Andrea Di Biagio cae1ea691d [X86] Always prefer to lower a VECTOR_SHUFFLE into a BLENDI instead of SHUFP (or VPERM2X128). ... This patch teaches method 'LowerVECTOR_SHUFFLE' to give higher precedence to the check for 'isBlendMask'; the idea is that, when possible, we should firstly check if a shuffle performs a blend, and in case, try to lower it into a BLENDI instead of selecting a SHUFP or (worse) a VPERM2X128. In general: - AVX VBLENDPS/D always have better latency and throughput than VPERM2F128; - BLENDPS/D instructions tend to always have better 'reciprocal throughput' than the equivalent SHUFPS/D; - Both BLENDPS/D and SHUFPS/D are often decoded into the same number of m-ops; however, a m-op obtained from a BLENDPS/D can be scheduled to more than one execution port. This patch: - Moves the check for 'isBlendMask' immediately before the check for 'isSHUFPMask' within method 'LowerVECTOR_SHUFFLE'; - Updates existing tests for sse/avx shuffle/blend instructions to verify that we select (v)blendps/d when possible (instead of (v)shufps/d or vperm2f128). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211720 91177308-0d34-0410-b5e6-96231b3b80d8		2014-06-25 17:41:58 +00:00
..
AArch64	Resubmit commit r211533	2014-06-24 16:21:38 +00:00
ARM	Fix up scoping in a few tests (and delete one that validates unnecessary behavior).	2014-06-24 20:10:27 +00:00
CPP
Generic
Hexagon
Inputs
Mips	Print a=b as an assignment.	2014-06-24 22:45:16 +00:00
MSP430
NVPTX
PowerPC	Rename loop unrolling and loop vectorizer metadata to have a common prefix.	2014-06-25 15:41:00 +00:00
R600	R600: Promote i64 stores to v2i32	2014-06-24 23:33:04 +00:00
SPARC
SystemZ
Thumb
Thumb2	ARM: Fix TPsoft for Thumb mode	2014-06-24 15:45:59 +00:00
X86	[X86] Always prefer to lower a VECTOR_SHUFFLE into a BLENDI instead of SHUFP (or VPERM2X128).	2014-06-25 17:41:58 +00:00
XCore