llvm/test/CodeGen/X86/vec_shuffle-13.ll
Evan Cheng 14b32e1941 - Improved v8i16 shuffle lowering. It now uses pshuflw and pshufhw as much as
possible before resorting to pextrw and pinsrw.
- Better codegen for v4i32 shuffles masquerading as v8i16 or v16i8 shuffles.
- Improves (i16 extract_vector_element 0) codegen by recognizing
  (i32 extract_vector_element 0) does not require a pextrw.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@44836 91177308-0d34-0410-b5e6-96231b3b80d8
2007-12-11 01:46:18 +00:00

22 lines
1003 B
LLVM

; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep movlhps | count 1
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep movss | count 1
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep pshufd | count 1
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep pshuflw | count 1
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep pshufhw | count 1
define <8 x i16> @t1(<8 x i16> %A, <8 x i16> %B) {
%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 8, i32 9, i32 0, i32 1, i32 10, i32 11, i32 2, i32 3 >
ret <8 x i16> %tmp
}
define <8 x i16> @t2(<8 x i16> %A, <8 x i16> %B) {
%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7 >
ret <8 x i16> %tmp
}
define <8 x i16> @t3(<8 x i16> %A, <8 x i16> %B) {
%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 0, i32 0, i32 3, i32 2, i32 4, i32 6, i32 4, i32 7 >
ret <8 x i16> %tmp
}