maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/v8i1-masks.ll

40 lines
1.1 KiB
LLVM
Raw Normal View History

On AVX/AVX2 the type v8i1 is legalized to v8i16, which is an XMM sized register. In most cases we actually compare or select YMM-sized registers and mixing the two types creates horrible code. This commit optimizes some of the transition sequences. PR14657. llvm-svn: 171148
2012-12-27 16:15:45 +08:00
; RUN: llc -march=x86-64 -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -o - < %s | FileCheck %s
Update to more CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change. 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. llvm-svn: 186624
2013-07-19 06:47:09 +08:00
;CHECK-LABEL: and_masks:
On Sandybridge loading unaligned 256bits using two XMM loads (vmovups and vinsertf128) is faster than using a single vmovups instruction. llvm-svn: 172868
2013-01-19 07:10:30 +08:00
;CHECK: vmovaps
AVX: Fix a bug in WidenMaskArithmetic. llvm-svn: 171397
2013-01-03 01:40:39 +08:00
;CHECK: vcmpltp
;CHECK: vcmpltp
;CHECK: vandps
;CHECK: vandps
On Sandybridge split unaligned 256bit stores into two xmm-sized stores. llvm-svn: 172894
2013-01-19 16:38:41 +08:00
;CHECK: vmovaps
On AVX/AVX2 the type v8i1 is legalized to v8i16, which is an XMM sized register. In most cases we actually compare or select YMM-sized registers and mixing the two types creates horrible code. This commit optimizes some of the transition sequences. PR14657. llvm-svn: 171148
2012-12-27 16:15:45 +08:00
;CHECK: ret
define void @and_masks(<8 x float>* %a, <8 x float>* %b, <8 x float>* %c) nounwind uwtable noinline ssp {
%v0 = load <8 x float>* %a, align 16
%v1 = load <8 x float>* %b, align 16
%m0 = fcmp olt <8 x float> %v1, %v0
%v2 = load <8 x float>* %c, align 16
%m1 = fcmp olt <8 x float> %v2, %v0
%mand = and <8 x i1> %m1, %m0
%r = zext <8 x i1> %mand to <8 x i32>
On Sandybridge split unaligned 256bit stores into two xmm-sized stores. llvm-svn: 172894
2013-01-19 16:38:41 +08:00
store <8 x i32> %r, <8 x i32>* undef, align 32
On AVX/AVX2 the type v8i1 is legalized to v8i16, which is an XMM sized register. In most cases we actually compare or select YMM-sized registers and mixing the two types creates horrible code. This commit optimizes some of the transition sequences. PR14657. llvm-svn: 171148
2012-12-27 16:15:45 +08:00
ret void
}
;CHECK: neg_mask
AVX: Fix a bug in WidenMaskArithmetic. llvm-svn: 171397
2013-01-03 01:40:39 +08:00
;CHECK: vcmpltps
;CHECK: vxorps
;CHECK: vandps
On Sandybridge split unaligned 256bit stores into two xmm-sized stores. llvm-svn: 172894
2013-01-19 16:38:41 +08:00
;CHECK: vmovaps
On AVX/AVX2 the type v8i1 is legalized to v8i16, which is an XMM sized register. In most cases we actually compare or select YMM-sized registers and mixing the two types creates horrible code. This commit optimizes some of the transition sequences. PR14657. llvm-svn: 171148
2012-12-27 16:15:45 +08:00
;CHECK: ret
define void @neg_masks(<8 x float>* %a, <8 x float>* %b, <8 x float>* %c) nounwind uwtable noinline ssp {
%v0 = load <8 x float>* %a, align 16
%v1 = load <8 x float>* %b, align 16
%m0 = fcmp olt <8 x float> %v1, %v0
%mand = xor <8 x i1> %m0, <i1 1, i1 1, i1 1, i1 1, i1 1, i1 1, i1 1, i1 1>
%r = zext <8 x i1> %mand to <8 x i32>
On Sandybridge split unaligned 256bit stores into two xmm-sized stores. llvm-svn: 172894
2013-01-19 16:38:41 +08:00
store <8 x i32> %r, <8 x i32>* undef, align 32
On AVX/AVX2 the type v8i1 is legalized to v8i16, which is an XMM sized register. In most cases we actually compare or select YMM-sized registers and mixing the two types creates horrible code. This commit optimizes some of the transition sequences. PR14657. llvm-svn: 171148
2012-12-27 16:15:45 +08:00
ret void
}