File: vec_shift.ll

package info (click to toggle)
llvm-toolchain-3.8 1%3A3.8.1-24
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 379,280 kB
  • ctags: 388,501
  • sloc: cpp: 2,309,705; ansic: 477,070; objc: 100,918; asm: 97,974; python: 95,911; sh: 18,634; makefile: 7,294; perl: 5,584; ml: 5,460; pascal: 4,661; lisp: 2,548; xml: 686; cs: 350; php: 212; csh: 117
file content (34 lines) | stat: -rw-r--r-- 1,549 bytes parent folder | download | duplicates (11)
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
; RUN: llc < %s -march=x86 -mattr=+sse2 | grep psllw
; RUN: llc < %s -march=x86 -mattr=+sse2 | grep psrlq
; RUN: llc < %s -march=x86 -mattr=+sse2 | grep psraw

define <2 x i64> @t1(<2 x i64> %b1, <2 x i64> %c) nounwind  {
entry:
	%tmp6 = bitcast <2 x i64> %c to <8 x i16>		; <<8 x i16>> [#uses=1]
	%tmp8 = bitcast <2 x i64> %b1 to <8 x i16>		; <<8 x i16>> [#uses=1]
	%tmp9 = tail call <8 x i16> @llvm.x86.sse2.psll.w( <8 x i16> %tmp8, <8 x i16> %tmp6 ) nounwind readnone 		; <<8 x i16>> [#uses=1]
	%tmp10 = bitcast <8 x i16> %tmp9 to <2 x i64>		; <<2 x i64>> [#uses=1]
	ret <2 x i64> %tmp10
}

define <2 x i64> @t3(<2 x i64> %b1, i32 %c) nounwind  {
entry:
	%tmp2 = bitcast <2 x i64> %b1 to <8 x i16>		; <<8 x i16>> [#uses=1]
	%tmp4 = insertelement <4 x i32> undef, i32 %c, i32 0		; <<4 x i32>> [#uses=1]
	%tmp8 = bitcast <4 x i32> %tmp4 to <8 x i16>		; <<8 x i16>> [#uses=1]
	%tmp9 = tail call <8 x i16> @llvm.x86.sse2.psra.w( <8 x i16> %tmp2, <8 x i16> %tmp8 )		; <<8 x i16>> [#uses=1]
	%tmp11 = bitcast <8 x i16> %tmp9 to <2 x i64>		; <<2 x i64>> [#uses=1]
	ret <2 x i64> %tmp11
}

declare <8 x i16> @llvm.x86.sse2.psra.w(<8 x i16>, <8 x i16>) nounwind readnone 

define <2 x i64> @t2(<2 x i64> %b1, <2 x i64> %c) nounwind  {
entry:
	%tmp9 = tail call <2 x i64> @llvm.x86.sse2.psrl.q( <2 x i64> %b1, <2 x i64> %c ) nounwind readnone 		; <<2 x i64>> [#uses=1]
	ret <2 x i64> %tmp9
}

declare <2 x i64> @llvm.x86.sse2.psrl.q(<2 x i64>, <2 x i64>) nounwind readnone 

declare <8 x i16> @llvm.x86.sse2.psll.w(<8 x i16>, <8 x i16>) nounwind readnone