mirror of
https://github.com/RPCS3/llvm.git
synced 2024-12-13 23:18:58 +00:00
af4a98fed6
Summary: When optimizing for size, sqrt calls can be incorrectly selected as AVX512 VSQRT instructions. This is because X86InstrAVX512.td has a `Requires<[OptForSize]>` in its `avx512_sqrt_scalar` multiclass definition. Even if the target does not support AVX512, the class can apparently still be chosen, leading to an incorrect selection of `vsqrtss`. In PR26625, this lead to an assertion: Reg >= X86::FP0 && Reg <= X86::FP6 && "Expected FP register!", because the `vsqrtss` instruction requires an XMM register, which is not available on i686 CPUs. Reviewers: grosbach, resistor, joker.eph Subscribers: spatel, emaste, llvm-commits Differential Revision: http://reviews.llvm.org/D17414 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@261360 91177308-0d34-0410-b5e6-96231b3b80d8
21 lines
453 B
LLVM
21 lines
453 B
LLVM
; RUN: llc < %s -mcpu=i686 2>&1 | FileCheck %s
|
|
; PR26625
|
|
|
|
target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
|
|
target triple = "i386"
|
|
|
|
define float @x0(float %f) #0 {
|
|
entry:
|
|
%call = tail call float @sqrtf(float %f) #1
|
|
ret float %call
|
|
; CHECK-LABEL: x0:
|
|
; CHECK: flds
|
|
; CHECK-NEXT: fsqrt
|
|
; CHECK-NOT: vsqrtss
|
|
}
|
|
|
|
declare float @sqrtf(float) #0
|
|
|
|
attributes #0 = { nounwind optsize readnone }
|
|
attributes #1 = { nounwind optsize readnone }
|