Chandler Carruth 9e2fe46484 [x86] Teach the new vector shuffle lowering to be even more aggressive ... in exposing the scalar value to the broadcast DAG fragment so that we can catch even reloads and fold them into the broadcast. This is somewhat magical I'm afraid but seems to work. It is also what the old lowering did, and I've switched an old test to run both lowerings demonstrating that we get the same result. Unlike the old code, I'm not lowering f32 or f64 scalars through this path when we only have AVX1. The target patterns include pretty heinous code to re-cast those as shuffles when the scalar happens to not be spilled because AVX1 provides no broadcast mechanism from registers what-so-ever. This is terribly brittle. I'd much rather go through our generic lowering code to get this. If needed, we can add a peephole to get even more opportunities to broadcast-from-spill-slots that are exposed post-RA, but my suspicion is this just doesn't matter that much. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218734 91177308-0d34-0410-b5e6-96231b3b80d8		2014-10-01 03:19:43 +00:00
..
AArch64	Recommit r218010 [FastISel][AArch64] Fold bit test and branch into TBZ and TBNZ.	2014-09-30 19:59:35 +00:00
ARM	Fix swift-atomics testcase	2014-09-23 23:18:01 +00:00
CPP
Generic	Fix crash with an insertvalue that produces an empty object.	2014-09-20 00:10:47 +00:00
Hexagon	Add missing attributes !cmp.[eq,gt,gtu] instructions.	2014-09-25 13:09:54 +00:00
Inputs
Mips	Add numeric extend, trunctate to mips fast-isel	2014-09-30 16:30:13 +00:00
MSP430	Drop the W postfix on the 16-bit registers.	2014-09-10 06:58:14 +00:00
NVPTX	[MachineSink] Use the real post dominator tree	2014-09-01 03:47:25 +00:00
PowerPC	Refactor reciprocal and reciprocal square root estimate into target-independent functions (part 2).	2014-09-26 23:01:47 +00:00
R600	R600/SI: Fix printing of clamp and omod	2014-09-30 19:49:48 +00:00
SPARC	Add back tests for empty function in SPARC and PowerPC.	2014-09-15 22:11:07 +00:00
SystemZ
Thumb	[Thumb] Make load/store optimizer less conservative.	2014-09-24 16:35:50 +00:00
Thumb2	ARM / x86_64 varargs: Don't save regparms in prologue without va_start	2014-08-22 21:59:26 +00:00
X86	[x86] Teach the new vector shuffle lowering to be even more aggressive	2014-10-01 03:19:43 +00:00
XCore