summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
Commit message (Expand)AuthorAgeFilesLines
* AMDGPU/SI: Implement sendmsghalt intrinsicJan Vesely2017-01-041-1/+8
* AMDGPU: Use i16 for i16 shift amountMatt Arsenault2016-12-221-2/+4
* AMDGPU: Use i16 comparison instructionsMatt Arsenault2016-12-221-3/+1
* AMDGPU: Swap order of operands in fadd/fsub combineMatt Arsenault2016-12-221-4/+4
* AMDGPU: Check fast math flags in fadd/fsub combinesMatt Arsenault2016-12-221-6/+13
* AMDGPU: Form more FMAs if fusion is allowedMatt Arsenault2016-12-221-30/+45
* AMDGPU: Move combines into separate functionsMatt Arsenault2016-12-221-152/+169
* AMDGPU: Enable some f32 fadd/fsub combines for f16Matt Arsenault2016-12-221-7/+12
* AMDGPU: Implement isFMAFasterThanFMulAndFAdd for f16Matt Arsenault2016-12-221-0/+2
* AMDGPU: Allow rcp and rsq usage with f16Matt Arsenault2016-12-221-3/+8
* AMDGPU: Custom lower f16 fdivMatt Arsenault2016-12-221-1/+21
* AMDGPU: Implement f16 fcanonicalizeMatt Arsenault2016-12-221-0/+3
* AMDGPU: Allow 16-bit types in inline asm constraintsMatt Arsenault2016-12-201-0/+2
* AMDGPU/SI: Add a MachineMemOperand when lowering llvm.amdgcn.buffer.load.*Tom Stellard2016-12-201-0/+26
* AMDGPU/SI: Add a MachineMemOperand to MIMG instructionsTom Stellard2016-12-201-6/+24
* AMDGPU: Select branch on undef to uniform scc branchMatt Arsenault2016-12-151-0/+9
* Fix for regression after Global Load Scalarization patchAlexander Timofeev2016-12-151-1/+2
* AMDGPU: Fix isTypeDesirableForOp for i16Matt Arsenault2016-12-091-4/+16
* AMDGPU: Make f16 ConstantFP legalMatt Arsenault2016-12-081-13/+1
* [AMDGPU] Scalarization of global uniform loads.Alexander Timofeev2016-12-081-2/+17
* AMDGPU : Add S_SETREG instructions to fix fdiv precision issues.Tom Stellard2016-12-071-11/+101
* AMDGPU: Add llvm.amdgcn.interp.mov intrinsicTom Stellard2016-12-061-0/+6
* AMDGPU: Refactor exp instructionsMatt Arsenault2016-12-051-0/+23
* AMDGPU: Implement isCheapAddrSpaceCastMatt Arsenault2016-12-021-2/+12
* AMDGPU: Use SGPR_64 for argument loweringsMatt Arsenault2016-11-291-7/+7
* AMDGPU/SI: Use float as the operand type for amdgcn.interp intrinsicsTom Stellard2016-11-261-0/+2
* AMDGPU/SI: Add back reverted SGPR spilling code, but disable itMarek Olsak2016-11-251-11/+11
* Revert "AMDGPU: Make m0 unallocatable"Marek Olsak2016-11-251-11/+11
* AMDGPU: Make m0 unallocatableMatt Arsenault2016-11-241-11/+11
* AMDGPU: Fix unused variable warningMatt Arsenault2016-11-181-5/+4
* AMDGPU: Fix crash on illegal type for inlineasmMatt Arsenault2016-11-181-0/+2
* [AMDGPU] Custom lower f16 = fp_round f64Konstantin Zhuravlyov2016-11-171-0/+20
* [AMDGPU] Promote f16/i16 conversions to f32/i32Konstantin Zhuravlyov2016-11-171-52/+8
* [AMDGPU] Expand `br_cc` for f16Konstantin Zhuravlyov2016-11-171-0/+1
* [AMDGPU] Handle f16 select{_cc}Konstantin Zhuravlyov2016-11-161-0/+1
* AMDGPU/SI: Support data types other than V4f32 in image intrinsicsChangpeng Fang2016-11-141-2/+5
* [AMDGPU] Add f16 support (VI+)Konstantin Zhuravlyov2016-11-131-13/+103
* AMDGPU/SI: Promote i16 = fp_[us]int f32 for VITom Stellard2016-11-121-0/+6
* AMDGPU: Add VI i16 supportTom Stellard2016-11-101-4/+72
* Revert "AMDGPU: Add VI i16 support"Tom Stellard2016-11-041-72/+4
* AMDGPU: Add VI i16 supportTom Stellard2016-11-031-4/+72
* AMDGPU/SI: Don't emit multi-dword flat memory ops when they might access scratchTom Stellard2016-10-261-0/+16
* AMDGPU: Fix Two Address problems with v_movreldNicolai Haehnle2016-10-241-27/+30
* [AMDGPU] Perform uchar to float combine for ISD::SINT_TO_FPKonstantin Zhuravlyov2016-10-211-4/+13
* [AMDGPU] Emit constant address space data in .rodata section and use relocati...Konstantin Zhuravlyov2016-10-201-22/+22
* AMDGPU/SI: LowerParameter() should be computing align based on memory typeTom Stellard2016-10-171-1/+1
* AMDGPU/SI: Fix LowerParameter() for i16 argumentsTom Stellard2016-10-171-10/+18
* AMDGPU/SI: Don't allow unaligned scratch accessTom Stellard2016-10-141-0/+9
* AMDGPU: Fix use-after-freesNicolai Haehnle2016-10-141-14/+15
* [AMDGPU] Emit 32-bit lo/hi got and pc relative variant kinds for external and...Konstantin Zhuravlyov2016-10-141-12/+43
OpenPOWER on IntegriCloud