1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
|
; Tests for SSE2 and below, without SSE3+.
; RUN: llc < %s -mtriple=i386-apple-darwin10 -mcpu=pentium4 | FileCheck %s
define void @t1(<2 x double>* %r, <2 x double>* %A, double %B) nounwind {
%tmp3 = load <2 x double>* %A, align 16
%tmp7 = insertelement <2 x double> undef, double %B, i32 0
%tmp9 = shufflevector <2 x double> %tmp3, <2 x double> %tmp7, <2 x i32> < i32 2, i32 1 >
store <2 x double> %tmp9, <2 x double>* %r, align 16
ret void
; CHECK: t1:
; CHECK: movl 8(%esp), %eax
; CHECK-NEXT: movapd (%eax), %xmm0
; CHECK-NEXT: movl 4(%esp), %eax
; CHECK-NEXT: movlpd 12(%esp), %xmm0
; CHECK-NEXT: movapd %xmm0, (%eax)
; CHECK-NEXT: ret
}
define void @t2(<2 x double>* %r, <2 x double>* %A, double %B) nounwind {
%tmp3 = load <2 x double>* %A, align 16
%tmp7 = insertelement <2 x double> undef, double %B, i32 0
%tmp9 = shufflevector <2 x double> %tmp3, <2 x double> %tmp7, <2 x i32> < i32 0, i32 2 >
store <2 x double> %tmp9, <2 x double>* %r, align 16
ret void
; CHECK: t2:
; CHECK: movl 8(%esp), %eax
; CHECK-NEXT: movapd (%eax), %xmm0
; CHECK-NEXT: movl 4(%esp), %eax
; CHECK-NEXT: movhpd 12(%esp), %xmm0
; CHECK-NEXT: movapd %xmm0, (%eax)
; CHECK-NEXT: ret
}
|
