RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-18 18:42:46 +02:00
Code Issues Projects Releases Wiki Activity

[InstCombine] add folds for min(~a, b) --> ~max(a, b)

Browse Source 
Besides the bug of omitting the inverse transform of max(~a, ~b) --> ~min(a, b),
the use checking and operand creation were off. We were potentially creating 
repeated identical instructions of existing values. This led to infinite
looping after I added the extra folds.

By using the simpler m_Not matcher and not creating new 'not' ops for a and b,
we avoid that problem. It's possible that not using IsFreeToInvert() here is
more limiting than the simpler matcher, but there are no tests for anything
more exotic. It's also possible that we should relax the use checking further
to handle a case like PR35834:
https://bugs.llvm.org/show_bug.cgi?id=35834
...but we can make that a follow-up if it is needed. 

llvm-svn: 321882
This commit is contained in:
Sanjay Patel 2018-01-05 19:01:17 +00:00
parent 16891b285a
commit 9884964af1
2 changed files with 40 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
lib/Transforms/InstCombine/InstCombineSelect.cpp
View File

@ -1551,6 +1551,18 @@ Instruction *InstCombiner::visitSelectInst(SelectInst &SI) {
Value *NewCast = Builder.CreateCast(CastOp, NewSI, SelType);
return replaceInstUsesWith(SI, NewCast);
}
// MAX(~a, ~b) -> ~MIN(a, b)
// MIN(~a, ~b) -> ~MAX(a, b)
Value *A, *B;
if (match(LHS, m_Not(m_Value(A))) && LHS->getNumUses() <= 2 &&
match(RHS, m_Not(m_Value(B))) && RHS->getNumUses() <= 2) {
CmpInst::Predicate InvertedPred =
getCmpPredicateForMinMax(getInverseMinMaxSelectPattern(SPF));
Value *InvertedCmp = Builder.CreateICmp(InvertedPred, A, B);
Value *NewSel = Builder.CreateSelect(InvertedCmp, A, B);
return BinaryOperator::CreateNot(NewSel);
}
}
if (SPF) {
@ -1570,28 +1582,6 @@ Instruction *InstCombiner::visitSelectInst(SelectInst &SI) {
return R;
}
// MAX(~a, ~b) -> ~MIN(a, b)
if ((SPF == SPF_SMAX || SPF == SPF_UMAX) &&
IsFreeToInvert(LHS, LHS->hasNUses(2)) &&
IsFreeToInvert(RHS, RHS->hasNUses(2))) {
// For this transform to be profitable, we need to eliminate at least two
// 'not' instructions if we're going to add one 'not' instruction.
int NumberOfNots =
(LHS->hasNUses(2) && match(LHS, m_Not(m_Value()))) +
(RHS->hasNUses(2) && match(RHS, m_Not(m_Value()))) +
(SI.hasOneUse() && match(*SI.user_begin(), m_Not(m_Value())));
if (NumberOfNots >= 2) {
Value *NewLHS = Builder.CreateNot(LHS);
Value *NewRHS = Builder.CreateNot(RHS);
Value *NewCmp = SPF == SPF_SMAX ? Builder.CreateICmpSLT(NewLHS, NewRHS)
: Builder.CreateICmpULT(NewLHS, NewRHS);
Value *NewSI =
Builder.CreateNot(Builder.CreateSelect(NewCmp, NewLHS, NewRHS));
return replaceInstUsesWith(SI, NewSI);
}
}
// TODO.
// ABS(-X) -> ABS(X)
}

28
test/Transforms/InstCombine/max-of-nots.ll
View File

@ -1,6 +1,34 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -instcombine < %s | FileCheck %s
define <2 x i32> @umin_of_nots(<2 x i32> %x, <2 x i32> %y) {
; CHECK-LABEL: @umin_of_nots(
; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt <2 x i32> %x, %y
; CHECK-NEXT: [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> %x, <2 x i32> %y
; CHECK-NEXT: [[MIN:%.*]] = xor <2 x i32> [[TMP2]], <i32 -1, i32 -1>
; CHECK-NEXT: ret <2 x i32> [[MIN]]
;
%notx = xor <2 x i32> %x, <i32 -1, i32 -1>
%noty = xor <2 x i32> %y, <i32 -1, i32 -1>
%cmp = icmp ult <2 x i32> %notx, %noty
%min = select <2 x i1> %cmp, <2 x i32> %notx, <2 x i32> %noty
ret <2 x i32> %min
}
define <2 x i32> @smin_of_nots(<2 x i32> %x, <2 x i32> %y) {
; CHECK-LABEL: @smin_of_nots(
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt <2 x i32> %x, %y
; CHECK-NEXT: [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> %x, <2 x i32> %y
; CHECK-NEXT: [[MIN:%.*]] = xor <2 x i32> [[TMP2]], <i32 -1, i32 -1>
; CHECK-NEXT: ret <2 x i32> [[MIN]]
;
%notx = xor <2 x i32> %x, <i32 -1, i32 -1>
%noty = xor <2 x i32> %y, <i32 -1, i32 -1>
%cmp = icmp sle <2 x i32> %notx, %noty
%min = select <2 x i1> %cmp, <2 x i32> %notx, <2 x i32> %noty
ret <2 x i32> %min
}
define i32 @compute_min_2(i32 %x, i32 %y) {
; CHECK-LABEL: @compute_min_2(
; CHECK-NEXT: [[TMP1:%.*]] = icmp slt i32 %x, %y