summaryrefslogtreecommitdiff
path: root/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
AgeCommit message (Expand)Author
2025-01-07[AMDGPU] Do not fold into v_accvpr_mov/write/read (#120475)bcahoon
2025-01-06[AMDGPU][True16][MC] true16 for v_fma_f16 (#119477)Brox Chen
2024-11-12AMDGPU: Do not fold copy to physreg from operation on frame index (#115977)Matt Arsenault
2024-11-07AMDGPU: Fold more scalar operations on frame index to VALU (#115059)Matt Arsenault
2024-11-06AMDGPU: Fold copy of scalar add of frame index (#115058)Matt Arsenault
2024-11-05[AMDGPU][True16][MC] VOP2 update instructions with fake16 format (#114436)Brox Chen
2024-10-29[AMDGPU] Fix machine verification failure after SIFoldOperandsImpl::tryFoldOM...Jay Foad
2024-10-19AMDGPU: Handle folding frame indexes into add with immediate (#110738)Matt Arsenault
2024-08-29AMDGPU/NewPM: Port SIFoldOperands to new pass manager (#105801)Akshat Oke
2024-08-08[AMDGPU][True16][CodeGen] support v_mov_b16 and v_swap_b16 in true16 format (...Brox Chen
2024-07-25[AMDGPU] Fix folding clamp into pseudo scalar instructions (#100568)Mirko Brkušanin
2024-07-19AMDGPU: Clear kill flags after FoldZeroHighBits (#99582)Changpeng Fang
2024-07-17[AMDGPU] Use range-based for loops. NFC. (#99047)Jay Foad
2024-06-18AMDGPU: Don't fold clamp/omod modifiers without nofpexcept (#95950)Matt Arsenault
2024-05-07[AMDGPU] Don't optimize agpr phis if the operand doesn't have subreg use (#91...Shilei Tian
2024-03-07Add non-null check before accessing pointer (#83459)Martin Wehking
2024-02-27[AMDGPU] Prevent hang in SIFoldOperands by caching uses (#82099)choikwa
2024-02-20[AMDGPU] Add v2bf16 for opsel immediate folding (#82435)Stanislav Mekhanoshin
2024-02-08[AMDGPU][True16] Support VOP3 source DPP operands. (#80892)Ivan Kosarev
2024-01-24[AMDGPU] Add GFX12 WMMA and SWMMAC instructions (#77795)Mirko Brkušanin
2024-01-18[AMDGPU] Update uses of new VOP2 pseudos for GFX12 (#78155)Jay Foad
2024-01-04AMDGPU: Fix packed 16-bit inline constants (#76522)Nicolai Hähnle
2023-11-28[AMDGPU] Fix folding of v2i16/v2f16 splat imms (#72709)Stanislav Mekhanoshin
2023-11-28[AMDGPU] Fixed folding of inline imm into dot w/o opsel (#73589)Stanislav Mekhanoshin
2023-11-13[AMDGPU] Revert "Preliminary patch for divergence driven instruction selectio...Jay Foad
2023-11-13[AMDGPU] Fix and use isSISrcInlinableOperand. NFC. (#72101)Jay Foad
2023-11-10[AMDGPU] Simplify commuted operand handling. NFCI. (#71965)Jay Foad
2023-09-23Reapply "[AMDGPU] Introduce real and keep fake True16 instructions."Ivan Kosarev
2023-09-22Revert "[AMDGPU] Introduce real and keep fake True16 instructions."Ivan Kosarev
2023-09-22[AMDGPU] Introduce real and keep fake True16 instructions.Ivan Kosarev
2023-09-21[AMDGPU] Select gfx1150 SALU Float instructions (#66885)Mirko Brkušanin
2023-08-11AMDGPU: Check for implicit defs before constant folding instructionMatt Arsenault
2023-07-13[AMDGPU] Corrrectly emit AGPR copies in tryFoldPhiAGPRpvanhout
2023-06-29[AMDGPU] Handle Additional Cases in tryFoldPhiAGPRpvanhout
2023-06-07[AMDGPU][NFC] Add a getRegBitWidth() helper for TargetRegisterClass operands.Ivan Kosarev
2023-03-28[AMDGPU] Fold more AGPR copies/PHIs in SIFoldOperandspvanhout
2023-02-22[AMDGPU] Fix an assertion failure when folding into src2 of V_FMAC_F16Jay Foad
2023-01-24[AMDGPU] Add missing physical register check in SIFoldOperands::tryFoldLoadYashwant Singh
2023-01-23[MC] Define and use MCInstrDesc implicit_uses and implicit_defs. NFC.Jay Foad
2023-01-23[MC] Make more use of MCInstrDesc::operands. NFC.Jay Foad
2022-12-21AMDGPU: Use DenormalMode type in FP mode trackingMatt Arsenault
2022-12-14[AMDGPU] Stop using make_pair and make_tuple. NFC.Jay Foad
2022-12-07[AMDGPU] Enable OMod on more VOP3 instructionsJoe Nash
2022-11-18[AMDGPU] Stop looking for implicit M0 uses on MOV instructionsJay Foad
2022-11-17[AMDGPU] Remove isLiteralConstant and isLiteralConstantLikeJay Foad
2022-11-08[AMDGPU] Add & use `hasNamedOperand`, NFCPierre van Houtryve
2022-11-08[SIFoldOperands] Small code cleanups, NFC.Pierre van Houtryve
2022-11-08[SIFoldOperands] Move `isFoldableCopy` into a separate helper, NFC.Pierre van Houtryve
2022-09-20[AMDGPU][GFX11] Use VGPR_32_Lo128 for VOP1,2,CJoe Nash
2022-09-12TableGen: Introduce generated getSubRegisterClass functionMatt Arsenault
generated by cgit v1.2.3 (git 2.25.1) at 2026-05-31 19:57:19 +0000