replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Don't vectorize if there are outside loop users of the induction variable. 

We would have to compute the pre increment value, either by computing it on
every loop iteration or by splitting the edge out of the loop and inserting a
computation for it there.

For now, just give up vectorizing such loops.

Fixes PR17179.

llvm-svn: 190790
This commit is contained in:
Arnold Schwaighofer 2013-09-16 16:17:24 +00:00
parent 3bde507a7a
commit 53e622cef4
2 changed files with 36 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -2866,6 +2866,12 @@ bool LoopVectorizationLegality::canVectorizeInstrs() {
DEBUG(dbgs() << "LV: Found an induction variable.\n");
Inductions[Phi] = InductionInfo(StartValue, IK);
// Until we explicitly handle the case of an induction variable with
// an outside loop user we have to give up vectorizing this loop.
if (hasOutsideLoopUser(TheLoop, it, AllowedExit))
return false;
continue;
}

30
llvm/test/Transforms/LoopVectorize/no_outside_user.ll
View File

@ -12,6 +12,7 @@ target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f3
; We used to vectorize this loop. But it has a value that is used outside of the
; and is not a recognized reduction variable "tmp17".
; CHECK-LABEL: main
; CHECK-NOT: <2 x i32>
define i32 @main() {
@ -38,4 +39,33 @@ f1.exit.loopexit:
ret i32 %.lcssa
}
; Don't vectorize this loop. Its phi node (induction variable) has an outside
; loop user. We currently don't handle this case.
; PR17179
; CHECK-LABEL: test2
; CHECK-NOT: <2 x
@x1 = common global i32 0, align 4
@x2 = common global i32 0, align 4
@x0 = common global i32 0, align 4
define i32 @test2() {
entry:
store i32 0, i32* @x1, align 4
%0 = load i32* @x0, align 4
br label %for.cond1.preheader
for.cond1.preheader:
%inc7 = phi i32 [ 0, %entry ], [ %inc, %for.cond1.preheader ]
%inc = add nsw i32 %inc7, 1
%cmp = icmp eq i32 %inc, 52
br i1 %cmp, label %for.end5, label %for.cond1.preheader
for.end5:
%inc7.lcssa = phi i32 [ %inc7, %for.cond1.preheader ]
%xor = xor i32 %inc7.lcssa, %0
store i32 52, i32* @x1, align 4
store i32 1, i32* @x2, align 4
ret i32 %xor
}