From 12367d94353605953c2b67fd9d0f69f3e5f81b95 Mon Sep 17 00:00:00 2001 From: Nikolai Bozhenov Date: Tue, 17 Oct 2017 11:50:48 +0000 Subject: [PATCH] Improve clamp recognition in ValueTracking. Summary: ValueTracking was recognizing not all variations of clamp. Swapping of true value and false value of select was added to fix this problem. This change breaks the canonical form of cmp inside the matchMinMax function, that is why additional checks for compare predicates is needed. Added corresponding test cases. Reviewers: spatel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D38531 Patch by: Artur Gainullin git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@315992 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/Analysis/ValueTracking.cpp | 45 ++++++++++++++++------ test/Transforms/InstCombine/minmax-fold.ll | 20 +++++----- 2 files changed, 43 insertions(+), 22 deletions(-) diff --git a/lib/Analysis/ValueTracking.cpp b/lib/Analysis/ValueTracking.cpp index 3eddebb8b41..f70f2d19ac6 100644 --- a/lib/Analysis/ValueTracking.cpp +++ b/lib/Analysis/ValueTracking.cpp @@ -4083,6 +4083,14 @@ static SelectPatternResult matchMinMax(CmpInst::Predicate Pred, Value *CmpLHS, Value *CmpRHS, Value *TrueVal, Value *FalseVal, Value *&LHS, Value *&RHS) { + assert(!ICmpInst::isEquality(Pred) && "Expected not equality predicate only!"); + + // First, check if select has inverse order of what we will check below: + if (CmpRHS == FalseVal) { + std::swap(TrueVal, FalseVal); + Pred = CmpInst::getInversePredicate(Pred); + } + // Assume success. If there's no match, callers should not use these anyway. LHS = TrueVal; RHS = FalseVal; @@ -4095,26 +4103,30 @@ static SelectPatternResult matchMinMax(CmpInst::Predicate Pred, // (X SMAX(SMIN(X, C2), C1) if (match(FalseVal, m_SMin(m_Specific(CmpLHS), m_APInt(C2))) && - C1->slt(*C2) && Pred == CmpInst::ICMP_SLT) + C1->slt(*C2) && + (Pred == CmpInst::ICMP_SLT || Pred == CmpInst::ICMP_SLE)) return {SPF_SMAX, SPNB_NA, false}; // (X >s C1) ? C1 : SMAX(X, C2) ==> SMIN(SMAX(X, C2), C1) if (match(FalseVal, m_SMax(m_Specific(CmpLHS), m_APInt(C2))) && - C1->sgt(*C2) && Pred == CmpInst::ICMP_SGT) + C1->sgt(*C2) && + (Pred == CmpInst::ICMP_SGT || Pred == CmpInst::ICMP_SGE)) return {SPF_SMIN, SPNB_NA, false}; // (X UMAX(UMIN(X, C2), C1) if (match(FalseVal, m_UMin(m_Specific(CmpLHS), m_APInt(C2))) && - C1->ult(*C2) && Pred == CmpInst::ICMP_ULT) + C1->ult(*C2) && + (Pred == CmpInst::ICMP_ULT || Pred == CmpInst::ICMP_ULE)) return {SPF_UMAX, SPNB_NA, false}; // (X >u C1) ? C1 : UMAX(X, C2) ==> UMIN(UMAX(X, C2), C1) if (match(FalseVal, m_UMax(m_Specific(CmpLHS), m_APInt(C2))) && - C1->ugt(*C2) && Pred == CmpInst::ICMP_UGT) + C1->ugt(*C2) && + (Pred == CmpInst::ICMP_UGT || Pred == CmpInst::ICMP_UGE)) return {SPF_UMIN, SPNB_NA, false}; } - if (Pred != CmpInst::ICMP_SGT && Pred != CmpInst::ICMP_SLT) + if (!CmpInst::isSigned(Pred)) return {SPF_UNKNOWN, SPNB_NA, false}; // Z = X -nsw Y @@ -4122,14 +4134,18 @@ static SelectPatternResult matchMinMax(CmpInst::Predicate Pred, // (X (Z SMAX(Z, 0) if (match(TrueVal, m_Zero()) && match(FalseVal, m_NSWSub(m_Specific(CmpLHS), m_Specific(CmpRHS)))) - return {Pred == CmpInst::ICMP_SGT ? SPF_SMIN : SPF_SMAX, SPNB_NA, false}; + return {(Pred == CmpInst::ICMP_SGT || Pred == CmpInst::ICMP_SGE) ? SPF_SMIN + : SPF_SMAX, + SPNB_NA, false}; // Z = X -nsw Y // (X >s Y) ? Z : 0 ==> (Z >s 0) ? Z : 0 ==> SMAX(Z, 0) // (X (Z SMIN(Z, 0) if (match(FalseVal, m_Zero()) && match(TrueVal, m_NSWSub(m_Specific(CmpLHS), m_Specific(CmpRHS)))) - return {Pred == CmpInst::ICMP_SGT ? SPF_SMAX : SPF_SMIN, SPNB_NA, false}; + return {(Pred == CmpInst::ICMP_SGT || Pred == CmpInst::ICMP_SGE) ? SPF_SMAX + : SPF_SMIN, + SPNB_NA, false}; if (!match(CmpRHS, m_APInt(C1))) return {SPF_UNKNOWN, SPNB_NA, false}; @@ -4141,14 +4157,15 @@ static SelectPatternResult matchMinMax(CmpInst::Predicate Pred, // Is the sign bit set? // (X (X >u MAXVAL) ? X : MAXVAL ==> UMAX // (X (X >u MAXVAL) ? MAXVAL : X ==> UMIN - if (Pred == CmpInst::ICMP_SLT && *C1 == 0 && C2->isMaxSignedValue()) + if ((Pred == CmpInst::ICMP_SLT || Pred == CmpInst::ICMP_SLE) && *C1 == 0 && + C2->isMaxSignedValue()) return {CmpLHS == TrueVal ? SPF_UMAX : SPF_UMIN, SPNB_NA, false}; // Is the sign bit clear? // (X >s -1) ? MINVAL : X ==> (X UMAX // (X >s -1) ? X : MINVAL ==> (X UMIN - if (Pred == CmpInst::ICMP_SGT && C1->isAllOnesValue() && - C2->isMinSignedValue()) + if ((Pred == CmpInst::ICMP_SGT || Pred == CmpInst::ICMP_SGE) && + C1->isAllOnesValue() && C2->isMinSignedValue()) return {CmpLHS == FalseVal ? SPF_UMAX : SPF_UMIN, SPNB_NA, false}; } @@ -4157,13 +4174,17 @@ static SelectPatternResult matchMinMax(CmpInst::Predicate Pred, // (X (~X >s ~C) ? ~X : ~C ==> SMAX(~X, ~C) if (match(TrueVal, m_Not(m_Specific(CmpLHS))) && match(FalseVal, m_APInt(C2)) && ~(*C1) == *C2) - return {Pred == CmpInst::ICMP_SGT ? SPF_SMIN : SPF_SMAX, SPNB_NA, false}; + return {(Pred == CmpInst::ICMP_SGT || Pred == CmpInst::ICMP_SGE) ? SPF_SMIN + : SPF_SMAX, + SPNB_NA, false}; // (X >s C) ? ~C : ~X ==> (~X SMAX(~C, ~X) // (X (~X >s ~C) ? ~C : ~X ==> SMIN(~C, ~X) if (match(FalseVal, m_Not(m_Specific(CmpLHS))) && match(TrueVal, m_APInt(C2)) && ~(*C1) == *C2) - return {Pred == CmpInst::ICMP_SGT ? SPF_SMAX : SPF_SMIN, SPNB_NA, false}; + return {(Pred == CmpInst::ICMP_SGT || Pred == CmpInst::ICMP_SGE) ? SPF_SMAX + : SPF_SMIN, + SPNB_NA, false}; return {SPF_UNKNOWN, SPNB_NA, false}; } diff --git a/test/Transforms/InstCombine/minmax-fold.ll b/test/Transforms/InstCombine/minmax-fold.ll index 20f8167777f..f0873147849 100644 --- a/test/Transforms/InstCombine/minmax-fold.ll +++ b/test/Transforms/InstCombine/minmax-fold.ll @@ -404,8 +404,8 @@ define i32 @clamp_signed3(i32 %x) { ; CHECK-LABEL: @clamp_signed3( ; CHECK-NEXT: [[CMP2:%.*]] = icmp slt i32 [[X:%.*]], 255 ; CHECK-NEXT: [[MIN:%.*]] = select i1 [[CMP2]], i32 [[X]], i32 255 -; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[X]], 15 -; CHECK-NEXT: [[R:%.*]] = select i1 [[CMP1]], i32 [[MIN]], i32 15 +; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[MIN]], 15 +; CHECK-NEXT: [[R:%.*]] = select i1 [[TMP1]], i32 [[MIN]], i32 15 ; CHECK-NEXT: ret i32 [[R]] ; %cmp2 = icmp slt i32 %x, 255 @@ -421,8 +421,8 @@ define i32 @clamp_signed4(i32 %x) { ; CHECK-LABEL: @clamp_signed4( ; CHECK-NEXT: [[CMP2:%.*]] = icmp sgt i32 [[X:%.*]], 15 ; CHECK-NEXT: [[MAX:%.*]] = select i1 [[CMP2]], i32 [[X]], i32 15 -; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i32 [[X]], 255 -; CHECK-NEXT: [[R:%.*]] = select i1 [[CMP1]], i32 [[MAX]], i32 255 +; CHECK-NEXT: [[TMP1:%.*]] = icmp slt i32 [[MAX]], 255 +; CHECK-NEXT: [[R:%.*]] = select i1 [[TMP1]], i32 [[MAX]], i32 255 ; CHECK-NEXT: ret i32 [[R]] ; %cmp2 = icmp sgt i32 %x, 15 @@ -472,8 +472,8 @@ define i32 @clamp_unsigned3(i32 %x) { ; CHECK-LABEL: @clamp_unsigned3( ; CHECK-NEXT: [[CMP2:%.*]] = icmp ult i32 [[X:%.*]], 255 ; CHECK-NEXT: [[MIN:%.*]] = select i1 [[CMP2]], i32 [[X]], i32 255 -; CHECK-NEXT: [[CMP1:%.*]] = icmp ugt i32 [[X]], 15 -; CHECK-NEXT: [[R:%.*]] = select i1 [[CMP1]], i32 [[MIN]], i32 15 +; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[MIN]], 15 +; CHECK-NEXT: [[R:%.*]] = select i1 [[TMP1]], i32 [[MIN]], i32 15 ; CHECK-NEXT: ret i32 [[R]] ; %cmp2 = icmp ult i32 %x, 255 @@ -489,8 +489,8 @@ define i32 @clamp_unsigned4(i32 %x) { ; CHECK-LABEL: @clamp_unsigned4( ; CHECK-NEXT: [[CMP2:%.*]] = icmp ugt i32 [[X:%.*]], 15 ; CHECK-NEXT: [[MAX:%.*]] = select i1 [[CMP2]], i32 [[X]], i32 15 -; CHECK-NEXT: [[CMP1:%.*]] = icmp ult i32 [[X]], 255 -; CHECK-NEXT: [[R:%.*]] = select i1 [[CMP1]], i32 [[MAX]], i32 255 +; CHECK-NEXT: [[TMP1:%.*]] = icmp ult i32 [[MAX]], 255 +; CHECK-NEXT: [[R:%.*]] = select i1 [[TMP1]], i32 [[MAX]], i32 255 ; CHECK-NEXT: ret i32 [[R]] ; %cmp2 = icmp ugt i32 %x, 15 @@ -523,8 +523,8 @@ define i32 @clamp_check_for_no_infinite_loop2(i32 %i) { ; CHECK-LABEL: @clamp_check_for_no_infinite_loop2( ; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[I:%.*]], -255 ; CHECK-NEXT: [[SEL1:%.*]] = select i1 [[CMP1]], i32 [[I]], i32 -255 -; CHECK-NEXT: [[CMP2:%.*]] = icmp slt i32 [[I]], 0 -; CHECK-NEXT: [[RES:%.*]] = select i1 [[CMP2]], i32 [[SEL1]], i32 0 +; CHECK-NEXT: [[TMP1:%.*]] = icmp slt i32 [[SEL1]], 0 +; CHECK-NEXT: [[RES:%.*]] = select i1 [[TMP1]], i32 [[SEL1]], i32 0 ; CHECK-NEXT: ret i32 [[RES]] ; %cmp1 = icmp sgt i32 %i, -255 -- 2.40.0