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/sandybridge-loads.ll

46 lines
1.8 KiB
LLVM
Raw Normal View History

[x86] auto-generate better checks; NFC llvm-svn: 304090
2017-05-28 21:57:59 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=corei7-avx | FileCheck %s
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
define void @wideloads(<8 x float>* %a, <8 x float>* %b, <8 x float>* %c) nounwind uwtable noinline ssp {
[x86] auto-generate better checks; NFC llvm-svn: 304090
2017-05-28 21:57:59 +08:00
; CHECK-LABEL: wideloads:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate better checks; NFC llvm-svn: 304090
2017-05-28 21:57:59 +08:00
; CHECK-NEXT: vmovaps (%rdi), %xmm0
; CHECK-NEXT: vinsertf128 $1, 16(%rdi), %ymm0, %ymm0
; CHECK-NEXT: vmovaps (%rsi), %ymm1
; CHECK-NEXT: vcmpltps %ymm0, %ymm1, %ymm1
; CHECK-NEXT: vmovaps (%rdx), %ymm2
; CHECK-NEXT: vcmpltps %ymm0, %ymm2, %ymm0
; CHECK-NEXT: vandps %ymm1, %ymm0, %ymm0
; CHECK-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; CHECK-NEXT: vmovaps %ymm0, (%rax)
; CHECK-NEXT: vzeroupper
; CHECK-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 ; <---- unaligned!
%v1 = load <8 x float>, <8 x float>* %b, align 32 ; <---- aligned!
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
%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 32 ; <---- aligned!
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
%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
ret void
}
define void @widestores(<8 x float>* %a, <8 x float>* %b, <8 x float>* %c) nounwind uwtable noinline ssp {
[x86] auto-generate better checks; NFC llvm-svn: 304090
2017-05-28 21:57:59 +08:00
; CHECK-LABEL: widestores:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate better checks; NFC llvm-svn: 304090
2017-05-28 21:57:59 +08:00
; CHECK-NEXT: vmovaps (%rdi), %ymm0
; CHECK-NEXT: vmovaps (%rsi), %ymm1
; CHECK-NEXT: vmovaps %ymm0, (%rsi)
; CHECK-NEXT: vextractf128 $1, %ymm1, 16(%rdi)
; CHECK-NEXT: vmovaps %xmm1, (%rdi)
; CHECK-NEXT: vzeroupper
; CHECK-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 32
%v1 = load <8 x float>, <8 x float>* %b, align 32
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 float> %v0, <8 x float>* %b, align 32 ; <--- aligned
store <8 x float> %v1, <8 x float>* %a, align 16 ; <--- unaligned
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
ret void
}