maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[LoopInterchange][PR57148] Ensure the correct form of IR after transformation 

This is a bugfix patch that resolves the following two bugs in loop interchange:

1. PR57148 which is an assertion error due to of loss of LCSSA form after interchange,
   as referred to test1() in pr57148.ll.
2. Use before def for the outermost loop induction variables after interchange,
   as referred to test2() in pr57148.ll.

The fix in this patch is that:

1. In cases where the LCSSA form is not maintained after interchange, we update the IR
   to the LCSSA form again.
2. We split the phi nodes in the inner loop header into a separate basic block to avoid
   the situation where use of the outer indvar appears before its def after interchange.
   Previously we already did this for innermost loops, now we do it for non-innermost
   loops (e.g., middle loops) as well.

Reviewed By: bmahjour, Meinersbur, #loopoptwg

Differential Revision: https://reviews.llvm.org/D132055
This commit is contained in:
Congzhe Cao 2022-09-22 00:00:52 -04:00 committed by CongzheUalberta
parent 8a2729fea7
commit 22c91df52c
3 changed files with 175 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/lib/Transforms/Scalar/LoopInterchange.cpp
View File

@ -573,11 +573,7 @@ struct LoopInterchange {
LLVM_DEBUG(dbgs() << "Loops interchanged.\n");
LoopsInterchanged++;
assert(InnerLoop->isLCSSAForm(*DT) &&
"Inner loop not left in LCSSA form after loop interchange!");
assert(OuterLoop->isLCSSAForm(*DT) &&
"Outer loop not left in LCSSA form after loop interchange!");
llvm::formLCSSARecursively(*OuterLoop, *DT, LI, SE);
return true;
}
};
@ -1354,9 +1350,11 @@ bool LoopInterchangeTransform::transform() {
for (Instruction *InnerIndexVar : InnerIndexVarList)
WorkList.insert(cast<Instruction>(InnerIndexVar));
MoveInstructions();
}
// Splits the inner loops phi nodes out into a separate basic block.
// Ensure the inner loop phi nodes have a separate basic block.
BasicBlock *InnerLoopHeader = InnerLoop->getHeader();
if (InnerLoopHeader->getFirstNonPHI() != InnerLoopHeader->getTerminator()) {
SplitBlock(InnerLoopHeader, InnerLoopHeader->getFirstNonPHI(), DT, LI);
LLVM_DEBUG(dbgs() << "splitting InnerLoopHeader done\n");
}

8
llvm/test/Transforms/LoopInterchange/pr43176-move-to-new-latch.ll
View File

@ -13,14 +13,12 @@ define void @test1() {
; CHECK-NEXT: [[INC41:%.*]] = phi i32 [ [[INC4:%.*]], [[FOR_INC3:%.*]] ], [ undef, [[FOR_BODY_PREHEADER:%.*]] ]
; CHECK-NEXT: [[IDXPROM:%.*]] = sext i32 [[INC41]] to i64
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @b, i64 0, i64 [[IDXPROM]]
; CHECK-NEXT: br label [[FOR_BODY2_SPLIT:%.*]]
; CHECK-NEXT: br label [[FOR_INC:%.*]]
; CHECK: for.body2.preheader:
; CHECK-NEXT: br label [[FOR_BODY2:%.*]]
; CHECK: for.body2:
; CHECK-NEXT: [[LSR_IV:%.*]] = phi i32 [ [[TMP1:%.*]], [[FOR_INC_SPLIT:%.*]] ], [ 1, [[FOR_BODY2_PREHEADER]] ]
; CHECK-NEXT: br label [[FOR_BODY_PREHEADER]]
; CHECK: for.body2.split:
; CHECK-NEXT: br label [[FOR_INC:%.*]]
; CHECK: for.inc:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: store i32 undef, i32* [[ARRAYIDX]], align 4
@ -80,14 +78,12 @@ define void @test2() {
; CHECK-NEXT: [[INC41:%.*]] = phi i32 [ [[INC4:%.*]], [[FOR_INC3:%.*]] ], [ undef, [[FOR_BODY_PREHEADER:%.*]] ]
; CHECK-NEXT: [[IDXPROM:%.*]] = sext i32 [[INC41]] to i64
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @b, i64 0, i64 [[IDXPROM]]
; CHECK-NEXT: br label [[FOR_BODY2_SPLIT:%.*]]
; CHECK-NEXT: br label [[FOR_INC:%.*]]
; CHECK: for.body2.preheader:
; CHECK-NEXT: br label [[FOR_BODY2:%.*]]
; CHECK: for.body2:
; CHECK-NEXT: [[LSR_IV:%.*]] = phi i32 [ [[TMP1:%.*]], [[FOR_INC_SPLIT:%.*]] ], [ 1, [[FOR_BODY2_PREHEADER]] ]
; CHECK-NEXT: br label [[FOR_BODY_PREHEADER]]
; CHECK: for.body2.split:
; CHECK-NEXT: br label [[FOR_INC:%.*]]
; CHECK: for.inc:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[LSR_IV]], 4

168
llvm/test/Transforms/LoopInterchange/pr57148.ll Normal file
View File

@ -0,0 +1,168 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=loop-interchange -cache-line-size=4 -verify-dom-info -verify-loop-info -verify-scev -verify-loop-lcssa -S | FileCheck %s
; Make sure the loops are in LCSSA form after loop interchange,
; and loop interchange does not hit assertion errors and crash.
target triple = "x86_64-unknown-linux-gnu"
@b = external global [512 x [4 x i32]], align 1
@c = external global [2 x [4 x i32]], align 1
define void @test1() {
; CHECK-LABEL: @test1(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_COND37_PREHEADER_PREHEADER:%.*]]
; CHECK: for.cond33.preheader.preheader:
; CHECK-NEXT: br label [[FOR_COND33_PREHEADER:%.*]]
; CHECK: for.cond33.preheader:
; CHECK-NEXT: [[I_011:%.*]] = phi i16 [ [[INC69:%.*]], [[FOR_END67:%.*]] ], [ 0, [[FOR_COND33_PREHEADER_PREHEADER:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY42_SPLIT1:%.*]]
; CHECK: for.body42.preheader:
; CHECK-NEXT: br label [[FOR_BODY42:%.*]]
; CHECK: for.cond37.preheader.preheader:
; CHECK-NEXT: br label [[FOR_COND37_PREHEADER:%.*]]
; CHECK: for.cond37.preheader:
; CHECK-NEXT: [[J_010:%.*]] = phi i16 [ [[INC66:%.*]], [[FOR_END64:%.*]] ], [ 0, [[FOR_COND37_PREHEADER_PREHEADER]] ]
; CHECK-NEXT: br label [[FOR_BODY42_PREHEADER:%.*]]
; CHECK: for.body42:
; CHECK-NEXT: [[K_09:%.*]] = phi i16 [ [[TMP1:%.*]], [[FOR_BODY42_SPLIT:%.*]] ], [ -512, [[FOR_BODY42_PREHEADER]] ]
; CHECK-NEXT: br label [[FOR_COND33_PREHEADER_PREHEADER]]
; CHECK: for.body42.split1:
; CHECK-NEXT: [[SUB51:%.*]] = add nsw i16 [[K_09]], 512
; CHECK-NEXT: [[ARRAYIDX55:%.*]] = getelementptr inbounds [512 x [4 x i32]], ptr @b, i16 0, i16 [[SUB51]], i16 [[J_010]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX55]], align 1
; CHECK-NEXT: [[ADD61:%.*]] = add i32 undef, undef
; CHECK-NEXT: [[INC63:%.*]] = add nsw i16 [[K_09]], 1
; CHECK-NEXT: br label [[FOR_END67]]
; CHECK: for.body42.split:
; CHECK-NEXT: [[ADD61_LCSSA:%.*]] = phi i32 [ [[ADD61]], [[FOR_END67]] ]
; CHECK-NEXT: [[TMP1]] = add nsw i16 [[K_09]], 1
; CHECK-NEXT: br i1 true, label [[FOR_END64]], label [[FOR_BODY42]]
; CHECK: for.end64:
; CHECK-NEXT: [[ADD61_LCSSA_LCSSA:%.*]] = phi i32 [ [[ADD61_LCSSA]], [[FOR_BODY42_SPLIT]] ]
; CHECK-NEXT: store i32 [[ADD61_LCSSA_LCSSA]], ptr undef, align 1
; CHECK-NEXT: [[INC66]] = add nuw nsw i16 [[J_010]], 1
; CHECK-NEXT: br i1 true, label [[FOR_COND75_PREHEADER:%.*]], label [[FOR_COND37_PREHEADER]]
; CHECK: for.end67:
; CHECK-NEXT: [[INC69]] = add nuw nsw i16 [[I_011]], 1
; CHECK-NEXT: [[EXITCOND13_NOT:%.*]] = icmp eq i16 [[INC69]], 2
; CHECK-NEXT: br i1 [[EXITCOND13_NOT]], label [[FOR_BODY42_SPLIT]], label [[FOR_COND33_PREHEADER]]
; CHECK: for.cond75.preheader:
; CHECK-NEXT: br label [[FOR_COND75:%.*]]
; CHECK: for.cond75:
; CHECK-NEXT: br label [[FOR_COND75]]
;
entry:
br label %for.cond33.preheader
for.cond33.preheader: ; preds = %for.end67, %entry
%i.011 = phi i16 [ 0, %entry ], [ %inc69, %for.end67 ]
br label %for.cond37.preheader
for.cond37.preheader: ; preds = %for.end64, %for.cond33.preheader
%j.010 = phi i16 [ 0, %for.cond33.preheader ], [ %inc66, %for.end64 ]
br label %for.body42
for.body42: ; preds = %for.body42, %for.cond37.preheader
%k.09 = phi i16 [ -512, %for.cond37.preheader ], [ %inc63, %for.body42 ]
%sub51 = add nsw i16 %k.09, 512
%arrayidx55 = getelementptr inbounds [512 x [4 x i32]], ptr @b, i16 0, i16 %sub51, i16 %j.010
%0 = load i32, ptr %arrayidx55, align 1
%add61 = add i32 undef, undef
%inc63 = add nsw i16 %k.09, 1
br i1 true, label %for.end64, label %for.body42
for.end64: ; preds = %for.body42
store i32 %add61, ptr undef, align 1
%inc66 = add nuw nsw i16 %j.010, 1
br i1 true, label %for.end67, label %for.cond37.preheader
for.end67: ; preds = %for.end64
%inc69 = add nuw nsw i16 %i.011, 1
%exitcond13.not = icmp eq i16 %inc69, 2
br i1 %exitcond13.not, label %for.cond75, label %for.cond33.preheader
for.cond75: ; preds = %for.cond75, %for.end67
br label %for.cond75
}
; Make sure that we split the phi nodes in the middle loop header
; into a separate basic block to avoid the situation where use of
; the outermost indvar appears before its def after interchanging
; the outermost and the middle loop. Otherwise loop interchange
; would crash.
define void @test2() {
; CHECK-LABEL: @test2(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_COND37_PREHEADER_PREHEADER:%.*]]
; CHECK: for.cond33.preheader.preheader:
; CHECK-NEXT: br label [[FOR_COND33_PREHEADER:%.*]]
; CHECK: for.cond33.preheader:
; CHECK-NEXT: [[I_166:%.*]] = phi i16 [ [[INC69:%.*]], [[FOR_INC68:%.*]] ], [ 0, [[FOR_COND33_PREHEADER_PREHEADER:%.*]] ]
; CHECK-NEXT: [[ARRAYIDX60:%.*]] = getelementptr inbounds [2 x [4 x i32]], ptr @c, i16 0, i16 [[I_166]], i16 [[J_165:%.*]]
; CHECK-NEXT: br label [[VECTOR_BODY85_SPLIT1:%.*]]
; CHECK: for.cond37.preheader.preheader:
; CHECK-NEXT: br label [[FOR_COND37_PREHEADER:%.*]]
; CHECK: for.cond37.preheader:
; CHECK-NEXT: [[J_165]] = phi i16 [ [[INC66:%.*]], [[MIDDLE_BLOCK80:%.*]] ], [ 0, [[FOR_COND37_PREHEADER_PREHEADER]] ]
; CHECK-NEXT: br label [[FOR_COND37_PREHEADER_SPLIT:%.*]]
; CHECK: for.cond37.preheader.split:
; CHECK-NEXT: br label [[VECTOR_BODY85:%.*]]
; CHECK: vector.body85:
; CHECK-NEXT: [[INDEX86:%.*]] = phi i16 [ 0, [[FOR_COND37_PREHEADER_SPLIT]] ], [ [[TMP3:%.*]], [[VECTOR_BODY85_SPLIT:%.*]] ]
; CHECK-NEXT: br label [[FOR_COND33_PREHEADER_PREHEADER]]
; CHECK: vector.body85.split1:
; CHECK-NEXT: [[TMP0:%.*]] = or i16 [[INDEX86]], 2
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [512 x [4 x i32]], ptr @b, i16 0, i16 [[TMP0]], i16 [[J_165]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 1
; CHECK-NEXT: [[INDEX_NEXT87:%.*]] = add nuw i16 [[INDEX86]], 4
; CHECK-NEXT: br label [[FOR_INC68]]
; CHECK: vector.body85.split:
; CHECK-NEXT: [[TMP3]] = add nuw i16 [[INDEX86]], 4
; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK80]], label [[VECTOR_BODY85]]
; CHECK: middle.block80:
; CHECK-NEXT: [[INC66]] = add nuw nsw i16 [[J_165]], 1
; CHECK-NEXT: br i1 true, label [[FOR_COND75_PREHEADER:%.*]], label [[FOR_COND37_PREHEADER]]
; CHECK: for.inc68:
; CHECK-NEXT: [[INC69]] = add nuw nsw i16 [[I_166]], 1
; CHECK-NEXT: [[EXITCOND77_NOT:%.*]] = icmp eq i16 [[INC69]], 2
; CHECK-NEXT: br i1 [[EXITCOND77_NOT]], label [[VECTOR_BODY85_SPLIT]], label [[FOR_COND33_PREHEADER]]
; CHECK: for.cond75.preheader:
; CHECK-NEXT: unreachable
;
entry:
br label %for.cond33.preheader
for.cond33.preheader: ; preds = %for.inc68, %entry
%i.166 = phi i16 [ %inc69, %for.inc68 ], [ 0, %entry ]
br label %for.cond37.preheader
for.cond37.preheader: ; preds = %middle.block80, %for.cond33.preheader
%j.165 = phi i16 [ 0, %for.cond33.preheader ], [ %inc66, %middle.block80 ]
%arrayidx60 = getelementptr inbounds [2 x [4 x i32]], ptr @c, i16 0, i16 %i.166, i16 %j.165
br label %vector.body85
vector.body85: ; preds = %vector.body85, %for.cond37.preheader
%index86 = phi i16 [ 0, %for.cond37.preheader ], [ %index.next87, %vector.body85 ]
%0 = or i16 %index86, 2
%1 = getelementptr inbounds [512 x [4 x i32]], ptr @b, i16 0, i16 %0, i16 %j.165
%2 = load i32, ptr %1, align 1
%index.next87 = add nuw i16 %index86, 4
br i1 undef, label %middle.block80, label %vector.body85
middle.block80: ; preds = %vector.body85
%inc66 = add nuw nsw i16 %j.165, 1
br i1 undef, label %for.inc68, label %for.cond37.preheader
for.inc68: ; preds = %middle.block80
%inc69 = add nuw nsw i16 %i.166, 1
%exitcond77.not = icmp eq i16 %inc69, 2
br i1 %exitcond77.not, label %for.cond75.preheader, label %for.cond33.preheader
for.cond75.preheader: ; preds = %for.inc68
unreachable
}