| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | AMDGPU: Generalize matching of v_med3_f32 | Matt Arsenault | 2017-01-31 | 1 | -0/+20 |
| * | AMDGPU: Make i32 uaddo/usubo legal | Matt Arsenault | 2017-01-30 | 1 | -0/+17 |
| * | AMDGPU/SI: Move some ISel helpers into utils so they can be shared with GISel | Tom Stellard | 2017-01-27 | 1 | -13/+2 |
| * | AMDGPU: Remove modifiers from v_div_scale_* | Matt Arsenault | 2017-01-19 | 1 | -8/+2 |
| * | AMDGPU/R600: Don't use REGISTER_{LOAD,STORE} ISD nodes | Jan Vesely | 2017-01-06 | 1 | -0/+4 |
| * | AMDGPU: Select branch on undef to uniform scc branch | Matt Arsenault | 2016-12-15 | 1 | -0/+6 |
| * | [AMDGPU, PowerPC, TableGen] Fix some Clang-tidy modernize and Include What Yo... | Eugene Zelenko | 2016-12-09 | 1 | -13/+30 |
| * | AMDGPU : Add S_SETREG instructions to fix fdiv precision issues. | Tom Stellard | 2016-12-07 | 1 | -0/+38 |
| * | AMDGPU/SI: Add back reverted SGPR spilling code, but disable it | Marek Olsak | 2016-11-25 | 1 | -1/+1 |
| * | Revert "AMDGPU: Make m0 unallocatable" | Marek Olsak | 2016-11-25 | 1 | -1/+1 |
| * | AMDGPU: Make m0 unallocatable | Matt Arsenault | 2016-11-24 | 1 | -1/+1 |
| * | AMDGPU: Remove unnecessary and on conditional branch | Matt Arsenault | 2016-11-07 | 1 | -16/+2 |
| * | AMDGPU: Handle CopyToReg in getOperandRegClass | Matt Arsenault | 2016-11-01 | 1 | -1/+14 |
| * | AMDGPU: Select 64-bit {ADD,SUB}{C,E} nodes | Nicolai Haehnle | 2016-10-14 | 1 | -10/+37 |
| * | [AMDGPU] Pass optimization level to SelectionDAGISel | Konstantin Zhuravlyov | 2016-10-03 | 1 | -6/+6 |
| * | Use StringRef in Pass/PassManager APIs (NFC) | Mehdi Amini | 2016-10-01 | 1 | -2/+2 |
| * | AMDGPU: Fix broken FrameIndex handling | Matt Arsenault | 2016-09-17 | 1 | -59/+9 |
| * | AMDGPU: Use i64 scalar compare instructions | Matt Arsenault | 2016-09-17 | 1 | -12/+27 |
| * | AMDGPU: Run LoadStoreVectorizer pass by default | Matt Arsenault | 2016-09-09 | 1 | -0/+3 |
| * | MachineFunction: Return reference for getFrameInfo(); NFC | Matthias Braun | 2016-07-28 | 1 | -2/+2 |
| * | AMDGPU: Remove analyzeImmediate | Matt Arsenault | 2016-07-28 | 1 | -5/+12 |
| * | AMDGPU: Unify MOVRELSOffset and MOVRELDOffset | Nicolai Haehnle | 2016-07-12 | 1 | -30/+6 |
| * | AMDGPU: Improve offset folding for register indexing | Matt Arsenault | 2016-07-09 | 1 | -0/+49 |
| * | AMDGPU/SI: Remove address space query functions from AMDGPUDAGToDAGISel | Tom Stellard | 2016-07-05 | 1 | -56/+3 |
| * | AMDGPU/R600: Add PatFrags for selecting the correct vtx id for loads | Tom Stellard | 2016-07-05 | 1 | -5/+0 |
| * | AMDGPU/SI: Remove hack for selecting < 32-bit loads to MUBUF instructions | Tom Stellard | 2016-07-04 | 1 | -4/+0 |
| * | AMDGPU: Cleanup subtarget handling. | Matt Arsenault | 2016-06-24 | 1 | -1/+1 |
| * | AMDGPU: Fix gcc warnings | Matt Arsenault | 2016-06-22 | 1 | -90/+0 |
| * | Delete more dead code. | Rafael Espindola | 2016-06-21 | 1 | -32/+0 |
| * | Delete some dead code. | Rafael Espindola | 2016-06-21 | 1 | -5/+0 |
| * | Reformat blank lines. | NAKAMURA Takumi | 2016-06-20 | 1 | -1/+0 |
| * | Untabify. | NAKAMURA Takumi | 2016-06-20 | 1 | -5/+3 |
| * | AMDGPU: Fix MUBUF offset bugs affecting llvm.amdgcn.buffer.* intrinsics | Nicolai Haehnle | 2016-06-15 | 1 | -13/+30 |
| * | Pass DebugLoc and SDLoc by const ref. | Benjamin Kramer | 2016-06-12 | 1 | -3/+4 |
| * | AMDGPU/SI: Make sure to emit TargetConstant nodes when matching ds_*permute | Tom Stellard | 2016-06-10 | 1 | -2/+2 |
| * | AMDGPU: Fix flat atomics | Matt Arsenault | 2016-06-09 | 1 | -0/+17 |
| * | AMDGPU: Fix i64 global cmpxchg | Matt Arsenault | 2016-06-09 | 1 | -6/+75 |
| * | AMDGPU/R600: Implement memory loads from constant AS | Jan Vesely | 2016-05-13 | 1 | -3/+10 |
| * | SDAG: Implement Select instead of SelectImpl in AMDGPUDAGToDAGISel | Justin Bogner | 2016-05-12 | 1 | -49/+67 |
| * | Fixed unused but set variable warning | Simon Pilgrim | 2016-05-09 | 1 | -3/+0 |
| * | SDAG: Rename Select->SelectImpl and repurpose Select as returning void | Justin Bogner | 2016-05-05 | 1 | -2/+2 |
| * | AMDGPU: Make i64 loads/stores promote to v2i32 | Matt Arsenault | 2016-05-02 | 1 | -55/+0 |
| * | AMDGPU/SI: Add offset field to ds_permute/ds_bpermute instructions | Tom Stellard | 2016-04-29 | 1 | -2/+2 |
| * | AMDGPU: Implement addrspacecast | Matt Arsenault | 2016-04-25 | 1 | -66/+0 |
| * | AMDGPU: sext_inreg (srl x, K), vt -> bfe x, K, vt.Size | Matt Arsenault | 2016-04-22 | 1 | -0/+16 |
| * | [StructurizeCFG] Annotate branches that were treated as uniform | Nicolai Haehnle | 2016-04-14 | 1 | -1/+3 |
| * | AMDGPU: Add atomic_inc + atomic_dec intrinsics | Matt Arsenault | 2016-04-12 | 1 | -1/+2 |
| * | AMDGPU/SI: Implement atomic load/store for i32 and i64 | Jan Vesely | 2016-04-07 | 1 | -12/+33 |
| * | Fix sequence point warning. NFC. | Vasileios Kalintiris | 2016-03-24 | 1 | -1/+1 |
| * | AMDGPU: Insert moves of frame index to value operands | Matt Arsenault | 2016-03-23 | 1 | -0/+56 |
