1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 04:32:44 +01:00
llvm-mirror/test/Transforms/LoopDistribute/crash-in-memcheck-generation.ll
Adam Nemet ffa0068101 [LDist] Match behavior between invoking via optimization pipeline or opt -loop-distribute
In r267672, where the loop distribution pragma was introduced, I tried
it hard to keep the old behavior for opt: when opt is invoked
with -loop-distribute, it should distribute the loop (it's off by
default when ran via the optimization pipeline).

As MichaelZ has discovered this has the unintended consequence of
breaking a very common developer work-flow to reproduce compilations
using opt: First you print the pass pipeline of clang
with -debug-pass=Arguments and then invoking opt with the returned
arguments.

clang -debug-pass will include -loop-distribute but the pass is invoked
with default=off so nothing happens unless the loop carries the pragma.
While through opt (default=on) we will try to distribute all loops.

This changes opt's default to off as well to match clang.  The tests are
modified to explicitly enable the transformation.

llvm-svn: 290235
2016-12-21 04:07:40 +00:00

60 lines
1.8 KiB
LLVM

; RUN: opt -basicaa -loop-distribute -enable-loop-distribute -loop-vectorize -force-vector-width=4 \
; RUN: -verify-loop-info -verify-dom-info -S < %s | FileCheck %s
; If only A and B can alias here, we don't need memchecks to distribute since
; A and B are in the same partition. This used to cause a crash in the
; memcheck generation.
;
; for (i = 0; i < n; i++) {
; A[i + 1] = A[i] * B[i];
; ------------------------------
; C[i] = D[i] * E[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* %a,
i32* %b,
i32* noalias %c,
i32* noalias %d,
i32* noalias %e) {
entry:
br label %for.body
; CHECK-NOT: memcheck:
; CHECK: mul <4 x i32>
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
}