RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
Code Issues Projects Releases Wiki Activity

LoopVectorizer: Don't attempt to vectorize extractelement instructions

Browse Source 
The loop vectorizer does not currently understand how to vectorize
extractelement instructions. The existing check, which excluded all
vector-valued instructions, did not catch extractelement instructions because
it checked only the return value. As a result, vectorization would proceed,
producing illegal instructions like this:

  %58 = extractelement <2 x i32> %15, i32 0
  %59 = extractelement i32 %58, i32 0

where the second extractelement is illegal because its first operand is not a vector.

llvm-svn: 193434
This commit is contained in:
Hal Finkel 2013-10-25 20:40:15 +00:00
parent e9525a4ff2
commit d554c99b37
2 changed files with 38 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -2965,8 +2965,9 @@ bool LoopVectorizationLegality::canVectorizeInstrs() {
}
// Check that the instruction return type is vectorizable.
if (!VectorType::isValidElementType(it->getType()) &&
!it->getType()->isVoidTy()) {
// Also, we can't vectorize extractelement instructions.
if ((!VectorType::isValidElementType(it->getType()) &&
!it->getType()->isVoidTy()) || isa<ExtractElementInst>(it)) {
DEBUG(dbgs() << "LV: Found unvectorizable type.\n");
return false;
}

35
test/Transforms/LoopVectorize/ee-crash.ll Normal file
View File

@ -0,0 +1,35 @@
; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -S | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.8.0"
; This test checks that we deal with an in-loop extractelement (for now, this
; means not crashing by not vectorizing).
; CHECK-LABEL: @_Z4foo1Pii(
; CHECK-NOT: <4 x i32>
; CHECK: ret
define i32 @_Z4foo1Pii(i32* %A, i32 %n, <2 x i32> %q) #0 {
entry:
%idx.ext = sext i32 %n to i64
%add.ptr = getelementptr inbounds i32* %A, i64 %idx.ext
%cmp3.i = icmp eq i32 %n, 0
br i1 %cmp3.i, label %_ZSt10accumulateIPiiET0_T_S2_S1_.exit, label %for.body.i
for.body.i: ; preds = %entry, %for.body.i
%__init.addr.05.i = phi i32 [ %add.i, %for.body.i ], [ 0, %entry ]
%__first.addr.04.i = phi i32* [ %incdec.ptr.i, %for.body.i ], [ %A, %entry ]
%0 = load i32* %__first.addr.04.i, align 4
%q1 = extractelement <2 x i32> %q, i32 %n
%q2 = add nsw i32 %0, %q1
%add.i = add nsw i32 %q2, %__init.addr.05.i
%incdec.ptr.i = getelementptr inbounds i32* %__first.addr.04.i, i64 1
%cmp.i = icmp eq i32* %incdec.ptr.i, %add.ptr
br i1 %cmp.i, label %_ZSt10accumulateIPiiET0_T_S2_S1_.exit, label %for.body.i
_ZSt10accumulateIPiiET0_T_S2_S1_.exit: ; preds = %for.body.i, %entry
%__init.addr.0.lcssa.i = phi i32 [ 0, %entry ], [ %add.i, %for.body.i ]
ret i32 %__init.addr.0.lcssa.i
}
attributes #0 = { nounwind readonly ssp uwtable }