[CK_TILE] FA bwd kernels optimization (#1397)

* tmp save

* fix batch deterministic bugs

* fix group deterministic bugs

* codegen update

* reorder files

* bias support

* hd256 bias support

* bwd smoke test update

* simplify convert dq

* fix hd256 dropout scratch

* do{}while() -> while(){}

* comments

* remove FmhaBwdTilePartitioner

* save clear_tile

* refactor dropout

* code cleanup

* code cleanup

* comments

* fix epilogue problem

* fix fwd dropout

* group convert_dq opt

* fix dq alignment

* Do not store storerandval in bwd for flash attention integration

* fix hd32 error and boost performance

* revert

* Remove duplicated WarpGemm definitions in the policy file

* dropout patch for mrepeat 16*16

* code sync up

* dq_acc stride

* dq_acc stride stuff

* codegen update

* fwd dropout revert

* fix hd128 scratches and boost performance

* receipt 3 for simplified smoke test

* more strides for fa integration

* fix hd64 scratches and boost performance

* non-iglp pipeline for headdim padding cases

* dpad same as dvpad for flash attention integration

* unpadded lse&d for group mode

* Support unpad layout for group lse

* Support unpad lse layout for splitkv

* Fix stride for splitkv kernel

* fix unpadded lse issue in fwd splitkv

* comment

* solve lds read&write conflicts

* rename

* bias rename

* tile index revert

---------

Co-authored-by: danyao12 <danyao12>
Co-authored-by: rocking <ChunYu.Lai@amd.com>
Co-authored-by: Qianfeng Zhang <Qianfeng.Zhang@amd.com>

include/ck_tile/ops/gemm/warp/warp_gemm_dispatcher.hpp

@@ -15,7 +15,8 @@ template <typename AType,
           index_t MPerWave,
           index_t NPerWave,
           index_t KPerWave,
-          bool TransposeC>
+          bool TransposeC,
+          bool SwizzleA = false>
 struct WarpGemmMfmaDispatcher;
 
 // clang-format off
@@ -29,6 +30,9 @@ template<> struct WarpGemmMfmaDispatcher<ck_tile::half_t, ck_tile::half_t, float
 template<> struct WarpGemmMfmaDispatcher<ck_tile::half_t, ck_tile::half_t, float, 16, 16, 32, false> { using Type = WarpGemmMfmaF16F16F32M16N16K32; };
 template<> struct WarpGemmMfmaDispatcher<ck_tile::half_t, ck_tile::half_t, float, 16, 16, 32, true> { using Type = WarpGemmMfmaF16F16F32M16N16K32TransposedCDistribution; };
 
+template<> struct WarpGemmMfmaDispatcher<ck_tile::half_t, ck_tile::half_t, float, 32, 32,  8, false, true> { using Type = WarpGemmMfmaF16F16F32M32N32K8SwizzleA; };
+template<> struct WarpGemmMfmaDispatcher<ck_tile::half_t, ck_tile::half_t, float, 32, 32, 16, false, true> { using Type = WarpGemmMfmaF16F16F32M32N32K16SwizzleA; };
+
 // bf16
 template<> struct WarpGemmMfmaDispatcher<ck_tile::bf16_t, ck_tile::bf16_t, float, 32, 32,  8, false> { using Type = WarpGemmMfmaBf16Bf16F32M32N32K8; };
 template<> struct WarpGemmMfmaDispatcher<ck_tile::bf16_t, ck_tile::bf16_t, float, 32, 32,  8, true> { using Type = WarpGemmMfmaBf16Bf16F32M32N32K8TransposedCDistribution; };
@@ -39,6 +43,9 @@ template<> struct WarpGemmMfmaDispatcher<ck_tile::bf16_t, ck_tile::bf16_t, float
 template<> struct WarpGemmMfmaDispatcher<ck_tile::bf16_t, ck_tile::bf16_t, float, 16, 16, 32, false> { using Type = WarpGemmMfmaBf16Bf16F32M16N16K32; };
 template<> struct WarpGemmMfmaDispatcher<ck_tile::bf16_t, ck_tile::bf16_t, float, 16, 16, 32, true> { using Type = WarpGemmMfmaBf16Bf16F32M16N16K32TransposedCDistribution; };
 
+template<> struct WarpGemmMfmaDispatcher<ck_tile::bf16_t, ck_tile::bf16_t, float, 32, 32,  8, false, true> { using Type = WarpGemmMfmaBf16Bf16F32M32N32K8SwizzleA; };
+template<> struct WarpGemmMfmaDispatcher<ck_tile::bf16_t, ck_tile::bf16_t, float, 32, 32, 16, false, true> { using Type = WarpGemmMfmaBf16Bf16F32M32N32K16SwizzleA; };
+
 // fp8
 template<> struct WarpGemmMfmaDispatcher<ck_tile::fp8_t, ck_tile::fp8_t, float, 32, 32,  16, false> { using Type = WarpGemmMfma_f32_32x32x16_fp8_fp8; };
 template<> struct WarpGemmMfmaDispatcher<ck_tile::fp8_t, ck_tile::fp8_t, float, 32, 32,  16, true> { using Type = WarpGemmMfma_f32_32x32x16_fp8_fp8_CTransposed; };
@@ -58,8 +65,15 @@ template <typename AType,
           index_t MPerWave,
           index_t NPerWave,
           index_t KPerWave,
-          bool TransposeC>
-using WarpGemmMfmaDispatcher = typename impl::
-    WarpGemmMfmaDispatcher<AType, BType, CType, MPerWave, NPerWave, KPerWave, TransposeC>::Type;
+          bool TransposeC,
+          bool SwizzleA = false>
+using WarpGemmMfmaDispatcher = typename impl::WarpGemmMfmaDispatcher<AType,
+                                                                     BType,
+                                                                     CType,
+                                                                     MPerWave,
+                                                                     NPerWave,
+                                                                     KPerWave,
+                                                                     TransposeC,
+                                                                     SwizzleA>::Type;
 
 } // namespace ck_tile