2013-08-27 |
Joey Gouly | [ARMv8] Add some negative tests for the recent VFP... |
blob | commitdiff | raw |
2013-08-27 |
Tim Northover | ARM: add natural patterns for vaddhl and vsubhl. |
blob | commitdiff | raw | diff to current |
2013-08-22 |
Mihai Popa | Fix ARM vcvt encoding when the number of fractional... |
blob | commitdiff | raw | diff to current |
2013-07-22 |
Tim Northover | ARM: remove now unneeded custom Asm converters |
blob | commitdiff | raw | diff to current |
2013-07-19 |
Joey Gouly | [ARMv8] Implement the NEON instructions VRINT{N, X... |
blob | commitdiff | raw | diff to current |
2013-07-18 |
Joey Gouly | Change 'n' to 'N' to keep consistent with other instruc... |
blob | commitdiff | raw | diff to current |
2013-07-18 |
Joey Gouly | [ARMv8] Add NEON instructions VCVT{A, N, P, M}. |
blob | commitdiff | raw | diff to current |
2013-07-18 |
Joey Gouly | Remove the extra leading 0 from VMAXNMND. |
blob | commitdiff | raw | diff to current |
2013-07-17 |
Joey Gouly | [ARMv8] Add support for the NEON instructions vmaxnm... |
blob | commitdiff | raw | diff to current |
2013-06-18 |
Jim Grosbach | ARM: Add optional datatype suffix to NEON mvn asm syntax. |
blob | commitdiff | raw | diff to current |
2013-06-11 |
Amaury de la Vieuville | ARM: Enforce decoding rules for VLDn instructions |
blob | commitdiff | raw | diff to current |
2013-05-31 |
Tim Northover | ARM: fix VEXT encoding corner case |
blob | commitdiff | raw | diff to current |
2013-05-20 |
Mihai Popa | VSTn instructions have a number of encoding constraints... |
blob | commitdiff | raw | diff to current |
2013-04-26 |
Benjamin Kramer | ARM/NEON: Pattern match vector integer abs to vabs. |
blob | commitdiff | raw | diff to current |
2013-04-15 |
Jim Grosbach | ARM: Add VACLT and VACLE assembly aliases. |
blob | commitdiff | raw | diff to current |
2013-02-19 |
Arnold Schwaighofer | ARM NEON: Don't need COPY_TO_REGCLASS in pattern |
blob | commitdiff | raw | diff to current |
2013-02-19 |
Arnold Schwaighofer | ARM NEON: Merge a f32 bitcast of a v2i32 extractelt |
blob | commitdiff | raw | diff to current |
2013-02-14 |
Joel Jones | The ARM NEON vector compare instructions take three... |
blob | commitdiff | raw | diff to current |
2012-12-20 |
Bob Wilson | Revert "Adding support for llvm.arm.neon.vaddl[su]... |
blob | commitdiff | raw | diff to current |
2012-12-20 |
Renato Golin | Adding support for llvm.arm.neon.vaddl[su].* and |
blob | commitdiff | raw | diff to current |
2012-11-16 |
Anton Korobeynikov | Make sure FABS on v2f32 and v4f32 is legal on ARM NEON |
blob | commitdiff | raw | diff to current |
2012-10-26 |
Jakob Stoklund Olesen | Revert r163298 "Optimize codegen for VSETLNi{8,16,32... |
blob | commitdiff | raw | diff to current |
2012-10-15 |
Jim Grosbach | ARM: v1i64 and v2i64 VBSL intrinsic support. |
blob | commitdiff | raw | diff to current |
2012-10-10 |
Evan Cheng | Add isel patterns for v2f32 / v4f32 neon.vbsl intrinsic... |
blob | commitdiff | raw | diff to current |
2012-09-29 |
Bob Wilson | Add LLVM support for Swift. |
blob | commitdiff | raw | diff to current |
2012-09-21 |
Jim Grosbach | ARM: Use a dedicated intrinsic for vector bitwise select. |
blob | commitdiff | raw | diff to current |
2012-09-18 |
Evan Cheng | Use vld1 / vst2 for unaligned v2f64 load / store. e... |
blob | commitdiff | raw | diff to current |
2012-09-06 |
Tim Northover | Use correct part of complex operand to encode VST1... |
blob | commitdiff | raw | diff to current |
2012-09-06 |
James Molloy | Optimize codegen for VSETLNi{8,16,32} operating on... |
blob | commitdiff | raw | diff to current |
2012-08-15 |
Evan Cheng | Use vld1/vst1 to load/store f64 if alignment is < 4... |
blob | commitdiff | raw | diff to current |
2012-08-13 |
Tim Northover | Use correct loads for vector types during extending... |
blob | commitdiff | raw | diff to current |
2012-07-18 |
Joel Jones | More replacing of target-dependent intrinsics with... |
blob | commitdiff | raw | diff to current |
2012-07-13 |
Joel Jones | This is one of the first steps at moving to replace... |
blob | commitdiff | raw | diff to current |
2012-07-10 |
Jim Grosbach | ARM: Allow more flexible patterns in NEON formats. |
blob | commitdiff | raw | diff to current |
2012-05-02 |
Jim Grosbach | ARM: Add missing two-operand VBIC aliases. |
blob | commitdiff | raw | diff to current |
2012-04-27 |
Lang Hames | Fix the order of the operands in the llvm.fma intrinsic... |
blob | commitdiff | raw | diff to current |
2012-04-26 |
Tim Northover | Use VLD1 in NEON extenting-load patterns instead of... |
blob | commitdiff | raw | diff to current |
2012-04-23 |
Jim Grosbach | Tidy up. 80 columns, whitespace, et. al. |
blob | commitdiff | raw | diff to current |
2012-04-23 |
Jim Grosbach | ARM: VSLI two-operand assmebly aliases are tblgen'erated. |
blob | commitdiff | raw | diff to current |
2012-04-23 |
Jim Grosbach | ARM: tblgen'erate VSRA/VRSRA/VSRI assembly two-operand... |
blob | commitdiff | raw | diff to current |
2012-04-23 |
Jim Grosbach | ARM: vqdmulh two-operand aliases are tblgen'erated... |
blob | commitdiff | raw | diff to current |
2012-04-20 |
Jim Grosbach | ARM: tblgen'erate more NEON two-operand aliases. |
blob | commitdiff | raw | diff to current |
2012-04-20 |
Jim Grosbach | ARM: tblgen'erate more NEON two-operand aliases. |
blob | commitdiff | raw | diff to current |
2012-04-20 |
Jim Grosbach | ARM: Update NEON assembly two-operand aliases. |
blob | commitdiff | raw | diff to current |
2012-04-17 |
James Molloy | Fix bad EXTRACT_SUBREG in instruction selection for... |
blob | commitdiff | raw | diff to current |
2012-04-16 |
Jim Grosbach | ARM two-operand forms for vhadd and vhsub instructions. |
blob | commitdiff | raw | diff to current |
2012-04-16 |
Jim Grosbach | ARM assembly two-operand forms for VRSHL. |
blob | commitdiff | raw | diff to current |
2012-04-16 |
Jim Grosbach | ARM two-operand aliases for VRHADD instructions. |
blob | commitdiff | raw | diff to current |
2012-04-11 |
Jim Grosbach | ARM 'vuzp.32 Dd, Dm' is a pseudo-instruction. |
blob | commitdiff | raw | diff to current |
2012-04-11 |
Jim Grosbach | ARM 'vzip.32 Dd, Dm' is a pseudo-instruction. |
blob | commitdiff | raw | diff to current |
2012-04-11 |
Evan Cheng | Add more fused mul+add/sub patterns. rdar://10139676 |
blob | commitdiff | raw | diff to current |
2012-04-11 |
Evan Cheng | Clean up ARM fused multiply + add/sub support some... |
blob | commitdiff | raw | diff to current |
2012-04-11 |
Evan Cheng | Fix a number of problems with ARM fused multiply add... |
blob | commitdiff | raw | diff to current |
2012-04-10 |
Evan Cheng | Handle llvm.fma.* intrinsics. rdar://10914096 |
blob | commitdiff | raw | diff to current |
2012-04-05 |
Jim Grosbach | ARM assembly aliases for two-operand V[R]SHR instructions. |
blob | commitdiff | raw | diff to current |
2012-03-30 |
Jim Grosbach | ARM encoding for VSWP got the second operand incorrect. |
blob | commitdiff | raw | diff to current |
2012-03-28 |
Jakob Stoklund Olesen | Spill DPair registers, not just QPR. |
blob | commitdiff | raw | diff to current |
2012-03-28 |
Richard Barton | Fixup VST1.32 with writeback instruction. Also re-facto... |
blob | commitdiff | raw | diff to current |
2012-03-06 |
Jim Grosbach | ARM more NEON VLD/VST composite physical register refac... |
blob | commitdiff | raw | diff to current |
2012-03-06 |
Jim Grosbach | ARM refactor more NEON VLD/VST instructions to use... |
blob | commitdiff | raw | diff to current |
2012-03-05 |
Jim Grosbach | ARM Refactor VLD/VST spaced pair instructions. |
blob | commitdiff | raw | diff to current |
2012-03-05 |
Jim Grosbach | ARM Remove a bit of dead code. |
blob | commitdiff | raw | diff to current |
2012-03-05 |
Jim Grosbach | ARM refactor away a bunch of VLD/VST pseudo instructions. |
blob | commitdiff | raw | diff to current |
2012-03-05 |
Sebastian Pop | updated patch for the ARM fused multiply add/sub |
blob | commitdiff | raw | diff to current |
2012-02-28 |
Jim Grosbach | ARM vbit/vbif/vbsl assembly optional size suffix. |
blob | commitdiff | raw | diff to current |
2012-02-20 |
James Molloy | Improve generated code for extending loads and some... |
blob | commitdiff | raw | diff to current |
2012-02-18 |
Jia Liu | Emacs-tag and some comment fix for all ARM, CellSPU... |
blob | commitdiff | raw | diff to current |
2012-02-14 |
Lang Hames | Third time's the charm...? |
blob | commitdiff | raw | diff to current |
2012-02-14 |
Lang Hames | Unswap swap operands, partially reducing confusion. |
blob | commitdiff | raw | diff to current |
2012-02-13 |
Lang Hames | Make operands for VSWP read-modify-write. |
blob | commitdiff | raw | diff to current |
2012-01-25 |
Jim Grosbach | NEON VLD4(all lanes) assembly parsing and encoding. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | Tidy up. Rename VLD4DUP patterns for consistency. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | NEON VLD3(all lanes) assembly parsing and encoding. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | NEON VST4(one lane) assembly parsing and encoding. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | NEON VLD4(one lane) assembly parsing and encoding. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | NEON Two-operand assembly aliases for VSRA. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | NEON Two-operand assembly aliases for VSLI. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | NEON Two-operand assembly aliases for VSRI. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | NEON add correct predicates for some asm aliases. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | NEON VST4(multiple 4 element structures) assembly parsing. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | NEON VLD4(multiple 4 element structures) assembly parsing. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | Fix typo. |
blob | commitdiff | raw | diff to current |
2012-01-24 |
Jim Grosbach | NEON VST3(single element from one lane) assembly parsing. |
blob | commitdiff | raw | diff to current |
2012-01-23 |
Jim Grosbach | NEON VST3(multiple 3-element structures) assembly parsing. |
blob | commitdiff | raw | diff to current |
2012-01-23 |
Jim Grosbach | NEON VLD3(multiple 3-element structures) assembly parsing. |
blob | commitdiff | raw | diff to current |
2012-01-23 |
Jim Grosbach | NEON VLD3 lane-indexed assembly parsing and encoding. |
blob | commitdiff | raw | diff to current |
2012-01-23 |
Jim Grosbach | Simplify some NEON assembly pseudo definitions. |
blob | commitdiff | raw | diff to current |
2012-01-22 |
Anton Korobeynikov | Add fused multiple+add instructions from VFPv4. |
blob | commitdiff | raw | diff to current |
2012-01-20 |
Bob Wilson | ARM vector any_extends need to be selected to vmovl... |
blob | commitdiff | raw | diff to current |
2012-01-20 |
Jim Grosbach | VST2 four-register w/ update pseudos for fixed/register... |
blob | commitdiff | raw | diff to current |
2012-01-20 |
Jim Grosbach | NEON use vmov.i32 to splat some f32 values into vectors. |
blob | commitdiff | raw | diff to current |
2012-01-10 |
Jim Grosbach | ARM updating VST2 pseudo-lowering fixed vs. register... |
blob | commitdiff | raw | diff to current |
2011-12-21 |
Jim Grosbach | ARM NEON mnemonic aliase for vrecpeq. |
blob | commitdiff | raw | diff to current |
2011-12-21 |
Jim Grosbach | ARM NEON optional data type on VSWP instructions. |
blob | commitdiff | raw | diff to current |
2011-12-21 |
Jim Grosbach | ARM NEON mnemonic aliases for vzipq and vswpq. |
blob | commitdiff | raw | diff to current |
2011-12-21 |
Jim Grosbach | ARM NEON assmebly parsing for VLD2 to all lanes instruc... |
blob | commitdiff | raw | diff to current |
2011-12-21 |
Jim Grosbach | ARM NEON VLD2 assembly parsing for structure to all... |
blob | commitdiff | raw | diff to current |
2011-12-20 |
Jim Grosbach | ARM assembly parsing and encoding for VST2 single-eleme... |
blob | commitdiff | raw | diff to current |
2011-12-20 |
Jim Grosbach | ARM assembly parsing and encoding for VLD2 single-eleme... |
blob | commitdiff | raw | diff to current |
2011-12-19 |
Jim Grosbach | ARM NEON assembly aliases for VMOV<-->VMVN for i32... |
blob | commitdiff | raw | diff to current |
next |