llvm - http://llvm.org

Age	Commit message (Collapse)	Author
2013-03-25	Revise alignment checking/calculation on 256-bit unaligned memory access	Michael Liao
	- It's still considered aligned when the specified alignment is larger than the natural alignment; - The new alignment for the high 128-bit vector should be min(16, alignment) as the pointer is advanced by 16, a power-of-2 offset. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177947 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-25	Enhance folding of (extract_subvec (insert_subvec V1, V2, IIdx), EIdx)	Michael Liao
	- Handle the case where the result of 'insert_subvect' is bitcasted before 'extract_subvec'. This removes the redundant insertf128/extractf128 pair on unaligned 256-bit vector load/store on vectors of non 64-bit integer. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177945 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-14	Unaligned loads should use the VMOVUPS opcode.	Nadav Rotem
	git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177130 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-19	On Sandybridge split unaligned 256bit stores into two xmm-sized stores.	Nadav Rotem
	git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172894 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-11	Fix a bug in the lowering of BUILD_VECTOR for AVX. SCALAR_TO_VECTOR does not ↵	Nadav Rotem
	zero untouched elements. Use INSERT_VECTOR_ELT instead. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147948 91177308-0d34-0410-b5e6-96231b3b80d8
2011-09-27	Remove X86-dependent stuff from SSEDomainFix.	Jakob Stoklund Olesen
	This also enables domain swizzling for AVX code which required a few trivial test changes. The pass will be moved to lib/CodeGen shortly. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@140659 91177308-0d34-0410-b5e6-96231b3b80d8
2011-09-08	Fix PR10844: Add patterns to cover non foldable versions of X86vzmovl.	Bruno Cardoso Lopes
	Triggered using llc -O0. Also fix some SET0PS patterns to their AVX forms and test it on the testcase. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@139304 91177308-0d34-0410-b5e6-96231b3b80d8
2011-08-11	Fix the test added by Nadav in r137308. Make it more strict:	Bruno Cardoso Lopes
	1) check for the "v" version of movaps 2) add a couple of CHECK-NOT to guarantee the behavior 3) move to a more appropriate test file git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137361 91177308-0d34-0410-b5e6-96231b3b80d8
2011-08-09	Add v16i16 and v32i8 store patterns	Bruno Cardoso Lopes
	git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137166 91177308-0d34-0410-b5e6-96231b3b80d8
2011-08-09	Add two patterns to match special vmovss and vmovsd cases. Also fix	Bruno Cardoso Lopes
	the patterns already there to be more strict regarding the predicate. This fixes PR10558 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137100 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-14	Add 256-bit load/store recognition and matching in several places.	Bruno Cardoso Lopes
	git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@135171 91177308-0d34-0410-b5e6-96231b3b80d8