Improve long vector sext/zext lowering on ARM
[oota-llvm.git] / lib / Target / ARM / ARMISelLowering.cpp
2013-03-19 Renato GolinImprove long vector sext/zext lowering on ARM
2013-03-02 Jim GrosbachARM: Creating a vector from a lane of another.
2013-03-02 Jim GrosbachClean up code format a bit.
2013-03-02 Jim GrosbachTidy up. Trailing whitespace.
2013-03-02 Arnold SchwaighoferARM NEON: Fix v2f32 float intrinsics
2013-03-01 Chad RosierAdd support for using non-pic code for arm and thumb1...
2013-02-28 Chad RosierTidy up; no functional change.
2013-02-28 Chad RosierStyle; no functional change.
2013-02-27 Jim GrosbachARM: FMA is legal only if VFP4 is available.
2013-02-27 Chad RosierRemove this instance of dl as it's defined in a previou...
2013-02-20 Jim GrosbachUpdate TargetLowering ivars for name policy.
2013-02-13 David PeixottoTest commit. Fixed typo.
2013-02-12 Arnold SchwaighoferARM NEON: Handle v16i8 and v8i16 reverse shuffles
2013-02-05 Jakob Stoklund OlesenMove MRI liveouts to ARM return instructions.
2013-01-30 Eli BenderskyAdd a special ARM trap encoding for NaCl.
2013-01-29 Tim NorthoverFix 64-bit atomic operations in Thumb mode.
2013-01-29 Evan ChengTeach SDISel to combine fsin / fcos into a fsincos...
2013-01-25 Silviu BarangaFixed the condition codes for the atomic64 min/umin...
2013-01-07 Chandler CarruthSwitch TargetTransformInfo from an immutable analysis...
2013-01-02 Chandler CarruthMove all of the header files which are involved in...
2012-12-30 Bill WendlingRemove the Function::getFnAttributes method in favor...
2012-12-20 Bob WilsonRevert "Adding support for llvm.arm.neon.vaddl[su]...
2012-12-20 Renato GolinAdding support for llvm.arm.neon.vaddl[su].* and
2012-12-19 Jakob Stoklund OlesenRemove the explicit MachineInstrBuilder(MI) constructor.
2012-12-19 Patrik HagglundChange TargetLowering::findRepresentativeClass to take...
2012-12-19 Bill WendlingRename the 'Attributes' class to 'Attribute'. It's...
2012-12-13 Patrik HagglundChange TargetLowering::getRegClassFor to take an MVT...
2012-12-12 Evan ChengSorry about the churn. One more change to getOptimalMem...
2012-12-12 Evan Cheng- Rename isLegalMemOpType to isSafeMemOpType. "Legal...
2012-12-12 Evan ChengAvoid using lossy load / stores for memcpy / memset...
2012-12-11 Evan ChengReplace TargetLowering::isIntImmLegal() with
2012-12-11 Patrik HagglundRevert EVT->MVT changes, r169836-169851, due to buildbo...
2012-12-11 Patrik HagglundChange TargetLowering::findRepresentativeClass to take...
2012-12-11 Patrik HagglundChange TargetLowering::getRegClassFor to take an MVT...
2012-12-11 Evan ChengStylistic tweak.
2012-12-10 Evan ChengSome enhancements for memcpy / memset inline expansion.
2012-12-06 Evan ChengReplace r169459 with something safer. Rather than havin...
2012-12-06 Evan ChengLet targets provide hooks that compute known zero and...
2012-12-04 Matt Beaumont-GayAppease GCC's -Wparentheses.
2012-12-04 Evan ChengARM custom lower ctpop for vector types. Patch by Pete...
2012-12-03 Chandler CarruthUse the new script to sort the includes of every file...
2012-11-30 Sebastian PopCodegen failure for vmull with small vectors
2012-11-29 Silviu BarangaAdded atomic 64 min/max/umin/umax instrinsics support...
2012-11-28 Benjamin KramerARM: Implement CanLowerReturn so large vectors get...
2012-11-17 Eli FriedmanMark FP_EXTEND form v2f32 to v2f64 as "expand" for...
2012-11-16 Weiming ZhaoRemove hard coded registers in ARM ldrexd and strexd...
2012-11-16 Anton KorobeynikovMake sure FABS on v2f32 and v4f32 is legal on ARM NEON
2012-11-15 Eli FriedmanMark FP_ROUND for converting NEON v2f64 to v2f32 as...
2012-11-15 Craig TopperRevert changing FNEG of v4f32 to Expand. It's legal.
2012-11-15 Craig TopperMake FNEG and FABS of v4f32 Expand.
2012-11-15 Craig TopperAdd llvm.ceil, llvm.trunc, llvm.rint, llvm.nearbyint...
2012-11-10 Evan ChengDisable the Thumb no-return call optimization:
2012-11-09 Chad RosierRevert r167620; this can be implemented using an existi...
2012-11-09 Chad RosierAdd support for -mstrict-align compiler option for...
2012-11-06 Chad RosierMark the Int_eh_sjlj_dispatchsetup pseudo instruction...
2012-11-02 Quentin ColombetVext Lowering was missing opportunities
2012-10-30 Quentin ColombetChange ForceSizeOpt attribute into MinSize attribute
2012-10-27 Quentin Colombet[code size][ARM] Emit regular call instructions instead...
2012-10-19 Stepan DyatkovskiyARM:
2012-10-16 Stepan DyatkovskiyIssue:
2012-10-15 Silviu BarangaFixed PR13938: the ARM backend was crashing because...
2012-10-12 Manman RenARM: tail-call inside a function where part of a byval...
2012-10-12 Jim GrosbachARM: Mark VSELECT as 'expand'.
2012-10-10 Stepan DyatkovskiyFix for LDRB instruction:
2012-10-10 Stepan DyatkovskiyIssue description:
2012-10-09 Bill WendlingCreate enums for the different attributes.
2012-10-08 Micah VillmowMove TargetData to DataLayout.
2012-09-29 Bob WilsonAdd LLVM support for Swift.
2012-09-27 Sylvestre LedruRevert 'Fix a typo 'iff' => 'if''. iff is an abreviatio...
2012-09-27 Sylvestre LedruFix a typo 'iff' => 'if'
2012-09-26 Bill WendlingRemove the `hasFnAttr' method from Function.
2012-09-26 James MolloyFix ordering of operands on lowering of atomicrmw min...
2012-09-18 Evan ChengUse vld1 / vst2 for unaligned v2f64 load / store. e...
2012-09-13 Silviu BarangaThis patch introduces A15 as a target in LLVM.
2012-09-08 Craig TopperSet operation action for FFLOOR to Expand for all vecto...
2012-09-07 Jakob Stoklund OlesenCustom DAGCombine for and/or/xor are for all ARMs.
2012-09-06 James MolloyFix self-host; ensure signedness is consistent.
2012-09-06 James MolloyImprove codegen for BUILD_VECTORs on ARM.
2012-09-04 Arnold SchwaighoferPatch to implement UMLAL/SMLAL instructions for the...
2012-08-31 Jakob Stoklund OlesenFix a couple of typos in EmitAtomic.
2012-08-20 Jakob Stoklund OlesenUse a SmallPtrSet to dedup successors in EmitSjLjDispat...
2012-08-18 Jakob Stoklund OlesenRemove the CAND/COR/CXOR custom ISD nodes and their...
2012-08-18 Jakob Stoklund OlesenAlso combine zext/sext into selects for ARM.
2012-08-18 Jakob Stoklund OlesenAlso pass logical ops to combineSelectAndUse.
2012-08-17 Jakob Stoklund OlesenAdd comment, clean up code. No functional change.
2012-08-16 Jakob Stoklund OlesenHandle ARM MOVCC optimization in PeepholeOptimizer.
2012-08-15 Jakob Stoklund OlesenFold predicable instructions into MOVCC / t2MOVCC.
2012-08-15 Evan ChengUse vld1/vst1 to load/store f64 if alignment is < 4...
2012-08-13 Nadav RotemDo not optimize (or (and X,Y), Z) into BFI and other...
2012-08-12 Arnold SchwaighoferRevert 161581: Patch to implement UMLAL/SMLAL instructi...
2012-08-12 Craig TopperChange addTypeForNeon to use MVT instead of EVT so...
2012-08-09 Arnold SchwaighoferPatch to implement UMLAL/SMLAL instructions for the...
2012-08-03 Bob WilsonFall back to selection DAG isel for calls to builtin...
2012-08-03 Eric ChristopherAdd support for the ARM GHC calling convention, this...
2012-07-25 Jim GrosbachARM: Don't assume an SDNode is a constant.
2012-07-18 Andrew TrickFix ARMTargetLowering::isLegalAddImmediate to consider...
2012-07-18 Andrew Trickwhitespace
2012-06-18 Manman RenARM: use NOEN loads and stores if possible when handlin...
2012-06-15 Manman RenARM: optimization for sub+abs.
2012-06-11 Bill WendlingRe-enable the CMN instruction.
next