llvm/test/CodeGen/X86/vec_shuffle-16.ll
Nate Begeman 9008ca6b6b 2nd attempt, fixing SSE4.1 issues and implementing feedback from duncan.
PR2957

ISD::VECTOR_SHUFFLE now stores an array of integers representing the shuffle
mask internal to the node, rather than taking a BUILD_VECTOR of ConstantSDNodes
as the shuffle mask.  A value of -1 represents UNDEF.

In addition to eliminating the creation of illegal BUILD_VECTORS just to 
represent shuffle masks, we are better about canonicalizing the shuffle mask,
resulting in substantially better code for some classes of shuffles.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70225 91177308-0d34-0410-b5e6-96231b3b80d8
2009-04-27 18:41:29 +00:00

28 lines
1.0 KiB
LLVM

; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse,-sse2 -mtriple=i386-apple-darwin -o %t -f
; RUN: grep shufps %t | count 4
; RUN: grep movaps %t | count 2
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 -mtriple=i386-apple-darwin -o %t -f
; RUN: grep pshufd %t | count 4
; RUN: not grep shufps %t
; RUN: not grep mov %t
define <4 x float> @t1(<4 x float> %a, <4 x float> %b) nounwind {
%tmp1 = shufflevector <4 x float> %b, <4 x float> undef, <4 x i32> zeroinitializer
ret <4 x float> %tmp1
}
define <4 x float> @t2(<4 x float> %A, <4 x float> %B) nounwind {
%tmp = shufflevector <4 x float> %A, <4 x float> %B, <4 x i32> < i32 3, i32 3, i32 3, i32 3 >
ret <4 x float> %tmp
}
define <4 x float> @t3(<4 x float> %A, <4 x float> %B) nounwind {
%tmp = shufflevector <4 x float> %A, <4 x float> %B, <4 x i32> < i32 4, i32 4, i32 4, i32 4 >
ret <4 x float> %tmp
}
define <4 x float> @t4(<4 x float> %A, <4 x float> %B) nounwind {
%tmp = shufflevector <4 x float> %A, <4 x float> %B, <4 x i32> < i32 1, i32 3, i32 2, i32 0 >
ret <4 x float> %tmp
}