[Mlir-commits] [mlir] [mlir][vectorize] Support affine.apply in SuperVectorize (PR #77968)

[Sergei Grechanik]

================
@@ -0,0 +1,65 @@
+// RUN: mlir-opt %s -affine-super-vectorize="virtual-vector-size=8 test-fastest-varying=0" -split-input-file | FileCheck %s
+
----------------
sergei-grechanik wrote:

Please check this example, I see it crashing in my local setup with your patch:
```mlir
func.func @crash(%arg0: memref<8x12x16xf32>, %arg1: memref<8x24x48xf32>) {
  affine.for %arg2 = 0 to 8 {
    affine.for %arg3 = 0 to 12 {
      affine.for %arg4 = 0 to 48 {
        %1 = affine.apply affine_map<(d0) -> (d0 mod 16)>(%arg4)
        %2 = affine.load %arg0[%arg2, %arg3, %1 + 1] : memref<8x12x16xf32>
        affine.store %2, %arg1[%arg2, %arg3, %arg4] : memref<8x24x48xf32>
      }
    }
  }
  return
}
```

https://github.com/llvm/llvm-project/pull/77968