[rocm-libraries] ROCm/rocm-libraries#4834 (commit e75e6cb)

[CK_TILE][GEMM] Fix eightwarp error & Add eightwarp unit test
 (#4834)

## Motivation

The primary goal of this PR is to fix a critical issue in the EightWarps
implementation within ck_tile. Additionally, unit tests were added to
ensure that CI can detect errors.

## Test Plan

ninja test_tile_gemm_quant_abquant_eightwarps
./bin/test_tile_gemm_quant_abquant_eightwarps

## Test Result

All EightWarps related test cases in TestCkTileGemmABQuant completed
successfully without linker errors or validation mismatches.

## Submission Checklist

- [ ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.

include/ck_tile/ops/epilogue/cshuffle_epilogue.hpp

@@ -116,7 +116,7 @@ struct CShuffleEpilogue
     static constexpr index_t isCTransposed = Problem::isCTransposed;
     static constexpr bool FixedVectorSize  = Problem::FixedVectorSize;
     static constexpr bool TiledMMAPermuteN = Problem::TiledMMAPermuteN;
-#ifdef __gfx95__
+#if defined(CK_GFX950_SUPPORT)
     static constexpr bool EightWave = (MWave * NWave == 8);
 #else
     static constexpr bool EightWave = false;

include/ck_tile/ops/gemm_quant/kernel/gemm_quant_kernel.hpp

@@ -1328,7 +1328,8 @@ struct QuantGemmKernel
             // For RowMajor C, M is the row dimension — check M alignment here because
             // ALayout=RowMajor does not check M (it only checks K), leaving a gap for
             // the RowMajorA + RowMajorC combination.
-            if(kargs.M % TilePartitioner::MPerBlock != 0 && GemmPipeline::kPadM == false)
+            if(kargs.M % TilePartitioner::MPerBlock != 0 && GemmPipeline::kPadM == false &&
+               GemmPipeline::BlockGemmShape::NumWarps != 8)
             {
                 if(ck_tile::EnvIsEnabled(CK_TILE_ENV(CK_TILE_LOGGING)))
                 {