diff options
10 files changed, 75 insertions, 71 deletions
diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp index 2958a5054afc..c784c27d36b4 100644 --- a/llvm/lib/Analysis/ScalarEvolution.cpp +++ b/llvm/lib/Analysis/ScalarEvolution.cpp @@ -5917,8 +5917,13 @@ const SCEV *ScalarEvolution::createNodeForPHI(PHINode *PN) { if (const SCEV *S = createNodeFromSelectLikePHI(PN)) return S; + // If the PHI has a single incoming value, follow that value, unless the + // PHI's incoming blocks are in a different loop, in which case doing so + // risks breaking LCSSA form. Instcombine would normally zap these, but + // it doesn't have DominatorTree information, so it may miss cases. if (Value *V = simplifyInstruction(PN, {getDataLayout(), &TLI, &DT, &AC})) - return getSCEV(V); + if (LI.replacementPreservesLCSSAForm(PN, V)) + return getSCEV(V); // If it's not a loop phi, we can't handle it yet. return getUnknown(PN); diff --git a/llvm/test/Analysis/DependenceAnalysis/lcssa.ll b/llvm/test/Analysis/DependenceAnalysis/lcssa.ll index 801b24276f5b..2bd20f39f4a7 100644 --- a/llvm/test/Analysis/DependenceAnalysis/lcssa.ll +++ b/llvm/test/Analysis/DependenceAnalysis/lcssa.ll @@ -2,7 +2,7 @@ ; RUN: "-aa-pipeline=basic-aa,tbaa" 2>&1 | FileCheck %s ; CHECK: Src: %v = load i32, i32* %arrayidx1, align 4 --> Dst: store i32 %add, i32* %a.lcssa, align 4 -; CHECK-NEXT: da analyze - anti [*|<]! +; CHECK-NEXT: da analyze - confused! define void @f(i32 *%a, i32 %n, i64 %n2) { entry: diff --git a/llvm/test/Analysis/ScalarEvolution/cycled_phis.ll b/llvm/test/Analysis/ScalarEvolution/cycled_phis.ll index 80cf153c913b..7183bb8c0a63 100644 --- a/llvm/test/Analysis/ScalarEvolution/cycled_phis.ll +++ b/llvm/test/Analysis/ScalarEvolution/cycled_phis.ll @@ -46,7 +46,7 @@ define void @test_02(i32* %p, i32* %q) { ; CHECK-NEXT: %inner_cond = call i1 @cond() ; CHECK-NEXT: --> %inner_cond U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %inner_loop: Variant, %outer_loop: Variant } ; CHECK-NEXT: %inner_lcssa = phi i32 [ %inner_phi, %inner_loop ] -; CHECK-NEXT: --> %inner_phi U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %outer_loop: Variant, %inner_loop: Variant } +; CHECK-NEXT: --> %inner_lcssa U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %outer_loop: Variant, %inner_loop: Invariant } ; CHECK-NEXT: %outer_cond = call i1 @cond() ; CHECK-NEXT: --> %outer_cond U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %outer_loop: Variant, %inner_loop: Invariant } ; CHECK-NEXT: Determining loop execution counts for: @test_02 @@ -97,7 +97,7 @@ define void @test_03(i32* %p, i32* %q) { ; CHECK-NEXT: %inner_cond = call i1 @cond() ; CHECK-NEXT: --> %inner_cond U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %inner_loop: Variant, %outer_loop: Variant } ; CHECK-NEXT: %inner_lcssa = phi i32 [ %inner_phi_1, %inner_loop ] -; CHECK-NEXT: --> %inner_phi_1 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %outer_loop: Variant, %inner_loop: Variant } +; CHECK-NEXT: --> %inner_lcssa U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %outer_loop: Variant, %inner_loop: Invariant } ; CHECK-NEXT: %outer_cond = call i1 @cond() ; CHECK-NEXT: --> %outer_cond U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %outer_loop: Variant, %inner_loop: Invariant } ; CHECK-NEXT: Determining loop execution counts for: @test_03 diff --git a/llvm/test/Analysis/ScalarEvolution/incorrect-exit-count.ll b/llvm/test/Analysis/ScalarEvolution/incorrect-exit-count.ll index daf12d0dc710..11a053f5e5fc 100644 --- a/llvm/test/Analysis/ScalarEvolution/incorrect-exit-count.ll +++ b/llvm/test/Analysis/ScalarEvolution/incorrect-exit-count.ll @@ -53,7 +53,7 @@ define dso_local i32 @f() { ; CHECK-NEXT: %dec.3 = add nsw i32 %storemerge1921.3, -1 ; CHECK-NEXT: --> {2,+,-1}<nsw><%inner.loop> U: [2,3) S: [2,3) Exits: <<Unknown>> LoopDispositions: { %inner.loop: Computable, %outer.loop: Variant } ; CHECK-NEXT: %storemerge1921.lcssa25.3 = phi i32 [ %storemerge1921.3, %for.end.3 ] -; CHECK-NEXT: --> {3,+,-1}<nuw><nsw><%inner.loop> U: [3,4) S: [3,4) Exits: <<Unknown>> LoopDispositions: { %outer.loop: Variant, %for.cond6: Variant, %inner.loop: Computable } +; CHECK-NEXT: --> %storemerge1921.lcssa25.3 U: [3,4) S: [3,4) Exits: <<Unknown>> LoopDispositions: { %outer.loop: Variant, %for.cond6: Invariant, %inner.loop: Invariant } ; CHECK-NEXT: %dec16 = add nsw i32 %storemerge23, -1 ; CHECK-NEXT: --> {2,+,-1}<nsw><%outer.loop> U: [0,3) S: [0,3) Exits: <<Unknown>> LoopDispositions: { %outer.loop: Computable, %for.cond6: Invariant, %inner.loop: Invariant } ; CHECK-NEXT: Determining loop execution counts for: @f diff --git a/llvm/test/Analysis/ScalarEvolution/solve-quadratic-i1.ll b/llvm/test/Analysis/ScalarEvolution/solve-quadratic-i1.ll index bc6f14135b1a..490ba57a92df 100644 --- a/llvm/test/Analysis/ScalarEvolution/solve-quadratic-i1.ll +++ b/llvm/test/Analysis/ScalarEvolution/solve-quadratic-i1.ll @@ -59,9 +59,9 @@ define void @f1() #0 { ; CHECK-NEXT: %v6 = add nuw nsw i32 %v1, 1 ; CHECK-NEXT: --> {4,+,1}<nuw><nsw><%b1> U: [4,7) S: [4,7) Exits: 6 LoopDispositions: { %b1: Computable } ; CHECK-NEXT: %v7 = phi i32 [ %v1, %b1 ] -; CHECK-NEXT: --> {3,+,1}<nuw><nsw><%b1> U: [3,6) S: [3,6) --> 5 U: [5,6) S: [5,6) +; CHECK-NEXT: --> %v7 U: [3,6) S: [3,6) --> 5 U: [5,6) S: [5,6) ; CHECK-NEXT: %v8 = phi i16 [ %v3, %b1 ] -; CHECK-NEXT: --> {3,+,4,+,1}<%b1> U: full-set S: full-set --> 12 U: [12,13) S: [12,13) +; CHECK-NEXT: --> %v8 U: full-set S: full-set --> 12 U: [12,13) S: [12,13) ; CHECK-NEXT: Determining loop execution counts for: @f1 ; CHECK-NEXT: Loop %b3: <multiple exits> Unpredictable backedge-taken count. ; CHECK-NEXT: Loop %b3: Unpredictable max backedge-taken count. diff --git a/llvm/test/Analysis/ScalarEvolution/solve-quadratic-overflow.ll b/llvm/test/Analysis/ScalarEvolution/solve-quadratic-overflow.ll index 10473e238583..519450720cde 100644 --- a/llvm/test/Analysis/ScalarEvolution/solve-quadratic-overflow.ll +++ b/llvm/test/Analysis/ScalarEvolution/solve-quadratic-overflow.ll @@ -12,11 +12,11 @@ ; CHECK-NEXT: %v3 = mul i16 %v2, %v2 ; CHECK-NEXT: --> {1,+,3,+,2}<%b1> U: full-set S: full-set Exits: 0 LoopDispositions: { %b1: Computable } ; CHECK-NEXT: %v5 = phi i16 [ %v2, %b1 ] -; CHECK-NEXT: --> {-1,+,-1}<%b1> U: [-256,0) S: [-256,0) --> -256 U: [-256,-255) S: [-256,-255) +; CHECK-NEXT: --> %v5 U: [-256,0) S: [-256,0) ; CHECK-NEXT: %v6 = phi i16 [ %v3, %b1 ] -; CHECK-NEXT: --> {1,+,3,+,2}<%b1> U: full-set S: full-set --> 0 U: [0,1) S: [0,1) +; CHECK-NEXT: --> %v6 U: full-set S: full-set ; CHECK-NEXT: %v7 = sext i16 %v5 to i32 -; CHECK-NEXT: --> {-1,+,-1}<nsw><%b1> U: [-256,0) S: [-256,0) --> -256 U: [-256,-255) S: [-256,-255) +; CHECK-NEXT: --> (sext i16 %v5 to i32) U: [-256,0) S: [-256,0) ; CHECK-NEXT: Determining loop execution counts for: @f0 ; CHECK-NEXT: Loop %b1: backedge-taken count is 255 ; CHECK-NEXT: Loop %b1: max backedge-taken count is 255 diff --git a/llvm/test/Analysis/ScalarEvolution/trivial-phis.ll b/llvm/test/Analysis/ScalarEvolution/trivial-phis.ll index 45a567bfbe3c..b3192cbf16d2 100644 --- a/llvm/test/Analysis/ScalarEvolution/trivial-phis.ll +++ b/llvm/test/Analysis/ScalarEvolution/trivial-phis.ll @@ -2,7 +2,7 @@ ; CHECK-LABEL: @test1 ; CHECK: %add.lcssa.wide = phi i64 [ %indvars.iv.next, %do.body ] -; CHECK-NEXT: --> {1,+,1}<nuw><nsw><%do.body> U: [1,2147483648) S: [1,2147483648) +; CHECK-NEXT: --> %add.lcssa.wide U: [1,2147483648) S: [1,2147483648) define i64 @test1(i32 signext %n, float* %A) { entry: diff --git a/llvm/test/Transforms/LoopStrengthReduce/funclet.ll b/llvm/test/Transforms/LoopStrengthReduce/funclet.ll index ca0a86635ec0..c6b2029fc18d 100644 --- a/llvm/test/Transforms/LoopStrengthReduce/funclet.ll +++ b/llvm/test/Transforms/LoopStrengthReduce/funclet.ll @@ -15,21 +15,23 @@ define void @f() personality i32 (...)* @_except_handler3 { ; CHECK-NEXT: entry: ; CHECK-NEXT: br label [[THROW:%.*]] ; CHECK: throw: +; CHECK-NEXT: [[TMP96:%.*]] = getelementptr inbounds i8, i8* undef, i32 1 ; CHECK-NEXT: invoke void @reserve() ; CHECK-NEXT: to label [[THROW]] unwind label [[PAD:%.*]] ; CHECK: pad: +; CHECK-NEXT: [[PHI2:%.*]] = phi i8* [ [[TMP96]], [[THROW]] ] ; CHECK-NEXT: [[CS:%.*]] = catchswitch within none [label %unreachable] unwind label [[BLAH2:%.*]] ; CHECK: unreachable: ; CHECK-NEXT: [[TMP0:%.*]] = catchpad within [[CS]] [] ; CHECK-NEXT: unreachable ; CHECK: blah2: ; CHECK-NEXT: [[CLEANUPPADI4_I_I_I:%.*]] = cleanuppad within none [] +; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[PHI2]], i32 -1 ; CHECK-NEXT: br label [[LOOP_BODY:%.*]] ; CHECK: loop_body: -; CHECK-NEXT: [[LSR_IV:%.*]] = phi i32 [ [[LSR_IV_NEXT:%.*]], [[ITER:%.*]] ], [ 0, [[BLAH2]] ] -; CHECK-NEXT: [[LSR_IV_NEXT]] = add nuw nsw i32 [[LSR_IV]], -1 -; CHECK-NEXT: [[LSR_IV_NEXT1:%.*]] = inttoptr i32 [[LSR_IV_NEXT]] to i8* -; CHECK-NEXT: [[TMP100:%.*]] = icmp eq i8* [[LSR_IV_NEXT1]], null +; CHECK-NEXT: [[LSR_IV:%.*]] = phi i8* [ [[SCEVGEP1:%.*]], [[ITER:%.*]] ], [ [[SCEVGEP]], [[BLAH2]] ] +; CHECK-NEXT: [[SCEVGEP1]] = getelementptr i8, i8* [[LSR_IV]], i32 1 +; CHECK-NEXT: [[TMP100:%.*]] = icmp eq i8* [[SCEVGEP1]], undef ; CHECK-NEXT: br i1 [[TMP100]], label [[UNWIND_OUT:%.*]], label [[ITER]] ; CHECK: iter: ; CHECK-NEXT: br i1 true, label [[UNWIND_OUT]], label [[LOOP_BODY]] @@ -74,25 +76,27 @@ define void @g() personality i32 (...)* @_except_handler3 { ; CHECK-NEXT: entry: ; CHECK-NEXT: br label [[THROW:%.*]] ; CHECK: throw: +; CHECK-NEXT: [[TMP96:%.*]] = getelementptr inbounds i8, i8* undef, i32 1 ; CHECK-NEXT: invoke void @reserve() ; CHECK-NEXT: to label [[THROW]] unwind label [[PAD:%.*]] ; CHECK: pad: +; CHECK-NEXT: [[PHI2:%.*]] = phi i8* [ [[TMP96]], [[THROW]] ] ; CHECK-NEXT: [[CS:%.*]] = catchswitch within none [label [[UNREACHABLE:%.*]], label %blah] unwind to caller ; CHECK: unreachable: ; CHECK-NEXT: [[TMP0:%.*]] = catchpad within [[CS]] [] ; CHECK-NEXT: unreachable ; CHECK: blah: ; CHECK-NEXT: [[CATCHPAD:%.*]] = catchpad within [[CS]] [] +; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[PHI2]], i32 -1 ; CHECK-NEXT: br label [[LOOP_BODY:%.*]] ; CHECK: unwind_out: ; CHECK-NEXT: catchret from [[CATCHPAD]] to label [[LEAVE:%.*]] ; CHECK: leave: ; CHECK-NEXT: ret void ; CHECK: loop_body: -; CHECK-NEXT: [[LSR_IV:%.*]] = phi i32 [ [[LSR_IV_NEXT:%.*]], [[ITER:%.*]] ], [ 0, [[BLAH:%.*]] ] -; CHECK-NEXT: [[LSR_IV_NEXT]] = add nuw nsw i32 [[LSR_IV]], -1 -; CHECK-NEXT: [[LSR_IV_NEXT1:%.*]] = inttoptr i32 [[LSR_IV_NEXT]] to i8* -; CHECK-NEXT: [[TMP100:%.*]] = icmp eq i8* [[LSR_IV_NEXT1]], null +; CHECK-NEXT: [[LSR_IV:%.*]] = phi i8* [ [[SCEVGEP1:%.*]], [[ITER:%.*]] ], [ [[SCEVGEP]], [[BLAH:%.*]] ] +; CHECK-NEXT: [[SCEVGEP1]] = getelementptr i8, i8* [[LSR_IV]], i32 1 +; CHECK-NEXT: [[TMP100:%.*]] = icmp eq i8* [[SCEVGEP1]], undef ; CHECK-NEXT: br i1 [[TMP100]], label [[UNWIND_OUT:%.*]], label [[ITER]] ; CHECK: iter: ; CHECK-NEXT: br i1 true, label [[UNWIND_OUT]], label [[LOOP_BODY]] @@ -138,6 +142,7 @@ define void @h() personality i32 (...)* @_except_handler3 { ; CHECK-NEXT: entry: ; CHECK-NEXT: br label [[THROW:%.*]] ; CHECK: throw: +; CHECK-NEXT: [[TMP96:%.*]] = getelementptr inbounds i8, i8* undef, i32 1 ; CHECK-NEXT: invoke void @reserve() ; CHECK-NEXT: to label [[THROW]] unwind label [[PAD:%.*]] ; CHECK: pad: @@ -146,17 +151,18 @@ define void @h() personality i32 (...)* @_except_handler3 { ; CHECK-NEXT: [[TMP0:%.*]] = catchpad within [[CS]] [] ; CHECK-NEXT: unreachable ; CHECK: blug: +; CHECK-NEXT: [[PHI2:%.*]] = phi i8* [ [[TMP96]], [[PAD]] ] ; CHECK-NEXT: [[CATCHPAD:%.*]] = catchpad within [[CS]] [] +; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[PHI2]], i32 -1 ; CHECK-NEXT: br label [[LOOP_BODY:%.*]] ; CHECK: unwind_out: ; CHECK-NEXT: catchret from [[CATCHPAD]] to label [[LEAVE:%.*]] ; CHECK: leave: ; CHECK-NEXT: ret void ; CHECK: loop_body: -; CHECK-NEXT: [[LSR_IV:%.*]] = phi i32 [ [[LSR_IV_NEXT:%.*]], [[ITER:%.*]] ], [ 0, [[BLUG:%.*]] ] -; CHECK-NEXT: [[LSR_IV_NEXT]] = add nuw nsw i32 [[LSR_IV]], -1 -; CHECK-NEXT: [[LSR_IV_NEXT1:%.*]] = inttoptr i32 [[LSR_IV_NEXT]] to i8* -; CHECK-NEXT: [[TMP100:%.*]] = icmp eq i8* [[LSR_IV_NEXT1]], null +; CHECK-NEXT: [[LSR_IV:%.*]] = phi i8* [ [[SCEVGEP1:%.*]], [[ITER:%.*]] ], [ [[SCEVGEP]], [[BLUG:%.*]] ] +; CHECK-NEXT: [[SCEVGEP1]] = getelementptr i8, i8* [[LSR_IV]], i32 1 +; CHECK-NEXT: [[TMP100:%.*]] = icmp eq i8* [[SCEVGEP1]], undef ; CHECK-NEXT: br i1 [[TMP100]], label [[UNWIND_OUT:%.*]], label [[ITER]] ; CHECK: iter: ; CHECK-NEXT: br i1 true, label [[UNWIND_OUT]], label [[LOOP_BODY]] @@ -202,9 +208,11 @@ define void @i() personality i32 (...)* @_except_handler3 { ; CHECK-NEXT: entry: ; CHECK-NEXT: br label [[THROW:%.*]] ; CHECK: throw: +; CHECK-NEXT: [[TMP96:%.*]] = getelementptr inbounds i8, i8* undef, i32 1 ; CHECK-NEXT: invoke void @reserve() ; CHECK-NEXT: to label [[THROW]] unwind label [[CATCHPAD:%.*]] ; CHECK: catchpad: +; CHECK-NEXT: [[PHI2:%.*]] = phi i8* [ [[TMP96]], [[THROW]] ] ; CHECK-NEXT: [[CS:%.*]] = catchswitch within none [label %cp_body] unwind label [[CLEANUPPAD:%.*]] ; CHECK: cp_body: ; CHECK-NEXT: [[TMP0:%.*]] = catchpad within [[CS]] [] @@ -213,12 +221,12 @@ define void @i() personality i32 (...)* @_except_handler3 { ; CHECK-NEXT: [[TMP1:%.*]] = cleanuppad within none [] ; CHECK-NEXT: br label [[LOOP_HEAD]] ; CHECK: loop_head: +; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[PHI2]], i32 -1 ; CHECK-NEXT: br label [[LOOP_BODY:%.*]] ; CHECK: loop_body: -; CHECK-NEXT: [[LSR_IV:%.*]] = phi i32 [ [[LSR_IV_NEXT:%.*]], [[ITER:%.*]] ], [ 0, [[LOOP_HEAD]] ] -; CHECK-NEXT: [[LSR_IV_NEXT]] = add nuw nsw i32 [[LSR_IV]], -1 -; CHECK-NEXT: [[LSR_IV_NEXT1:%.*]] = inttoptr i32 [[LSR_IV_NEXT]] to i8* -; CHECK-NEXT: [[TMP100:%.*]] = icmp eq i8* [[LSR_IV_NEXT1]], null +; CHECK-NEXT: [[LSR_IV:%.*]] = phi i8* [ [[SCEVGEP1:%.*]], [[ITER:%.*]] ], [ [[SCEVGEP]], [[LOOP_HEAD]] ] +; CHECK-NEXT: [[SCEVGEP1]] = getelementptr i8, i8* [[LSR_IV]], i32 1 +; CHECK-NEXT: [[TMP100:%.*]] = icmp eq i8* [[SCEVGEP1]], undef ; CHECK-NEXT: br i1 [[TMP100]], label [[UNWIND_OUT:%.*]], label [[ITER]] ; CHECK: iter: ; CHECK-NEXT: br i1 true, label [[UNWIND_OUT]], label [[LOOP_BODY]] diff --git a/llvm/test/Transforms/LoopVectorize/create-induction-resume.ll b/llvm/test/Transforms/LoopVectorize/create-induction-resume.ll index 6aec21ead0fd..2e59e856d3ea 100644 --- a/llvm/test/Transforms/LoopVectorize/create-induction-resume.ll +++ b/llvm/test/Transforms/LoopVectorize/create-induction-resume.ll @@ -9,29 +9,21 @@ target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16 define void @test(i32 %arg, i32 %L1.limit, i32 %L2.switch, i1 %c) { ; CHECK-LABEL: @test( ; CHECK-NEXT: L1.preheader: -; CHECK-NEXT: [[TMP0:%.*]] = sub i32 -1, [[ARG:%.*]] ; CHECK-NEXT: br label [[L1_HEADER:%.*]] ; CHECK: L1.header: -; CHECK-NEXT: [[INDUCTION_IV:%.*]] = phi i32 [ [[INDUCTION_IV_NEXT:%.*]], [[L1_BACKEDGE:%.*]] ], [ [[TMP0]], [[L1_PREHEADER:%.*]] ] -; CHECK-NEXT: [[INDVAR:%.*]] = phi i32 [ [[INDVAR_NEXT:%.*]], [[L1_BACKEDGE]] ], [ 0, [[L1_PREHEADER]] ] -; CHECK-NEXT: [[L1_SUM:%.*]] = phi i32 [ [[ARG]], [[L1_PREHEADER]] ], [ [[L1_SUM_NEXT:%.*]], [[L1_BACKEDGE]] ] +; CHECK-NEXT: [[L1_SUM:%.*]] = phi i32 [ [[ARG:%.*]], [[L1_PREHEADER:%.*]] ], [ [[L1_SUM_NEXT:%.*]], [[L1_BACKEDGE:%.*]] ] ; CHECK-NEXT: [[L1_IV:%.*]] = phi i32 [ 1, [[L1_PREHEADER]] ], [ [[L1_IV_NEXT:%.*]], [[L1_BACKEDGE]] ] -; CHECK-NEXT: [[TMP1:%.*]] = mul nsw i32 [[INDVAR]], -1 -; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[TMP1]], -2 ; CHECK-NEXT: br i1 [[C:%.*]], label [[L1_BACKEDGE]], label [[L1_EARLY_EXIT:%.*]] ; CHECK: L1.backedge: ; CHECK-NEXT: [[L1_SUM_NEXT]] = add i32 [[L1_IV]], [[L1_SUM]] ; CHECK-NEXT: [[L1_IV_NEXT]] = add nuw nsw i32 [[L1_IV]], 1 ; CHECK-NEXT: [[L1_EXIT_COND:%.*]] = icmp ult i32 [[L1_IV_NEXT]], [[L1_LIMIT:%.*]] -; CHECK-NEXT: [[INDVAR_NEXT]] = add i32 [[INDVAR]], 1 -; CHECK-NEXT: [[INDUCTION_IV_NEXT]] = add i32 [[INDUCTION_IV]], [[TMP2]] ; CHECK-NEXT: br i1 [[L1_EXIT_COND]], label [[L1_HEADER]], label [[L1_EXIT:%.*]] ; CHECK: L1.early.exit: ; CHECK-NEXT: ret void ; CHECK: L1.exit: -; CHECK-NEXT: [[INDUCTION_IV_LCSSA3:%.*]] = phi i32 [ [[INDUCTION_IV]], [[L1_BACKEDGE]] ] -; CHECK-NEXT: [[INDUCTION_IV_LCSSA1:%.*]] = phi i32 [ [[INDUCTION_IV]], [[L1_BACKEDGE]] ] ; CHECK-NEXT: [[L1_EXIT_VAL:%.*]] = phi i32 [ [[L1_SUM_NEXT]], [[L1_BACKEDGE]] ] +; CHECK-NEXT: [[TMP0:%.*]] = sub i32 0, [[L1_EXIT_VAL]] ; CHECK-NEXT: br label [[L2_HEADER:%.*]] ; CHECK: L2.header.loopexit: ; CHECK-NEXT: br label [[L2_HEADER_BACKEDGE:%.*]] @@ -45,24 +37,24 @@ define void @test(i32 %arg, i32 %L1.limit, i32 %L2.switch, i1 %c) { ; CHECK: L2.Inner.header.preheader: ; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] ; CHECK: vector.ph: -; CHECK-NEXT: [[TMP3:%.*]] = mul i32 12, [[INDUCTION_IV_LCSSA1]] -; CHECK-NEXT: [[IND_END:%.*]] = add i32 1, [[TMP3]] +; CHECK-NEXT: [[TMP1:%.*]] = mul i32 12, [[TMP0]] +; CHECK-NEXT: [[IND_END:%.*]] = add i32 1, [[TMP1]] ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4 -; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], 12 -; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] +; CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], 12 +; CHECK-NEXT: br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] ; CHECK: middle.block: ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 12, 12 ; CHECK-NEXT: br i1 [[CMP_N]], label [[L2_HEADER_LOOPEXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 1, [[L2_INNER_HEADER_PREHEADER]] ] -; CHECK-NEXT: [[BC_RESUME_VAL2:%.*]] = phi i64 [ 13, [[MIDDLE_BLOCK]] ], [ 1, [[L2_INNER_HEADER_PREHEADER]] ] +; CHECK-NEXT: [[BC_RESUME_VAL1:%.*]] = phi i64 [ 13, [[MIDDLE_BLOCK]] ], [ 1, [[L2_INNER_HEADER_PREHEADER]] ] ; CHECK-NEXT: br label [[L2_INNER_HEADER:%.*]] ; CHECK: L2.Inner.header: ; CHECK-NEXT: [[L2_ACCUM:%.*]] = phi i32 [ [[L2_ACCUM_NEXT:%.*]], [[L2_INNER_HEADER]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ] -; CHECK-NEXT: [[L2_IV:%.*]] = phi i64 [ [[L2_IV_NEXT:%.*]], [[L2_INNER_HEADER]] ], [ [[BC_RESUME_VAL2]], [[SCALAR_PH]] ] +; CHECK-NEXT: [[L2_IV:%.*]] = phi i64 [ [[L2_IV_NEXT:%.*]], [[L2_INNER_HEADER]] ], [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ] ; CHECK-NEXT: [[L2_ACCUM_NEXT]] = sub i32 [[L2_ACCUM]], [[L1_EXIT_VAL]] ; CHECK-NEXT: [[L2_DUMMY_BUT_NEED_IT:%.*]] = sext i32 [[L2_ACCUM_NEXT]] to i64 ; CHECK-NEXT: [[L2_IV_NEXT]] = add nuw nsw i64 [[L2_IV]], 1 diff --git a/llvm/test/Transforms/LoopVectorize/pr45259.ll b/llvm/test/Transforms/LoopVectorize/pr45259.ll index aa7df10bc828..dc6a4b9e3d9a 100644 --- a/llvm/test/Transforms/LoopVectorize/pr45259.ll +++ b/llvm/test/Transforms/LoopVectorize/pr45259.ll @@ -6,7 +6,7 @@ define i8 @widget(i8* %arr, i8 %t9) { ; CHECK-LABEL: @widget( ; CHECK-NEXT: bb: -; CHECK-NEXT: [[ARR1:%.*]] = ptrtoint i8* [[ARR:%.*]] to i64 +; CHECK-NEXT: [[ARR2:%.*]] = ptrtoint i8* [[ARR:%.*]] to i64 ; CHECK-NEXT: br label [[BB6:%.*]] ; CHECK: bb6: ; CHECK-NEXT: [[T1_0:%.*]] = phi i8* [ [[ARR]], [[BB:%.*]] ], [ null, [[BB6]] ] @@ -14,25 +14,24 @@ define i8 @widget(i8* %arr, i8 %t9) { ; CHECK-NEXT: br i1 [[C]], label [[FOR_PREHEADER:%.*]], label [[BB6]] ; CHECK: for.preheader: ; CHECK-NEXT: [[T1_0_LCSSA:%.*]] = phi i8* [ [[T1_0]], [[BB6]] ] -; CHECK-NEXT: [[T1_0_LCSSA2:%.*]] = ptrtoint i8* [[T1_0_LCSSA]] to i64 -; CHECK-NEXT: [[TMP0:%.*]] = trunc i64 [[ARR1]] to i32 -; CHECK-NEXT: [[TMP1:%.*]] = sub i32 0, [[TMP0]] -; CHECK-NEXT: [[TMP2:%.*]] = trunc i64 [[T1_0_LCSSA2]] to i32 -; CHECK-NEXT: [[TMP3:%.*]] = add i32 [[TMP1]], [[TMP2]] -; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP3]], 4 +; CHECK-NEXT: [[T1_0_LCSSA1:%.*]] = ptrtoint i8* [[T1_0_LCSSA]] to i64 +; CHECK-NEXT: [[TMP0:%.*]] = trunc i64 [[T1_0_LCSSA1]] to i32 +; CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[ARR2]] to i32 +; CHECK-NEXT: [[TMP2:%.*]] = sub i32 [[TMP0]], [[TMP1]] +; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP2]], 4 ; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]] ; CHECK: vector.scevcheck: -; CHECK-NEXT: [[TMP4:%.*]] = sub i64 -1, [[ARR1]] -; CHECK-NEXT: [[TMP5:%.*]] = add i64 [[TMP4]], [[T1_0_LCSSA2]] -; CHECK-NEXT: [[TMP6:%.*]] = trunc i64 [[TMP5]] to i8 -; CHECK-NEXT: [[TMP7:%.*]] = add i8 1, [[TMP6]] -; CHECK-NEXT: [[TMP8:%.*]] = icmp slt i8 [[TMP7]], 1 -; CHECK-NEXT: [[TMP9:%.*]] = icmp ugt i64 [[TMP5]], 255 -; CHECK-NEXT: [[TMP10:%.*]] = or i1 [[TMP8]], [[TMP9]] -; CHECK-NEXT: br i1 [[TMP10]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]] +; CHECK-NEXT: [[TMP3:%.*]] = add i64 [[T1_0_LCSSA1]], -1 +; CHECK-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], [[ARR2]] +; CHECK-NEXT: [[TMP5:%.*]] = trunc i64 [[TMP4]] to i8 +; CHECK-NEXT: [[TMP6:%.*]] = add i8 1, [[TMP5]] +; CHECK-NEXT: [[TMP9:%.*]] = icmp slt i8 [[TMP6]], 1 +; CHECK-NEXT: [[TMP11:%.*]] = icmp ugt i64 [[TMP4]], 255 +; CHECK-NEXT: [[TMP12:%.*]] = or i1 [[TMP9]], [[TMP11]] +; CHECK-NEXT: br i1 [[TMP12]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]] ; CHECK: vector.ph: -; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP3]], 4 -; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP3]], [[N_MOD_VF]] +; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP2]], 4 +; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF]] ; CHECK-NEXT: [[IND_END:%.*]] = trunc i32 [[N_VEC]] to i8 ; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i8> poison, i8 [[T9:%.*]], i32 0 ; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT]], <4 x i8> poison, <4 x i32> zeroinitializer @@ -40,20 +39,20 @@ define i8 @widget(i8* %arr, i8 %t9) { ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] ; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i8> [ <i8 0, i8 1, i8 2, i8 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[TMP11:%.*]] = add <4 x i8> [[VEC_IND]], <i8 1, i8 1, i8 1, i8 1> -; CHECK-NEXT: [[TMP12:%.*]] = extractelement <4 x i8> [[TMP11]], i32 0 -; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, i8* [[ARR]], i8 [[TMP12]] -; CHECK-NEXT: [[TMP14:%.*]] = icmp slt <4 x i8> [[TMP11]], [[BROADCAST_SPLAT]] -; CHECK-NEXT: [[TMP15:%.*]] = zext <4 x i1> [[TMP14]] to <4 x i8> -; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, i8* [[TMP13]], i32 0 -; CHECK-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to <4 x i8>* -; CHECK-NEXT: store <4 x i8> [[TMP15]], <4 x i8>* [[TMP17]], align 1 +; CHECK-NEXT: [[TMP14:%.*]] = add <4 x i8> [[VEC_IND]], <i8 1, i8 1, i8 1, i8 1> +; CHECK-NEXT: [[TMP15:%.*]] = extractelement <4 x i8> [[TMP14]], i32 0 +; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, i8* [[ARR]], i8 [[TMP15]] +; CHECK-NEXT: [[TMP17:%.*]] = icmp slt <4 x i8> [[TMP14]], [[BROADCAST_SPLAT]] +; CHECK-NEXT: [[TMP18:%.*]] = zext <4 x i1> [[TMP17]] to <4 x i8> +; CHECK-NEXT: [[TMP19:%.*]] = getelementptr inbounds i8, i8* [[TMP16]], i32 0 +; CHECK-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to <4 x i8>* +; CHECK-NEXT: store <4 x i8> [[TMP18]], <4 x i8>* [[TMP20]], align 1 ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4 ; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i8> [[VEC_IND]], <i8 4, i8 4, i8 4, i8 4> -; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]] -; CHECK-NEXT: br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] +; CHECK-NEXT: [[TMP21:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]] +; CHECK-NEXT: br i1 [[TMP21]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] ; CHECK: middle.block: -; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP3]], [[N_VEC]] +; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC]] ; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_EXIT:%.*]], label [[SCALAR_PH]] ; CHECK: scalar.ph: ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_PREHEADER]] ], [ 0, [[VECTOR_SCEVCHECK]] ] |