1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 11:13:28 +01:00
llvm-mirror/test/Transforms/LoopDistribute/no-if-convert.ll
Adam Nemet b3422c24d4 New Loop Distribution pass
Summary:
This implements the initial version as was proposed earlier this year
(http://lists.cs.uiuc.edu/pipermail/llvmdev/2015-January/080462.html).
Since then Loop Access Analysis was split out from the Loop Vectorizer
and was made into a separate analysis pass.  Loop Distribution becomes
the second user of this analysis.

The pass is off by default and can be enabled
with -enable-loop-distribution.  There is currently no notion of
profitability; if there is a loop with dependence cycles, the pass will
try to split them off from other memory operations into a separate loop.

I decided to remove the control-dependence calculation from this first
version.  This and the issues with the PDT are actively discussed so it
probably makes sense to treat it separately.  Right now I just mark all
terminator instruction required which keeps identical CFGs for each
distributed loop.  This seems to be working pretty well for 456.hmmer
where even though there is an empty if-then block in the distributed
loop initially, it gets completely removed.

The pass keeps DominatorTree and LoopInfo updated.  I've tested this
with -loop-distribute-verify with the testsuite where we distribute ~90
loops.  SimplifyLoop is violated in some cases and I have a FIXME
covering this.

Reviewers: hfinkel, nadav, aschwaighofer

Reviewed By: aschwaighofer

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D8831

llvm-svn: 237358
2015-05-14 12:05:18 +00:00

96 lines
2.9 KiB
LLVM

; RUN: opt -basicaa -loop-distribute -verify-loop-info -verify-dom-info -S < %s \
; RUN: | FileCheck %s
; We should distribute this loop along === but not along ---. The last
; partition won't be vectorized due to conditional stores so it's better to
; keep it with the second partition which has a dependence cycle.
; (1st statement):
; for (i = 0; i < n; i++) {
; C[i] = D[i] * E[i];
;=============================
; A[i + 1] = A[i] * B[i];
;-----------------------------
; if (F[i])
; G[i] = H[i] * J[i];
; }
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.10.0"
define void @f(i32* noalias %a,
i32* noalias %b,
i32* noalias %c,
i32* noalias %d,
i32* noalias %e,
i32* noalias %g,
i32* noalias %h,
i32* noalias %j,
i64 %x) {
entry:
br label %for.body
; Ensure that we have only two partitions, the first with one multiplication
; and the second with two.
; CHECK: for.body.ldist1:
; CHECK: %mulC.ldist1 = mul i32 %loadD.ldist1, %loadE.ldist1
; CHECK: br i1 %exitcond.ldist1, label %entry.split, label %for.body.ldist1
; CHECK: entry.split:
; CHECK: br label %for.body
; CHECK: for.body:
; CHECK: %mulA = mul i32 %loadB, %loadA
; CHECK: %mulG = mul i32 %loadH, %loadJ
; CHECK: for.end:
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %if.end ]
%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
%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
%if.cond = icmp eq i64 %ind, %x
br i1 %if.cond, label %if.then, label %if.end
if.then:
%arrayidxH = getelementptr inbounds i32, i32* %h, i64 %ind
%loadH = load i32, i32* %arrayidxH, align 4
%arrayidxJ = getelementptr inbounds i32, i32* %j, i64 %ind
%loadJ = load i32, i32* %arrayidxJ, align 4
%mulG = mul i32 %loadH, %loadJ
%arrayidxG = getelementptr inbounds i32, i32* %g, i64 %ind
store i32 %mulG, i32* %arrayidxG, align 4
br label %if.end
if.end:
%exitcond = icmp eq i64 %add, 20
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}