summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/ARM/ARMISelLowering.cpp
Commit message (Expand)AuthorAgeFilesLines
* Fix some typos and use type-based isel for VZIP/VUZP/VTRNAnton Korobeynikov2009-08-211-17/+8
* Add lowering of ARM 4-element shuffles to multiple instructios via perfectshu...Anton Korobeynikov2009-08-211-8/+123
* Add nodes & dummy matchers for some v{zip,uzp,trn} instructionsAnton Korobeynikov2009-08-211-0/+9
* Expand EXTRACT_SUBVECTORAnton Korobeynikov2009-08-211-0/+1
* Provide vext.{16,32}Anton Korobeynikov2009-08-211-3/+0
* Use masks not nodes for vector shuffle predicates. Provide set of 'legal' mas...Anton Korobeynikov2009-08-211-15/+33
* Add support for Neon VEXT (vector extract) shuffles.Bob Wilson2009-08-191-1/+49
* Reapply r79127. It was fixed by d0k.Bill Wendling2009-08-151-0/+21
* Revert r79127. It was causing compilation errors.Bill Wendling2009-08-151-21/+0
* Change allowsUnalignedMemoryAccesses to take type argument since some targetsEvan Cheng2009-08-151-0/+21
* Turn on if-conversion for thumb2.Evan Cheng2009-08-151-20/+13
* Allow targets to specify their choice of calling conventions perAnton Korobeynikov2009-08-141-0/+9
* Add Thumb2 lsr hooks.Evan Cheng2009-08-141-36/+105
* 80 col violation.Evan Cheng2009-08-141-1/+2
* Now that all the legal Neon shuffles (or at least the ones that have beenBob Wilson2009-08-141-1/+1
* Create a new ARM-specific DAG node, VDUP, to represent a splat from aBob Wilson2009-08-141-3/+7
* During legalization, change Neon vdup_lane operations from shuffles toBob Wilson2009-08-141-1/+7
* Push LLVMContexts through the IntegerType APIs.Owen Anderson2009-08-131-5/+8
* Add a fixme message about canonicalizing floating-point vector types.Bob Wilson2009-08-131-0/+2
* Revert r78852 for now. I want to do this differently, but I don't have timeBob Wilson2009-08-131-3/+0
* Add a comment to describe why vector shuffles are legalized to custom DAG nodes.Bob Wilson2009-08-131-0/+4
* Use cast<> instead of dyn_cast<> in places where the type is known.Bob Wilson2009-08-131-5/+3
* Recognize Neon VDUP shuffles during legalization instead of selection.Bob Wilson2009-08-121-0/+3
* Recognize Neon VREV shuffles during legalization instead of selection.Bob Wilson2009-08-121-1/+16
* Add catch block handling to SjLj exception handling.Jim Grosbach2009-08-121-0/+4
* Shrink Thumb2 movcc instructions.Evan Cheng2009-08-121-1/+1
* Split EVT into MVT and EVT, the former representing _just_ a primitive type, ...Owen Anderson2009-08-111-305/+305
* Whitespace cleanup. Remove trailing whitespace.Jim Grosbach2009-08-111-5/+5
* Use vAny type to get rid of Neon intrinsics that differed only in whetherBob Wilson2009-08-111-12/+6
* SjLj based exception handling unwinding support. This patch is nasty, brutishJim Grosbach2009-08-111-0/+31
* Rename MVT to EVT, in preparation for splitting SimpleValueType out into its ...Owen Anderson2009-08-101-361/+361
* SimpleValueType-ify a few more methods on TargetLowering.Owen Anderson2009-08-101-5/+10
* Continue the SimpleValueType-ification.Owen Anderson2009-08-101-14/+14
* It turns out most of the thumb2 instructions are not allowed to touch SP. The...Evan Cheng2009-08-071-2/+128
* Implement Neon VST[234] operations.Bob Wilson2009-08-061-0/+25
* Remove redundand checks: the only way to have, e.g. f32 RegVT is exactlyAnton Korobeynikov2009-08-051-11/+7
* Unbreak the stuff, this is ugly, but we cannot do better for now with 'plain'...Anton Korobeynikov2009-08-051-5/+4
* Missed pieces for ARM HardFP ABI.Anton Korobeynikov2009-08-051-23/+33
* Major calling convention code refactoring.Dan Gohman2009-08-051-99/+80
* Change DAG nodes for Neon VLD2/3/4 operations to return multiple results.Bob Wilson2009-08-051-23/+6
* Lower Neon VLD* intrinsics to custom DAG nodes, and manually allocate theBob Wilson2009-08-041-0/+59
* Minor cleanup. No functional changes intended.Bob Wilson2009-08-041-6/+5
* Lower CONCAT_VECTOR during legalization instead of matching it during isel.Bob Wilson2009-08-031-5/+19
* convert ctors/dtors section to be in TLOF instead ofChris Lattner2009-08-021-2/+2
* Fix Thumb2 function call isel. Thumb1 and Thumb2 should share the sameEvan Cheng2009-08-011-3/+3
* refactor section construction in TLOF to be through an explicitChris Lattner2009-07-311-1/+1
* Lower a 128-bit BUILD_VECTOR with 2 elements to a pair of INSERT_VECTOR_ELTs.Bob Wilson2009-07-301-1/+19
* Optimize Thumb2 jumptable to use tbb / tbh when all the offsets fit in byte /...Evan Cheng2009-07-291-1/+3
* In thumb2 mode, add pc is unpredictable. Use add + mov pc instead (that is un...Evan Cheng2009-07-281-6/+3
* the apple "ld_classic" linker doesn't support .literal16 in 32-bitChris Lattner2009-07-281-1/+1
OpenPOWER on IntegriCloud