summaryrefslogtreecommitdiff
path: root/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
AgeCommit message (Expand)Author
2025-09-04[AMDGPU][gfx1250] Add 128B cooperative atomics (#156418)Pierre van Houtryve
2025-08-21[Target] Remove SoftFail field on targets that don't use it (NFC) (#154659)Sergei Barannikov
2025-08-19[AMDGPU] Add support for store to constant address space (#153835)Shilei Tian
2025-07-31[AMDGPU] Remove `UnsafeFPMath` uses (#151079)paperchalice
2025-06-18AMDGPU: Directly select minimumnum/maximumnum with ieee_mode=0 (#141903)Matt Arsenault
2025-05-22[AMDGPU] Simplify definition of AddrSpaces. NFC. (#141030)Jay Foad
2025-04-28[Targets] Migrate from atomic_load_8/16/32/64 to atomic_load_nonext_8/16/32/6...Craig Topper
2025-04-25[SelectionDAG][Targets] Replace atomic_load_8/atomic_load_16 with atomic_load...Craig Topper
2024-11-21AMDGPU: Define v_mfma_f32_{16x16x128|32x32x64}_f8f6f4 instructions (#116723)Matt Arsenault
2024-10-31AMDGPU/GlobalISel: Handle atomic sextload and zextload (#111721)Matt Arsenault
2024-10-09AMDGPU: Remove flat/global fmin/fmax intrinsics (#105642)Matt Arsenault
2024-08-22AMDGPU: Remove global/flat atomic fadd intrinics (#97051)Matt Arsenault
2024-08-21AMDGPU: Remove flat/global atomic fadd v2bf16 intrinsics (#97050)Matt Arsenault
2024-06-23AMDGPU: Remove ds atomic fadd intrinsics (#95396)Matt Arsenault
2024-06-18AMDGPU: Support local atomicrmw fmin/fmax for float/double (#95590)Matt Arsenault
2024-06-18[AMDGPU][MC] Support UC_VERSION_* constants. (#95618)Ivan Kosarev
2024-06-18AMDGPU: Flat instructions do not have signed offsets gfx7-gfx11 (#95852)Matt Arsenault
2024-06-13DAG: Replace bitwidth with type in suffix in atomic tablegen ops (#94845)Matt Arsenault
2024-05-21[AMDGPU] HasOneUse uses (#92534)jofrn
2024-03-13[AMDGPU] Fix canonicalization of truncated values. (#83054)Harald van Dijk
2024-02-20[AMDGPU][NFC] Extend PredicateControl to support True16 predicates. (#82245)Ivan Kosarev
2024-01-17[AMDGPU][GFX12] Add Atomic cond_sub_u32 (#76224)Mariusz Sikora
2024-01-02[AMDGPU] GFX12 global_atomic_ordered_add_b64 instruction and intrinsic (#76149)Jay Foad
2023-12-15[AMDGPU] CodeGen for GFX12 VFLAT, VSCRATCH and VGLOBAL instructions (#75493)Mirko BrkuĊĦanin
2023-12-13[AMDGPU] Min/max changes for GFX12 (#75214)Piotr Sobczak
2023-11-10[AMDGPU] Fix operand definitions for atomic scalar memory instructions. (#71799)Ivan Kosarev
2023-10-17[AMDGPU][AsmParser] Eliminate custom predicates for named-bit operands. (#69243)Ivan Kosarev
2023-10-11[AMDGPU] Add encoding/decoding support for non-result-returning ATOMIC_CSUB i...Stephen Thomas
2023-08-31SelectionDAG: Swap operands of atomic_storeMatt Arsenault
2023-07-11AMDGPU: Partially fix not respecting dynamic denormal modeMatt Arsenault
2023-07-05[AMDGPU][AsmParser] Simplify the implementation of SWZ operands.Ivan Kosarev
2023-06-15[AMDGPU][AsmParser][NFC] Simplify v_interp-related operand definitions.Ivan Kosarev
2023-06-14[AMDGPU][AsmParser][NFC] Get rid of custom default operand handlers.Ivan Kosarev
2023-06-05AMDGPU: Fold zext into result of v_mad_u16 on high zeroing targetsMatt Arsenault
2023-06-05[AMDGPU][AsmParser][NFC] Specify parser methods directly in operand classes.Ivan Kosarev
2023-06-05[AMDGPU][AsmParser][NFC] Immediate operand classes to derive from custom oper...Ivan Kosarev
2023-03-31Revert "[AMDGPU] Select v_sat_pk_u8_i16"pvanhout
2023-03-30[AMDGPU][AsmParser][NFC] Refine immediate operand definitions.Ivan Kosarev
2023-03-15[AMDGPU] Select v_sat_pk_u8_i16pvanhout
2023-02-28[AMDGPU][NFC] Eliminate the u32imm operand definition.Ivan Kosarev
2023-02-10[RFC][GISel] Add a way to ignore COPY instructions in InstructionSelectorPierre van Houtryve
2023-02-07[AMDGPU] Remove the unused u8imm operand definition.Ivan Kosarev
2023-01-27AMDGPU: Support atomicrmw uinc_wrap/udec_wrapMatt Arsenault
2022-12-12[AMDGPU] Make use of !listremove. NFCI.Jay Foad
2022-12-06[AMDGPU] Handle nnan and fast on the call in fpmed3 patternsJustin Bogner
2022-10-03[AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (...jeff
2022-09-25[AMDGPU] Pattern for flat atomic fadd f64 intrinsic with local addrPetar Avramovic
2022-09-23AMDGPU: Use tablegen patterns for buffer global and flat atomic faddPetar Avramovic
2022-07-08[AMDGPU] Use the HasNoUse predicate for no-ret atomic op selectionAbinav Puthan Purayil
2022-07-08[AMDGPU] Use AddedComplexity for ret and noret atomic ops selectionAbinav Puthan Purayil
generated by cgit v1.2.3 (git 2.25.1) at 2026-06-01 13:16:12 +0000