2014-09-10 19:58:16 +02:00
|
|
|
; RUN: opt < %s -tbaa -basicaa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -simplifycfg -S | FileCheck %s
|
|
|
|
|
; RUN: opt < %s -basicaa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -simplifycfg -S | FileCheck %s --check-prefix=CHECK-NOTBAA
|
[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 01:07:52 +02:00
|
|
|
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 }
|
|
|
|
|
|
IR: Make metadata typeless in assembly
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
llvm-svn: 224257
2014-12-15 20:07:53 +01:00
|
|
|
!0 = !{!1, !1, i64 0}
|
|
|
|
|
!1 = !{!"float", !2, i64 0}
|
|
|
|
|
!2 = !{!"omnipotent char", !3, i64 0}
|
|
|
|
|
!3 = !{!"Simple C/C++ TBAA"}
|
|
|
|
|
!4 = !{!5, !5, i64 0}
|
|
|
|
|
!5 = !{!"int", !2, i64 0}
|
[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 01:07:52 +02:00
|
|
|
|
