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

78 lines
2.9 KiB
LLVM
Raw Normal View History

[X86][SSE] Regenerated comparison mask and float immediate tests llvm-svn: 265184
2016-04-02 05:00:00 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=+avx | FileCheck %s --check-prefix=CHECK --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx | FileCheck %s --check-prefix=CHECK --check-prefix=X64
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
define void @and_masks(<8 x float>* %a, <8 x float>* %b, <8 x float>* %c) nounwind uwtable noinline ssp {
[X86][SSE] Regenerated comparison mask and float immediate tests llvm-svn: 265184
2016-04-02 05:00:00 +08:00
; X32-LABEL: and_masks:
; X32: ## BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
; X32-NEXT: vmovups (%edx), %ymm0
; X32-NEXT: vmovups (%ecx), %ymm1
; X32-NEXT: vcmpltps %ymm0, %ymm1, %ymm1
; X32-NEXT: vmovups (%eax), %ymm2
; X32-NEXT: vcmpltps %ymm0, %ymm2, %ymm0
[X86] Add floating point packed logical ops to X86InstrInfo::isAssociativeAndCommutative. llvm-svn: 275768
2016-07-18 14:14:50 +08:00
; X32-NEXT: vandps LCPI0_0, %ymm1, %ymm1
[X86][SSE] Regenerated comparison mask and float immediate tests llvm-svn: 265184
2016-04-02 05:00:00 +08:00
; X32-NEXT: vandps %ymm1, %ymm0, %ymm0
; X32-NEXT: vmovaps %ymm0, (%eax)
; X32-NEXT: vzeroupper
; X32-NEXT: retl
;
; X64-LABEL: and_masks:
; X64: ## BB#0:
; X64-NEXT: vmovups (%rdi), %ymm0
; X64-NEXT: vmovups (%rsi), %ymm1
; X64-NEXT: vcmpltps %ymm0, %ymm1, %ymm1
; X64-NEXT: vmovups (%rdx), %ymm2
; X64-NEXT: vcmpltps %ymm0, %ymm2, %ymm0
[X86] Add floating point packed logical ops to X86InstrInfo::isAssociativeAndCommutative. llvm-svn: 275768
2016-07-18 14:14:50 +08:00
; X64-NEXT: vandps {{.*}}(%rip), %ymm1, %ymm1
[X86][SSE] Regenerated comparison mask and float immediate tests llvm-svn: 265184
2016-04-02 05:00:00 +08:00
; X64-NEXT: vandps %ymm1, %ymm0, %ymm0
; X64-NEXT: vmovaps %ymm0, (%rax)
; X64-NEXT: vzeroupper
; X64-NEXT: retq
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%v0 = load <8 x float>, <8 x float>* %a, align 16
%v1 = load <8 x float>, <8 x float>* %b, align 16
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
%m0 = fcmp olt <8 x float> %v1, %v0
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%v2 = load <8 x float>, <8 x float>* %c, align 16
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
%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
}
define void @neg_masks(<8 x float>* %a, <8 x float>* %b, <8 x float>* %c) nounwind uwtable noinline ssp {
[X86][SSE] Regenerated comparison mask and float immediate tests llvm-svn: 265184
2016-04-02 05:00:00 +08:00
; X32-LABEL: neg_masks:
; X32: ## BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: vmovups (%ecx), %ymm0
; X32-NEXT: vcmpltps (%eax), %ymm0, %ymm0
; X32-NEXT: vmovaps {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
; X32-NEXT: vxorps %ymm1, %ymm0, %ymm0
; X32-NEXT: vandps %ymm1, %ymm0, %ymm0
; X32-NEXT: vmovaps %ymm0, (%eax)
; X32-NEXT: vzeroupper
; X32-NEXT: retl
;
; X64-LABEL: neg_masks:
; X64: ## BB#0:
; X64-NEXT: vmovups (%rsi), %ymm0
; X64-NEXT: vcmpltps (%rdi), %ymm0, %ymm0
; X64-NEXT: vmovaps {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
; X64-NEXT: vxorps %ymm1, %ymm0, %ymm0
; X64-NEXT: vandps %ymm1, %ymm0, %ymm0
; X64-NEXT: vmovaps %ymm0, (%rax)
; X64-NEXT: vzeroupper
; X64-NEXT: retq
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%v0 = load <8 x float>, <8 x float>* %a, align 16
%v1 = load <8 x float>, <8 x float>* %b, align 16
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
%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
}