[all-commits] [llvm/llvm-project] 38faec: [MLIR] SM_90 integration test of TMA with 128b Swi...

[Guray Ozen via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 38faecc692f18730c387914ecce309e257aac14a
      https://github.com/llvm/llvm-project/commit/38faecc692f18730c387914ecce309e257aac14a
  Author: Guray Ozen <guray.ozen at gmail.com>
  Date:   2023-09-13 (Wed, 13 Sep 2023)

  Changed paths:
    A mlir/test/Integration/GPU/CUDA/sm90/tmaload_128_64_swizzle128b.mlir

  Log Message:
  -----------
  [MLIR] SM_90 integration test of TMA with 128b Swizzling (#65953)

An integration test for the 128b Swizzling TMA.

TMA with 128B Swizzle loads data as follows (each numbered cell is 16
bytes). The program tests this pattern for `128x64xf16` type.

```
|-------------------------------|
| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
| 1 | 0 | 3 | 2 | 5 | 4 | 7 | 6 |
| 2 | 3 | 0 | 1 | 6 | 7 | 4 | 5 |
| 3 | 2 | 1 | 0 | 7 | 6 | 5 | 4 |
| 4 | 5 | 6 | 7 | 0 | 1 | 2 | 3 |
| 5 | 4 | 7 | 6 | 1 | 0 | 3 | 2 |
| 6 | 7 | 4 | 5 | 2 | 3 | 0 | 1 |
|-------------------------------|
| ... pattern repeats ...       |
|-------------------------------|
```