mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-12-13 14:35:54 +00:00
cc03ee5234
This was reverted because of a miscompilation. At closer inspection, the problem was actually visible in a changed llvm regression test too. This one-line follow up fix/recommit will splat the IV, which is what we are trying to avoid if unnecessary in general, if tail-folding is requested even if all users are scalar instructions after vectorisation. Because with tail-folding, the splat IV will be used by the predicate of the masked loads/stores instructions. The previous version omitted this, which caused the miscompilation. The original commit message was: If tail-folding of the scalar remainder loop is applied, the primary induction variable is splat to a vector and used by the masked load/store vector instructions, thus the IV does not remain scalar. Because we now mark that the IV does not remain scalar for these cases, we don't emit the vector IV if it is not used. Thus, the vectoriser produces less dead code. Thanks to Ayal Zaks for the direction how to fix this.
24 lines
779 B
LLVM
24 lines
779 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: %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
|
|
}
|