| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | AVX-512: Added SHIFT instructions. | Elena Demikhovsky | 2013-08-21 | 4 | -6/+178 |
| * | Synchronize VEX JIT encoding code with the MCJIT version. Fix a bug in the MC... | Craig Topper | 2013-08-21 | 2 | -12/+11 |
| * | In LLVM FMA3 operands are dst, src1, src2, src3, however dst is not encoded a... | Nadav Rotem | 2013-08-21 | 1 | -2/+8 |
| * | Rename mattr names for AVX-512 to from avx-512 -> avx512f, avx-512-pfi -> av5... | Craig Topper | 2013-08-21 | 3 | -7/+7 |
| * | X86TargetMachine.cpp: Clarify to emit GOT in i686-{cygming|win32}-elf for mcjit. | NAKAMURA Takumi | 2013-08-21 | 1 | -1/+1 |
| * | AVX-512: Added more patterns for VMOVSS, VMOVSD, VMOVD, VMOVQ | Elena Demikhovsky | 2013-08-20 | 2 | -12/+71 |
| * | Fix formatting. No functional change. | Craig Topper | 2013-08-20 | 1 | -1/+1 |
| * | Add AVX-512 and related features to the CPUID detection code. | Craig Topper | 2013-08-20 | 1 | -3/+19 |
| * | Move AVX and non-AVX replication inside a couple multiclasses to avoid repeat... | Craig Topper | 2013-08-20 | 1 | -87/+60 |
| * | AVX-512: added arithmetic and logical operations. | Elena Demikhovsky | 2013-08-19 | 3 | -27/+249 |
| * | AVX-512: Added VMOVD, VMOVQ, VMOVSS, VMOVSD instructions. | Elena Demikhovsky | 2013-08-18 | 6 | -44/+335 |
| * | Make more of the lowering helpers static. Also use MVT instead of EVT in a co... | Craig Topper | 2013-08-18 | 2 | -24/+17 |
| * | Don't use v16i32 for load pattern matching. All 512-bit loads are cated to v8... | Craig Topper | 2013-08-16 | 2 | -12/+12 |
| * | Constify the function parameters. | Bill Wendling | 2013-08-15 | 1 | -2/+2 |
| * | Revert r188449 as it turns out we're just missing the instructions that need ... | Craig Topper | 2013-08-15 | 1 | -9/+26 |
| * | Don't let isPermImmMask handle v16i32 since VPERMI doesn't match on that type... | Craig Topper | 2013-08-15 | 1 | -26/+9 |
| * | Use MVT instead of EVT in X86ISelDAGToDAG since all the types should be legal. | Craig Topper | 2013-08-15 | 1 | -29/+29 |
| * | Use MVT in place of EVT in more X86 operation lowering functions. | Craig Topper | 2013-08-15 | 1 | -38/+33 |
| * | Replace getValueType().getSimpleVT() with getSimpleValueType(). Also remove o... | Craig Topper | 2013-08-15 | 3 | -72/+72 |
| * | Make more helper methods into static functions. | Craig Topper | 2013-08-14 | 2 | -17/+17 |
| * | Remove tab characters. | Craig Topper | 2013-08-14 | 1 | -1/+1 |
| * | Make some helper methods static. | Craig Topper | 2013-08-14 | 2 | -34/+27 |
| * | Use MVT in more lowering code. | Craig Topper | 2013-08-14 | 1 | -6/+6 |
| * | Replace EVT with MVT in isVectorShift. Keeps compiler from generating unneede... | Craig Topper | 2013-08-14 | 1 | -3/+5 |
| * | Replace EVT with MVT in many of the shuffle lowering functions. Keeps compile... | Craig Topper | 2013-08-14 | 1 | -37/+46 |
| * | Fix compiler warnings. | Evgeniy Stepanov | 2013-08-13 | 1 | -6/+4 |
| * | AVX-512: Added CMP and BLEND instructions. | Elena Demikhovsky | 2013-08-13 | 4 | -9/+293 |
| * | Fix a crash with X86 Mach-O and a subtraction expression where both symbols are | Kevin Enderby | 2013-08-12 | 1 | -0/+5 |
| * | AVX-512: Added more tests for BROADCAST | Elena Demikhovsky | 2013-08-11 | 1 | -1/+1 |
| * | AVX-512: Added VPERM* instructons and MOV* zmm-to-zmm instructions. | Elena Demikhovsky | 2013-08-11 | 5 | -47/+432 |
| * | Add a overload to CostTable which allows it to infer the size of the table. | Benjamin Kramer | 2013-08-09 | 1 | -33/+25 |
| * | [Object] Split the ELF interface into 3 parts. | Michael J. Spencer | 2013-08-08 | 1 | -1/+1 |
| * | Use pop_back() instead of pop_back_val() when the returned value is not used. | Jakub Staszak | 2013-08-08 | 1 | -4/+4 |
| * | Fix the comment. | Jakub Staszak | 2013-08-08 | 1 | -1/+1 |
| * | AVX-512 set: Added BROADCAST instructions | Elena Demikhovsky | 2013-08-07 | 4 | -7/+146 |
| * | Simplify code. No functional change intended. | Craig Topper | 2013-08-07 | 1 | -4/+1 |
| * | Refactor isInTailCallPosition handling | Tim Northover | 2013-08-06 | 2 | -0/+16 |
| * | Simplify vector lane handling math a bit. No functional change intended. | Craig Topper | 2013-08-06 | 1 | -22/+16 |
| * | Simplify math a little bit. | Craig Topper | 2013-08-06 | 1 | -16/+17 |
| * | Target/*/CMakeLists.txt: Add the dependency to CommonTableGen explicitly for ... | NAKAMURA Takumi | 2013-08-06 | 1 | -1/+1 |
| * | Replace EVT with MVT in isHorizontalBinOp as it is only called with legal types. | Craig Topper | 2013-08-06 | 1 | -1/+1 |
| * | Simplify code slightly. No functional change. | Craig Topper | 2013-08-06 | 1 | -4/+2 |
| * | Silencing an MSVC11 type conversion warning. | Aaron Ballman | 2013-08-05 | 1 | -1/+1 |
| * | AVX-512 set: added mask operations, lowering BUILD_VECTOR for i1 vector types. | Elena Demikhovsky | 2013-08-05 | 4 | -0/+354 |
| * | X86: Turn fp selects into mask operations. | Benjamin Kramer | 2013-08-04 | 5 | -70/+91 |
| * | AVX-512 set: added VEXTRACTPS instruction | Elena Demikhovsky | 2013-08-04 | 2 | -6/+15 |
| * | X86: correct tail return address calculation | Tim Northover | 2013-08-04 | 2 | -4/+6 |
| * | Use function attributes to indicate that we don't want to realign the stack. | Bill Wendling | 2013-08-01 | 1 | -2/+3 |
| * | Fixed the Intel-syntax X86 disassembler to respect the (existing) option for ... | Daniel Malea | 2013-08-01 | 2 | -7/+5 |
| * | EVEX and compressed displacement encoding for AVX512 | Elena Demikhovsky | 2013-08-01 | 2 | -54/+278 |
