[MLIR] Incorrect fusion pass behavior with -test-loop-fusion=test-loop-fusion-transformation #132172
Description
My git version is 6003c30.
Description:
I am experiencing an inconsistent result when executing the same MLIR program with and without the -test-loop-fusion=test-loop-fusion-transformation.
Steps to Reproduce:
1. MLIR Program (test.mlir):
test.mlir:
module {
memref.global "private" constant @__constant_5x1x2x3xi16 : memref<5x1x2x3xi16> = dense<81> {alignment = 64 : i64}
func.func private @printMemrefI16(memref<*xi16>) attributes {llvm.emit_c_interface}
func.func @main() {
%c81_i16 = arith.constant 81 : i16
%c1_i16 = arith.constant 1 : i16
%alloc = memref.alloc() {alignment = 64 : i64} : memref<1x2x3xi16>
affine.for %arg0 = 0 to 1 {
affine.for %arg1 = 0 to 2 {
affine.for %arg2 = 0 to 3 {
affine.store %c1_i16, %alloc[%arg0, %arg1, %arg2] : memref<1x2x3xi16>
}
}
}
affine.for %arg0 = 0 to 5 {
affine.for %arg1 = 0 to 1 {
affine.for %arg2 = 0 to 2 {
affine.for %arg3 = 0 to 3 {
%0 = affine.load %alloc[%arg1, %arg2, %arg3] : memref<1x2x3xi16>
%1 = arith.muli %0, %c81_i16 : i16
affine.store %1, %alloc[%arg1, %arg2, %arg3] : memref<1x2x3xi16>
}
}
}
}
%expand_shape = memref.expand_shape %alloc [[0, 1], [2], [3]] output_shape [1, 1, 2, 3] : memref<1x2x3xi16> into memref<1x1x2x3xi16>
%cast = memref.cast %expand_shape : memref<1x1x2x3xi16> to memref<*xi16>
call @printMemrefI16(%cast) : (memref<*xi16>) -> ()
return
}
}
output:
module {
memref.global "private" constant @__constant_5x1x2x3xi16 : memref<5x1x2x3xi16> = dense<81> {alignment = 64 : i64}
func.func private @printMemrefI16(memref<*xi16>) attributes {llvm.emit_c_interface}
func.func @main() {
%c0 = arith.constant 0 : index
%c81_i16 = arith.constant 81 : i16
%c1_i16 = arith.constant 1 : i16
%alloc = memref.alloc() {alignment = 64 : i64} : memref<1x2x3xi16>
affine.for %arg0 = 0 to 5 {
affine.for %arg1 = 0 to 1 {
affine.for %arg2 = 0 to 2 {
affine.for %arg3 = 0 to 3 {
affine.store %c1_i16, %alloc[%c0, %arg2, %arg3] : memref<1x2x3xi16>
%0 = affine.load %alloc[%arg1, %arg2, %arg3] : memref<1x2x3xi16>
%1 = arith.muli %0, %c81_i16 : i16
affine.store %1, %alloc[%arg1, %arg2, %arg3] : memref<1x2x3xi16>
}
}
}
}
%expand_shape = memref.expand_shape %alloc [[0, 1], [2], [3]] output_shape [1, 1, 2, 3] : memref<1x2x3xi16> into memref<1x1x2x3xi16>
%cast = memref.cast %expand_shape : memref<1x1x2x3xi16> to memref<*xi16>
call @printMemrefI16(%cast) : (memref<*xi16>) -> ()
return
}
}
Obviously, the two nested loops here should not fuse together.