mirror of
https://github.com/RPCSX/llvm.git
synced 2024-12-13 23:18:51 +00:00
8d171c8f85
Summary: D19403 adds a new pragma for loop distribution. This change adds support for the corresponding metadata that the pragma is translated to by the FE. As part of this I had to rethink the flag -enable-loop-distribute. My goal was to be backward compatible with the existing behavior: A1. pass is off by default from the optimization pipeline unless -enable-loop-distribute is specified A2. pass is on when invoked directly from opt (e.g. for unit-testing) The new pragma/metadata overrides these defaults so the new behavior is: B1. A1 + enable distribution for individual loop with the pragma/metadata B2. A2 + disable distribution for individual loop with the pragma/metadata The default value whether the pass is on or off comes from the initiator of the pass. From the PassManagerBuilder the default is off, from opt it's on. I moved -enable-loop-distribute under the pass. If the flag is specified it overrides the default from above. Then the pragma/metadata can further modifies this per loop. As a side-effect, we can now also use -enable-loop-distribute=0 from opt to emulate the default from the optimization pipeline. So to be precise this is the new behavior: C1. pass is off by default from the optimization pipeline unless -enable-loop-distribute or the pragma/metadata enables it C2. pass is on when invoked directly from opt unless -enable-loop-distribute=0 or the pragma/metadata disables it Reviewers: hfinkel Subscribers: joker.eph, mzolotukhin, llvm-commits Differential Revision: http://reviews.llvm.org/D19431 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@267672 91177308-0d34-0410-b5e6-96231b3b80d8
150 lines
4.8 KiB
LLVM
150 lines
4.8 KiB
LLVM
; RUN: opt -basicaa -loop-distribute -enable-loop-distribute=0 -S < %s | FileCheck %s --check-prefix=CHECK --check-prefix=EXPLICIT --check-prefix=DEFAULT_OFF
|
|
; RUN: opt -basicaa -loop-distribute -enable-loop-distribute=1 -S < %s | FileCheck %s --check-prefix=CHECK --check-prefix=EXPLICIT --check-prefix=DEFAULT_ON
|
|
|
|
; Same loop as in basic.ll. Check that distribution is enabled/disabled
|
|
; properly according to -enable-loop-distribute=0/1 and the
|
|
; llvm.loop.distribute.enable metadata.
|
|
|
|
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-apple-macosx10.10.0"
|
|
|
|
; CHECK-LABEL: @explicit_on(
|
|
define void @explicit_on(i32* noalias %a,
|
|
i32* noalias %b,
|
|
i32* noalias %c,
|
|
i32* noalias %d,
|
|
i32* noalias %e) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
; EXPLICIT: for.body.ldist1:
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
|
|
|
|
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
|
|
%loadA = load i32, i32* %arrayidxA, align 4
|
|
|
|
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
|
|
%loadB = load i32, i32* %arrayidxB, align 4
|
|
|
|
%mulA = mul i32 %loadB, %loadA
|
|
|
|
%add = add nuw nsw i64 %ind, 1
|
|
%arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
|
|
store i32 %mulA, i32* %arrayidxA_plus_4, align 4
|
|
|
|
%arrayidxD = getelementptr inbounds i32, i32* %d, i64 %ind
|
|
%loadD = load i32, i32* %arrayidxD, align 4
|
|
|
|
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
|
|
%loadE = load i32, i32* %arrayidxE, align 4
|
|
|
|
%mulC = mul i32 %loadD, %loadE
|
|
|
|
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
|
|
store i32 %mulC, i32* %arrayidxC, align 4
|
|
|
|
%exitcond = icmp eq i64 %add, 20
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: @explicit_off(
|
|
define void @explicit_off(i32* noalias %a,
|
|
i32* noalias %b,
|
|
i32* noalias %c,
|
|
i32* noalias %d,
|
|
i32* noalias %e) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
; EXPLICIT-NOT: for.body.ldist1:
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
|
|
|
|
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
|
|
%loadA = load i32, i32* %arrayidxA, align 4
|
|
|
|
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
|
|
%loadB = load i32, i32* %arrayidxB, align 4
|
|
|
|
%mulA = mul i32 %loadB, %loadA
|
|
|
|
%add = add nuw nsw i64 %ind, 1
|
|
%arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
|
|
store i32 %mulA, i32* %arrayidxA_plus_4, align 4
|
|
|
|
%arrayidxD = getelementptr inbounds i32, i32* %d, i64 %ind
|
|
%loadD = load i32, i32* %arrayidxD, align 4
|
|
|
|
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
|
|
%loadE = load i32, i32* %arrayidxE, align 4
|
|
|
|
%mulC = mul i32 %loadD, %loadE
|
|
|
|
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
|
|
store i32 %mulC, i32* %arrayidxC, align 4
|
|
|
|
%exitcond = icmp eq i64 %add, 20
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !2
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: @default_distribute(
|
|
define void @default_distribute(i32* noalias %a,
|
|
i32* noalias %b,
|
|
i32* noalias %c,
|
|
i32* noalias %d,
|
|
i32* noalias %e) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
; Verify the two distributed loops.
|
|
|
|
; DEFAULT_ON: for.body.ldist1:
|
|
; DEFAULT_OFF-NOT: for.body.ldist1:
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
|
|
|
|
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
|
|
%loadA = load i32, i32* %arrayidxA, align 4
|
|
|
|
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
|
|
%loadB = load i32, i32* %arrayidxB, align 4
|
|
|
|
%mulA = mul i32 %loadB, %loadA
|
|
|
|
%add = add nuw nsw i64 %ind, 1
|
|
%arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
|
|
store i32 %mulA, i32* %arrayidxA_plus_4, align 4
|
|
|
|
%arrayidxD = getelementptr inbounds i32, i32* %d, i64 %ind
|
|
%loadD = load i32, i32* %arrayidxD, align 4
|
|
|
|
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
|
|
%loadE = load i32, i32* %arrayidxE, align 4
|
|
|
|
%mulC = mul i32 %loadD, %loadE
|
|
|
|
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
|
|
store i32 %mulC, i32* %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
|
|
}
|
|
|
|
!0 = distinct !{!0, !1}
|
|
!1 = !{!"llvm.loop.distribute.enable", i1 true}
|
|
!2 = distinct !{!2, !3}
|
|
!3 = !{!"llvm.loop.distribute.enable", i1 false}
|