Giuseppe Rossini 1387ba48a3

[MLIR][AMDGPU] Introduce fp16 packed arithmetic (#105688) ...

This PR is introducing rocdl.cvt.pkrtz in the ROCDL dialect and it is
using that instruction when lowering `arith::TruncFOp`.

2024-08-26 12:48:57 -05:00

..

8-bit-float-saturation.mlir

[MLIR][AMDGPU] Introduce fp16 packed arithmetic (#105688)

2024-08-26 12:48:57 -05:00

8-bit-floats.mlir

[MLIR][AMDGPU] Introduce fp16 packed arithmetic (#105688)

2024-08-26 12:48:57 -05:00

16-bit-floats.mlir

[MLIR][AMDGPU] Introduce fp16 packed arithmetic (#105688)

2024-08-26 12:48:57 -05:00