e949b54a5b
Update LAA to use PSE::getSymbolicMaxBackedgeTakenCount which returns the minimum of the countable exits. When analyzing dependences and computing runtime checks, we need the smallest upper bound on the number of iterations. In terms of memory safety, it shouldn't matter if any uncomputable exits leave the loop, as long as we prove that there are no dependences given the minimum of the countable exits. The same should apply also for generating runtime checks. Note that this shifts the responsiblity of checking whether all exit counts are computable or handling early-exits to the users of LAA. Depends on https://github.com/llvm/llvm-project/pull/93498 PR: https://github.com/llvm/llvm-project/pull/93499
97 lines
3.9 KiB
LLVM
97 lines
3.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; REQUIRES: x86-registered-target
|
|
; RUN: opt -aa-pipeline=basic-aa -passes=loop-distribute -enable-loop-distribute -verify-loop-info -verify-dom-info -S %s | FileCheck %s
|
|
|
|
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-apple-macosx10.10.0"
|
|
|
|
@B = common global ptr null, align 8
|
|
@A = common global ptr null, align 8
|
|
@C = common global ptr null, align 8
|
|
@D = common global ptr null, align 8
|
|
@E = common global ptr null, align 8
|
|
|
|
define void @f() {
|
|
; CHECK-LABEL: define void @f() {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: [[A:%.*]] = load ptr, ptr @A, align 8
|
|
; CHECK-NEXT: [[B:%.*]] = load ptr, ptr @B, align 8
|
|
; CHECK-NEXT: [[C:%.*]] = load ptr, ptr @C, align 8
|
|
; CHECK-NEXT: [[D:%.*]] = load ptr, ptr @D, align 8
|
|
; CHECK-NEXT: [[E:%.*]] = load ptr, ptr @E, align 8
|
|
; CHECK-NEXT: br label %[[FOR_BODY:.*]]
|
|
; CHECK: [[FOR_BODY]]:
|
|
; CHECK-NEXT: [[IND:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[ADD:%.*]], %[[LATCH:.*]] ]
|
|
; CHECK-NEXT: [[ARRAYIDXA:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IND]]
|
|
; CHECK-NEXT: [[LOADA:%.*]] = load i32, ptr [[ARRAYIDXA]], align 4
|
|
; CHECK-NEXT: [[ARRAYIDXB:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[IND]]
|
|
; CHECK-NEXT: [[LOADB:%.*]] = load i32, ptr [[ARRAYIDXB]], align 4
|
|
; CHECK-NEXT: [[UNCOUNTABLE_C:%.*]] = icmp eq i32 [[LOADB]], 10
|
|
; CHECK-NEXT: br i1 [[UNCOUNTABLE_C]], label %[[FOR_END:.*]], label %[[LATCH]]
|
|
; CHECK: [[LATCH]]:
|
|
; CHECK-NEXT: [[MULA:%.*]] = mul i32 [[LOADB]], [[LOADA]]
|
|
; CHECK-NEXT: [[ADD]] = add nuw nsw i64 [[IND]], 1
|
|
; CHECK-NEXT: [[ARRAYIDXA_PLUS_4:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[ADD]]
|
|
; CHECK-NEXT: store i32 [[MULA]], ptr [[ARRAYIDXA_PLUS_4]], align 4
|
|
; CHECK-NEXT: [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, ptr [[D]], i64 [[IND]]
|
|
; CHECK-NEXT: [[LOADD:%.*]] = load i32, ptr [[ARRAYIDXD]], align 4
|
|
; CHECK-NEXT: [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, ptr [[E]], i64 [[IND]]
|
|
; CHECK-NEXT: [[LOADE:%.*]] = load i32, ptr [[ARRAYIDXE]], align 4
|
|
; CHECK-NEXT: [[MULC:%.*]] = mul i32 [[LOADD]], [[LOADE]]
|
|
; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[IND]]
|
|
; CHECK-NEXT: store i32 [[MULC]], ptr [[ARRAYIDXC]], align 4
|
|
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], 20
|
|
; CHECK-NEXT: br i1 [[EXITCOND]], label %[[FOR_END]], label %[[FOR_BODY]]
|
|
; CHECK: [[FOR_END]]:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%a = load ptr, ptr @A, align 8
|
|
%b = load ptr, ptr @B, align 8
|
|
%c = load ptr, ptr @C, align 8
|
|
%d = load ptr, ptr @D, align 8
|
|
%e = load ptr, ptr @E, align 8
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%ind = phi i64 [ 0, %entry ], [ %add, %latch ]
|
|
|
|
%arrayidxA = getelementptr inbounds i32, ptr %a, i64 %ind
|
|
%loadA = load i32, ptr %arrayidxA, align 4
|
|
|
|
%arrayidxB = getelementptr inbounds i32, ptr %b, i64 %ind
|
|
%loadB = load i32, ptr %arrayidxB, align 4
|
|
%uncountable.c = icmp eq i32 %loadB, 10
|
|
br i1 %uncountable.c, label %for.end, label %latch
|
|
|
|
latch:
|
|
%mulA = mul i32 %loadB, %loadA
|
|
|
|
%add = add nuw nsw i64 %ind, 1
|
|
%arrayidxA_plus_4 = getelementptr inbounds i32, ptr %a, i64 %add
|
|
store i32 %mulA, ptr %arrayidxA_plus_4, align 4
|
|
|
|
%arrayidxD = getelementptr inbounds i32, ptr %d, i64 %ind
|
|
%loadD = load i32, ptr %arrayidxD, align 4
|
|
|
|
%arrayidxE = getelementptr inbounds i32, ptr %e, i64 %ind
|
|
%loadE = load i32, ptr %arrayidxE, align 4
|
|
|
|
%mulC = mul i32 %loadD, %loadE
|
|
|
|
%arrayidxC = getelementptr inbounds i32, ptr %c, i64 %ind
|
|
store i32 %mulC, ptr %arrayidxC, align 4
|
|
|
|
%exitcond = icmp eq i64 %add, 20
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind readnone convergent }
|
|
attributes #1 = { nounwind convergent }
|
|
|
|
!0 = distinct !{!0, !1}
|
|
!1 = !{!"llvm.loop.distribute.enable", i1 true}
|