Bruno Cardoso Lopes 3b86598cfa Instead of always leaving the work to the generic legalizer when ... there is no support for native 256-bit shuffles, be more smart in some cases, for example, when you can extract specific 128-bit parts and use regular 128-bit shuffles for them. Example: For this shuffle: shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 1, i32 0, i32 7, i32 6> This was expanded to: vextractf128 $1, %ymm1, %xmm2 vpextrq $0, %xmm2, %rax vmovd %rax, %xmm1 vpextrq $1, %xmm2, %rax vmovd %rax, %xmm2 vpunpcklqdq %xmm1, %xmm2, %xmm1 vpextrq $0, %xmm0, %rax vmovd %rax, %xmm2 vpextrq $1, %xmm0, %rax vmovd %rax, %xmm0 vpunpcklqdq %xmm2, %xmm0, %xmm0 vinsertf128 $1, %xmm1, %ymm0, %ymm0 ret Now we get: vshufpd $1, %xmm0, %xmm0, %xmm0 vextractf128 $1, %ymm1, %xmm1 vshufpd $1, %xmm1, %xmm1, %xmm1 vinsertf128 $1, %xmm1, %ymm0, %ymm0 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137733 91177308-0d34-0410-b5e6-96231b3b80d8		2011-08-16 18:21:54 +00:00
..
Analysis
Archive
Assembler	Move "atomic" and "volatile" designations on instructions after the opcode	2011-08-12 22:50:01 +00:00
Bindings/Ocaml
Bitcode
BugPoint
CodeGen	Instead of always leaving the work to the generic legalizer when	2011-08-16 18:21:54 +00:00
DebugInfo
ExecutionEngine
Feature
FrontendC++	Fix test.	2011-08-13 17:06:34 +00:00
FrontendObjC
FrontendObjC++
Integer
lib
Linker
LLVMC
MC	ARM .align NOP padding uses different encoding pre-ARMv6.	2011-08-16 17:06:20 +00:00
Object
Other
Scripts
TableGen
Transforms	Fix test.	2011-08-16 01:42:56 +00:00
Unit
Verifier
CMakeLists.txt
lit.cfg
lit.site.cfg.in
Makefile
Makefile.tests
site.exp.in
TestRunner.sh