RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2025-02-12 22:30:12 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[X86] Adding a test point for PR34149 'Suboptimal codegen for "fast" minnum and maxnum'

Browse Source 
Differential Revision: https://reviews.llvm.org/D37614

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@312778 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Jatin Bhateja 2017-09-08 09:15:36 +00:00
parent 6b1b54293c
commit 8277ad7473
1 changed files with 40 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
test/CodeGen/X86/pr34149.ll Normal file
View File

@ -0,0 +1,40 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=haswell | FileCheck %s
declare <4 x double> @llvm.minnum.v4f64(<4 x double> %x, <4 x double> %y)
declare <4 x double> @llvm.maxnum.v4f64(<4 x double> %x, <4 x double> %y)
define <4 x double> @via_minnum(<4 x double> %x, <4 x double> %y) {
; CHECK-LABEL: via_minnum:
; CHECK: # BB#0:
; CHECK-NEXT: vminpd %ymm0, %ymm1, %ymm2
; CHECK-NEXT: vcmpunordpd %ymm0, %ymm0, %ymm0
; CHECK-NEXT: vblendvpd %ymm0, %ymm1, %ymm2, %ymm0
; CHECK-NEXT: retq
%z = call fast <4 x double> @llvm.minnum.v4f64(<4 x double> %x, <4 x double> %y) readnone
ret <4 x double> %z
}
define <4 x double> @via_maxnum(<4 x double> %x, <4 x double> %y) {
; CHECK-LABEL: via_maxnum:
; CHECK: # BB#0:
; CHECK-NEXT: vmaxpd %ymm0, %ymm1, %ymm2
; CHECK-NEXT: vcmpunordpd %ymm0, %ymm0, %ymm0
; CHECK-NEXT: vblendvpd %ymm0, %ymm1, %ymm2, %ymm0
; CHECK-NEXT: retq
%z = call fast <4 x double> @llvm.maxnum.v4f64(<4 x double> %x, <4 x double> %y) readnone
ret <4 x double> %z
}
define <4 x double> @via_fcmp(<4 x double> %x, <4 x double> %y) {
; CHECK-LABEL: via_fcmp:
; CHECK: # BB#0:
; CHECK-NEXT: vminpd %ymm0, %ymm1, %ymm0
; CHECK-NEXT: retq
%c = fcmp ule <4 x double> %x, %y
%z = select <4 x i1> %c, <4 x double> %x, <4 x double> %y
ret <4 x double> %z
}