forked from OSchip/llvm-project
[InstCombine] Take 3: Perform trivial PHI CSE
The original take 1 was6102310d81, which taught InstSimplify to do that, which seemed better at time, since we got EarlyCSE support for free. However, it was proven that we can not do that there, the simplified-to PHI would not be reachable from the original PHI, and that is not something InstSimplify is allowed to do, as noted in the commited90f15efbthat reverted it: > It appears to cause compilation non-determinism and caused stage3 mismatches. Then there was take 23e69871ab5, which was InstCombine-specific, but it again showed stage2-stage3 differences, and reverted inbdaa3f86a0. This is quite alarming. Here, let's try to change how we find existing PHI candidate: due to the worklist order, and the way PHI nodes are inserted (it may be inserted as the first one, or maybe not), let's look at *all* PHI nodes in the block. Effects on vanilla llvm test-suite + RawSpeed: ``` | statistic name | baseline | proposed | Δ | % | \|%\| | |----------------------------------------------------|-----------|-----------|-------:|---------:|---------:| | asm-printer.EmittedInsts | 7942329 | 7942457 | 128 | 0.00% | 0.00% | | assembler.ObjectBytes | 254295632 | 254312480 | 16848 | 0.01% | 0.01% | | correlated-value-propagation.NumPhis | 18412 | 18347 | -65 | -0.35% | 0.35% | | early-cse.NumCSE | 2183283 | 2183267 | -16 | 0.00% | 0.00% | | early-cse.NumSimplify | 550105 | 541842 | -8263 | -1.50% | 1.50% | | instcombine.NumAggregateReconstructionsSimplified | 73 | 4506 | 4433 | 6072.60% | 6072.60% | | instcombine.NumCombined | 3640311 | 3644419 | 4108 | 0.11% | 0.11% | | instcombine.NumDeadInst | 1778204 | 1783205 | 5001 | 0.28% | 0.28% | | instcombine.NumPHICSEs | 0 | 22490 | 22490 | 0.00% | 0.00% | | instcombine.NumWorklistIterations | 2023272 | 2024400 | 1128 | 0.06% | 0.06% | | instcount.NumCallInst | 1758395 |1758802| 407 | 0.02% | 0.02% | | instcount.NumInvokeInst | 59478 | 59502 | 24 | 0.04% | 0.04% | | instcount.NumPHIInst | 330557 | 330545 | -12 | 0.00% | 0.00% | | instcount.TotalBlocks | 1077138 | 1077220 | 82 | 0.01% | 0.01% | | instcount.TotalFuncs | 101442 | 101441 | -1 | 0.00% | 0.00% | | instcount.TotalInsts | 8831946 | 8832606 | 660 | 0.01% | 0.01% | | simplifycfg.NumHoistCommonCode | 24186 | 24187 | 1 | 0.00% | 0.00% | | simplifycfg.NumInvokes | 4300 | 4410 | 110 | 2.56% | 2.56% | | simplifycfg.NumSimpl | 1019813 | 999767 | -20046 | -1.97% | 1.97% | ``` So it fires 22490 times, which is less than ~24k the take 1 did, but more than what take 2 did (22228 times) . It allows foldAggregateConstructionIntoAggregateReuse() to actually work after PHI-of-extractvalue folds did their thing. Previously SimplifyCFG would have done this PHI CSE, of all places. Additionally, allows some more `invoke`->`call` folds to happen (+110, +2.56%). All in all, expectedly, this catches less things overall, but all the motivational cases are still caught, so all good.
This commit is contained in:
Roman Lebedev
parent
b5dd2cd27f
commit
bf21ce7b90
|
|
@ -34,6 +34,7 @@ STATISTIC(NumPHIsOfInsertValues,
|
|||
"Number of phi-of-insertvalue turned into insertvalue-of-phis");
|
||||
STATISTIC(NumPHIsOfExtractValues,
|
||||
"Number of phi-of-extractvalue turned into extractvalue-of-phi");
|
||||
STATISTIC(NumPHICSEs, "Number of PHI's that got CSE'd");
|
||||
|
||||
/// The PHI arguments will be folded into a single operation with a PHI node
|
||||
/// as input. The debug location of the single operation will be the merged
|
||||
|
|
@ -1426,6 +1427,32 @@ Instruction *InstCombinerImpl::visitPHINode(PHINode &PN) {
|
|||
}
|
||||
}
|
||||
|
||||
// Is there an identical PHI node in this basic block?
|
||||
for (PHINode &IdenticalPN : PN.getParent()->phis()) {
|
||||
// Ignore the PHI node itself.
|
||||
if (&IdenticalPN == &PN)
|
||||
continue;
|
||||
// Note that even though we've just canonicalized this PHI, due to the
|
||||
// worklist visitation order, there are no guarantess that *every* PHI
|
||||
// has been canonicalized, so we can't just compare operands ranges.
|
||||
if (!PN.isIdenticalToWhenDefined(&IdenticalPN))
|
||||
continue;
|
||||
// Just use that PHI instead then.
|
||||
++NumPHICSEs;
|
||||
// Note that we can't necessarily just replace the PN with IdenticalPN,
|
||||
// because IdenticalPN might be *after* PN, and PN might have uses
|
||||
// in PHI nodes inbetween the two.
|
||||
// So we need to pick the earliest PHI node as being the canonical one.
|
||||
Instruction *OldPN = &PN;
|
||||
Instruction *NewPN = &IdenticalPN;
|
||||
if (!NewPN->comesBefore(OldPN))
|
||||
std::swap(OldPN, NewPN);
|
||||
replaceInstUsesWith(*OldPN, NewPN);
|
||||
// Also, just to be extra safe, make sure the non-canonical PHI goes away.
|
||||
eraseInstFromFunction(*OldPN);
|
||||
return nullptr; // Signal that thange happened.
|
||||
}
|
||||
|
||||
// If this is an integer PHI and we know that it has an illegal type, see if
|
||||
// it is only used by trunc or trunc(lshr) operations. If so, we split the
|
||||
// PHI into the various pieces being extracted. This sort of thing is
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
||||
; RUN: opt %s -instcombine -instcombine-infinite-loop-threshold=2 -S | FileCheck %s
|
||||
; RUN: opt %s -instcombine -instcombine-infinite-loop-threshold=3 -S | FileCheck %s
|
||||
|
||||
@var_7 = external global i8, align 1
|
||||
@var_1 = external global i32, align 4
|
||||
|
|
@ -29,11 +29,10 @@ define void @_Z4testv() {
|
|||
; CHECK-NEXT: br label [[BB12]]
|
||||
; CHECK: bb12:
|
||||
; CHECK-NEXT: [[STOREMERGE1:%.*]] = phi i32 [ [[I11]], [[BB10]] ], [ 1, [[BB9]] ]
|
||||
; CHECK-NEXT: [[STOREMERGE:%.*]] = phi i32 [ [[I11]], [[BB10]] ], [ 1, [[BB9]] ]
|
||||
; CHECK-NEXT: store i32 [[STOREMERGE1]], i32* getelementptr inbounds ([0 x i32], [0 x i32]* @arr_2, i64 0, i64 0), align 4
|
||||
; CHECK-NEXT: store i16 [[I4]], i16* getelementptr inbounds ([0 x i16], [0 x i16]* @arr_4, i64 0, i64 0), align 2
|
||||
; CHECK-NEXT: store i32 [[I8]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @arr_3, i64 0, i64 0), align 16
|
||||
; CHECK-NEXT: store i32 [[STOREMERGE]], i32* getelementptr inbounds ([0 x i32], [0 x i32]* @arr_2, i64 0, i64 1), align 4
|
||||
; CHECK-NEXT: store i32 [[STOREMERGE1]], i32* getelementptr inbounds ([0 x i32], [0 x i32]* @arr_2, i64 0, i64 1), align 4
|
||||
; CHECK-NEXT: store i16 [[I4]], i16* getelementptr inbounds ([0 x i16], [0 x i16]* @arr_4, i64 0, i64 1), align 2
|
||||
; CHECK-NEXT: store i32 [[I8]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @arr_3, i64 0, i64 1), align 4
|
||||
; CHECK-NEXT: ret void
|
||||
|
|
|
|||
|
|
@ -25,13 +25,8 @@ define { i32, i32 } @test0({ i32, i32 } %agg_left, { i32, i32 } %agg_right, i1 %
|
|||
; CHECK-NEXT: br label [[END]]
|
||||
; CHECK: end:
|
||||
; CHECK-NEXT: [[AGG_LEFT_PN:%.*]] = phi { i32, i32 } [ [[AGG_LEFT:%.*]], [[LEFT]] ], [ [[AGG_RIGHT:%.*]], [[RIGHT]] ]
|
||||
; CHECK-NEXT: [[AGG_LEFT_PN1:%.*]] = phi { i32, i32 } [ [[AGG_LEFT]], [[LEFT]] ], [ [[AGG_RIGHT]], [[RIGHT]] ]
|
||||
; CHECK-NEXT: [[I6:%.*]] = extractvalue { i32, i32 } [[AGG_LEFT_PN1]], 1
|
||||
; CHECK-NEXT: [[I5:%.*]] = extractvalue { i32, i32 } [[AGG_LEFT_PN]], 0
|
||||
; CHECK-NEXT: call void @baz()
|
||||
; CHECK-NEXT: [[I7:%.*]] = insertvalue { i32, i32 } undef, i32 [[I5]], 0
|
||||
; CHECK-NEXT: [[I8:%.*]] = insertvalue { i32, i32 } [[I7]], i32 [[I6]], 1
|
||||
; CHECK-NEXT: ret { i32, i32 } [[I8]]
|
||||
; CHECK-NEXT: ret { i32, i32 } [[AGG_LEFT_PN]]
|
||||
;
|
||||
entry:
|
||||
br i1 %c, label %left, label %right
|
||||
|
|
@ -162,19 +157,13 @@ define { i32, i32 } @test3({ i32, i32 } %agg_00, { i32, i32 } %agg_01, { i32, i3
|
|||
; CHECK-NEXT: br label [[BB0_MERGE]]
|
||||
; CHECK: bb0.merge:
|
||||
; CHECK-NEXT: [[AGG_00_PN:%.*]] = phi { i32, i32 } [ [[AGG_00:%.*]], [[BB00]] ], [ [[AGG_01:%.*]], [[BB01]] ]
|
||||
; CHECK-NEXT: [[AGG_00_PN1:%.*]] = phi { i32, i32 } [ [[AGG_00]], [[BB00]] ], [ [[AGG_01]], [[BB01]] ]
|
||||
; CHECK-NEXT: br label [[END:%.*]]
|
||||
; CHECK: bb10:
|
||||
; CHECK-NEXT: br label [[END]]
|
||||
; CHECK: end:
|
||||
; CHECK-NEXT: [[AGG_00_PN_PN:%.*]] = phi { i32, i32 } [ [[AGG_00_PN]], [[BB0_MERGE]] ], [ [[AGG_10:%.*]], [[BB10]] ]
|
||||
; CHECK-NEXT: [[AGG_00_PN1_PN:%.*]] = phi { i32, i32 } [ [[AGG_00_PN1]], [[BB0_MERGE]] ], [ [[AGG_10]], [[BB10]] ]
|
||||
; CHECK-NEXT: [[I9:%.*]] = extractvalue { i32, i32 } [[AGG_00_PN1_PN]], 1
|
||||
; CHECK-NEXT: [[I8:%.*]] = extractvalue { i32, i32 } [[AGG_00_PN_PN]], 0
|
||||
; CHECK-NEXT: call void @baz()
|
||||
; CHECK-NEXT: [[I10:%.*]] = insertvalue { i32, i32 } undef, i32 [[I8]], 0
|
||||
; CHECK-NEXT: [[I11:%.*]] = insertvalue { i32, i32 } [[I10]], i32 [[I9]], 1
|
||||
; CHECK-NEXT: ret { i32, i32 } [[I11]]
|
||||
; CHECK-NEXT: ret { i32, i32 } [[AGG_00_PN_PN]]
|
||||
;
|
||||
entry:
|
||||
br i1 %c0, label %bb0.dispatch, label %bb10
|
||||
|
|
@ -277,17 +266,12 @@ define { i32, i32 } @test5({ i32, i32 } %agg_left, { i32, i32 } %agg_right, i1 %
|
|||
; CHECK-NEXT: call void @bar()
|
||||
; CHECK-NEXT: br label [[MIDDLE]]
|
||||
; CHECK: middle:
|
||||
; CHECK-NEXT: [[AGG_LEFT_PN:%.*]] = phi { i32, i32 } [ [[AGG_LEFT:%.*]], [[LEFT]] ], [ [[AGG_RIGHT:%.*]], [[RIGHT]] ], [ [[I8:%.*]], [[MIDDLE]] ]
|
||||
; CHECK-NEXT: [[AGG_LEFT_PN1:%.*]] = phi { i32, i32 } [ [[AGG_LEFT]], [[LEFT]] ], [ [[AGG_RIGHT]], [[RIGHT]] ], [ [[I8]], [[MIDDLE]] ]
|
||||
; CHECK-NEXT: [[I6:%.*]] = extractvalue { i32, i32 } [[AGG_LEFT_PN1]], 1
|
||||
; CHECK-NEXT: [[I5:%.*]] = extractvalue { i32, i32 } [[AGG_LEFT_PN]], 0
|
||||
; CHECK-NEXT: [[AGG_LEFT_PN:%.*]] = phi { i32, i32 } [ [[AGG_LEFT:%.*]], [[LEFT]] ], [ [[AGG_RIGHT:%.*]], [[RIGHT]] ], [ [[AGG_LEFT_PN]], [[MIDDLE]] ]
|
||||
; CHECK-NEXT: call void @baz()
|
||||
; CHECK-NEXT: [[I7:%.*]] = insertvalue { i32, i32 } undef, i32 [[I5]], 0
|
||||
; CHECK-NEXT: [[I8]] = insertvalue { i32, i32 } [[I7]], i32 [[I6]], 1
|
||||
; CHECK-NEXT: [[C1:%.*]] = call i1 @geni1()
|
||||
; CHECK-NEXT: br i1 [[C1]], label [[END:%.*]], label [[MIDDLE]]
|
||||
; CHECK: end:
|
||||
; CHECK-NEXT: ret { i32, i32 } [[I8]]
|
||||
; CHECK-NEXT: ret { i32, i32 } [[AGG_LEFT_PN]]
|
||||
;
|
||||
entry:
|
||||
br i1 %c0, label %left, label %right
|
||||
|
|
@ -332,19 +316,14 @@ define { i32, i32 } @test6({ i32, i32 } %agg_left, { i32, i32 } %agg_right, i1 %
|
|||
; CHECK-NEXT: br label [[MERGE]]
|
||||
; CHECK: merge:
|
||||
; CHECK-NEXT: [[AGG_LEFT_PN:%.*]] = phi { i32, i32 } [ [[AGG_LEFT:%.*]], [[LEFT]] ], [ [[AGG_RIGHT:%.*]], [[RIGHT]] ]
|
||||
; CHECK-NEXT: [[AGG_LEFT_PN1:%.*]] = phi { i32, i32 } [ [[AGG_LEFT]], [[LEFT]] ], [ [[AGG_RIGHT]], [[RIGHT]] ]
|
||||
; CHECK-NEXT: call void @baz()
|
||||
; CHECK-NEXT: br i1 [[C1:%.*]], label [[END:%.*]], label [[PASSTHROUGH:%.*]]
|
||||
; CHECK: passthrough:
|
||||
; CHECK-NEXT: call void @qux()
|
||||
; CHECK-NEXT: br label [[END]]
|
||||
; CHECK: end:
|
||||
; CHECK-NEXT: [[I6:%.*]] = extractvalue { i32, i32 } [[AGG_LEFT_PN1]], 1
|
||||
; CHECK-NEXT: [[I5:%.*]] = extractvalue { i32, i32 } [[AGG_LEFT_PN]], 0
|
||||
; CHECK-NEXT: call void @quux()
|
||||
; CHECK-NEXT: [[I7:%.*]] = insertvalue { i32, i32 } undef, i32 [[I5]], 0
|
||||
; CHECK-NEXT: [[I8:%.*]] = insertvalue { i32, i32 } [[I7]], i32 [[I6]], 1
|
||||
; CHECK-NEXT: ret { i32, i32 } [[I8]]
|
||||
; CHECK-NEXT: ret { i32, i32 } [[AGG_LEFT_PN]]
|
||||
;
|
||||
entry:
|
||||
br i1 %c0, label %left, label %right
|
||||
|
|
@ -451,13 +430,8 @@ define { i32, i32 } @test8({ i32, i32 } %agg_left, { i32, i32 } %agg_right, i1 %
|
|||
; CHECK-NEXT: unreachable
|
||||
; CHECK: end:
|
||||
; CHECK-NEXT: [[AGG_LEFT_PN:%.*]] = phi { i32, i32 } [ [[AGG_LEFT:%.*]], [[LEFT]] ], [ [[AGG_LEFT]], [[LEFT]] ], [ [[AGG_RIGHT:%.*]], [[RIGHT]] ], [ [[AGG_RIGHT]], [[RIGHT]] ]
|
||||
; CHECK-NEXT: [[AGG_LEFT_PN1:%.*]] = phi { i32, i32 } [ [[AGG_LEFT]], [[LEFT]] ], [ [[AGG_LEFT]], [[LEFT]] ], [ [[AGG_RIGHT]], [[RIGHT]] ], [ [[AGG_RIGHT]], [[RIGHT]] ]
|
||||
; CHECK-NEXT: [[I6:%.*]] = extractvalue { i32, i32 } [[AGG_LEFT_PN1]], 1
|
||||
; CHECK-NEXT: [[I5:%.*]] = extractvalue { i32, i32 } [[AGG_LEFT_PN]], 0
|
||||
; CHECK-NEXT: call void @baz()
|
||||
; CHECK-NEXT: [[I7:%.*]] = insertvalue { i32, i32 } undef, i32 [[I5]], 0
|
||||
; CHECK-NEXT: [[I8:%.*]] = insertvalue { i32, i32 } [[I7]], i32 [[I6]], 1
|
||||
; CHECK-NEXT: ret { i32, i32 } [[I8]]
|
||||
; CHECK-NEXT: ret { i32, i32 } [[AGG_LEFT_PN]]
|
||||
;
|
||||
entry:
|
||||
br i1 %c, label %left, label %right
|
||||
|
|
@ -505,13 +479,8 @@ define { i32, i32 } @test9({ i32, i32 } %agg_left, { i32, i32 } %agg_right, i1 %
|
|||
; CHECK-NEXT: br label [[END]]
|
||||
; CHECK: end:
|
||||
; CHECK-NEXT: [[AGG_LEFT_PN:%.*]] = phi { i32, i32 } [ [[AGG_LEFT:%.*]], [[LEFT]] ], [ [[AGG_RIGHT:%.*]], [[RIGHT]] ]
|
||||
; CHECK-NEXT: [[AGG_LEFT_PN1:%.*]] = phi { i32, i32 } [ [[AGG_LEFT]], [[LEFT]] ], [ [[AGG_RIGHT]], [[RIGHT]] ]
|
||||
; CHECK-NEXT: [[I7:%.*]] = extractvalue { i32, i32 } [[AGG_LEFT_PN1]], 1
|
||||
; CHECK-NEXT: [[I0_PN:%.*]] = extractvalue { i32, i32 } [[AGG_LEFT_PN]], 0
|
||||
; CHECK-NEXT: [[I6:%.*]] = insertvalue { i32, i32 } undef, i32 [[I0_PN]], 0
|
||||
; CHECK-NEXT: call void @baz()
|
||||
; CHECK-NEXT: [[I8:%.*]] = insertvalue { i32, i32 } [[I6]], i32 [[I7]], 1
|
||||
; CHECK-NEXT: ret { i32, i32 } [[I8]]
|
||||
; CHECK-NEXT: ret { i32, i32 } [[AGG_LEFT_PN]]
|
||||
;
|
||||
entry:
|
||||
br i1 %c, label %left, label %right
|
||||
|
|
|
|||
|
|
@ -12,9 +12,8 @@ define void @test0(i32 %v0, i32 %v1, i1 %c, i32* %d0, i32* %d1) {
|
|||
; CHECK-NEXT: br label [[END]]
|
||||
; CHECK: end:
|
||||
; CHECK-NEXT: [[I0:%.*]] = phi i32 [ [[V0:%.*]], [[B0]] ], [ [[V1:%.*]], [[B1]] ]
|
||||
; CHECK-NEXT: [[I1:%.*]] = phi i32 [ [[V0]], [[B0]] ], [ [[V1]], [[B1]] ]
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D0:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I1]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
|
|
@ -45,9 +44,8 @@ define void @test1(i32 %v0, i32 %v1, i1 %c, i32* %d0, i32* %d1) {
|
|||
; CHECK-NEXT: br label [[END]]
|
||||
; CHECK: end:
|
||||
; CHECK-NEXT: [[I0:%.*]] = phi i32 [ [[V0:%.*]], [[B0]] ], [ [[V1:%.*]], [[B1]] ]
|
||||
; CHECK-NEXT: [[I1:%.*]] = phi i32 [ [[V0]], [[B0]] ], [ [[V1]], [[B1]] ]
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D0:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I1]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
|
|
@ -140,9 +138,8 @@ define void @negative_test4(i32 %v0, i32 %v1, i1 %c, i32* %d0, i32* %d1) {
|
|||
; CHECK-NEXT: br label [[END]]
|
||||
; CHECK: end:
|
||||
; CHECK-NEXT: [[I0:%.*]] = phi i32 [ [[V0:%.*]], [[B0]] ], [ [[V1:%.*]], [[B1]] ]
|
||||
; CHECK-NEXT: [[I1:%.*]] = phi i32 [ [[V0]], [[B0]] ], [ [[V1]], [[B1]] ]
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D0:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I1]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
|
|
@ -233,9 +230,8 @@ define void @test7(i32 %v0, i32 %v1, i16 %v2, i16 %v3, i1 %c, i32* %d0, i32* %d1
|
|||
; CHECK: end:
|
||||
; CHECK-NEXT: [[IBAD:%.*]] = phi i16 [ [[V2:%.*]], [[B0]] ], [ [[V3:%.*]], [[B1]] ]
|
||||
; CHECK-NEXT: [[I0:%.*]] = phi i32 [ [[V0:%.*]], [[B0]] ], [ [[V1:%.*]], [[B1]] ]
|
||||
; CHECK-NEXT: [[I1:%.*]] = phi i32 [ [[V0]], [[B0]] ], [ [[V1]], [[B1]] ]
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D0:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I1]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: store i16 [[IBAD]], i16* [[D2:%.*]], align 2
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
|
|
@ -268,9 +264,8 @@ define void @test8(i32 %v0, i32 %v1, i16 %v2, i16 %v3, i1 %c, i32* %d0, i32* %d1
|
|||
; CHECK: end:
|
||||
; CHECK-NEXT: [[I0:%.*]] = phi i32 [ [[V0:%.*]], [[B0]] ], [ [[V1:%.*]], [[B1]] ]
|
||||
; CHECK-NEXT: [[IBAD:%.*]] = phi i16 [ [[V2:%.*]], [[B0]] ], [ [[V3:%.*]], [[B1]] ]
|
||||
; CHECK-NEXT: [[I1:%.*]] = phi i32 [ [[V0]], [[B0]] ], [ [[V1]], [[B1]] ]
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D0:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I1]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: store i16 [[IBAD]], i16* [[D2:%.*]], align 2
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
|
|
@ -302,10 +297,9 @@ define void @test9(i32 %v0, i32 %v1, i16 %v2, i16 %v3, i1 %c, i32* %d0, i32* %d1
|
|||
; CHECK-NEXT: br label [[END]]
|
||||
; CHECK: end:
|
||||
; CHECK-NEXT: [[I0:%.*]] = phi i32 [ [[V0:%.*]], [[B0]] ], [ [[V1:%.*]], [[B1]] ]
|
||||
; CHECK-NEXT: [[I1:%.*]] = phi i32 [ [[V0]], [[B0]] ], [ [[V1]], [[B1]] ]
|
||||
; CHECK-NEXT: [[IBAD:%.*]] = phi i16 [ [[V2:%.*]], [[B0]] ], [ [[V3:%.*]], [[B1]] ]
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D0:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I1]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: store i32 [[I0]], i32* [[D1:%.*]], align 4
|
||||
; CHECK-NEXT: store i16 [[IBAD]], i16* [[D2:%.*]], align 2
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
|
|
|
|||
|
|
@ -15,17 +15,13 @@ define i32 @test_gep_and_bitcast(i1 %cond, i1 %cond2) {
|
|||
; ALL-NEXT: [[OBJ:%.*]] = call i8* @get_ptr.i8()
|
||||
; ALL-NEXT: br i1 [[COND:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
|
||||
; ALL: bb1:
|
||||
; ALL-NEXT: [[PTR1:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; ALL-NEXT: [[PTR1_TYPED:%.*]] = bitcast i8* [[PTR1]] to i32*
|
||||
; ALL-NEXT: br label [[EXIT:%.*]]
|
||||
; ALL: bb2:
|
||||
; ALL-NEXT: [[PTR2:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; ALL-NEXT: [[PTR2_TYPED:%.*]] = bitcast i8* [[PTR2]] to i32*
|
||||
; ALL-NEXT: br label [[EXIT]]
|
||||
; ALL: exit:
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = phi i32* [ [[PTR1_TYPED]], [[BB1]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; ALL-NEXT: [[RES_PHI_IN:%.*]] = phi i32* [ [[PTR1_TYPED]], [[BB1]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[RES_PHI_IN]], align 4
|
||||
; ALL-NEXT: [[PTR_TYPED_IN:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = bitcast i8* [[PTR_TYPED_IN]] to i32*
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: store i32 1, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: [[RES:%.*]] = select i1 [[COND2:%.*]], i32 [[RES_PHI]], i32 1
|
||||
; ALL-NEXT: ret i32 [[RES]]
|
||||
|
|
@ -60,17 +56,13 @@ define i32 @test_gep_and_bitcast_arg(i8* %obj, i1 %cond, i1 %cond2) {
|
|||
; ALL-NEXT: entry:
|
||||
; ALL-NEXT: br i1 [[COND:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
|
||||
; ALL: bb1:
|
||||
; ALL-NEXT: [[PTR1:%.*]] = getelementptr inbounds i8, i8* [[OBJ:%.*]], i64 16
|
||||
; ALL-NEXT: [[PTR1_TYPED:%.*]] = bitcast i8* [[PTR1]] to i32*
|
||||
; ALL-NEXT: br label [[EXIT:%.*]]
|
||||
; ALL: bb2:
|
||||
; ALL-NEXT: [[PTR2:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; ALL-NEXT: [[PTR2_TYPED:%.*]] = bitcast i8* [[PTR2]] to i32*
|
||||
; ALL-NEXT: br label [[EXIT]]
|
||||
; ALL: exit:
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = phi i32* [ [[PTR1_TYPED]], [[BB1]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; ALL-NEXT: [[RES_PHI_IN:%.*]] = phi i32* [ [[PTR1_TYPED]], [[BB1]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[RES_PHI_IN]], align 4
|
||||
; ALL-NEXT: [[PTR_TYPED_IN:%.*]] = getelementptr inbounds i8, i8* [[OBJ:%.*]], i64 16
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = bitcast i8* [[PTR_TYPED_IN]] to i32*
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: store i32 1, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: [[RES:%.*]] = select i1 [[COND2:%.*]], i32 [[RES_PHI]], i32 1
|
||||
; ALL-NEXT: ret i32 [[RES]]
|
||||
|
|
@ -116,17 +108,13 @@ define i32 @test_gep_and_bitcast_phi(i1 %cond, i1 %cond2, i1 %cond3) {
|
|||
; ALL-NEXT: call void @foo.i8(i8* [[ANOTHER_PHI]])
|
||||
; ALL-NEXT: br i1 [[COND2:%.*]], label [[BB3:%.*]], label [[BB4:%.*]]
|
||||
; ALL: bb3:
|
||||
; ALL-NEXT: [[PTR1:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; ALL-NEXT: [[PTR1_TYPED:%.*]] = bitcast i8* [[PTR1]] to i32*
|
||||
; ALL-NEXT: br label [[EXIT:%.*]]
|
||||
; ALL: bb4:
|
||||
; ALL-NEXT: [[PTR2:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; ALL-NEXT: [[PTR2_TYPED:%.*]] = bitcast i8* [[PTR2]] to i32*
|
||||
; ALL-NEXT: br label [[EXIT]]
|
||||
; ALL: exit:
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = phi i32* [ [[PTR1_TYPED]], [[BB3]] ], [ [[PTR2_TYPED]], [[BB4]] ]
|
||||
; ALL-NEXT: [[RES_PHI_IN:%.*]] = phi i32* [ [[PTR1_TYPED]], [[BB3]] ], [ [[PTR2_TYPED]], [[BB4]] ]
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[RES_PHI_IN]], align 4
|
||||
; ALL-NEXT: [[PTR_TYPED_IN:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = bitcast i8* [[PTR_TYPED_IN]] to i32*
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: store i32 1, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: [[RES:%.*]] = select i1 [[COND3:%.*]], i32 [[RES_PHI]], i32 1
|
||||
; ALL-NEXT: ret i32 [[RES]]
|
||||
|
|
@ -176,15 +164,12 @@ define i32 @test_gep_i32ptr(i1 %cond, i1 %cond2) {
|
|||
; ALL-NEXT: [[OBJ:%.*]] = call i32* @get_ptr.i32()
|
||||
; ALL-NEXT: br i1 [[COND:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
|
||||
; ALL: bb1:
|
||||
; ALL-NEXT: [[PTR1_TYPED:%.*]] = getelementptr inbounds i32, i32* [[OBJ]], i64 16
|
||||
; ALL-NEXT: br label [[EXIT:%.*]]
|
||||
; ALL: bb2:
|
||||
; ALL-NEXT: [[PTR2_TYPED:%.*]] = getelementptr inbounds i32, i32* [[OBJ]], i64 16
|
||||
; ALL-NEXT: br label [[EXIT]]
|
||||
; ALL: exit:
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = phi i32* [ [[PTR1_TYPED]], [[BB1]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; ALL-NEXT: [[RES_PHI_IN:%.*]] = phi i32* [ [[PTR1_TYPED]], [[BB1]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[RES_PHI_IN]], align 4
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = getelementptr inbounds i32, i32* [[OBJ]], i64 16
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: store i32 1, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: [[RES:%.*]] = select i1 [[COND2:%.*]], i32 [[RES_PHI]], i32 1
|
||||
; ALL-NEXT: ret i32 [[RES]]
|
||||
|
|
@ -218,17 +203,13 @@ define i32 @test_gep_and_bitcast_gep_base_ptr(i1 %cond, i1 %cond2) {
|
|||
; ALL-NEXT: [[OBJ0:%.*]] = call i8* @get_ptr.i8()
|
||||
; ALL-NEXT: br i1 [[COND:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
|
||||
; ALL: bb1:
|
||||
; ALL-NEXT: [[PTR1:%.*]] = getelementptr inbounds i8, i8* [[OBJ0]], i64 32
|
||||
; ALL-NEXT: [[PTR1_TYPED:%.*]] = bitcast i8* [[PTR1]] to i32*
|
||||
; ALL-NEXT: br label [[EXIT:%.*]]
|
||||
; ALL: bb2:
|
||||
; ALL-NEXT: [[PTR2:%.*]] = getelementptr inbounds i8, i8* [[OBJ0]], i64 32
|
||||
; ALL-NEXT: [[PTR2_TYPED:%.*]] = bitcast i8* [[PTR2]] to i32*
|
||||
; ALL-NEXT: br label [[EXIT]]
|
||||
; ALL: exit:
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = phi i32* [ [[PTR1_TYPED]], [[BB1]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; ALL-NEXT: [[RES_PHI_IN:%.*]] = phi i32* [ [[PTR1_TYPED]], [[BB1]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[RES_PHI_IN]], align 4
|
||||
; ALL-NEXT: [[PTR_TYPED_IN:%.*]] = getelementptr inbounds i8, i8* [[OBJ0]], i64 32
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = bitcast i8* [[PTR_TYPED_IN]] to i32*
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: store i32 1, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: [[RES:%.*]] = select i1 [[COND2:%.*]], i32 [[RES_PHI]], i32 1
|
||||
; ALL-NEXT: ret i32 [[RES]]
|
||||
|
|
@ -260,37 +241,19 @@ exit:
|
|||
}
|
||||
|
||||
define i32 @test_gep_and_bitcast_same_bb(i1 %cond, i1 %cond2) {
|
||||
; INSTCOMBINE-LABEL: @test_gep_and_bitcast_same_bb(
|
||||
; INSTCOMBINE-NEXT: entry:
|
||||
; INSTCOMBINE-NEXT: [[OBJ:%.*]] = call i8* @get_ptr.i8()
|
||||
; INSTCOMBINE-NEXT: [[PTR1:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; INSTCOMBINE-NEXT: [[PTR1_TYPED:%.*]] = bitcast i8* [[PTR1]] to i32*
|
||||
; INSTCOMBINE-NEXT: br i1 [[COND:%.*]], label [[EXIT:%.*]], label [[BB2:%.*]]
|
||||
; INSTCOMBINE: bb2:
|
||||
; INSTCOMBINE-NEXT: [[PTR2:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; INSTCOMBINE-NEXT: [[PTR2_TYPED:%.*]] = bitcast i8* [[PTR2]] to i32*
|
||||
; INSTCOMBINE-NEXT: br label [[EXIT]]
|
||||
; INSTCOMBINE: exit:
|
||||
; INSTCOMBINE-NEXT: [[PTR_TYPED:%.*]] = phi i32* [ [[PTR1_TYPED]], [[ENTRY:%.*]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; INSTCOMBINE-NEXT: [[RES_PHI_IN:%.*]] = phi i32* [ [[PTR1_TYPED]], [[ENTRY]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; INSTCOMBINE-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[RES_PHI_IN]], align 4
|
||||
; INSTCOMBINE-NEXT: store i32 1, i32* [[PTR_TYPED]], align 4
|
||||
; INSTCOMBINE-NEXT: [[RES:%.*]] = select i1 [[COND2:%.*]], i32 [[RES_PHI]], i32 1
|
||||
; INSTCOMBINE-NEXT: ret i32 [[RES]]
|
||||
;
|
||||
; INSTCOMBINEGVN-LABEL: @test_gep_and_bitcast_same_bb(
|
||||
; INSTCOMBINEGVN-NEXT: entry:
|
||||
; INSTCOMBINEGVN-NEXT: [[OBJ:%.*]] = call i8* @get_ptr.i8()
|
||||
; INSTCOMBINEGVN-NEXT: [[PTR1:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; INSTCOMBINEGVN-NEXT: [[PTR1_TYPED:%.*]] = bitcast i8* [[PTR1]] to i32*
|
||||
; INSTCOMBINEGVN-NEXT: br i1 [[COND:%.*]], label [[EXIT:%.*]], label [[BB2:%.*]]
|
||||
; INSTCOMBINEGVN: bb2:
|
||||
; INSTCOMBINEGVN-NEXT: br label [[EXIT]]
|
||||
; INSTCOMBINEGVN: exit:
|
||||
; INSTCOMBINEGVN-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[PTR1_TYPED]], align 4
|
||||
; INSTCOMBINEGVN-NEXT: store i32 1, i32* [[PTR1_TYPED]], align 4
|
||||
; INSTCOMBINEGVN-NEXT: [[RES:%.*]] = select i1 [[COND2:%.*]], i32 [[RES_PHI]], i32 1
|
||||
; INSTCOMBINEGVN-NEXT: ret i32 [[RES]]
|
||||
; ALL-LABEL: @test_gep_and_bitcast_same_bb(
|
||||
; ALL-NEXT: entry:
|
||||
; ALL-NEXT: [[OBJ:%.*]] = call i8* @get_ptr.i8()
|
||||
; ALL-NEXT: br i1 [[COND:%.*]], label [[EXIT:%.*]], label [[BB2:%.*]]
|
||||
; ALL: bb2:
|
||||
; ALL-NEXT: br label [[EXIT]]
|
||||
; ALL: exit:
|
||||
; ALL-NEXT: [[PTR_TYPED_IN:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = bitcast i8* [[PTR_TYPED_IN]] to i32*
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: store i32 1, i32* [[PTR_TYPED]], align 4
|
||||
; ALL-NEXT: [[RES:%.*]] = select i1 [[COND2:%.*]], i32 [[RES_PHI]], i32 1
|
||||
; ALL-NEXT: ret i32 [[RES]]
|
||||
;
|
||||
entry:
|
||||
%obj = call i8* @get_ptr.i8()
|
||||
|
|
@ -328,8 +291,7 @@ define i32 @test_gep_and_bitcast_same_bb_and_extra_use(i1 %cond, i1 %cond2) {
|
|||
; INSTCOMBINE-NEXT: br label [[EXIT]]
|
||||
; INSTCOMBINE: exit:
|
||||
; INSTCOMBINE-NEXT: [[PTR_TYPED:%.*]] = phi i32* [ [[PTR1_TYPED]], [[ENTRY:%.*]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; INSTCOMBINE-NEXT: [[RES_PHI_IN:%.*]] = phi i32* [ [[PTR1_TYPED]], [[ENTRY]] ], [ [[PTR2_TYPED]], [[BB2]] ]
|
||||
; INSTCOMBINE-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[RES_PHI_IN]], align 4
|
||||
; INSTCOMBINE-NEXT: [[RES_PHI:%.*]] = load i32, i32* [[PTR_TYPED]], align 4
|
||||
; INSTCOMBINE-NEXT: store i32 1, i32* [[PTR_TYPED]], align 4
|
||||
; INSTCOMBINE-NEXT: [[RES:%.*]] = select i1 [[COND2:%.*]], i32 [[RES_PHI]], i32 1
|
||||
; INSTCOMBINE-NEXT: ret i32 [[RES]]
|
||||
|
|
@ -378,15 +340,12 @@ define i8 @test_gep(i1 %cond, i1 %cond2) {
|
|||
; ALL-NEXT: [[OBJ:%.*]] = call i8* @get_ptr.i8()
|
||||
; ALL-NEXT: br i1 [[COND:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
|
||||
; ALL: bb1:
|
||||
; ALL-NEXT: [[PTR1:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; ALL-NEXT: br label [[EXIT:%.*]]
|
||||
; ALL: bb2:
|
||||
; ALL-NEXT: [[PTR2:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; ALL-NEXT: br label [[EXIT]]
|
||||
; ALL: exit:
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = phi i8* [ [[PTR1]], [[BB1]] ], [ [[PTR2]], [[BB2]] ]
|
||||
; ALL-NEXT: [[RES_PHI_IN:%.*]] = phi i8* [ [[PTR1]], [[BB1]] ], [ [[PTR2]], [[BB2]] ]
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i8, i8* [[RES_PHI_IN]], align 1
|
||||
; ALL-NEXT: [[PTR_TYPED:%.*]] = getelementptr inbounds i8, i8* [[OBJ]], i64 16
|
||||
; ALL-NEXT: [[RES_PHI:%.*]] = load i8, i8* [[PTR_TYPED]], align 1
|
||||
; ALL-NEXT: store i8 1, i8* [[PTR_TYPED]], align 1
|
||||
; ALL-NEXT: [[RES:%.*]] = select i1 [[COND2:%.*]], i8 [[RES_PHI]], i8 1
|
||||
; ALL-NEXT: ret i8 [[RES]]
|
||||
|
|
|
|||
|
|
@ -1903,7 +1903,6 @@ exit:
|
|||
}
|
||||
|
||||
; Shows how we can leverage dominance to eliminate duplicating selects.
|
||||
; TODO: We can optimize further if we eliminate duplicating Phis and similify the whole thing to phi[x, y] * 3.
|
||||
define i32 @select_dominance_chain(i1 %cond, i32 %x, i32 %y) {
|
||||
; CHECK-LABEL: @select_dominance_chain(
|
||||
; CHECK-NEXT: entry:
|
||||
|
|
@ -1926,10 +1925,7 @@ define i32 @select_dominance_chain(i1 %cond, i32 %x, i32 %y) {
|
|||
; CHECK-NEXT: br label [[MERGE_3]]
|
||||
; CHECK: merge.3:
|
||||
; CHECK-NEXT: [[S_3:%.*]] = phi i32 [ [[Y:%.*]], [[IF_FALSE_3]] ], [ [[X:%.*]], [[IF_TRUE_3]] ]
|
||||
; CHECK-NEXT: [[S_2:%.*]] = phi i32 [ [[Y]], [[IF_FALSE_3]] ], [ [[X]], [[IF_TRUE_3]] ]
|
||||
; CHECK-NEXT: [[S_1:%.*]] = phi i32 [ [[Y]], [[IF_FALSE_3]] ], [ [[X]], [[IF_TRUE_3]] ]
|
||||
; CHECK-NEXT: [[SUM_1:%.*]] = add i32 [[S_1]], [[S_2]]
|
||||
; CHECK-NEXT: [[SUM_2:%.*]] = add i32 [[SUM_1]], [[S_3]]
|
||||
; CHECK-NEXT: [[SUM_2:%.*]] = mul i32 [[S_3]], 3
|
||||
; CHECK-NEXT: ret i32 [[SUM_2]]
|
||||
;
|
||||
entry:
|
||||
|
|
|
|||
|
|
@ -504,7 +504,6 @@ exit:
|
|||
;CHECK: add <4 x i32>
|
||||
;CHECK: extractelement <4 x i32> %{{.*}}, i32 0
|
||||
;CHECK: %sum.lcssa = phi i32 [ %[[SCALAR:.*]], %.lr.ph ], [ %[[VECTOR:.*]], %middle.block ]
|
||||
;CHECK: %sum.copy = phi i32 [ %[[SCALAR]], %.lr.ph ], [ %[[VECTOR]], %middle.block ]
|
||||
;CHECK: ret i32
|
||||
define i32 @reduction_sum_multiuse(i32 %n, i32* noalias nocapture %A, i32* noalias nocapture %B) {
|
||||
%1 = icmp sgt i32 %n, 0
|
||||
|
|
@ -544,7 +543,7 @@ end:
|
|||
; variable. We cannot vectorize this.
|
||||
; CHECK-LABEL: reduction_reset(
|
||||
; CHECK-NOT: <4 x i32>
|
||||
define void @reduction_reset(i32 %N, i32* nocapture readonly %arrayA, i32* nocapture %arrayB) {
|
||||
define void @reduction_reset(i32 %N, i32* nocapture readonly %arrayA, i32* nocapture %arrayB) {
|
||||
entry:
|
||||
%c4 = icmp sgt i32 %N, 0
|
||||
br i1 %c4, label %.lr.ph.preheader, label %._crit_edge
|
||||
|
|
|
|||
Loading…
Reference in New Issue