File: vector_memcpy.ll

package info (click to toggle)
llvm 2.6-9.1
  • links: PTS
  • area: main
  • in suites: squeeze
  • size: 57,604 kB
  • ctags: 44,336
  • sloc: cpp: 344,766; sh: 12,407; ansic: 10,617; ada: 3,070; ml: 2,505; perl: 2,496; makefile: 1,426; pascal: 1,163; exp: 389; asm: 307; python: 298; objc: 260; lisp: 182; csh: 117; xml: 38; f90: 36; tcl: 20
file content (29 lines) | stat: -rw-r--r-- 915 bytes parent folder | download 
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
 
; RUN: llvm-as < %s | opt -scalarrepl | llvm-dis > %t
; RUN: grep {ret <16 x float> %A} %t
; RUN: grep {ret <16 x float> zeroinitializer} %t

define <16 x float> @foo(<16 x float> %A) nounwind {
	%tmp = alloca <16 x float>, align 16
	%tmp2 = alloca <16 x float>, align 16
	store <16 x float> %A, <16 x float>* %tmp
	%s = bitcast <16 x float>* %tmp to i8*
	%s2 = bitcast <16 x float>* %tmp2 to i8*
	call void @llvm.memcpy.i64(i8* %s2, i8* %s, i64 64, i32 16)
	
	%R = load <16 x float>* %tmp2
	ret <16 x float> %R
}

define <16 x float> @foo2(<16 x float> %A) nounwind {
	%tmp2 = alloca <16 x float>, align 16

	%s2 = bitcast <16 x float>* %tmp2 to i8*
	call void @llvm.memset.i64(i8* %s2, i8 0, i64 64, i32 16)
	
	%R = load <16 x float>* %tmp2
	ret <16 x float> %R
}


declare void @llvm.memcpy.i64(i8* nocapture, i8* nocapture, i64, i32) nounwind
declare void @llvm.memset.i64(i8* nocapture, i8, i64, i32) nounwind