ampere-computing/llvm.git - LLVM including Ampere Computing toolchain specific patches

Age	Commit message (Expand)	Author
2017-08-02	X86: Do not use llc -march in tests.	Matthias Braun
2016-02-15	Implemented stack symbol table ordering/packing optimization to improve data ...	Zia Ansari
2015-04-17	[X86, AVX] add an exedepfix entry for vmovq == vmovlps == vmovlpd	Sanjay Patel
2015-02-27	[opaque pointer type] Add textual IR support for explicit type parameter to l...	David Blaikie
2015-02-27	[opaque pointer type] Add textual IR support for explicit type parameter to g...	David Blaikie
2015-02-16	[X86][SSE] Add SSE MOVQ instructions to SSEPackedInt domain	Simon Pilgrim
2013-06-09	Removed PackedDouble domain from scalar instructions. Added more formats for ...	Elena Demikhovsky
2012-08-30	Introduce 'UseSSEx' to force SSE legacy encoding	Michael Liao
2011-11-28	Revert r145273 and fix in SelectionDAG::InferPtrAlignment() instead.	Evan Cheng
2011-11-28	DAG combine should not increase alignment of loads / stores with alignment less	Evan Cheng
2010-12-19	now that generic vector types aren't selected onto MMX registers, these	Chris Lattner
2010-01-24	Improved widening loads by adding support for wider loads if	Mon P Wang
2009-12-18	Instruction fixes, added instructions, and AsmString changes in the	Sean Callanan
2009-09-09	When widening a vector load, use the correct chain. This fixes PR4891.	Dan Gohman