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
..
Analysis	[BasicAA] Make better use of zext and sign information	2014-09-30 22:43:40 +00:00
AsmParser
Bitcode
CodeGen	Implement DW_TAG_subrange_type with DW_AT_count rather than DW_AT_upper_bound	2014-10-01 00:56:55 +00:00
DebugInfo	Store TypeUnits in a SmallVector<DWARFUnitSection> instead of a single DWARFUnitSection.	2014-09-29 13:56:39 +00:00
ExecutionEngine	Unit test r218187, changing RTDyldMemoryManager::getSymbolAddress's behavior favor mangled lookup over unmangled lookup.	2014-09-29 21:25:13 +00:00
IR	[AVX512] Added intrinsics for VPCMPEQB and VPCMPEQW.	2014-09-30 11:32:22 +00:00
IRReader
LineEditor
Linker
LTO
MC	Extend C disassembler API to allow specifying target features	2014-09-30 16:31:40 +00:00
Object	Object: BSS/virtual sections don't have contents	2014-09-26 22:32:16 +00:00
Option
ProfileData	llvm-cov: Use the number of executed functions for the function coverage metric.	2014-09-30 12:45:13 +00:00
Support	Fix llvm::huge_valf multiple initializations with Visual C++.	2014-09-27 14:41:29 +00:00
TableGen
Target	[x86] Teach the new vector shuffle lowering to be even more aggressive	2014-10-01 03:19:43 +00:00
Transforms	[InstCombine] Optimize icmp-select-icmp	2014-10-01 00:13:22 +00:00
CMakeLists.txt
LLVMBuild.txt
Makefile