[llvm] a8d7451 - [PassManager] Run Induction Variable Simplification pass *after* Recognize loop idioms pass, not before
Roman Lebedev via llvm-commits
llvm-commits at lists.llvm.org
Wed Nov 25 08:20:46 PST 2020
Author: Roman Lebedev
Date: 2020-11-25T19:20:07+03:00
New Revision: a8d74517dcff42d3300aa144820b2772c1560a96
URL: https://github.com/llvm/llvm-project/commit/a8d74517dcff42d3300aa144820b2772c1560a96
DIFF: https://github.com/llvm/llvm-project/commit/a8d74517dcff42d3300aa144820b2772c1560a96.diff
LOG: [PassManager] Run Induction Variable Simplification pass *after* Recognize loop idioms pass, not before
Currently, `-indvars` runs first, and then immediately after `-loop-idiom` does.
I'm not really sure if `-loop-idiom` requires `-indvars` to run beforehand,
but i'm *very* sure that `-indvars` requires `-loop-idiom` to run afterwards,
as it can be seen in the phase-ordering test.
LoopIdiom runs on two types of loops: countable ones, and uncountable ones.
For uncountable ones, IndVars obviously didn't make any change to them,
since they are uncountable, so for them the order should be irrelevant.
For countable ones, well, they should have been countable before IndVars
for IndVars to make any change to them, and since SCEV is used on them,
it shouldn't matter if IndVars have already canonicalized them.
So i don't really see why we'd want the current ordering.
Should this cause issues, it will give us a reproducer test case
that shows flaws in this logic, and we then could adjust accordingly.
While this is quite likely beneficial in-the-wild already,
it's a required part for the full motivational pattern
behind `left-shift-until-bittest` loop idiom (D91038).
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D91800
Added:
Modified:
llvm/lib/Passes/PassBuilder.cpp
llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
llvm/test/CodeGen/AMDGPU/opt-pipeline.ll
llvm/test/Other/new-pm-defaults.ll
llvm/test/Other/new-pm-thinlto-defaults.ll
llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll
llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll
llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll
llvm/test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll
llvm/test/Other/opt-O2-pipeline.ll
llvm/test/Other/opt-O3-pipeline-enable-matrix.ll
llvm/test/Other/opt-O3-pipeline.ll
llvm/test/Other/opt-Os-pipeline.ll
llvm/test/Transforms/PhaseOrdering/ARM/arm_fill_q7.ll
llvm/test/Transforms/PhaseOrdering/X86/loop-idiom-vs-indvars.ll
Removed:
################################################################################
diff --git a/llvm/lib/Passes/PassBuilder.cpp b/llvm/lib/Passes/PassBuilder.cpp
index af3eae47d242..2a9b0c1e4f6b 100644
--- a/llvm/lib/Passes/PassBuilder.cpp
+++ b/llvm/lib/Passes/PassBuilder.cpp
@@ -521,8 +521,8 @@ PassBuilder::buildO1FunctionSimplificationPipeline(OptimizationLevel Level,
if (EnableLoopFlatten)
FPM.addPass(LoopFlattenPass());
- LPM2.addPass(IndVarSimplifyPass());
LPM2.addPass(LoopIdiomRecognizePass());
+ LPM2.addPass(IndVarSimplifyPass());
for (auto &C : LateLoopOptimizationsEPCallbacks)
C(LPM2, Level);
@@ -682,8 +682,8 @@ PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
// TODO: Investigate promotion cap for O1.
LPM1.addPass(LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap));
LPM1.addPass(SimpleLoopUnswitchPass());
- LPM2.addPass(IndVarSimplifyPass());
LPM2.addPass(LoopIdiomRecognizePass());
+ LPM2.addPass(IndVarSimplifyPass());
for (auto &C : LateLoopOptimizationsEPCallbacks)
C(LPM2, Level);
@@ -712,7 +712,7 @@ PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
DebugLogging));
FPM.addPass(SimplifyCFGPass());
FPM.addPass(InstCombinePass());
- // The loop passes in LPM2 (IndVarSimplifyPass, LoopIdiomRecognizePass,
+ // The loop passes in LPM2 (LoopIdiomRecognizePass, IndVarSimplifyPass,
// LoopDeletionPass and LoopFullUnrollPass) do not preserve MemorySSA.
// *All* loop passes must preserve it, in order to be able to use it.
FPM.addPass(createFunctionToLoopPassAdaptor(
diff --git a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
index f05fc36c182a..e03015f8b0aa 100644
--- a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -445,8 +445,8 @@ void PassManagerBuilder::addFunctionSimplificationPasses(
MPM.add(createLoopFlattenPass()); // Flatten loops
MPM.add(createLoopSimplifyCFGPass());
}
- MPM.add(createIndVarSimplifyPass()); // Canonicalize indvars
MPM.add(createLoopIdiomPass()); // Recognize idioms like memset.
+ MPM.add(createIndVarSimplifyPass()); // Canonicalize indvars
addExtensionsToPM(EP_LateLoopOptimizations, MPM);
MPM.add(createLoopDeletionPass()); // Delete dead loops
diff --git a/llvm/test/CodeGen/AMDGPU/opt-pipeline.ll b/llvm/test/CodeGen/AMDGPU/opt-pipeline.ll
index 55461ea5b66e..2184a80b6782 100644
--- a/llvm/test/CodeGen/AMDGPU/opt-pipeline.ll
+++ b/llvm/test/CodeGen/AMDGPU/opt-pipeline.ll
@@ -163,8 +163,8 @@
; GCN-O1-NEXT: Loop-Closed SSA Form Pass
; GCN-O1-NEXT: Scalar Evolution Analysis
; GCN-O1-NEXT: Loop Pass Manager
-; GCN-O1-NEXT: Induction Variable Simplification
; GCN-O1-NEXT: Recognize loop idioms
+; GCN-O1-NEXT: Induction Variable Simplification
; GCN-O1-NEXT: Delete dead loops
; GCN-O1-NEXT: Unroll loops
; GCN-O1-NEXT: SROA
diff --git a/llvm/test/Other/new-pm-defaults.ll b/llvm/test/Other/new-pm-defaults.ll
index 9e27486e981b..261dbe0057f3 100644
--- a/llvm/test/Other/new-pm-defaults.ll
+++ b/llvm/test/Other/new-pm-defaults.ll
@@ -163,8 +163,8 @@
; CHECK-O-NEXT: Running pass: LCSSAPass
; CHECK-O-NEXT: Finished llvm::Function pass manager run.
; CHECK-O-NEXT: Starting Loop pass manager run.
-; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-O-NEXT: Running pass: LoopIdiomRecognizePass
+; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-EP-LOOP-LATE-NEXT: Running pass: NoOpLoopPass
; CHECK-O-NEXT: Running pass: LoopDeletionPass
; CHECK-O-NEXT: Running pass: LoopFullUnrollPass
diff --git a/llvm/test/Other/new-pm-thinlto-defaults.ll b/llvm/test/Other/new-pm-thinlto-defaults.ll
index 675047421503..a62f27f79c2c 100644
--- a/llvm/test/Other/new-pm-thinlto-defaults.ll
+++ b/llvm/test/Other/new-pm-thinlto-defaults.ll
@@ -147,8 +147,8 @@
; CHECK-O-NEXT: Running pass: LCSSAPass
; CHECK-O-NEXT: Finished llvm::Function pass manager run
; CHECK-O-NEXT: Starting Loop pass manager run.
-; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-O-NEXT: Running pass: LoopIdiomRecognizePass
+; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-O-NEXT: Running pass: LoopDeletionPass
; CHECK-O-NEXT: Running pass: LoopFullUnrollPass
; CHECK-O-NEXT: Finished Loop pass manager run.
diff --git a/llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll b/llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll
index b53f85e2db8e..996f5f49b42b 100644
--- a/llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll
+++ b/llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll
@@ -120,8 +120,8 @@
; CHECK-O-NEXT: Running pass: LCSSAPass
; CHECK-O-NEXT: Finished {{.*}}Function pass manager run
; CHECK-O-NEXT: Starting Loop pass manager run.
-; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-O-NEXT: Running pass: LoopIdiomRecognizePass
+; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-O-NEXT: Running pass: LoopDeletionPass
; CHECK-O-NEXT: Running pass: LoopFullUnrollPass
; CHECK-O-NEXT: Finished Loop pass manager run.
diff --git a/llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll b/llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll
index 4f3c00e65908..2587d07b229b 100644
--- a/llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll
+++ b/llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll
@@ -128,8 +128,8 @@
; CHECK-O-NEXT: Running pass: LCSSAPass
; CHECK-O-NEXT: Finished {{.*}}Function pass manager run
; CHECK-O-NEXT: Starting Loop pass manager run.
-; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-O-NEXT: Running pass: LoopIdiomRecognizePass
+; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-O-NEXT: Running pass: LoopDeletionPass
; CHECK-O-NEXT: Running pass: LoopFullUnrollPass
; CHECK-O-NEXT: Finished Loop pass manager run.
diff --git a/llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll b/llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll
index a420062390d0..d1a9b00e65f7 100644
--- a/llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll
+++ b/llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll
@@ -168,8 +168,8 @@
; CHECK-O-NEXT: Running pass: LCSSAPass
; CHECK-O-NEXT: Finished {{.*}}Function pass manager run
; CHECK-O-NEXT: Starting Loop pass manager run.
-; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-O-NEXT: Running pass: LoopIdiomRecognizePass
+; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-O-NEXT: Running pass: LoopDeletionPass
; CHECK-O-NEXT: Running pass: LoopFullUnrollPass
; CHECK-O-NEXT: Finished Loop pass manager run.
diff --git a/llvm/test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll b/llvm/test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll
index 57e1cd926948..7078c6d8cb75 100644
--- a/llvm/test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll
+++ b/llvm/test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll
@@ -124,8 +124,8 @@
; CHECK-O-NEXT: Running pass: LCSSAPass
; CHECK-O-NEXT: Finished {{.*}}Function pass manager run
; CHECK-O-NEXT: Starting Loop pass manager run.
-; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-O-NEXT: Running pass: LoopIdiomRecognizePass
+; CHECK-O-NEXT: Running pass: IndVarSimplifyPass
; CHECK-O-NEXT: Running pass: LoopDeletionPass
; CHECK-O-NEXT: Finished Loop pass manager run.
; CHECK-O-NEXT: Running pass: SROA on foo
diff --git a/llvm/test/Other/opt-O2-pipeline.ll b/llvm/test/Other/opt-O2-pipeline.ll
index 46ed056f267d..7d7934e6e4ab 100644
--- a/llvm/test/Other/opt-O2-pipeline.ll
+++ b/llvm/test/Other/opt-O2-pipeline.ll
@@ -131,8 +131,8 @@
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Loop Pass Manager
-; CHECK-NEXT: Induction Variable Simplification
; CHECK-NEXT: Recognize loop idioms
+; CHECK-NEXT: Induction Variable Simplification
; CHECK-NEXT: Delete dead loops
; CHECK-NEXT: Unroll loops
; CHECK-NEXT: SROA
diff --git a/llvm/test/Other/opt-O3-pipeline-enable-matrix.ll b/llvm/test/Other/opt-O3-pipeline-enable-matrix.ll
index 218f9c09f21d..bd77a8bac87c 100644
--- a/llvm/test/Other/opt-O3-pipeline-enable-matrix.ll
+++ b/llvm/test/Other/opt-O3-pipeline-enable-matrix.ll
@@ -136,8 +136,8 @@
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Loop Pass Manager
-; CHECK-NEXT: Induction Variable Simplification
; CHECK-NEXT: Recognize loop idioms
+; CHECK-NEXT: Induction Variable Simplification
; CHECK-NEXT: Delete dead loops
; CHECK-NEXT: Unroll loops
; CHECK-NEXT: SROA
diff --git a/llvm/test/Other/opt-O3-pipeline.ll b/llvm/test/Other/opt-O3-pipeline.ll
index 5875049dd0ef..85f25363d232 100644
--- a/llvm/test/Other/opt-O3-pipeline.ll
+++ b/llvm/test/Other/opt-O3-pipeline.ll
@@ -136,8 +136,8 @@
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Loop Pass Manager
-; CHECK-NEXT: Induction Variable Simplification
; CHECK-NEXT: Recognize loop idioms
+; CHECK-NEXT: Induction Variable Simplification
; CHECK-NEXT: Delete dead loops
; CHECK-NEXT: Unroll loops
; CHECK-NEXT: SROA
diff --git a/llvm/test/Other/opt-Os-pipeline.ll b/llvm/test/Other/opt-Os-pipeline.ll
index f5a03d2a9294..6d42b39fb8a5 100644
--- a/llvm/test/Other/opt-Os-pipeline.ll
+++ b/llvm/test/Other/opt-Os-pipeline.ll
@@ -117,8 +117,8 @@
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Loop Pass Manager
-; CHECK-NEXT: Induction Variable Simplification
; CHECK-NEXT: Recognize loop idioms
+; CHECK-NEXT: Induction Variable Simplification
; CHECK-NEXT: Delete dead loops
; CHECK-NEXT: Unroll loops
; CHECK-NEXT: SROA
diff --git a/llvm/test/Transforms/PhaseOrdering/ARM/arm_fill_q7.ll b/llvm/test/Transforms/PhaseOrdering/ARM/arm_fill_q7.ll
index e82a1820f6e1..dc5d363400b9 100644
--- a/llvm/test/Transforms/PhaseOrdering/ARM/arm_fill_q7.ll
+++ b/llvm/test/Transforms/PhaseOrdering/ARM/arm_fill_q7.ll
@@ -12,22 +12,15 @@ target triple = "thumbv6m-none-none-eabi"
define dso_local void @arm_fill_q7(i8 signext %value, i8* %pDst, i32 %blockSize) #0 {
; OLDPM-LABEL: @arm_fill_q7(
; OLDPM-NEXT: entry:
-; OLDPM-NEXT: [[SHR:%.*]] = lshr i32 [[BLOCKSIZE:%.*]], 2
-; OLDPM-NEXT: [[CMP_NOT20:%.*]] = icmp eq i32 [[SHR]], 0
+; OLDPM-NEXT: [[CMP_NOT20:%.*]] = icmp ult i32 [[BLOCKSIZE:%.*]], 4
; OLDPM-NEXT: br i1 [[CMP_NOT20]], label [[WHILE_END:%.*]], label [[WHILE_BODY_PREHEADER:%.*]]
; OLDPM: while.body.preheader:
; OLDPM-NEXT: [[TMP0:%.*]] = and i32 [[BLOCKSIZE]], -4
; OLDPM-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 [[PDST:%.*]], i8 [[VALUE:%.*]], i32 [[TMP0]], i1 false)
-; OLDPM-NEXT: br label [[WHILE_BODY:%.*]]
-; OLDPM: while.body:
-; OLDPM-NEXT: [[BLKCNT_022:%.*]] = phi i32 [ [[DEC:%.*]], [[WHILE_BODY]] ], [ [[SHR]], [[WHILE_BODY_PREHEADER]] ]
-; OLDPM-NEXT: [[PDST_ADDR_021:%.*]] = phi i8* [ [[ADD_PTR_I:%.*]], [[WHILE_BODY]] ], [ [[PDST]], [[WHILE_BODY_PREHEADER]] ]
-; OLDPM-NEXT: [[ADD_PTR_I]] = getelementptr inbounds i8, i8* [[PDST_ADDR_021]], i32 4
-; OLDPM-NEXT: [[DEC]] = add nsw i32 [[BLKCNT_022]], -1
-; OLDPM-NEXT: [[CMP_NOT:%.*]] = icmp eq i32 [[DEC]], 0
-; OLDPM-NEXT: br i1 [[CMP_NOT]], label [[WHILE_END]], label [[WHILE_BODY]], [[LOOP3:!llvm.loop !.*]]
+; OLDPM-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[PDST]], i32 [[TMP0]]
+; OLDPM-NEXT: br label [[WHILE_END]]
; OLDPM: while.end:
-; OLDPM-NEXT: [[PDST_ADDR_0_LCSSA:%.*]] = phi i8* [ [[PDST]], [[ENTRY:%.*]] ], [ [[ADD_PTR_I]], [[WHILE_BODY]] ]
+; OLDPM-NEXT: [[PDST_ADDR_0_LCSSA:%.*]] = phi i8* [ [[PDST]], [[ENTRY:%.*]] ], [ [[SCEVGEP]], [[WHILE_BODY_PREHEADER]] ]
; OLDPM-NEXT: [[REM:%.*]] = and i32 [[BLOCKSIZE]], 3
; OLDPM-NEXT: [[CMP14_NOT17:%.*]] = icmp eq i32 [[REM]], 0
; OLDPM-NEXT: br i1 [[CMP14_NOT17]], label [[WHILE_END18:%.*]], label [[WHILE_BODY16_PREHEADER:%.*]]
@@ -39,22 +32,15 @@ define dso_local void @arm_fill_q7(i8 signext %value, i8* %pDst, i32 %blockSize)
;
; NEWPM-LABEL: @arm_fill_q7(
; NEWPM-NEXT: entry:
-; NEWPM-NEXT: [[SHR:%.*]] = lshr i32 [[BLOCKSIZE:%.*]], 2
-; NEWPM-NEXT: [[CMP_NOT17:%.*]] = icmp eq i32 [[SHR]], 0
+; NEWPM-NEXT: [[CMP_NOT17:%.*]] = icmp ult i32 [[BLOCKSIZE:%.*]], 4
; NEWPM-NEXT: br i1 [[CMP_NOT17]], label [[WHILE_END:%.*]], label [[WHILE_BODY_PREHEADER:%.*]]
; NEWPM: while.body.preheader:
; NEWPM-NEXT: [[TMP0:%.*]] = and i32 [[BLOCKSIZE]], -4
; NEWPM-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 [[PDST:%.*]], i8 [[VALUE:%.*]], i32 [[TMP0]], i1 false)
-; NEWPM-NEXT: br label [[WHILE_BODY:%.*]]
-; NEWPM: while.body:
-; NEWPM-NEXT: [[BLKCNT_019:%.*]] = phi i32 [ [[DEC:%.*]], [[WHILE_BODY]] ], [ [[SHR]], [[WHILE_BODY_PREHEADER]] ]
-; NEWPM-NEXT: [[PDST_ADDR_018:%.*]] = phi i8* [ [[ADD_PTR_I:%.*]], [[WHILE_BODY]] ], [ [[PDST]], [[WHILE_BODY_PREHEADER]] ]
-; NEWPM-NEXT: [[ADD_PTR_I]] = getelementptr inbounds i8, i8* [[PDST_ADDR_018]], i32 4
-; NEWPM-NEXT: [[DEC]] = add nsw i32 [[BLKCNT_019]], -1
-; NEWPM-NEXT: [[CMP_NOT:%.*]] = icmp eq i32 [[DEC]], 0
-; NEWPM-NEXT: br i1 [[CMP_NOT]], label [[WHILE_END]], label [[WHILE_BODY]], [[LOOP3:!llvm.loop !.*]]
+; NEWPM-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[PDST]], i32 [[TMP0]]
+; NEWPM-NEXT: br label [[WHILE_END]]
; NEWPM: while.end:
-; NEWPM-NEXT: [[PDST_ADDR_0_LCSSA:%.*]] = phi i8* [ [[PDST]], [[ENTRY:%.*]] ], [ [[ADD_PTR_I]], [[WHILE_BODY]] ]
+; NEWPM-NEXT: [[PDST_ADDR_0_LCSSA:%.*]] = phi i8* [ [[PDST]], [[ENTRY:%.*]] ], [ [[SCEVGEP]], [[WHILE_BODY_PREHEADER]] ]
; NEWPM-NEXT: [[REM:%.*]] = and i32 [[BLOCKSIZE]], 3
; NEWPM-NEXT: [[CMP14_NOT20:%.*]] = icmp eq i32 [[REM]], 0
; NEWPM-NEXT: br i1 [[CMP14_NOT20]], label [[WHILE_END18:%.*]], label [[WHILE_BODY16_PREHEADER:%.*]]
diff --git a/llvm/test/Transforms/PhaseOrdering/X86/loop-idiom-vs-indvars.ll b/llvm/test/Transforms/PhaseOrdering/X86/loop-idiom-vs-indvars.ll
index ee1430b9def4..c06342d6022a 100644
--- a/llvm/test/Transforms/PhaseOrdering/X86/loop-idiom-vs-indvars.ll
+++ b/llvm/test/Transforms/PhaseOrdering/X86/loop-idiom-vs-indvars.ll
@@ -13,62 +13,10 @@ define i32 @cttz(i32 %n, i32* %p1) {
; ALL-NEXT: entry:
; ALL-NEXT: [[TMP0:%.*]] = shl i32 [[N:%.*]], 1
; ALL-NEXT: [[TMP1:%.*]] = call i32 @llvm.cttz.i32(i32 [[TMP0]], i1 false), [[RNG0:!range !.*]]
-; ALL-NEXT: [[TMP2:%.*]] = sub nuw nsw i32 33, [[TMP1]]
-; ALL-NEXT: [[TMP3:%.*]] = sub nuw nsw i32 33, [[TMP1]]
-; ALL-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ugt i32 [[TMP1]], 25
-; ALL-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[WHILE_COND_PREHEADER:%.*]], label [[VECTOR_PH:%.*]]
-; ALL: vector.ph:
-; ALL-NEXT: [[N_VEC:%.*]] = and i32 [[TMP3]], -8
-; ALL-NEXT: [[IND_END:%.*]] = sub nsw i32 [[TMP2]], [[N_VEC]]
-; ALL-NEXT: [[TMP4:%.*]] = add nsw i32 [[N_VEC]], -8
-; ALL-NEXT: [[TMP5:%.*]] = lshr exact i32 [[TMP4]], 3
-; ALL-NEXT: [[TMP6:%.*]] = add nuw nsw i32 [[TMP5]], 1
-; ALL-NEXT: [[XTRAITER:%.*]] = and i32 [[TMP6]], 7
-; ALL-NEXT: [[TMP7:%.*]] = icmp ult i32 [[TMP4]], 56
-; ALL-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK_UNR_LCSSA:%.*]], label [[VECTOR_PH_NEW:%.*]]
-; ALL: vector.ph.new:
-; ALL-NEXT: [[UNROLL_ITER:%.*]] = and i32 [[TMP6]], 1073741816
-; ALL-NEXT: br label [[VECTOR_BODY:%.*]]
-; ALL: vector.body:
-; ALL-NEXT: [[VEC_PHI:%.*]] = phi <8 x i32> [ <i32 42, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>, [[VECTOR_PH_NEW]] ], [ [[TMP8:%.*]], [[VECTOR_BODY]] ]
-; ALL-NEXT: [[NITER:%.*]] = phi i32 [ [[UNROLL_ITER]], [[VECTOR_PH_NEW]] ], [ [[NITER_NSUB_7:%.*]], [[VECTOR_BODY]] ]
-; ALL-NEXT: [[TMP8]] = add <8 x i32> [[VEC_PHI]], <i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8>
-; ALL-NEXT: [[NITER_NSUB_7]] = add i32 [[NITER]], -8
-; ALL-NEXT: [[NITER_NCMP_7:%.*]] = icmp eq i32 [[NITER_NSUB_7]], 0
-; ALL-NEXT: br i1 [[NITER_NCMP_7]], label [[MIDDLE_BLOCK_UNR_LCSSA]], label [[VECTOR_BODY]], [[LOOP1:!llvm.loop !.*]]
-; ALL: middle.block.unr-lcssa:
-; ALL-NEXT: [[DOTLCSSA_PH:%.*]] = phi <8 x i32> [ undef, [[VECTOR_PH]] ], [ [[TMP8]], [[VECTOR_BODY]] ]
-; ALL-NEXT: [[VEC_PHI_UNR:%.*]] = phi <8 x i32> [ <i32 42, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>, [[VECTOR_PH]] ], [ [[TMP8]], [[VECTOR_BODY]] ]
-; ALL-NEXT: [[LCMP_MOD_NOT:%.*]] = icmp eq i32 [[XTRAITER]], 0
-; ALL-NEXT: br i1 [[LCMP_MOD_NOT]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY_EPIL:%.*]]
-; ALL: vector.body.epil:
-; ALL-NEXT: [[VEC_PHI_EPIL:%.*]] = phi <8 x i32> [ [[TMP9:%.*]], [[VECTOR_BODY_EPIL]] ], [ [[VEC_PHI_UNR]], [[MIDDLE_BLOCK_UNR_LCSSA]] ]
-; ALL-NEXT: [[EPIL_ITER:%.*]] = phi i32 [ [[EPIL_ITER_SUB:%.*]], [[VECTOR_BODY_EPIL]] ], [ [[XTRAITER]], [[MIDDLE_BLOCK_UNR_LCSSA]] ]
-; ALL-NEXT: [[TMP9]] = add <8 x i32> [[VEC_PHI_EPIL]], <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
-; ALL-NEXT: [[EPIL_ITER_SUB]] = add i32 [[EPIL_ITER]], -1
-; ALL-NEXT: [[EPIL_ITER_CMP_NOT:%.*]] = icmp eq i32 [[EPIL_ITER_SUB]], 0
-; ALL-NEXT: br i1 [[EPIL_ITER_CMP_NOT]], label [[MIDDLE_BLOCK]], label [[VECTOR_BODY_EPIL]], [[LOOP3:!llvm.loop !.*]]
-; ALL: middle.block:
-; ALL-NEXT: [[DOTLCSSA:%.*]] = phi <8 x i32> [ [[DOTLCSSA_PH]], [[MIDDLE_BLOCK_UNR_LCSSA]] ], [ [[TMP9]], [[VECTOR_BODY_EPIL]] ]
-; ALL-NEXT: [[TMP10:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[DOTLCSSA]])
-; ALL-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP3]], [[N_VEC]]
-; ALL-NEXT: br i1 [[CMP_N]], label [[WHILE_END:%.*]], label [[WHILE_COND_PREHEADER]]
-; ALL: while.cond.preheader:
-; ALL-NEXT: [[TCPHI_PH:%.*]] = phi i32 [ [[TMP2]], [[ENTRY:%.*]] ], [ [[IND_END]], [[MIDDLE_BLOCK]] ]
-; ALL-NEXT: [[WHATEVER_PH:%.*]] = phi i32 [ 42, [[ENTRY]] ], [ [[TMP10]], [[MIDDLE_BLOCK]] ]
-; ALL-NEXT: br label [[WHILE_COND:%.*]]
-; ALL: while.cond:
-; ALL-NEXT: [[TCPHI:%.*]] = phi i32 [ [[TCDEC:%.*]], [[WHILE_COND]] ], [ [[TCPHI_PH]], [[WHILE_COND_PREHEADER]] ]
-; ALL-NEXT: [[WHATEVER:%.*]] = phi i32 [ [[WHATEVER_NEXT:%.*]], [[WHILE_COND]] ], [ [[WHATEVER_PH]], [[WHILE_COND_PREHEADER]] ]
-; ALL-NEXT: [[TCDEC]] = add nsw i32 [[TCPHI]], -1
-; ALL-NEXT: [[TOBOOL:%.*]] = icmp eq i32 [[TCDEC]], 0
-; ALL-NEXT: [[WHATEVER_NEXT]] = add nuw nsw i32 [[WHATEVER]], 1
-; ALL-NEXT: br i1 [[TOBOOL]], label [[WHILE_END]], label [[WHILE_COND]], [[LOOP5:!llvm.loop !.*]]
-; ALL: while.end:
-; ALL-NEXT: [[WHATEVER_NEXT_LCSSA:%.*]] = phi i32 [ [[TMP10]], [[MIDDLE_BLOCK]] ], [ [[WHATEVER_NEXT]], [[WHILE_COND]] ]
-; ALL-NEXT: [[TMP11:%.*]] = sub nuw nsw i32 32, [[TMP1]]
-; ALL-NEXT: store i32 [[WHATEVER_NEXT_LCSSA]], i32* [[P1:%.*]], align 4
-; ALL-NEXT: ret i32 [[TMP11]]
+; ALL-NEXT: [[TMP2:%.*]] = sub nuw nsw i32 32, [[TMP1]]
+; ALL-NEXT: [[TMP3:%.*]] = sub nuw nsw i32 75, [[TMP1]]
+; ALL-NEXT: store i32 [[TMP3]], i32* [[P1:%.*]], align 4
+; ALL-NEXT: ret i32 [[TMP2]]
;
entry:
br label %while.cond
More information about the llvm-commits
mailing list