aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
AgeCommit message (Expand)AuthorFilesLines
2025-11-25[AMDGPU] Remove isKernelLDS, add isKernel(const Function &). NFC. (#167300)Jay Foad1-1/+1
2025-11-14[AMDGPU] Make use of getFunction and getMF. NFC. (#167872)Jay Foad1-1/+1
2025-09-17[AMDGPU][CodeGen][True16] Track waitcnt as vgpr32 instead of vgpr16 for D16 I...Brox Chen1-0/+4
2025-08-29[AMDGPU] Mark workitem IDs uniform in more cases (#152581)Krzysztof Drewniak1-8/+28
2025-08-27[AMDGPU][Attributor] Remove final update of waves-per-eu after the attributor...Shilei Tian1-5/+0
2025-08-25[NFC][AMDGPU] Remove redundant code in `AMDGPUSubtarget::getWavesPerEU` (#155...Shilei Tian1-8/+5
2025-05-22[AMDGPU] Fix computation of waves/EU maximum (#140921)Lucas Ramirez1-8/+8
2025-05-17[AMDGPU][Attributor] Rework update of `AAAMDWavesPerEU` (#123995)Shilei Tian1-0/+9
2025-05-01[AMDGPU] Max. WG size-induced occupancy limits max. waves/EU (#137807)Lucas Ramirez1-28/+35
2025-03-14[NFC][AMDGPU] Replace direct arch comparison with `isAMDGCN()` (#131357)Shilei Tian1-2/+2
2025-01-23[AMDGPU] Occupancy w.r.t. workgroup size range is also a range (#123748)Lucas Ramirez1-44/+79
2024-12-09AMDGPU: Mark grid size loads with range metadata (#113019)Matt Arsenault1-0/+1
2024-11-13[AMDGPU] Remove unused includes (NFC) (#116154)Kazu Hirata1-3/+0
2024-11-05AMDGPU: Treat uint32_max as the default value for amdgpu-max-num-workgroups (...Matt Arsenault1-1/+2
2024-10-06[AMDGPU] Support preloading hidden kernel arguments (#98861)Austin Kerbow1-0/+3
2024-10-03[AMDGPU] Qualify auto. NFC. (#110878)Jay Foad1-1/+1
2024-08-21[AMDGPU] Split GCNSubtarget into its own file. NFC. (#105525)Jay Foad1-761/+0
2024-07-17[AMDGPU] clang-tidy: no else after return etc. NFC. (#99298)Jay Foad1-4/+3
2024-07-17[AMDGPU] clang-tidy: use std::make_unique. NFC.Jay Foad1-5/+7
2024-07-16[AMDGPU] clang-format: pass Triple by value and std::move it. NFC.Jay Foad1-1/+1
2024-07-16[AMDGPU] Remove wavefrontsize feature from GFX10+ (#98400)Stanislav Mekhanoshin1-0/+8
2024-07-10[AMDGPU] Remove unneed static_cast from GCNSubtarget constructor. NFCCraig Topper1-2/+1
2024-06-28[IR] Add getDataLayout() helpers to Function and GlobalValue (#96919)Nikita Popov1-1/+1
2024-06-25AMDGPU: Add plumbing for private segment size argument (#96445)Nicolai Hähnle1-0/+3
2024-06-09[AMDGPU] Swap range metadata to attribute for workitem id. (#94871)Andreas Jonson1-4/+10
2024-05-09MCExpr-ify SIProgramInfo (#88257)Janek van Oirschot1-23/+2
2024-05-09RFC: [AMDGPU] Check subtarget features for consistency (#86957)Jay Foad1-0/+10
2024-04-12[AArch64] Improve scheduling latency into Bundles (#86310)David Green1-2/+3
2024-04-09[AMDGPU] Fix implicit $vcc operands after parsing MIR (#87781)Jay Foad1-0/+11
2024-03-12[AMDGPU] Adding the amdgpu_num_work_groups function attribute (#79035)Jun Wang1-1/+6
2024-01-21[AMDGPU] Add an asm directive to track code_object_version (#76267)Emma Pilkington1-1/+1
2023-12-12[AMDGPU] Update VOP instructions for GFX12 (#74853)Mariusz Sikora1-0/+4
2023-12-04[AMDGPU][MC] Add GFX12 VIMAGE and VSAMPLE encodings (#74062)Mirko Brkušanin1-0/+3
2023-09-25[AMDGPU] Add DAG ISel support for preloaded kernel argumentsAustin Kerbow1-12/+18
2023-09-22[AMDGPU] Have a subtarget feature to control use of real True16 instructions.Ivan Kosarev1-0/+4
2023-09-13[AMDGPU] Remove constexpr from getNumUserSGPRForField/getMaxNumPreloadedSGPRs...Simon Pilgrim1-1/+1
2023-09-12[AMDGPU] Add utilities to track number of user SGPRs. NFC.Austin Kerbow1-15/+88
2023-06-28AMDGPU: Special case uniformity info for single lane workgroupsMatt Arsenault1-0/+9
2023-06-16AMDGPU: Propagate amdgpu-waves-per-eu with attributorMatt Arsenault1-6/+14
2023-06-09[AMDGPU] Port no-hsa-graphic-shaders.ll to code object V4pvanhout1-0/+4
2023-06-07AMDGPU: Add MF independent version of getImplicitParameterOffsetMatt Arsenault1-1/+1
2023-02-10AMDGPU: Use module flag to get code object version at IR level folow-upChangpeng Fang1-1/+2
2023-02-02AMDGPU: Use module flag to get code object version at IR levelChangpeng Fang1-1/+2
2023-01-23AMDGPU: Clean up LDS-related occupancy calculationsNicolai Hähnle1-12/+31
2023-01-23AMDGPU: Add AMDGPUSubtarget::getEUsPerCU()Nicolai Hähnle1-0/+1
2022-12-14Attributes: Add function getter to parse integer string attributesMatt Arsenault1-6/+8
2022-12-14[AMDGPU] Stop using make_pair and make_tuple. NFC.Jay Foad1-2/+2
2022-12-06[AMDGPU] Fix GCNSubtarget::getMinNumVGPRs, add unit test to check consistency...Valery Pykhtin1-7/+2
2022-12-02[Target] Use std::nullopt instead of None (NFC)Kazu Hirata1-1/+1
2022-09-28[AMDGPU] Add MIMG NSA threshold configuration attributeCarl Ritson1-0/+15
generated by cgit v1.2.3 (git 2.39.1) at 2026-05-20 09:01:51 +0000