mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-28 04:33:05 +00:00
cf2ab764db
All changes were made by the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" grep -q "^; *RUN: *llc.*debug" $NAME && continue grep -q "^; *RUN:.*llvm-objdump" $NAME && continue grep -q "^; *RUN: *opt.*" $NAME && continue TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\([A-Za-z0-9_-]*\)\([A-Za-z0-9_-]*\):\( *\)$FUNC[:]* *\$/;\1\2-LABEL:\3$FUNC:/g" $TEMP done sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME done This script catches a superset of the cases caught by the script associated with commit r186280. It initially found some false positives due to unusual constructs in a minority of tests; all such cases were disambiguated first in commit r186621. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186624 91177308-0d34-0410-b5e6-96231b3b80d8
39 lines
1.5 KiB
LLVM
39 lines
1.5 KiB
LLVM
; RUN: llc < %s -mcpu=corei7-avx -mtriple=x86_64-linux | FileCheck %s
|
|
|
|
;CHECK-LABEL: cftx020:
|
|
;CHECK: vmovsd (%rdi), %xmm{{.*}}
|
|
;CHECK: vmovsd 16(%rdi), %xmm{{.*}}
|
|
;CHECK: vmovhpd 8(%rdi), %xmm{{.*}}
|
|
;CHECK: vmovsd 24(%rdi), %xmm{{.*}}
|
|
;CHECK: vmovupd %xmm{{.*}}, (%rdi)
|
|
;CHECK: vmovupd %xmm{{.*}}, 16(%rdi)
|
|
;CHECK: ret
|
|
|
|
; A test from pifft (after SLP-vectorization) that fails when we drop the chain on newly merged loads.
|
|
define void @cftx020(double* nocapture %a) {
|
|
entry:
|
|
%0 = load double* %a, align 8
|
|
%arrayidx1 = getelementptr inbounds double* %a, i64 2
|
|
%1 = load double* %arrayidx1, align 8
|
|
%arrayidx2 = getelementptr inbounds double* %a, i64 1
|
|
%2 = load double* %arrayidx2, align 8
|
|
%arrayidx3 = getelementptr inbounds double* %a, i64 3
|
|
%3 = load double* %arrayidx3, align 8
|
|
%4 = insertelement <2 x double> undef, double %0, i32 0
|
|
%5 = insertelement <2 x double> %4, double %3, i32 1
|
|
%6 = insertelement <2 x double> undef, double %1, i32 0
|
|
%7 = insertelement <2 x double> %6, double %2, i32 1
|
|
%8 = fadd <2 x double> %5, %7
|
|
%9 = bitcast double* %a to <2 x double>*
|
|
store <2 x double> %8, <2 x double>* %9, align 8
|
|
%10 = insertelement <2 x double> undef, double %0, i32 0
|
|
%11 = insertelement <2 x double> %10, double %2, i32 1
|
|
%12 = insertelement <2 x double> undef, double %1, i32 0
|
|
%13 = insertelement <2 x double> %12, double %3, i32 1
|
|
%14 = fsub <2 x double> %11, %13
|
|
%15 = bitcast double* %arrayidx1 to <2 x double>*
|
|
store <2 x double> %14, <2 x double>* %15, align 8
|
|
ret void
|
|
}
|
|
|