aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Target/ARM
Commit message (Expand)AuthorAgeFilesLines
* Remove the isMoveInstr() hook.Jakob Stoklund Olesen2010-07-162-48/+0
* Use a small local function for a single remaining late isMoveInstr call inJakob Stoklund Olesen2010-07-161-24/+42
* Rename DBG_LABEL PROLOG_LABEL, because it's only used during prolog emission andBill Wendling2010-07-162-2/+2
* Split -enable-finite-only-fp-math to two options:Evan Cheng2010-07-152-4/+5
* Random note about bswap.Eli Friedman2010-07-151-0/+26
* Remove restriction on NEON alignment values. Some of the NEON ld/stBob Wilson2010-07-143-9/+4
* Don't pass StringRef by reference.Benjamin Kramer2010-07-141-7/+7
* Improve 64-subtraction of immediates when parts of the immediate can fitJim Grosbach2010-07-142-11/+40
* Add missing address register update to t2LDM_RET instruction.Bob Wilson2010-07-141-1/+1
* A couple potential optimizations inspired by comment 4 in PR6773.Eli Friedman2010-07-141-0/+41
* Add support for NEON VMVN immediate instructions.Bob Wilson2010-07-143-7/+48
* The bits in the cmode field of 32-bit VMOV immediate instructions all dependBob Wilson2010-07-141-2/+2
* Add an ARM-specific DAG combining to avoid redundant VDUPLANE nodes.Bob Wilson2010-07-141-0/+29
* Use a target-specific VMOVIMM DAG node instead of BUILD_VECTOR to representBob Wilson2010-07-133-192/+78
* Extend the r107852 optimization which turns some fp compare to code sequence ...Evan Cheng2010-07-133-71/+240
* Add an ARM "feature". Cortex-a8 fp comparison is very slow (> 20 cycles).Evan Cheng2010-07-132-1/+7
* Move NEON "modified immediate" encode/decode into ARMAddressingModes.h toBob Wilson2010-07-134-77/+84
* Remove some code that doesn't appear to do anything. All the ARM callBob Wilson2010-07-121-5/+0
* Convert some tab stops into spaces.Duncan Sands2010-07-123-8/+8
* RISC architectures get their memory operand folding for free.Jakob Stoklund Olesen2010-07-114-320/+0
* Make getPhysicalRegisterRegClass non-virtual. Should be able to remove it soon.Rafael Espindola2010-07-112-18/+0
* Replace copyRegToReg with copyPhysReg for ARM.Jakob Stoklund Olesen2010-07-116-146/+84
* Fix va_arg for doubles. With this patch VAARG nodes always contain theRafael Espindola2010-07-111-0/+4
* Add parentheses yet again to satisfy GCC's warnings.Chandler Carruth2010-07-101-3/+3
* Automatically fold COPY instructions into stack load/store.Jakob Stoklund Olesen2010-07-091-1/+1
* In the presence of variable sized objects, allocate an emergency spill slot.Jim Grosbach2010-07-091-3/+10
* Print "dregpair" NEON operands with a space between them, for readability andBob Wilson2010-07-091-1/+1
* Check for FiniteOnlyFPMath as well.Evan Cheng2010-07-081-1/+1
* The NEONPreAllocPass should never have to assign fixed registers anymore.Bob Wilson2010-07-081-34/+1
* For big-endian systems, VLD2/VST2 with 32-bit vector elements will swap theBob Wilson2010-07-081-2/+2
* Clean up a comment.Bob Wilson2010-07-081-5/+5
* Convert EXTRACT_SUBREG to COPY when emitting machine instrs.Jakob Stoklund Olesen2010-07-081-3/+3
* r107852 is only safe with -enable-unsafe-fp-math to account for +0.0 == -0.0.Evan Cheng2010-07-081-3/+5
* Optimize some vfp comparisons to integer ones. This patch implements the simp...Evan Cheng2010-07-082-10/+48
* Changes to ARM tail calls, mostly cosmetic.Dale Johannesen2010-07-083-8/+20
* grammarJim Grosbach2010-07-071-1/+1
* Handle cases where the post-RA scheduler may move instructions between theJim Grosbach2010-07-071-6/+21
* grammar and trailing whitespaceJim Grosbach2010-07-071-6/+6
* Split the SDValue out of OutputArg so that SelectionDAG-independentDan Gohman2010-07-072-4/+10
* Also use REG_SEQUENCE for VTBX instructions.Bob Wilson2010-07-072-24/+30
* Mark eh.sjlj.set/longjmp custom lowerings as Darwin-only since that's whereJim Grosbach2010-07-071-2/+4
* By default, the eh.sjlj.setjmp/longjmp intrinsics should just do nothing ratherJim Grosbach2010-07-061-0/+2
* Use REG_SEQUENCE nodes to make the table registers for VTBL instructions beBob Wilson2010-07-062-10/+61
* Track defs for all aliases in NEONMoveFix.Jakob Stoklund Olesen2010-07-061-2/+2
* Propagate debug loc.Devang Patel2010-07-061-2/+2
* Represent NEON load/store alignments in bytes, not bits.Bob Wilson2010-07-063-7/+13
* Reapply r107655 with fixes; insert the pseudo instruction intoDan Gohman2010-07-061-21/+31
* Don't create neon moves in CopyRegToReg. NEONMoveFixPass will do the conversionRafael Espindola2010-07-061-4/+6
* Revert r107655.Dan Gohman2010-07-061-31/+21
* Fix a bunch of custom-inserter functions to handle the case whereDan Gohman2010-07-061-21/+31
generated by cgit v1.1 at 2025-03-20 10:07:11 +0000