, 8, 8, 2, 16, 16, 1, 16, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 8, S<1, 16, 1,16>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<BF16>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 64, 256, 64, 64, 32, 8, 8, 2, 16, 16, 1, 16, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 4, S<1, 32, 1, 8>, 8, MaskingSpec>,
// Padded fallback kernel
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<BF16>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 128, 64, 128, 32, 8, 8, 2, 32, 32, 1, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<BF16>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 64, 32, 128, 32, 8, 8, 2, 32, 32, 1, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<BF16>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 128, 64, 128, 32, 8, 8, 2, 32, 32, 1, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec, 1>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<BF16>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 128, 64, 128, 32, 8, 8, 2, 32, 32, 1, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<BF16>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 64, 32, 128, 32, 8, 8, 2, 32, 32, 1, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>
// clang-format on
>;

10
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
View File

@@ -41,10 +41,11 @@ template <index_t NumDimG,
using device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instances =
std::tuple<
// clang-format off
// #############################################| NumDimG| NumDimM| NumDimN| NumDimK| NumDimO| AData| B0Data| B1Data| CData| Acc0BiasData| Acc1BiasData| AccData| CShuffle| A| B0| Acc0| B1| C| GEMM| ATensorSpec| B0TensorSpec| B1TensorSpec| CTensorSpec| NumGemmK| Block| Gemm01| Gemm0| Gemm0| Gemm1| Gemm1| AK1| BK1| B1K1| MPer| NPer| Gemm0| Gemm0| Gemm1| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockLds| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| MaskingSpec|
// #############################################| | | | | | Type| Type| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Elementwise| Elementwise| Specialization| | | | | Prefetch| Size| MPer| NPer| KPer| NPer| KPer| | | | XDL| XDL| MXdl| NXdl| NXdl| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector| |
// #############################################| | | | | | | | | | | | | | Operation| Operation| Operation| Operation| Operation| | | | | | Stage| | Block| Block| Block| Block| Block| | | | | | Per| Per| Per| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl| |
// #############################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | | |
// #############################################| NumDimG| NumDimM| NumDimN| NumDimK| NumDimO| AData| B0Data| B1Data| CData| Acc0BiasData| Acc1BiasData| AccData| CShuffle| A| B0| Acc0| B1| C| GEMM| ATensorSpec| B0TensorSpec| B1TensorSpec| CTensorSpec| NumGemmK| Block| Gemm01| Gemm0| Gemm0| Gemm1| Gemm1| AK1| BK1| B1K1| MPer| NPer| Gemm0| Gemm0| Gemm1| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockLds| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| MaskingSpec| D0s Bias|
// #############################################| | | | | | Type| Type| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Elementwise| Elementwise| Specialization| | | | | Prefetch| Size| MPer| NPer| KPer| NPer| KPer| | | | XDL| XDL| MXdl| NXdl| NXdl| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector| | SrcScalar|
// #############################################| | | | | | | | | | | | | | Operation| Operation| Operation| Operation| Operation| | | | | | Stage| | Block| Block| Block| Block| Block| | | | | | Per| Per| Per| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl| | PerVector|
// #############################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<F16>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 64, 32, 128, 32, 8, 8, 2, 32, 32, 1, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec, 1>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<F16>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 256, 128, 32, 64, 32, 8, 8, 2, 32, 32, 2, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<F16>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 256, 128, 32, 128, 32, 8, 8, 2, 32, 32, 2, 4, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
#if CK_WORKAROUND_SWDEV_388832
@@ -60,6 +61,7 @@ using device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<F16>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 64, 256, 64, 128, 32, 8, 8, 2, 16, 16, 1, 16, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 8, S<1, 16, 1,16>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<F16>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 64, 256, 64, 64, 32, 8, 8, 2, 16, 16, 1, 16, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 4, S<1, 32, 1, 8>, 8, MaskingSpec>,
// Padded fallback kernel
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<F16>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 128, 64, 128, 32, 8, 8, 2, 32, 32, 1, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec, 1>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<F16>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 128, 64, 128, 32, 8, 8, 2, 32, 32, 1, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<F16>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, ScaleAdd, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 64, 32, 128, 32, 8, 8, 2, 32, 32, 1, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>
// clang-format on

4
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
View File

@@ -45,6 +45,7 @@ using device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_
// #############################################| | | | | | Type| Type| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Elementwise| Elementwise| Specialization| | | | | Prefetch| Size| MPer| NPer| KPer| NPer| KPer| | | | XDL| XDL| MXdl| NXdl| NXdl| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector| |
// #############################################| | | | | | | | | | | | | | Operation| Operation| Operation| Operation| Operation| | | | | | Stage| | Block| Block| Block| Block| Block| | | | | | Per| Per| Per| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl| |
// #############################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 64, 32, 128, 32, 8, 8, 2, 32, 32, 1, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 256, 128, 32, 64, 32, 8, 8, 2, 32, 32, 2, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 256, 128, 32, 128, 32, 8, 8, 2, 32, 32, 2, 4, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 256, 32, 64, 32, 8, 8, 2, 32, 32, 1, 8, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
@@ -58,8 +59,7 @@ using device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 64, 256, 64, 128, 32, 8, 8, 2, 16, 16, 1, 16, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 8, S<1, 16, 1,16>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 64, 256, 64, 64, 32, 8, 8, 2, 16, 16, 1, 16, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 4, S<1, 32, 1, 8>, 8, MaskingSpec>,
// Padded fallback kernel
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 128, 64, 128, 32, 8, 8, 2, 32, 32, 1, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 64, 32, 128, 32, 8, 8, 2, 32, 32, 1, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, BF16, BF16, BF16, BF16, ck::Tuple<>, ck::Tuple<>, F32, BF16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 128, 64, 128, 32, 8, 8, 2, 32, 32, 1, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>
// clang-format on
>;

4
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
View File

@@ -45,6 +45,7 @@ using device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_
// #############################################| | | | | | Type| Type| Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Elementwise| Elementwise| Specialization| | | | | Prefetch| Size| MPer| NPer| KPer| NPer| KPer| | | | XDL| XDL| MXdl| NXdl| NXdl| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector| |
// #############################################| | | | | | | | | | | | | | Operation| Operation| Operation| Operation| Operation| | | | | | Stage| | Block| Block| Block| Block| Block| | | | | | Per| Per| Per| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl| |
// #############################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 64, 32, 128, 32, 8, 8, 2, 32, 32, 1, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 256, 128, 32, 64, 32, 8, 8, 2, 32, 32, 2, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 256, 128, 32, 128, 32, 8, 8, 2, 32, 32, 2, 4, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
#if CK_WORKAROUND_SWDEV_388832
@@ -60,8 +61,7 @@ using device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 64, 256, 64, 128, 32, 8, 8, 2, 16, 16, 1, 16, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 8, S<1, 16, 1,16>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmDefault, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 64, 256, 64, 64, 32, 8, 8, 2, 16, 16, 1, 16, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 4, S<1, 32, 1, 8>, 8, MaskingSpec>,
// Padded fallback kernel
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 128, 64, 128, 32, 8, 8, 2, 32, 32, 1, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 64, 32, 128, 32, 8, 8, 2, 32, 32, 1, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, true, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, F16, F16, F16, F16, ck::Tuple<>, ck::Tuple<>, F32, F16, PassThrough, PassThrough, Scale, PassThrough, PassThrough, GemmPadded, TensorDefault, TensorDefault, TensorDefault, TensorDefault, 1, 256, 128, 128, 64, 128, 32, 8, 8, 2, 32, 32, 1, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, false, S< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8, MaskingSpec>
// clang-format on
>;