[all-commits] [llvm/llvm-project] 15f5a7: [MLIR][NVGPU] Use `gpu.dynamic_shared_memory` in t...

[Guray Ozen via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 15f5a7a3ec71c624cea0cbdf02e3c5205ba81d9d
      https://github.com/llvm/llvm-project/commit/15f5a7a3ec71c624cea0cbdf02e3c5205ba81d9d
  Author: Guray Ozen <guray.ozen at gmail.com>
  Date:   2025-03-26 (Wed, 26 Mar 2025)

  Changed paths:
    M mlir/test/Integration/GPU/CUDA/sm90/gemm_f32_f16_f16_128x128x128.mlir
    M mlir/test/Integration/GPU/CUDA/sm90/gemm_pred_f32_f16_f16_128x128x128.mlir
    M mlir/test/Integration/GPU/CUDA/sm90/tma_load_64x64_swizzle128b.mlir

  Log Message:
  -----------
  [MLIR][NVGPU] Use `gpu.dynamic_shared_memory` in tests (#133051)

The `memref.subview` ops in the test case were incorrect: they extracted
out-of-bounds.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications