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/avx2-nontemporal.ll

20 lines
838 B
LLVM
Raw Normal View History

Clean up patterns for MOVNT*. Not sure why there were floating point types on MOVNTPS and MOVNTDQ. And v4i64 was completely missing. llvm-svn: 147767
2012-01-09 14:52:46 +08:00
; RUN: llc < %s -march=x86 -mattr=+avx2 | FileCheck %s
[X86] Cleanup nontemporal tests a little. NFC. Also: add a missing test for movntiq. llvm-svn: 246730
2015-09-03 06:47:09 +08:00
define void @f(<8 x float> %A, i8* %B, <4 x double> %C, <4 x i64> %E) {
; CHECK: vmovntps %y
Clean up patterns for MOVNT*. Not sure why there were floating point types on MOVNTPS and MOVNTDQ. And v4i64 was completely missing. llvm-svn: 147767
2012-01-09 14:52:46 +08:00
%cast = bitcast i8* %B to <8 x float>*
%A2 = fadd <8 x float> %A, <float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x4200000000000000>
[X86] Require 32-byte alignment for 32-byte VMOVNTs. We used to accept (and even test, and generate) 16-byte alignment for 32-byte nontemporal stores, but they require 32-byte alignment, per SDM. Found by inspection. Instead of hardcoding 16 in the patfrag, check for natural alignment. Also fix the autoupgrade and the various tests. Also, use explicit -mattr instead of -mcpu: I stared at the output several minutes wondering why I get 2x movntps for the unaligned case (which is the ideal output, but needs some work: see FIXME), until I remembered corei7-avx implies +slow-unaligned-mem-32. llvm-svn: 246733
2015-09-03 07:25:39 +08:00
store <8 x float> %A2, <8 x float>* %cast, align 32, !nontemporal !0
[X86] Cleanup nontemporal tests a little. NFC. Also: add a missing test for movntiq. llvm-svn: 246730
2015-09-03 06:47:09 +08:00
; CHECK: vmovntdq %y
Clean up patterns for MOVNT*. Not sure why there were floating point types on MOVNTPS and MOVNTDQ. And v4i64 was completely missing. llvm-svn: 147767
2012-01-09 14:52:46 +08:00
%cast1 = bitcast i8* %B to <4 x i64>*
%E2 = add <4 x i64> %E, <i64 1, i64 2, i64 3, i64 4>
[X86] Require 32-byte alignment for 32-byte VMOVNTs. We used to accept (and even test, and generate) 16-byte alignment for 32-byte nontemporal stores, but they require 32-byte alignment, per SDM. Found by inspection. Instead of hardcoding 16 in the patfrag, check for natural alignment. Also fix the autoupgrade and the various tests. Also, use explicit -mattr instead of -mcpu: I stared at the output several minutes wondering why I get 2x movntps for the unaligned case (which is the ideal output, but needs some work: see FIXME), until I remembered corei7-avx implies +slow-unaligned-mem-32. llvm-svn: 246733
2015-09-03 07:25:39 +08:00
store <4 x i64> %E2, <4 x i64>* %cast1, align 32, !nontemporal !0
[X86] Cleanup nontemporal tests a little. NFC. Also: add a missing test for movntiq. llvm-svn: 246730
2015-09-03 06:47:09 +08:00
; CHECK: vmovntpd %y
Clean up patterns for MOVNT*. Not sure why there were floating point types on MOVNTPS and MOVNTDQ. And v4i64 was completely missing. llvm-svn: 147767
2012-01-09 14:52:46 +08:00
%cast2 = bitcast i8* %B to <4 x double>*
%C2 = fadd <4 x double> %C, <double 0x0, double 0x0, double 0x0, double 0x4200000000000000>
[X86] Require 32-byte alignment for 32-byte VMOVNTs. We used to accept (and even test, and generate) 16-byte alignment for 32-byte nontemporal stores, but they require 32-byte alignment, per SDM. Found by inspection. Instead of hardcoding 16 in the patfrag, check for natural alignment. Also fix the autoupgrade and the various tests. Also, use explicit -mattr instead of -mcpu: I stared at the output several minutes wondering why I get 2x movntps for the unaligned case (which is the ideal output, but needs some work: see FIXME), until I remembered corei7-avx implies +slow-unaligned-mem-32. llvm-svn: 246733
2015-09-03 07:25:39 +08:00
store <4 x double> %C2, <4 x double>* %cast2, align 32, !nontemporal !0
Clean up patterns for MOVNT*. Not sure why there were floating point types on MOVNTPS and MOVNTDQ. And v4i64 was completely missing. llvm-svn: 147767
2012-01-09 14:52:46 +08:00
ret void
}
IR: Make metadata typeless in assembly Now that `Metadata` is typeless, reflect that in the assembly. These are the matching assembly changes for the metadata/value split in r223802. - Only use the `metadata` type when referencing metadata from a call intrinsic -- i.e., only when it's used as a `Value`. - Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode` when referencing it from call intrinsics. So, assembly like this: define @foo(i32 %v) { call void @llvm.foo(metadata !{i32 %v}, metadata !0) call void @llvm.foo(metadata !{i32 7}, metadata !0) call void @llvm.foo(metadata !1, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{metadata !3}, metadata !0) ret void, !bar !2 } !0 = metadata !{metadata !2} !1 = metadata !{i32* @global} !2 = metadata !{metadata !3} !3 = metadata !{} turns into this: define @foo(i32 %v) { call void @llvm.foo(metadata i32 %v, metadata !0) call void @llvm.foo(metadata i32 7, metadata !0) call void @llvm.foo(metadata i32* @global, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{!3}, metadata !0) ret void, !bar !2 } !0 = !{!2} !1 = !{i32* @global} !2 = !{!3} !3 = !{} I wrote an upgrade script that handled almost all of the tests in llvm and many of the tests in cfe (even handling many `CHECK` lines). I've attached it (or will attach it in a moment if you're speedy) to PR21532 to help everyone update their out-of-tree testcases. This is part of PR21532. llvm-svn: 224257
2014-12-16 03:07:53 +08:00
!0 = !{i32 1}