maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[DAG] matchRotateSub - ensure the (pre-extended) shift amount is wide enough for the amount mask (PR56859) 

matchRotateSub is given shift amounts that will already have stripped any/zero-extend nodes from - so make sure those values are wide enough to take a mask.
This commit is contained in:
Simon Pilgrim 2022-08-02 11:38:47 +01:00
parent b395c0f0cd
commit b651fdff79
2 changed files with 54 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -7317,12 +7317,14 @@ static bool matchRotateSub(SDValue Pos, SDValue Neg, unsigned EltSize,
unsigned MaskLoBits = 0;
if (IsRotate && isPowerOf2_64(EltSize)) {
unsigned Bits = Log2_64(EltSize);
APInt DemandedBits =
APInt::getLowBitsSet(Neg.getScalarValueSizeInBits(), Bits);
if (SDValue Inner =
TLI.SimplifyMultipleUseDemandedBits(Neg, DemandedBits, DAG)) {
Neg = Inner;
MaskLoBits = Bits;
unsigned NegBits = Neg.getScalarValueSizeInBits();
if (NegBits >= Bits) {
APInt DemandedBits = APInt::getLowBitsSet(NegBits, Bits);
if (SDValue Inner =
TLI.SimplifyMultipleUseDemandedBits(Neg, DemandedBits, DAG)) {
Neg = Inner;
MaskLoBits = Bits;
}
}
}
@ -7338,11 +7340,13 @@ static bool matchRotateSub(SDValue Pos, SDValue Neg, unsigned EltSize,
// affect Mask's demanded bits, just replace Pos with Pos'. These operations
// are redundant for the purpose of the equality.
if (MaskLoBits) {
APInt DemandedBits =
APInt::getLowBitsSet(Pos.getScalarValueSizeInBits(), MaskLoBits);
if (SDValue Inner =
TLI.SimplifyMultipleUseDemandedBits(Pos, DemandedBits, DAG)) {
Pos = Inner;
unsigned PosBits = Pos.getScalarValueSizeInBits();
if (PosBits >= MaskLoBits) {
APInt DemandedBits = APInt::getLowBitsSet(PosBits, MaskLoBits);
if (SDValue Inner =
TLI.SimplifyMultipleUseDemandedBits(Pos, DemandedBits, DAG)) {
Pos = Inner;
}
}
}

39
llvm/test/CodeGen/X86/rotate5.ll Normal file
View File

@ -0,0 +1,39 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s --check-prefixes=X86
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefixes=X64
; Ensure that the (pre-extended) shift amount type is wide enough to take any mask.
define void @PR56859() {
; X86-LABEL: PR56859:
; X86: # %bb.0: # %entry
; X86-NEXT: movl (%eax), %ecx
; X86-NEXT: testl %ecx, %ecx
; X86-NEXT: setne %al
; X86-NEXT: movl $1, %edx
; X86-NEXT: # kill: def $cl killed $cl killed $ecx
; X86-NEXT: shrl %cl, %edx
; X86-NEXT: btsl %eax, %edx
; X86-NEXT: movl %edx, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: PR56859:
; X64: # %bb.0: # %entry
; X64-NEXT: movl (%rax), %ecx
; X64-NEXT: testl %ecx, %ecx
; X64-NEXT: setne %al
; X64-NEXT: movl $1, %edx
; X64-NEXT: # kill: def $cl killed $cl killed $ecx
; X64-NEXT: shrl %cl, %edx
; X64-NEXT: btsl %eax, %edx
; X64-NEXT: movl %edx, (%rax)
; X64-NEXT: retq
entry:
%0 = load i32, ptr undef, align 4
%tobool = icmp ne i32 %0, 0
%lor.ext = zext i1 %tobool to i32
%shr = lshr i32 1, %0
%shl = shl i32 1, %lor.ext
%or = or i32 %shl, %shr
store i32 %or, ptr undef, align 4
ret void
}