1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Anna Thomas ce71877c5e [LoopVectorize] Fix assertion failure in Fcmp vectorization
Summary:
When vectorizing fcmps we can trip on incorrect cast assertion when setting the
FastMathFlags after generating the vectorized FCmp.
This can happen if the FCmp can be folded to true or false directly. The fix
here is to set the FastMathFlag using the FastMathFlagBuilder *before* creating
the FCmp Instruction. This is what's done by other optimizations such as
InstCombine.
Added a test case which trips on cast assertion without this patch.

Reviewers: Ayal, mssimpso, mkuper, gilr

Reviewed by: Ayal, mssimpso

Subscribers: llvm-commits, mzolotukhin

Differential Revision: https://reviews.llvm.org/D36244

llvm-svn: 310389
2017-08-08 18:07:44 +00:00

26 lines
961 B
LLVM

; RUN: opt -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S %s | FileCheck %s
; Avoid crashing while trying to vectorize fcmp that can be folded to vector of
; i1 true.
define void @test1() {
; CHECK-LABEL: test1(
; CHECK-LABEL: vector.body:
; CHECK-NEXT: %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK-NEXT: %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
; CHECK: %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
; CHECK: %index.next = add i32 %index, 4
entry:
br label %loop
loop: ; preds = %loop, %entry
%iv = phi i32 [ 0, %entry ], [ %ivnext, %loop ]
%fcmp = fcmp uno float 0.000000e+00, 0.000000e+00
%ivnext = add nsw i32 %iv, 1
%cnd = icmp sgt i32 %iv, 142
br i1 %cnd, label %exit, label %loop
exit: ; preds = %loop
ret void
}