WMMA GEMM universal pipeline v1, mixed precision and paddings, examples (#2230)

* Fixed cmake errors related to  gemm_bilinear. Previously, if the above flags are set, cmake build fails: GPU_TARGETS="gfx1100;gfx1201" -D DTYPES="fp16;bf16;fp8"

* Fixed cmake build errors related to test_fp8

* Updates to support mixed precision

* Adding support for RRR, F8xF16xF16 gemm_universal_wmma - wip

* Added support for F8xF16xF16 to gemm_wmma_universal

* Added support for F16xF8xF16 to gemm_wmma_universal

* Added support for BF16xI4xBF16 to gemm_wmma_universal

* Added support for F16xI4xF16 to gemm_wmma_universal

* Fixed IsSupportedArgument to check ComputeTypeA, ComputeTypeB instead of ADataType, BDataType

* Added missing test class for FP16_KM_NK

* Pre-commit hooks fixes

* Added padding instances for f16xf16xf16

* Fixed cmake errors related to  gemm_bilinear. Previously, if the above flags are set, cmake build fails: GPU_TARGETS="gfx1100;gfx1201" -D DTYPES="fp16;bf16;fp8"

* Fixed cmake build errors related to test_fp8

* Ammending changes for adding support for padding instances for f16xf16xf16

* Fixes for padding instances for f16xf16xf16

* Added padding instances for bf16xbf16, f8xf8

* Added packed instances for bf16xi4xbf16

* Added padding instances for f8xf16xf16

* Added padding instances for f16xf8xf16, f16xi4xf16

* Fixed typos for bf16xbf16xbf16 padding instances

* Fixed typos for padded instances

* Added tests for fp16, KM_KN and KM_NK

* Padding not supported for when BDataType is pk_i4_t. Added fix for correct check and removed padding instances.

* Fixed typos

* Updated the set of tests for FP16

* Updated the set of tests for FP16

* Fix typo

* Moved f16xi4 test under the correct data layout group

* example for gemm_universal_bf16

* Adding examples for gemm_wmma instances

* Added the  missing parameters

* Fixed review comments and added executable to cmakeLists

* Fixing clang format

* Fixing build erros

* Fixed compilation failure.

* Modified some code as per gemm_universal_examples

* Fixed the gemm specialization error

* Fixed the build errors.

* Fix strides of a/b_thread_desc

The descriptors are larger than needed (even though the compiler don't alloc registers for unused values).

* Load in M/NRepeat dims with thread copy's slice instead of a loop

* Clone BlockwiseGemmXdlops_pipeline_v1 for WMMA implementation

* Implement Intrawave and Interwave variants of pipeline v1

* Add instances for Interwave and Intrawave v1

* Add instances with ABlockLdsExtraM and BBlockLdsExtraN = 0

* Remove instances that are too slow (mostly because of register spilling)

* Add a workaround for fp8/bf8->f32 packed conversion issue

* Add instances for Interwave and Intrawave v1

* Enable profiling of mixed precision with f8 and int4 on WMMA

* Fix segfault in profiler when B is pk_i4_t

b_device_buf's size in bytes is larger than b_k_n_permute so b_device_buf.ToDevice reads out-of-bounds.

* Remove instances that are too slow (mostly because of register spilling)

* Add missing add_device_gemm_wmma_universal_f8_f8_bf16 declarations

* Add test case for bf16_i4

* Add missing Regular tests

* Add test_gemm_universal_xdl/wmma_fp16 to REGRESSION_TESTS

They take more than 30 seconds

* Fix a bug that fp16_i4 validation passes only with PermuteB

A permutation required by conversion from pk_i4_t to half_t does not
depend on PermuteB, they can be used independently.

* Use PermuteB with f16_i4 in most instances (as xdl)

Some instances use PermuteB = false for checking correctness.
See also the previous commit.

* Fix cache flushing for pk_i4

* Add mixed precision examples

* Disable all tests and instances with f8 on gfx11

Even though f8_f16 and f16_f8 don't require f8 WMMA instructions,
gfx11 still lacks hardware instructions for fast f8->f32 conversion.

* Add FP16 KM_NK and KM_KN test suites for XDL

These tests were added to common .inc for better testing of WMMA instances

* Fix int8 DTYPES check for gemm_bilinear

---------

Co-authored-by: Anca Hamuraru <anca@streamhpc.com>
Co-authored-by: Apoorva Kalyani <apoorva@streamhpc.com>

include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma_cshuffle_v3.hpp

@@ -200,12 +200,12 @@ template <typename ALayout,
           index_t CShuffleNRepeatPerShuffle,
           typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock,
           index_t CShuffleBlockTransferScalarPerVector_NPerBlock,
-          BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave,
-          BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v4,
-          typename ComputeTypeA                       = CDataType,
-          typename ComputeTypeB                       = ComputeTypeA,
-          bool PermuteA                               = false,
-          bool PermuteB                               = false>
+          BlockGemmPipelineScheduler BlkGemmPipeSched,
+          BlockGemmPipelineVersion BlkGemmPipelineVer,
+          typename ComputeTypeA,
+          typename ComputeTypeB,
+          bool PermuteA,
+          bool PermuteB>
 struct GridwiseGemm_wmma_cshuffle_v3
 {
     static constexpr auto I0 = Number<0>{};
@@ -302,7 +302,7 @@ struct GridwiseGemm_wmma_cshuffle_v3
     template <index_t MNRepeat, index_t MNWaves, index_t MNPerWmma, typename BlockDesc>
     __host__ __device__ static constexpr auto MakeWmmaTileDescriptor(const BlockDesc&)
     {
-        // K0_N_K1 -> K0_MNRepeat_MNWaves_MNPerWmma_K1
+        // K0_MN_K1 -> K0_MNRepeat_MNWaves_KRow_MNPerWmma_K1
         constexpr auto K0 = BlockDesc{}.GetLength(I0);
         constexpr auto K1 = BlockDesc{}.GetLength(I2);
 #ifdef __gfx12__
@@ -420,7 +420,7 @@ struct GridwiseGemm_wmma_cshuffle_v3
 
         using GemmSpecialization = tensor_operation::device::GemmSpecialization;
 
-        static_assert(!(is_same_v<remove_cvref_t<ADataType>, pk_i4_t> &&
+        static_assert(!(is_same_v<remove_cvref_t<BDataType>, pk_i4_t> &&
                         GemmSpec != GemmSpecialization::Default),
                       "pk_i4_t does not support padding");