aboutsummaryrefslogtreecommitdiff
path: root/lib/Target/ARM
AgeCommit message (Collapse)Author
2011-12-14ARM NEON improve factoring a bit. No functional change.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146585 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14Model ARM predicated write as read-mod-write. e.g.Evan Cheng
r0 = mov #0 r0 = moveq #1 Then the second instruction has an implicit data dependency on the first instruction. Sadly I have yet to come up with a small test case that demonstrate the post-ra scheduler taking advantage of this. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146583 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14ARM NEON VST2 assembly parsing and encoding.Jim Grosbach
Work in progress. Parsing for non-writeback, single spaced register lists works now. The rest have the representations better factored, but still need more to be able to parse properly. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146579 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14Fix speling and 80-col.Jakob Stoklund Olesen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146575 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14Fix copy/pasto that skipped the 'modify' step.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146571 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14ARM/Thumb2 mov vs. mvn alias goes both ways.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146570 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14VFP2 is required for FP loads. Noticed by inspection.Chad Rosier
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146569 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14Tidy up.Chad Rosier
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146568 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14ARM/Thumb2 'cmp rn, #imm' alias to cmn.Jim Grosbach
When 'cmp rn #imm' doesn't match due to the immediate not being representable, but 'cmn rn, #-imm' does match, use the latter in place of the former, as it's equivalent. rdar://10552389 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146567 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14Fix 80-column violation and extraneous brackets.Chad Rosier
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146566 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14ARM assembler support for the target-specific .req directive.Jim Grosbach
rdar://10549683 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146543 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14- Add MachineInstrBundle.h and MachineInstrBundle.cpp. This includes a functionEvan Cheng
to finalize MI bundles (i.e. add BUNDLE instruction and computing register def and use lists of the BUNDLE instruction) and a pass to unpack bundles. - Teach more of MachineBasic and MachineInstr methods to be bundle aware. - Switch Thumb2 IT block to MI bundles and delete the hazard recognizer hack to prevent IT blocks from being broken apart. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146542 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13Thumb2 assembler aliases for "mov(shifted register)"Jim Grosbach
rdar://10549767 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146520 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13ARM LDM/STM system instruction variants.Jim Grosbach
rdar://10550269 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146519 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13Thumb2 pre/post indexed stores can be from any non-PC GPR.Jim Grosbach
rdar://10549786 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146518 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13Thumb2 tweak for ccout handling in RSB parsing.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146516 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13ARM thumb2 parsing of "rsb rd, rn, #0".Jim Grosbach
rdar://10549741 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146515 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13ARM NEON two-operand aliases for VQDMULH.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146514 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13ARM pre-UAL NEG mnemonic for convenience when porting old code.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146511 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13ARM add some more pre-UAL VFP mnemonics for convenience when porting old code.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146508 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13ARM add more 'gas' compatibility aliases for NEON instructions.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146507 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13[fast-isel] Unaligned loads of floats are not supported. Therefore, convert ↵Chad Rosier
to a regular load and then move the result from a GPR to a FPR. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146502 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13Initial CodeGen support for CTTZ/CTLZ where a zero input produces anChandler Carruth
undefined result. This adds new ISD nodes for the new semantics, selecting them when the LLVM intrinsic indicates that the undef behavior is desired. The new nodes expand trivially to the old nodes, so targets don't actually need to do anything to support these new nodes besides indicating that they should be expanded. I've done this for all the operand types that I could figure out for all the targets. Owners of various targets, please review and let me know if any of these are incorrect. Note that the expand behavior is *conservatively correct*, and exactly matches LLVM's current behavior with these operations. Ideally this patch will not change behavior in any way. For example the regtest suite finds the exact same instruction sequences coming out of the code generator. That's why there are no new tests here -- all of this is being exercised by the existing test suite. Thanks to Duncan Sands for reviewing the various bits of this patch and helping me get the wrinkles ironed out with expanding for each target. Also thanks to Chris for clarifying through all the discussions that this is indeed the approach he was looking for. That said, there are likely still rough spots. Further review much appreciated. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146466 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-13Account for CPE alignment when searching for new water.Jakob Stoklund Olesen
Constant pool entries with different alignment may cause more alignment padding to be inserted. Compute the amount of padding needed, and try to pick the location that requires the least amount of padding. Also take the extra padding into account when the water is above the use. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146458 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-12LLVMBuild: Introduce a common section which currently has a list of theDaniel Dunbar
subdirectories to traverse into. - Originally I wanted to avoid this and just autoscan, but this has one key flaw in that new subdirectories can not automatically trigger a rerun of the llvm-build tool. This is particularly a pain when switching back and forth between trees where one has added a subdirectory, as the dependencies will tend to be wrong. This will also eliminates FIXME implicitly. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146436 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-12Implement 'e' and 'f' modifiers for Neon inline asm. <rdar://problem/10551006>Bob Wilson
These modifiers simply select either the low or high D subregister of a Neon Q register. I've also removed the unimplemented 'p' modifier, which turns out to be a bit different than the comment here suggests and as far as I can tell was only intended for internal use in Apple's version of gcc. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146417 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-12LLVMBuild: Remove trailing newline, which irked me.Daniel Dunbar
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146409 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-12Add a postOffset() alignment argument.Jakob Stoklund Olesen
This computes the offset of the layout sucessor block, considering its alignment as well. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146401 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-12Fix typo.Jakob Stoklund Olesen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146400 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-12Also set the proper alignment on inner islands and the function itself.Jakob Stoklund Olesen
Downgrade the alignment of the initial constant island when constant pool entries are moved elsewhere. This is all gated by -arm-align-constant-islands. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146391 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-12Make MF a class member instead of passing it around everywhere.Jakob Stoklund Olesen
Also add an MCP member pointing to the machine constant pool. No functional change intended. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146382 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-12Add a -arm-align-constant-islands flag, default off.Jakob Stoklund Olesen
Order constant pool entries by descending alignment in the initial island to ensure packing and correct alignment. When the command line flag is set, also align the basic block containing the constant pool entries. This is only a partial implementation of constant island alignment. More to come. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146375 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-11Fixed bug 9905: Failure in code selection for llvm intrinsics sqrt/exp (fix ↵Stepan Dyatkovskiy
for FSQRT, FSIN, FCOS, FPOWI, FPOW, FLOG, FLOG2, FLOG10, FEXP, FEXP2). Third attempt: simplified checks in test for armv7-apple-darwin11. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146341 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-10Revert r146322 to appease buildbots. Original commit message:Chad Rosier
Fixed bug 9905: Failure in code selection for llvm intrinsics sqrt/exp (fix for FSQRT, FSIN, FCOS, FPOWI, FPOW, FLOG, FLOG2, FLOG10, FEXP, FEXP2). Second attempt. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146328 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-10Fixed bug 9905: Failure in code selection for llvm intrinsics sqrt/exp (fix ↵Stepan Dyatkovskiy
for FSQRT, FSIN, FCOS, FPOWI, FPOW, FLOG, FLOG2, FLOG10, FEXP, FEXP2). Second attempt. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146322 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-10Try to align the point where a large basic block is split.Jakob Stoklund Olesen
The split point is picked such that the newly created water has the same alignment as the function. This makes the island suitable for constant pool entries with potentially higher alignment. This also fixes an issue where the basic block was split one instruction too late, causing nonconvergence of the algorithm. <rdar://problem/10550705> There is still an issue with correctly packing differently aligned entries in the island. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146314 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-10More debug output formatting.Jakob Stoklund Olesen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146313 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-10ARM add some more pre-UAL VFP mnemonics for convenience when porting old code.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146300 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-09Splats can contain undef's; make sure to handle them correctly. PR11526.Eli Friedman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146299 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-09ARM add some pre-UAL VFP mnemonics for convenience when porting old code.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146296 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-09ARM allows '' syntax, not just '#imm' for assembly.Jim Grosbach
Backwards compatibility with 'gas'. #imm is the preferered and documented syntax, but lots of existing code uses the '$' prefix, so we should support it if we can. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146285 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-09ARM assembly aliases for BIC<-->AND (immediate).Jim Grosbach
When the immediate operand of an AND or BIC instruction isn't representable in the immediate field of the instruction, but the bitwise negation of the immediate is, assemble the instruction as the inverse operation instead with the inverted immediate as the operand. rdar://10550057 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146283 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-09ARM NEON data type aliases for VBIC(register).Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146281 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-09ARM assembly parsing and encoding for VLD2 with writeback.Jim Grosbach
Refactor the instructions into fixed writeback and register-stride writeback variants to simplify the offset operand (no more optional register operand using reg0). This is a simpler representation and allows the assembly parser to more easily handle these instructions. Add tests for the instruction variants now supported. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146278 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-09User a helper overload for a common pattern.Jakob Stoklund Olesen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146270 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-09Tidy up. Better base class factoring.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146267 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-09Tidy up. Better base class factoring.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146266 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-09Tweak debugging output.Jakob Stoklund Olesen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146264 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-08ARM convenience aliases for VSQRT.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146201 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-08ARM 64-bit VEXT assembly uses a .64 suffix, not .32, amazingly enough.Jim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146194 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-09-21 11:07:44 +0000