llvm-mirror/test/CodeGen/AArch64/dag-combine-mul-shl.ll
John Brawn 216329b982 [DAGCombiner] Fix infinite loop in vector mul/shl combining
We have the following DAGCombiner transformations:
 (mul (shl X, c1), c2) -> (mul X, c2 << c1)
 (mul (shl X, C), Y) -> (shl (mul X, Y), C)
 (shl (mul x, c1), c2) -> (mul x, c1 << c2)
Usually the constant shift is optimised by SelectionDAG::getNode when it is
constructed, by SelectionDAG::FoldConstantArithmetic, but when we're dealing
with vectors and one of those vector constants contains an undef element
FoldConstantArithmetic does not fold and we enter an infinite loop.

Fix this by making FoldConstantArithmetic use getNode to decide how to fold each
vector element, the same as FoldConstantVectorArithmetic does, and rather than
adding the constant shift to the work list instead only apply the transformation
if it's already been folded into a constant, as if it's not we're going to loop
endlessly. Additionally add missing NoOpaques to one of those transformations,
which I noticed when writing the tests for this.

Differential Revision: https://reviews.llvm.org/D26605

llvm-svn: 287766
2016-11-23 16:05:51 +00:00

118 lines
3.5 KiB
LLVM

; RUN: llc -mtriple=aarch64 < %s | FileCheck %s
; CHECK-LABEL: fn1_vector:
; CHECK: adrp x[[BASE:[0-9]+]], .LCP
; CHECK-NEXT: ldr q[[NUM:[0-9]+]], [x[[BASE]],
; CHECK-NEXT: mul v0.16b, v0.16b, v[[NUM]].16b
; CHECK-NEXT: ret
define <16 x i8> @fn1_vector(<16 x i8> %arg) {
entry:
%shl = shl <16 x i8> %arg, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
%mul = mul <16 x i8> %shl, <i8 0, i8 1, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>
ret <16 x i8> %mul
}
; CHECK-LABEL: fn2_vector:
; CHECK: adrp x[[BASE:[0-9]+]], .LCP
; CHECK-NEXT: ldr q[[NUM:[0-9]+]], [x[[BASE]],
; CHECK-NEXT: mul v0.16b, v0.16b, v[[NUM]].16b
; CHECK-NEXT: ret
define <16 x i8> @fn2_vector(<16 x i8> %arg) {
entry:
%mul = mul <16 x i8> %arg, <i8 0, i8 1, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>
%shl = shl <16 x i8> %mul, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
ret <16 x i8> %shl
}
; CHECK-LABEL: fn1_vector_undef:
; CHECK: adrp x[[BASE:[0-9]+]], .LCP
; CHECK-NEXT: ldr q[[NUM:[0-9]+]], [x[[BASE]],
; CHECK-NEXT: mul v0.16b, v0.16b, v[[NUM]].16b
; CHECK-NEXT: ret
define <16 x i8> @fn1_vector_undef(<16 x i8> %arg) {
entry:
%shl = shl <16 x i8> %arg, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
%mul = mul <16 x i8> %shl, <i8 undef, i8 1, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>
ret <16 x i8> %mul
}
; CHECK-LABEL: fn2_vector_undef:
; CHECK: adrp x[[BASE:[0-9]+]], .LCP
; CHECK-NEXT: ldr q[[NUM:[0-9]+]], [x[[BASE]],
; CHECK-NEXT: mul v0.16b, v0.16b, v[[NUM]].16b
; CHECK-NEXT: ret
define <16 x i8> @fn2_vector_undef(<16 x i8> %arg) {
entry:
%mul = mul <16 x i8> %arg, <i8 undef, i8 1, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>
%shl = shl <16 x i8> %mul, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
ret <16 x i8> %shl
}
; CHECK-LABEL: fn1_scalar:
; CHECK: mov w[[REG:[0-9]+]], #1664
; CHECK-NEXT: mul w0, w0, w[[REG]]
; CHECK-NEXT: ret
define i32 @fn1_scalar(i32 %arg) {
entry:
%shl = shl i32 %arg, 7
%mul = mul i32 %shl, 13
ret i32 %mul
}
; CHECK-LABEL: fn2_scalar:
; CHECK: mov w[[REG:[0-9]+]], #1664
; CHECK-NEXT: mul w0, w0, w[[REG]]
; CHECK-NEXT: ret
define i32 @fn2_scalar(i32 %arg) {
entry:
%mul = mul i32 %arg, 13
%shl = shl i32 %mul, 7
ret i32 %shl
}
; CHECK-LABEL: fn1_scalar_undef:
; CHECK: mov w0
; CHECK-NEXT: ret
define i32 @fn1_scalar_undef(i32 %arg) {
entry:
%shl = shl i32 %arg, 7
%mul = mul i32 %shl, undef
ret i32 %mul
}
; CHECK-LABEL: fn2_scalar_undef:
; CHECK: mov w0
; CHECK-NEXT: ret
define i32 @fn2_scalar_undef(i32 %arg) {
entry:
%mul = mul i32 %arg, undef
%shl = shl i32 %mul, 7
ret i32 %shl
}
; CHECK-LABEL: fn1_scalar_opaque:
; CHECK: mov w[[REG:[0-9]+]], #13
; CHECK-NEXT: mul w[[REG]], w0, w[[REG]]
; CHECK-NEXT: lsl w0, w[[REG]], #7
; CHECK-NEXT: ret
define i32 @fn1_scalar_opaque(i32 %arg) {
entry:
%bitcast = bitcast i32 13 to i32
%shl = shl i32 %arg, 7
%mul = mul i32 %shl, %bitcast
ret i32 %mul
}
; CHECK-LABEL: fn2_scalar_opaque:
; CHECK: mov w[[REG:[0-9]+]], #13
; CHECK-NEXT: mul w[[REG]], w0, w[[REG]]
; CHECK-NEXT: lsl w0, w[[REG]], #7
; CHECK-NEXT: ret
define i32 @fn2_scalar_opaque(i32 %arg) {
entry:
%bitcast = bitcast i32 13 to i32
%mul = mul i32 %arg, %bitcast
%shl = shl i32 %mul, 7
ret i32 %shl
}