Age | Commit message (Expand) | Author | Files | Lines |
2023-07-25 | AMDGPU: Correctly expand f64 sqrt intrinsic | Matt Arsenault | 5 | -4/+186 |
2023-07-25 | Attributor: Fix typo | Matt Arsenault | 1 | -1/+1 |
2023-07-25 | [FuncSpec][NFC] Leave a comment for future improvements. | Alexandros Lamprineas | 1 | -0/+3 |
2023-07-25 | [RISCV] Remove zvk uimm constraints | 4vtomat | 2 | -12/+3 |
2023-07-25 | [SVE] Add vselect(mla/mls) patterns for cases where a multiplicand is used fo... | Paul Walker | 1 | -5/+10 |
2023-07-25 | [FuncSpec] Add Phi nodes to the InstCostVisitor. | Alexandros Lamprineas | 1 | -6/+76 |
2023-07-25 | Revert rGfae7b98c221b5b28797f7b56b656b6b819d99f27 "[Support] Change SetVector... | Simon Pilgrim | 1 | -29/+17 |
2023-07-25 | [AMDGPU] Remove unused variable 'CNI' in /AMDGPUMachineCFGStructurizer.cpp (NFC) | Jie Fu | 1 | -3/+0 |
2023-07-25 | [Support] Change SetVector's default template parameter to SmallVector<*, 0> | Fangrui Song | 1 | -17/+29 |
2023-07-25 | Revert "[LV] Re-use existing broadcast value for live-ins." | Martin Storsjö | 1 | -3/+0 |
2023-07-25 | [DAGCombiner] Minor improvements to foldAndOrOfSETCC. NFC | Craig Topper | 1 | -5/+4 |
2023-07-24 | [RISCV] Don't print a tab after mnemonics that don't have operands. | Craig Topper | 1 | -1/+1 |
2023-07-25 | [RISCV] Match ext_vl+sra_vl/srl_vl+trunc_vector_vl to vnsra.wv/vnsrl.wv | LiaoChunyu | 1 | -0/+28 |
2023-07-25 | [X86] Support -march=graniterapids-d and update -march=graniterapids | Freddy Ye | 3 | -5/+21 |
2023-07-25 | [AMDGPU] Allow vector access types in PromoteAllocaToVector | pvanhout | 1 | -26/+98 |
2023-07-25 | [AMDGPU] Use SSAUpdater in PromoteAlloca | pvanhout | 1 | -91/+293 |
2023-07-24 | [Support] Change MapVector's default template parameter to SmallVector<*, 0> | Fangrui Song | 1 | -1/+3 |
2023-07-25 | [X86] Update features for sierraforest, grandridge | Freddy Ye | 2 | -2/+4 |
2023-07-25 | [RISCV] Add a common class for cm.push, cm.popret, cm.popretz and cm.pop. | Jim Lin | 1 | -42/+16 |
2023-07-25 | [LoongArch] Implement isSExtCheaperThanZExt | WANG Rui | 2 | -0/+5 |
2023-07-25 | [LoongArch] Support InlineAsm for LSX and LASX | chenli | 2 | -1/+30 |
2023-07-25 | [PowerPC][AIX] Enable quadword atomics by default for AIX | Kai Luo | 1 | -10/+1 |
2023-07-24 | ConstantFolding: Constant fold denormal inputs to canonicalize for IEEE | Matt Arsenault | 1 | -2/+1 |
2023-07-24 | [TextAPI] Remove TBD file attributes that aren't used anymore. | Cyndy Ishida | 4 | -53/+9 |
2023-07-24 | [RISCV] Add lowering for scalar fmaximum/fminimum. | Craig Topper | 5 | -0/+53 |
2023-07-24 | [TextAPI] Introduce SymbolSet | Cyndy Ishida | 4 | -41/+41 |
2023-07-24 | [yaml2obj] Add support for load config section data. | Jacek Caban | 2 | -5/+106 |
2023-07-24 | [SLP] Fix -Wunused-variable in -DLLVM_ENABLE_ASSERTIONS=off builds after D154891 | Fangrui Song | 1 | -3/+2 |
2023-07-24 | [SLP]Check scalars before trying scheduling. | Alexey Bataev | 1 | -304/+361 |
2023-07-24 | RegisterCoaleser: Fix empty subrange verifier error | Matt Arsenault | 1 | -2/+9 |
2023-07-24 | RegisterCoalescer: Fix verifier error on redef of subregister for live out im... | Matt Arsenault | 1 | -1/+1 |
2023-07-24 | [RISCV] Remove combineCmpOp and associated code. NFCI | Craig Topper | 1 | -225/+0 |
2023-07-24 | AMDGPU: Implement combineRepeatedFPDivisors | Matt Arsenault | 1 | -0/+6 |
2023-07-24 | [NVPTX] Expand select_cc on bfloat16 type | Yuanqiang Liu | 1 | -2/+2 |
2023-07-24 | [ConstantFolding] Avoid use of ConstantExpr::getOr() (NFC) | Nikita Popov | 1 | -1/+2 |
2023-07-24 | [InstCombine] Avoid uses of ConstantExpr::getOr() | Nikita Popov | 2 | -14/+8 |
2023-07-24 | [RISCV] Add CZERO_EQZ/CZERO_NEZ to ComputeNumSignBitsForTargetNode. | Craig Topper | 1 | -0/+5 |
2023-07-24 | [RISCV] Add CZERO_EQZ/CZERO_NEZ to computeKnownBitsForTargetNode. | Craig Topper | 1 | -0/+7 |
2023-07-24 | [AArch64] Add vselect(fmin/fmax) SVE patterns | David Green | 1 | -4/+8 |
2023-07-24 | [X86] combineConcatVectorOps - add concat(ctpop)/concat(ctlz)/concat(cttz) ha... | Simon Pilgrim | 1 | -0/+11 |
2023-07-24 | [Remark] Overload `<<` for Remark, RemarkType and RemarkLocation. | Zain Jaffal | 1 | -1/+27 |
2023-07-24 | [OpenMP] Make the nested parallelism global hidden | Joseph Huber | 1 | -4/+5 |
2023-07-24 | [LAA] Add assertion to check both Start and End are invariant (NFC). | Florian Hahn | 1 | -0/+3 |
2023-07-24 | [llvm][nvptx] Add sm_90a | Guray Ozen | 1 | -0/+3 |
2023-07-24 | [X86] combineConcatVectorOps - add basic concat(unpack(x,y),unpack(z,w)) -> u... | Simon Pilgrim | 1 | -0/+18 |
2023-07-24 | [NVPTX] Fix lack of `.noreturn` on certain functions for aliases | Joseph Huber | 1 | -0/+2 |
2023-07-24 | [InstCombine] Transform bitwise (A >> C - 1, zext(icmp)) -> zext (bitwise(A <... | XChy | 1 | -15/+28 |
2023-07-24 | [LV] Re-use existing broadcast value for live-ins. | Florian Hahn | 1 | -0/+3 |
2023-07-24 | [X86] combineConcatVectorOps - add concat(psadbw(x,y),psadbw(z,w)) -> psadbw(... | Simon Pilgrim | 1 | -2/+6 |
2023-07-24 | [Mips] Fix argument lowering for illegal vector types (PR63608) | Nikita Popov | 1 | -12/+20 |