maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopVectorize/tbaa-nodep.ll

103 lines
3.7 KiB
LLVM
Raw Normal View History

[LoopVectorize] Use AA to partition potential dependency checks Prior to this change, the loop vectorizer did not make use of the alias analysis infrastructure. Instead, it performed memory dependence analysis using ScalarEvolution-based linear dependence checks within equivalence classes derived from the results of ValueTracking's GetUnderlyingObjects. Unfortunately, this meant that: 1. The loop vectorizer had logic that essentially duplicated that in BasicAA for aliasing based on identified objects. 2. The loop vectorizer could not partition the space of dependency checks based on information only easily available from within AA (TBAA metadata is currently the prime example). This means, for example, regardless of whether -fno-strict-aliasing was provided, the vectorizer would only vectorize this loop with a runtime memory-overlap check: void foo(int *a, float *b) { for (int i = 0; i < 1600; ++i) a[i] = b[i]; } This is suboptimal because the TBAA metadata already provides the information necessary to show that this check unnecessary. Of course, the vectorizer has a limit on the number of such checks it will insert, so in practice, ignoring TBAA means not vectorizing more-complicated loops that we should. This change causes the vectorizer to use an AliasSetTracker to keep track of the pointers in the loop. The resulting alias sets are then used to partition the space of dependency checks, and potential runtime checks; this results in more-efficient vectorizations. When pointer locations are added to the AliasSetTracker, two things are done: 1. The location size is set to UnknownSize (otherwise you'd not catch inter-iteration dependencies) 2. For instructions in blocks that would need to be predicated, TBAA is removed (because the metadata might have a control dependency on the condition being speculated). For non-predicated blocks, you can leave the TBAA metadata. This is safe because you can't have an iteration dependency on the TBAA metadata (if you did, and you unrolled sufficiently, you'd end up with the same pointer value used by two accesses that TBAA says should not alias, and that would yield undefined behavior). llvm-svn: 213486
2014-07-21 07:07:52 +08:00
; RUN: opt < %s -tbaa -basicaa -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -simplifycfg -S | FileCheck %s
; RUN: opt < %s -basicaa -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -simplifycfg -S | FileCheck %s --check-prefix=CHECK-NOTBAA
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
; Function Attrs: nounwind uwtable
define i32 @test1(i32* nocapture %a, float* nocapture readonly %b) #0 {
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds float* %b, i64 %indvars.iv
%0 = load float* %arrayidx, align 4, !tbaa !0
%conv = fptosi float %0 to i32
%arrayidx2 = getelementptr inbounds i32* %a, i64 %indvars.iv
store i32 %conv, i32* %arrayidx2, align 4, !tbaa !4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 1600
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret i32 0
; TBAA partitions the accesses in this loop, so it can be vectorized without
; runtime checks.
; CHECK-LABEL: @test1
; CHECK: entry:
; CHECK-NEXT: br label %vector.body
; CHECK: vector.body:
; CHECK: load <4 x float>* %{{.*}}, align 4, !tbaa
; CHECK: store <4 x i32> %{{.*}}, <4 x i32>* %{{.*}}, align 4, !tbaa
; CHECK: ret i32 0
; CHECK-NOTBAA-LABEL: @test1
; CHECK-NOTBAA: icmp uge i32*
; CHECK-NOTBAA: load <4 x float>* %{{.*}}, align 4, !tbaa
; CHECK-NOTBAA: store <4 x i32> %{{.*}}, <4 x i32>* %{{.*}}, align 4, !tbaa
; CHECK-NOTBAA: ret i32 0
}
; Function Attrs: nounwind uwtable
define i32 @test2(i32* nocapture readonly %a, float* nocapture readonly %b, float* nocapture %c) #0 {
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds float* %b, i64 %indvars.iv
%0 = load float* %arrayidx, align 4, !tbaa !0
%arrayidx2 = getelementptr inbounds i32* %a, i64 %indvars.iv
%1 = load i32* %arrayidx2, align 4, !tbaa !4
%conv = sitofp i32 %1 to float
%mul = fmul float %0, %conv
%arrayidx4 = getelementptr inbounds float* %c, i64 %indvars.iv
store float %mul, float* %arrayidx4, align 4, !tbaa !0
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 1600
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret i32 0
; This test is like the first, except here there is still one runtime check
; required. Without TBAA, however, two checks are required.
; CHECK-LABEL: @test2
; CHECK: icmp uge float*
; CHECK: icmp uge float*
; CHECK-NOT: icmp uge i32*
; CHECK: load <4 x float>* %{{.*}}, align 4, !tbaa
; CHECK: store <4 x float> %{{.*}}, <4 x float>* %{{.*}}, align 4, !tbaa
; CHECK: ret i32 0
; CHECK-NOTBAA-LABEL: @test2
; CHECK-NOTBAA: icmp uge float*
; CHECK-NOTBAA: icmp uge float*
; CHECK-NOTBAA-DAG: icmp uge float*
; CHECK-NOTBAA-DAG: icmp uge i32*
; CHECK-NOTBAA: load <4 x float>* %{{.*}}, align 4, !tbaa
; CHECK-NOTBAA: store <4 x float> %{{.*}}, <4 x float>* %{{.*}}, align 4, !tbaa
; CHECK-NOTBAA: ret i32 0
}
attributes #0 = { nounwind uwtable }
!0 = metadata !{metadata !1, metadata !1, i64 0}
!1 = metadata !{metadata !"float", metadata !2, i64 0}
!2 = metadata !{metadata !"omnipotent char", metadata !3, i64 0}
!3 = metadata !{metadata !"Simple C/C++ TBAA"}
!4 = metadata !{metadata !5, metadata !5, i64 0}
!5 = metadata !{metadata !"int", metadata !2, i64 0}