2016-06-03 17:56:24 +08:00
|
|
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
|
|
|
; RUN: llc < %s -mtriple=i686-unknown-linux-gnu -mattr=+avx2 | FileCheck %s --check-prefix=X32
|
|
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mattr=+avx2 | FileCheck %s --check-prefix=X64
|
2012-01-09 14:52:46 +08:00
|
|
|
|
2016-06-03 17:56:24 +08:00
|
|
|
define void @f(<8 x float> %A, i8* %B, <4 x double> %C, <4 x i64> %E, <8 x i32> %F, <16 x i16> %G, <32 x i8> %H) nounwind {
|
|
|
|
|
; X32-LABEL: f:
|
|
|
|
|
; X32: # BB#0:
|
|
|
|
|
; X32-NEXT: pushl %ebp
|
|
|
|
|
; X32-NEXT: movl %esp, %ebp
|
|
|
|
|
; X32-NEXT: andl $-32, %esp
|
|
|
|
|
; X32-NEXT: subl $32, %esp
|
|
|
|
|
; X32-NEXT: vmovdqa 104(%ebp), %ymm3
|
|
|
|
|
; X32-NEXT: vmovdqa 72(%ebp), %ymm4
|
|
|
|
|
; X32-NEXT: vmovdqa 40(%ebp), %ymm5
|
|
|
|
|
; X32-NEXT: movl 8(%ebp), %eax
|
|
|
|
|
; X32-NEXT: vaddps .LCPI0_0, %ymm0, %ymm0
|
|
|
|
|
; X32-NEXT: vmovntps %ymm0, (%eax)
|
|
|
|
|
; X32-NEXT: vpaddq .LCPI0_1, %ymm2, %ymm0
|
|
|
|
|
; X32-NEXT: vmovntdq %ymm0, (%eax)
|
|
|
|
|
; X32-NEXT: vaddpd .LCPI0_2, %ymm1, %ymm0
|
|
|
|
|
; X32-NEXT: vmovntpd %ymm0, (%eax)
|
|
|
|
|
; X32-NEXT: vpaddd .LCPI0_3, %ymm5, %ymm0
|
|
|
|
|
; X32-NEXT: vmovntdq %ymm0, (%eax)
|
|
|
|
|
; X32-NEXT: vpaddw .LCPI0_4, %ymm4, %ymm0
|
|
|
|
|
; X32-NEXT: vmovntdq %ymm0, (%eax)
|
|
|
|
|
; X32-NEXT: vpaddb .LCPI0_5, %ymm3, %ymm0
|
|
|
|
|
; X32-NEXT: vmovntdq %ymm0, (%eax)
|
|
|
|
|
; X32-NEXT: movl %ebp, %esp
|
|
|
|
|
; X32-NEXT: popl %ebp
|
|
|
|
|
; X32-NEXT: vzeroupper
|
|
|
|
|
; X32-NEXT: retl
|
|
|
|
|
;
|
|
|
|
|
; X64-LABEL: f:
|
|
|
|
|
; X64: # BB#0:
|
|
|
|
|
; X64-NEXT: vaddps {{.*}}(%rip), %ymm0, %ymm0
|
|
|
|
|
; X64-NEXT: vmovntps %ymm0, (%rdi)
|
|
|
|
|
; X64-NEXT: vpaddq {{.*}}(%rip), %ymm2, %ymm0
|
|
|
|
|
; X64-NEXT: vmovntdq %ymm0, (%rdi)
|
|
|
|
|
; X64-NEXT: vaddpd {{.*}}(%rip), %ymm1, %ymm0
|
|
|
|
|
; X64-NEXT: vmovntpd %ymm0, (%rdi)
|
|
|
|
|
; X64-NEXT: vpaddd {{.*}}(%rip), %ymm3, %ymm0
|
|
|
|
|
; X64-NEXT: vmovntdq %ymm0, (%rdi)
|
|
|
|
|
; X64-NEXT: vpaddw {{.*}}(%rip), %ymm4, %ymm0
|
|
|
|
|
; X64-NEXT: vmovntdq %ymm0, (%rdi)
|
|
|
|
|
; X64-NEXT: vpaddb {{.*}}(%rip), %ymm5, %ymm0
|
|
|
|
|
; X64-NEXT: vmovntdq %ymm0, (%rdi)
|
|
|
|
|
; X64-NEXT: vzeroupper
|
|
|
|
|
; X64-NEXT: retq
|
2012-01-09 14:52:46 +08:00
|
|
|
%cast = bitcast i8* %B to <8 x float>*
|
2016-06-03 17:56:24 +08:00
|
|
|
%A2 = fadd <8 x float> %A, <float 1.0, float 2.0, float 3.0, float 4.0, float 5.0, float 6.0, float 7.0, float 8.0>
|
2016-06-03 18:06:59 +08:00
|
|
|
store <8 x float> %A2, <8 x float>* %cast, align 32, !nontemporal !0
|
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>
|
2016-06-03 18:06:59 +08:00
|
|
|
store <4 x i64> %E2, <4 x i64>* %cast1, align 32, !nontemporal !0
|
2012-01-09 14:52:46 +08:00
|
|
|
%cast2 = bitcast i8* %B to <4 x double>*
|
2016-06-03 17:56:24 +08:00
|
|
|
%C2 = fadd <4 x double> %C, <double 1.0, double 2.0, double 3.0, double 4.0>
|
2016-06-03 18:06:59 +08:00
|
|
|
store <4 x double> %C2, <4 x double>* %cast2, align 32, !nontemporal !0
|
2016-06-03 17:56:24 +08:00
|
|
|
%cast3 = bitcast i8* %B to <8 x i32>*
|
|
|
|
|
%F2 = add <8 x i32> %F, <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
|
2016-06-03 18:06:59 +08:00
|
|
|
store <8 x i32> %F2, <8 x i32>* %cast3, align 32, !nontemporal !0
|
2016-06-03 17:56:24 +08:00
|
|
|
%cast4 = bitcast i8* %B to <16 x i16>*
|
|
|
|
|
%G2 = add <16 x i16> %G, <i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8>
|
2016-06-03 18:06:59 +08:00
|
|
|
store <16 x i16> %G2, <16 x i16>* %cast4, align 32, !nontemporal !0
|
2016-06-03 17:56:24 +08:00
|
|
|
%cast5 = bitcast i8* %B to <32 x i8>*
|
|
|
|
|
%H2 = add <32 x i8> %H, <i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8>
|
2016-06-03 18:06:59 +08:00
|
|
|
store <32 x i8> %H2, <32 x i8>* %cast5, align 32, !nontemporal !0
|
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}
|