mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 11:13:28 +01:00
216329b982
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
44 lines
1.4 KiB
LLVM
44 lines
1.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: llc < %s -o - -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE
|
|
; RUN: llc < %s -o - -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX
|
|
|
|
define <8 x i16> @foo(<8 x i16> %a, <8 x i16> %b) {
|
|
; SSE-LABEL: foo:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: pcmpeqw %xmm1, %xmm0
|
|
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: foo:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
;
|
|
%icmp = icmp eq <8 x i16> %a, %b
|
|
%zext = zext <8 x i1> %icmp to <8 x i16>
|
|
%shl = shl nuw nsw <8 x i16> %zext, <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>
|
|
ret <8 x i16> %shl
|
|
}
|
|
|
|
; Don't fail with an assert due to an undef in the buildvector
|
|
define <8 x i16> @bar(<8 x i16> %a, <8 x i16> %b) {
|
|
; SSE-LABEL: bar:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: pcmpeqw %xmm1, %xmm0
|
|
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: bar:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
;
|
|
%icmp = icmp eq <8 x i16> %a, %b
|
|
%zext = zext <8 x i1> %icmp to <8 x i16>
|
|
%shl = shl nuw nsw <8 x i16> %zext, <i16 5, i16 undef, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>
|
|
ret <8 x i16> %shl
|
|
}
|
|
|