[Mlir-commits] [mlir] [OpenMP][MLIR] Add omp.distribute op to the OMP dialect (PR #67720)

[Kiran Chandramohan]

kiranchandramohan wrote:

> I'm not quite sure I understand the example. Are the construct(%cli... ) the "outputs" and the loops(%cli, ..) the ones being operated on, or do I have it backwards? Does the modified example below make sense?
> 
> ```
> omp.distribute loops(%tloop1) { 
>  bb0 (%tloop1 : !omp.cli, %tloop2 : !omp.cli): // Is it legal to have %tloop2 without it being in omp.distribute? We only care about one of the loops.   
>   omp.tile loops(%loop), construct(%tloop1:!omp.cli, %tloop2:!omp.cli) { // Input 1 loop, output 2 loops
>   bb0 (%loop : !omp.cli):
>       omp.canonical_loop %iv : i32 in [0, %tc), construct(%inner : !omp.cli) {
>         %a = load %arrA[%iv] : memref<?x?xf32>
>         store %a, %arrB[%iv] : memref<?x?xf32>
>     }
>   }
> }
> ```


```
omp.distribute loops(%tloop1) { 
 bb0 (%tloop1 : !omp.cli):
  omp.tile loops(%loop), construct(%tloop1:!omp.cli) { // Input 1 loop, output is two but further transformation by distribute only affects outermost.
  bb0 (%loop : !omp.cli):
      omp.canonical_loop %iv : i32 in [0, %tc), construct(%loop : !omp.cli) {
        %a = load %arrA[%iv] : memref<?x?xf32>
        store %a, %arrB[%iv] : memref<?x?xf32>
    }
  }
}
```

https://github.com/llvm/llvm-project/pull/67720