From da6888ed6b6cf6d82b4effb588b4ce76f69a049a Mon Sep 17 00:00:00 2001 From: Diana Picus Date: Wed, 24 May 2017 14:16:04 +0000 Subject: [PATCH] Revert "[SCEV] Do not fold dominated SCEVUnknown into AddRecExpr start" This reverts commit r303730 because it broke all the buildbots. llvm-svn: 303747 --- include/llvm/Analysis/ScalarEvolution.h | 6 -- lib/Analysis/ScalarEvolution.cpp | 61 +----------------- test/Analysis/IVUsers/quadradic-exit-value.ll | 36 +---------- .../ScalarEvolution/different-loops-recs.ll | 64 +------------------ .../X86/incorrect-offset-scaling.ll | 12 ++-- .../lsr-expand-quadratic.ll | 17 ++--- .../LoopStrengthReduce/post-inc-icmpzero.ll | 4 +- 7 files changed, 20 insertions(+), 180 deletions(-) diff --git a/include/llvm/Analysis/ScalarEvolution.h b/include/llvm/Analysis/ScalarEvolution.h index 4a6fc245c22..ac54bd4cfff 100644 --- a/include/llvm/Analysis/ScalarEvolution.h +++ b/include/llvm/Analysis/ScalarEvolution.h @@ -1533,12 +1533,6 @@ public: /// specified loop. bool isLoopInvariant(const SCEV *S, const Loop *L); - /// Determine if the SCEV can be evaluated at loop's entry. It is true if it - /// doesn't depend on a SCEVUnknown of an instruction which is dominated by - /// the header of loop L. - bool isAvailableAtLoopEntry(const SCEV *S, const Loop *L, DominatorTree &DT, - LoopInfo &LI); - /// Return true if the given SCEV changes value in a known way in the /// specified loop. This property being true implies that the value is /// variant in the loop AND that we can emit an expression to compute the diff --git a/lib/Analysis/ScalarEvolution.cpp b/lib/Analysis/ScalarEvolution.cpp index 584419c1df3..78ded8141c0 100644 --- a/lib/Analysis/ScalarEvolution.cpp +++ b/lib/Analysis/ScalarEvolution.cpp @@ -2178,63 +2178,6 @@ StrengthenNoWrapFlags(ScalarEvolution *SE, SCEVTypes Type, return Flags; } -bool ScalarEvolution::isAvailableAtLoopEntry(const SCEV *S, const Loop *L, - DominatorTree &DT, LoopInfo &LI) { - if (!isLoopInvariant(S, L)) - return false; - // If a value depends on a SCEVUnknown which is defined after the loop, we - // conservatively assume that we cannot calculate it at the loop's entry. - struct FindDominatedSCEVUnknown { - bool Found = false; - const Loop *L; - DominatorTree &DT; - LoopInfo &LI; - - FindDominatedSCEVUnknown(const Loop *L, DominatorTree &DT, LoopInfo &LI) - : L(L), DT(DT), LI(LI) {} - - bool checkSCEVUnknown(const SCEVUnknown *SU) { - if (auto *I = dyn_cast(SU->getValue())) { - if (DT.dominates(L->getHeader(), I->getParent())) - Found = true; - else - assert(DT.dominates(I->getParent(), L->getHeader()) && - "No dominance relationship between SCEV and loop?"); - } - return false; - } - - bool follow(const SCEV *S) { - switch (static_cast(S->getSCEVType())) { - case scConstant: - return false; - case scAddRecExpr: - case scTruncate: - case scZeroExtend: - case scSignExtend: - case scAddExpr: - case scMulExpr: - case scUMaxExpr: - case scSMaxExpr: - case scUDivExpr: - return true; - case scUnknown: - return checkSCEVUnknown(cast(S)); - case scCouldNotCompute: - llvm_unreachable("Attempt to use a SCEVCouldNotCompute object!"); - } - return false; - } - - bool isDone() { return Found; } - }; - - FindDominatedSCEVUnknown FSU(L, DT, LI); - SCEVTraversal ST(FSU); - ST.visitAll(S); - return !FSU.Found; -} - /// Get a canonical add expression, or something simpler if possible. const SCEV *ScalarEvolution::getAddExpr(SmallVectorImpl &Ops, SCEV::NoWrapFlags Flags, @@ -2516,7 +2459,7 @@ const SCEV *ScalarEvolution::getAddExpr(SmallVectorImpl &Ops, const SCEVAddRecExpr *AddRec = cast(Ops[Idx]); const Loop *AddRecLoop = AddRec->getLoop(); for (unsigned i = 0, e = Ops.size(); i != e; ++i) - if (isAvailableAtLoopEntry(Ops[i], AddRecLoop, DT, LI)) { + if (isLoopInvariant(Ops[i], AddRecLoop)) { LIOps.push_back(Ops[i]); Ops.erase(Ops.begin()+i); --i; --e; @@ -2791,7 +2734,7 @@ const SCEV *ScalarEvolution::getMulExpr(SmallVectorImpl &Ops, const SCEVAddRecExpr *AddRec = cast(Ops[Idx]); const Loop *AddRecLoop = AddRec->getLoop(); for (unsigned i = 0, e = Ops.size(); i != e; ++i) - if (isAvailableAtLoopEntry(Ops[i], AddRecLoop, DT, LI)) { + if (isLoopInvariant(Ops[i], AddRecLoop)) { LIOps.push_back(Ops[i]); Ops.erase(Ops.begin()+i); --i; --e; diff --git a/test/Analysis/IVUsers/quadradic-exit-value.ll b/test/Analysis/IVUsers/quadradic-exit-value.ll index afc21519821..6d4f1b039b4 100644 --- a/test/Analysis/IVUsers/quadradic-exit-value.ll +++ b/test/Analysis/IVUsers/quadradic-exit-value.ll @@ -30,47 +30,13 @@ exit: ret i64 %r } -; PR15470: LSR miscompile. The test1 function should return '1'. -; It is valid to fold SCEVUnknown into the recurrence because it -; was defined before the loop. -; -; SCEV does not know how to denormalize chained recurrences, so make -; sure they aren't marked as post-inc users. -; -; CHECK-LABEL: IV Users for loop %test1.loop -; CHECK-NO-LCSSA: %sext.us = {0,+,(16777216 + (-16777216 * %sub.us)),+,33554432}<%test1.loop> (post-inc with loop %test1.loop) in %f = ashr i32 %sext.us, 24 -define i32 @test1(i1 %cond) { -entry: - %sub.us = select i1 %cond, i32 0, i32 0 - br label %test1.loop - -test1.loop: - %inc1115.us = phi i32 [ 0, %entry ], [ %inc11.us, %test1.loop ] - %inc11.us = add nsw i32 %inc1115.us, 1 - %cmp.us = icmp slt i32 %inc11.us, 2 - br i1 %cmp.us, label %test1.loop, label %for.end - -for.end: - %tobool.us = icmp eq i32 %inc1115.us, 0 - %mul.us = shl i32 %inc1115.us, 24 - %sub.cond.us = sub nsw i32 %inc1115.us, %sub.us - %sext.us = mul i32 %mul.us, %sub.cond.us - %f = ashr i32 %sext.us, 24 - br label %exit - -exit: - ret i32 %f -} - ; PR15470: LSR miscompile. The test2 function should return '1'. -; It is illegal to fold SCEVUnknown (sext.us) into the recurrence -; because it is defined after the loop where this recurrence belongs. ; ; SCEV does not know how to denormalize chained recurrences, so make ; sure they aren't marked as post-inc users. ; ; CHECK-LABEL: IV Users for loop %test2.loop -; CHECK-NO-LCSSA: %sub.cond.us = ((-1 * %sub.us) + {0,+,1}<%test2.loop>) (post-inc with loop %test2.loop) in %sext.us = mul i32 %mul.us, %sub.cond.us +; CHECK-NO-LCSSA: %sext.us = {0,+,(16777216 + (-16777216 * %sub.us)),+,33554432}<%test2.loop> (post-inc with loop %test2.loop) in %f = ashr i32 %sext.us, 24 define i32 @test2() { entry: br label %test2.loop diff --git a/test/Analysis/ScalarEvolution/different-loops-recs.ll b/test/Analysis/ScalarEvolution/different-loops-recs.ll index 6b88f09e936..ad3d1e0bd11 100644 --- a/test/Analysis/ScalarEvolution/different-loops-recs.ll +++ b/test/Analysis/ScalarEvolution/different-loops-recs.ll @@ -220,8 +220,7 @@ exit: ; Mix of previous use cases that demonstrates %s3 can be incorrectly treated as ; a recurrence of loop1 because of operands order if we pick recurrencies in an -; incorrect order. It also shows that we cannot safely fold v1 (SCEVUnknown) -; because we cannot prove for sure that it doesn't use Phis of loop 2. +; incorrect order. define void @test_03(i32 %a, i32 %b, i32 %c, i32* %p) { @@ -229,9 +228,9 @@ define void @test_03(i32 %a, i32 %b, i32 %c, i32* %p) { ; CHECK: %v1 = load i32, i32* %p ; CHECK-NEXT: --> %v1 ; CHECK: %s1 = add i32 %phi1, %v1 -; CHECK-NEXT: --> ({%a,+,1}<%loop1> + %v1) +; CHECK-NEXT: --> {(%a + %v1),+,1}<%loop1> ; CHECK: %s2 = add i32 %s1, %b -; CHECK-NEXT: --> ({(%a + %b),+,1}<%loop1> + %v1) +; CHECK-NEXT: --> {(%a + %b + %v1),+,1}<%loop1> ; CHECK: %s3 = add i32 %s2, %phi2 ; CHECK-NEXT: --> ({{{{}}((2 * %a) + %b),+,1}<%loop1>,+,2}<%loop2> + %v1) @@ -453,60 +452,3 @@ exit: %s6 = add i32 %phi3, %phi2 ret void } - -; Make sure that a complicated Phi does not get folded with rec's start value -; of a loop which is above. -define void @test_08() { - -; CHECK-LABEL: Classifying expressions for: @test_08 -; CHECK: %tmp11 = add i64 %iv.2.2, %iv.2.1 -; CHECK-NEXT: --> ({0,+,-1}<%loop_2> + %iv.2.1) -; CHECK: %tmp12 = trunc i64 %tmp11 to i32 -; CHECK-NEXT: --> (trunc i64 ({0,+,-1}<%loop_2> + %iv.2.1) to i32) -; CHECK: %tmp14 = mul i32 %tmp12, %tmp7 -; CHECK-NEXT: --> ((trunc i64 ({0,+,-1}<%loop_2> + %iv.2.1) to i32) * {-1,+,-1}<%loop_1>) -; CHECK: %tmp16 = mul i64 %iv.2.1, %iv.1.1 -; CHECK-NEXT: --> ({2,+,1}<%loop_1> * %iv.2.1) - -entry: - br label %loop_1 - -loop_1: - %iv.1.1 = phi i64 [ 2, %entry ], [ %iv.1.1.next, %loop_1_back_branch ] - %iv.1.2 = phi i32 [ -1, %entry ], [ %iv.1.2.next, %loop_1_back_branch ] - br label %loop_1_exit - -dead: - br label %loop_1_exit - -loop_1_exit: - %tmp5 = icmp sgt i64 %iv.1.1, 2 - br i1 %tmp5, label %loop_2_preheader, label %loop_1_back_branch - -loop_1_back_branch: - %iv.1.1.next = add nuw nsw i64 %iv.1.1, 1 - %iv.1.2.next = add nsw i32 %iv.1.2, 1 - br label %loop_1 - -loop_2_preheader: - %tmp6 = sub i64 1, %iv.1.1 - %tmp7 = trunc i64 %tmp6 to i32 - br label %loop_2 - -loop_2: - %iv.2.1 = phi i64 [ 0, %loop_2_preheader ], [ %tmp16, %loop_2 ] - %iv.2.2 = phi i64 [ 0, %loop_2_preheader ], [ %iv.2.2.next, %loop_2 ] - %iv.2.3 = phi i64 [ 2, %loop_2_preheader ], [ %iv.2.3.next, %loop_2 ] - %tmp11 = add i64 %iv.2.2, %iv.2.1 - %tmp12 = trunc i64 %tmp11 to i32 - %tmp14 = mul i32 %tmp12, %tmp7 - %tmp16 = mul i64 %iv.2.1, %iv.1.1 - %iv.2.3.next = add nuw nsw i64 %iv.2.3, 1 - %iv.2.2.next = add nsw i64 %iv.2.2, -1 - %tmp17 = icmp slt i64 %iv.2.3.next, %iv.1.1 - br i1 %tmp17, label %loop_2, label %exit - -exit: - %tmp10 = add i32 %iv.1.2, 3 - ret void -} diff --git a/test/Transforms/LoopStrengthReduce/X86/incorrect-offset-scaling.ll b/test/Transforms/LoopStrengthReduce/X86/incorrect-offset-scaling.ll index 00c3222b005..3adb8bcf514 100644 --- a/test/Transforms/LoopStrengthReduce/X86/incorrect-offset-scaling.ll +++ b/test/Transforms/LoopStrengthReduce/X86/incorrect-offset-scaling.ll @@ -25,7 +25,7 @@ L2: ; preds = %idxend.8 if6: ; preds = %idxend.8 %r2 = add i64 %0, -1 %r3 = load i64, i64* %1, align 8 -; CHECK: %r2 = add i64 %0, -1 +; CHECK-NOT: %r2 ; CHECK: %r3 = load i64 br label %ib @@ -36,11 +36,13 @@ ib: ; preds = %if6 %r4 = mul i64 %r3, %r0 %r5 = add i64 %r2, %r4 %r6 = icmp ult i64 %r5, undef -; CHECK: %r4 = mul i64 %r3, %lsr.iv -; CHECK: %r5 = add i64 %r2, %r4 -; CHECK: %r6 = icmp ult i64 %r5, undef -; CHECK: %r7 = getelementptr i64, i64* undef, i64 %r5 +; CHECK: [[MUL1:%[0-9]+]] = mul i64 %lsr.iv, %r3 +; CHECK: [[ADD1:%[0-9]+]] = add i64 [[MUL1]], -1 +; CHECK: add i64 %{{.}}, [[ADD1]] +; CHECK: %r6 %r7 = getelementptr i64, i64* undef, i64 %r5 store i64 1, i64* %r7, align 8 +; CHECK: [[MUL2:%[0-9]+]] = mul i64 %lsr.iv, %r3 +; CHECK: [[ADD2:%[0-9]+]] = add i64 [[MUL2]], -1 br label %L } diff --git a/test/Transforms/LoopStrengthReduce/lsr-expand-quadratic.ll b/test/Transforms/LoopStrengthReduce/lsr-expand-quadratic.ll index c7cdbec3c38..aa688d999e6 100644 --- a/test/Transforms/LoopStrengthReduce/lsr-expand-quadratic.ll +++ b/test/Transforms/LoopStrengthReduce/lsr-expand-quadratic.ll @@ -7,23 +7,16 @@ target triple = "x86_64-apple-macosx" ; ; SCEV expander cannot expand quadratic recurrences outside of the ; loop. This recurrence depends on %sub.us, so can't be expanded. -; We cannot fold SCEVUnknown (sub.us) with recurrences since it is -; declared after the loop. ; ; CHECK-LABEL: @test2 ; CHECK-LABEL: test2.loop: -; CHECK: %lsr.iv1 = phi i32 [ %lsr.iv.next2, %test2.loop ], [ -16777216, %entry ] -; CHECK: %lsr.iv = phi i32 [ %lsr.iv.next, %test2.loop ], [ -1, %entry ] -; CHECK: %lsr.iv.next = add nsw i32 %lsr.iv, 1 -; CHECK: %lsr.iv.next2 = add nsw i32 %lsr.iv1, 16777216 +; CHECK: %lsr.iv = phi i32 [ %lsr.iv.next, %test2.loop ], [ -16777216, %entry ] +; CHECK: %lsr.iv.next = add nsw i32 %lsr.iv, 16777216 ; ; CHECK-LABEL: for.end: -; CHECK: %tobool.us = icmp eq i32 %lsr.iv.next2, 0 -; CHECK: %sub.us = select i1 %tobool.us, i32 0, i32 0 -; CHECK: %1 = sub i32 0, %sub.us -; CHECK: %2 = add i32 %1, %lsr.iv.next -; CHECK: %sext.us = mul i32 %lsr.iv.next2, %2 -; CHECK: %f = ashr i32 %sext.us, 24 +; CHECK: %sub.cond.us = sub nsw i32 %inc1115.us, %sub.us +; CHECK: %sext.us = mul i32 %lsr.iv.next, %sub.cond.us +; CHECK: %f = ashr i32 %sext.us, 24 ; CHECK: ret i32 %f define i32 @test2() { entry: diff --git a/test/Transforms/LoopStrengthReduce/post-inc-icmpzero.ll b/test/Transforms/LoopStrengthReduce/post-inc-icmpzero.ll index cbf177c0d4b..fbf55fd81d2 100644 --- a/test/Transforms/LoopStrengthReduce/post-inc-icmpzero.ll +++ b/test/Transforms/LoopStrengthReduce/post-inc-icmpzero.ll @@ -25,8 +25,6 @@ define void @_Z15IntegerToStringjjR7Vector2(i32 %i, i32 %radix, %struct.Vector2* entry: %buffer = alloca [33 x i16], align 16 %add.ptr = getelementptr inbounds [33 x i16], [33 x i16]* %buffer, i64 0, i64 33 - %sub.ptr.lhs.cast = ptrtoint i16* %add.ptr to i64 - %sub.ptr.rhs.cast = ptrtoint i16* %add.ptr to i64 br label %do.body do.body: ; preds = %do.body, %entry @@ -48,6 +46,8 @@ do.body: ; preds = %do.body, %entry do.end: ; preds = %do.body %xap.0 = inttoptr i64 %0 to i1* %cap.0 = ptrtoint i1* %xap.0 to i64 + %sub.ptr.lhs.cast = ptrtoint i16* %add.ptr to i64 + %sub.ptr.rhs.cast = ptrtoint i16* %incdec.ptr to i64 %sub.ptr.sub = sub i64 %sub.ptr.lhs.cast, %sub.ptr.rhs.cast %sub.ptr.div39 = lshr exact i64 %sub.ptr.sub, 1 %conv11 = trunc i64 %sub.ptr.div39 to i32