Justin Holewinski a1535e3b9b [NVPTX] Honor alignment on vector loads/stores ... We were not considering the stated alignment on vector loads/stores, leading us to generate vector instructions even when we do not have sufficient alignment. Now, for IR like: %1 = load <4 x float>, <4 x float>* %ptr, align 4 we will generate correct, conservative PTX like: ld.f32 ... [%ptr] ld.f32 ... [%ptr+4] ld.f32 ... [%ptr+8] ld.f32 ... [%ptr+12] Or if we have an alignment of 8 (for example), we can generate code like: ld.v2.f32 ... [%ptr] ld.v2.f32 ... [%ptr+8] git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213186 91177308-0d34-0410-b5e6-96231b3b80d8		2014-07-16 19:45:35 +00:00
..
Analysis	Teach computeKnownBits to look through addrspacecast.	2014-07-15 01:55:03 +00:00
AsmParser
Bitcode	Roundtrip the inalloca bit on allocas through bitcode	2014-07-16 01:34:27 +00:00
CodeGen	CodeGen: don't form illegail EXTLOAD operations.	2014-07-16 15:37:24 +00:00
DebugInfo
ExecutionEngine	[RuntimeDyld] Revert r211652 - MachO object GDB registration support.	2014-07-15 19:35:22 +00:00
IR	Remove unnecessary/redundant std::move	2014-07-16 17:09:21 +00:00
IRReader
LineEditor
Linker
LTO	Prune Redundant libdeps in CMake's target_link_libraries and LLVMBuild.txt.	2014-07-15 11:37:03 +00:00
MC	CodeGen: Stick constant pool entries in COMDAT sections for WinCOFF	2014-07-14 22:57:27 +00:00
Object	[RuntimeDyld] Revert r211652 - MachO object GDB registration support.	2014-07-15 19:35:22 +00:00
Option
ProfileData
Support	Perform wildcard expansion in Process::GetArgumentVector on Windows (PR17098)	2014-07-16 00:52:11 +00:00
TableGen
Target	[NVPTX] Honor alignment on vector loads/stores	2014-07-16 19:45:35 +00:00
Transforms	Fix comment in InstCombiner::visitAddrSpaceCast.	2014-07-16 01:34:21 +00:00
CMakeLists.txt
LLVMBuild.txt
Makefile