| Commit message (Expand) | Author | Age | Files | Lines |
| * | Recommit r317904: [Hexagon] Create HexagonISelDAGToDAG.h, NFC | Krzysztof Parzyszek | 2017-11-10 | 2 | -109/+139 |
| * | AMDGPU/NFC: Split Processors.td into GCNProcessors.td and R600Processors.td | Konstantin Zhuravlyov | 2017-11-10 | 4 | -218/+258 |
| * | Revert "[Hexagon] Create HexagonISelDAGToDAG.h, NFC" | Krzysztof Parzyszek | 2017-11-10 | 2 | -139/+109 |
| * | [X86] Merge the template method selectAddrOfGatherScatterNode into selectVect... | Craig Topper | 2017-11-10 | 1 | -25/+16 |
| * | [RISCV] Silence an unused variable warning in release builds [NFC] | Mandeep Singh Grang | 2017-11-10 | 2 | -5/+5 |
| * | [Hexagon] Create HexagonISelDAGToDAG.h, NFC | Krzysztof Parzyszek | 2017-11-10 | 2 | -109/+139 |
| * | [RegAlloc, SystemZ] Increase number of LOCRs by passing "hard" regalloc hints. | Jonas Paulsson | 2017-11-10 | 5 | -4/+99 |
| * | [X86] Add support for combining FMADDSUB(A, B, FNEG(C))->FMSUBADD(A, B, C) | Craig Topper | 2017-11-10 | 1 | -0/+31 |
| * | [AMDGPU] Fix pointer info for lowering load/store for r600 for amdgiz environ... | Yaxun Liu | 2017-11-10 | 1 | -3/+7 |
| * | [AMDGPU] Fix pointer info for pseudo source for r600 | Yaxun Liu | 2017-11-10 | 2 | -0/+21 |
| * | [SystemZ] Add support for the "o" inline asm constraint | Ulrich Weigand | 2017-11-09 | 2 | -0/+5 |
| * | [mips] Correct microMIP's jump and add unconditional branch pseudo | Simon Dardis | 2017-11-09 | 4 | -18/+29 |
| * | [RISCV] MC layer support for the standard RV32A instruction set extension | Alex Bradbury | 2017-11-09 | 6 | -12/+128 |
| * | [RISCV] MC layer support for the standard RV32M instruction set extension | Alex Bradbury | 2017-11-09 | 4 | -4/+45 |
| * | Sched model improving on btver2: JFPU01 resource, vtestp* for xmm. | Andrew V. Tischenko | 2017-11-09 | 1 | -11/+26 |
| * | Add -print-schedule scheduling comments to inline asm. | Andrew V. Tischenko | 2017-11-09 | 3 | -14/+16 |
| * | [X86] Give priority to EVEX FMA instructions over FMA4 instructions. | Craig Topper | 2017-11-09 | 3 | -63/+69 |
| * | Fix "default label in switch which covers all enumeration values" warning | Vitaly Buka | 2017-11-09 | 1 | -2/+0 |
| * | [X86] Make X86ISD::FMADDS3 isel patterns commutable. | Craig Topper | 2017-11-09 | 1 | -4/+4 |
| * | AMDGPU: Merge BUFFER_STORE_DWORD_OFFEN/OFFSET into x2, x4 | Marek Olsak | 2017-11-09 | 1 | -4/+109 |
| * | AMDGPU: Lower buffer store and atomic intrinsics manually | Marek Olsak | 2017-11-09 | 5 | -20/+206 |
| * | AMDGPU: Merge BUFFER_LOAD_DWORD_OFFSET into x2, x4 | Marek Olsak | 2017-11-09 | 1 | -13/+37 |
| * | AMDGPU: Merge BUFFER_LOAD_DWORD_OFFEN into x2, x4 | Marek Olsak | 2017-11-09 | 1 | -26/+141 |
| * | AMDGPU: Merge S_BUFFER_LOAD_DWORD_IMM into x2, x4 | Marek Olsak | 2017-11-09 | 2 | -14/+125 |
| * | AMDGPU: Fold immediate offset into BUFFER_LOAD_DWORD lowered from SMEM | Marek Olsak | 2017-11-09 | 3 | -14/+40 |
| * | [X86] Make sure we don't read too many operands from X86ISD::FMADDS1/FMADDS3 ... | Craig Topper | 2017-11-09 | 1 | -2/+5 |
| * | [X86] X86MaskedGatherSDNode shouldn't inherit from MaskedGatherScatterSDNode | Craig Topper | 2017-11-08 | 1 | -2/+10 |
| * | [X86] Preserve memory refs when folding loads into divides. | Craig Topper | 2017-11-08 | 1 | -1/+5 |
| * | [X86] Remove an if check on the result of a cast. NFC | Craig Topper | 2017-11-08 | 1 | -12/+6 |
| * | Revert "Correct dwarf unwind information in function epilogue for X86" | Reid Kleckner | 2017-11-08 | 3 | -54/+0 |
| * | Set hasSideEffects=0 for PHI and fix affected passes | Alex Bradbury | 2017-11-08 | 1 | -3/+2 |
| * | [X86] Correct the implementation of BEXTR load folding to use the shift as th... | Craig Topper | 2017-11-08 | 1 | -6/+14 |
| * | [WebAssembly] Update test expectations | Sam Clegg | 2017-11-08 | 1 | -14/+3 |
| * | [X86] Don't call validateInstruction from MatchAndEmitInstruction when Matchi... | Craig Topper | 2017-11-08 | 1 | -2/+2 |
| * | [WebAssembly] Call signExtend to get sign extended register | Dan Gohman | 2017-11-08 | 1 | -1/+1 |
| * | [WebAssembly] Revise the strategy for inline asm. | Dan Gohman | 2017-11-08 | 2 | -6/+25 |
| * | [RISCV] Initial support for function calls | Alex Bradbury | 2017-11-08 | 8 | -4/+186 |
| * | [RISCV] Codegen for conditional branches | Alex Bradbury | 2017-11-08 | 8 | -4/+118 |
| * | [RISCV] Codegen support for memory operations on global addresses | Alex Bradbury | 2017-11-08 | 5 | -22/+99 |
| * | [RISCV] Codegen support for memory operations | Alex Bradbury | 2017-11-08 | 4 | -0/+47 |
| * | [RISCV] Codegen support for materializing constants | Alex Bradbury | 2017-11-08 | 1 | -0/+24 |
| * | [mips] Guard indirect and tailcall pseudo instructions correctly. | Simon Dardis | 2017-11-08 | 3 | -11/+23 |
| * | [NFCI] Ensure TargetOpcode::* are compatible with guessInstructionProperties=0 | Alex Bradbury | 2017-11-08 | 1 | -3/+1 |
| * | [X86] Add patterns to fold EVEX store with EVEX encoded vcvtps2ph instruction... | Craig Topper | 2017-11-08 | 1 | -11/+23 |
| * | [X86] Allow legacy vcvtps2ph intrinsics to select EVEX encoded instructions. ... | Craig Topper | 2017-11-08 | 2 | -18/+16 |
| * | Target/TargetInstrInfo.h -> CodeGen/TargetInstrInfo.h to match layering | David Blaikie | 2017-11-08 | 86 | -99/+99 |
| * | AMDGPU: Set correct sched model on v_mad_u64_u32 | Matt Arsenault | 2017-11-08 | 1 | -0/+2 |
| * | Attribute nonlazybind should not affect calls to functions with hidden visibi... | Sriraman Tallam | 2017-11-08 | 2 | -9/+11 |
| * | [NVPTX] Implement __nvvm_atom_add_gen_d builtin. | Justin Lebar | 2017-11-07 | 2 | -0/+14 |
| * | Use new vector insert half-word and byte instructions when we see inserteleme... | Graham Yiu | 2017-11-07 | 2 | -3/+33 |