llvm-6502/test/CodeGen/X86/vec_insert-2.ll
Evan Cheng 5e6ebaf4d1 Fix PR2485: do all 4-element SSE shuffles in max. of 2 shuffle instructions.
Based on patch by Nicolas Capens.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@53939 91177308-0d34-0410-b5e6-96231b3b80d8
2008-07-23 00:22:17 +00:00

26 lines
994 B
LLVM

; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep {\$36,} | count 2
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep shufps | count 2
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep pinsrw | count 1
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep movhpd | count 1
; RUN: llvm-as < %s | llc -march=x86-64 -mattr=+sse2 | grep unpcklpd | count 1
define <4 x float> @t1(float %s, <4 x float> %tmp) nounwind {
%tmp1 = insertelement <4 x float> %tmp, float %s, i32 3
ret <4 x float> %tmp1
}
define <4 x i32> @t2(i32 %s, <4 x i32> %tmp) nounwind {
%tmp1 = insertelement <4 x i32> %tmp, i32 %s, i32 3
ret <4 x i32> %tmp1
}
define <2 x double> @t3(double %s, <2 x double> %tmp) nounwind {
%tmp1 = insertelement <2 x double> %tmp, double %s, i32 1
ret <2 x double> %tmp1
}
define <8 x i16> @t4(i16 %s, <8 x i16> %tmp) nounwind {
%tmp1 = insertelement <8 x i16> %tmp, i16 %s, i32 5
ret <8 x i16> %tmp1
}