aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
AgeCommit message (Expand)AuthorFilesLines
2025-11-19[AMDGPU] Fixed crash in getLastMIForRegion when the region is empty. (#168653)Dhruva Chakrabarti1-9/+12
2025-11-12[AMDGPU] Avoid changing minOccupancy if unclustered schedule was not run for ...Dhruva Chakrabarti1-7/+30
2025-11-10CodeGen: Remove TRI argument from reMaterialize (#158229)Matt Arsenault1-3/+2
2025-10-16[AMDGPU] Examine instructions in pending queues during scheduling (#147653)Austin Kerbow1-17/+163
2025-10-13[AMDGPU] Add register usage debug printing the point of maximum register pres...Valery Pykhtin1-0/+31
2025-10-01[AMDGPU] Use common allUsesAvailableAt implementation [nfc] (#161418)Philip Reames1-60/+3
2025-09-24[TII] Split isTrivialReMaterializable into two versions [nfc] (#160377)Philip Reames1-4/+4
2025-08-08[AMDGPU][Scheduler] Consistent occupancy calculation during rematerialization...Lucas Ramirez1-77/+68
2025-08-01[AMDGPU][Scheduler] Delete RegionsWithMinOcc bitvector from scheduler (NFC) (...Lucas Ramirez1-27/+12
2025-08-01[MachineScheduler] Make cluster check more efficient (#150884)Ruiling, Song1-8/+14
2025-07-31[AMDGPU] Don't skip regions in getRegionLiveInMap (#151423)Jeffrey Byrnes1-9/+4
2025-07-25[AMDGPU][Scheduler] Use `AMDGPU::NoSubRegister` instead of 0 (NFC) (#150610)Lucas Ramirez1-3/+4
2025-07-25[AMDGPU][Scheduler] Fix usage of `TII.reMaterialize` (NFC) (#150259)Lucas Ramirez1-6/+2
2025-07-16[AMDGPU] NFC: Decouple getRealRegPressure from current region (#149219)Jeffrey Byrnes1-1/+2
2025-06-26[AMDGPU] Add `GCNRPTarget` to track register pressure against a target (#145...Lucas Ramirez1-197/+29
2025-06-24[AMDGPU][Scheduler] Support for rematerializing SGPRs and AGPRs (#140036)Lucas Ramirez1-74/+81
2025-06-24[AMDGPU] Replace dynamic VGPR feature with attribute (#133444)Diana Picus1-21/+39
2025-06-12Fix two instances of -Wparentheses warnings [NFC]Mikael Holmen1-2/+2
2025-06-05MachineScheduler: Improve instruction clustering (#137784)Ruiling, Song1-12/+10
2025-05-27[AMDGPU][Scheduler] Delete RescheduleRegions bitvector from scheduler (NFC) (...Lucas Ramirez1-14/+4
2025-05-13Reapply "[AMDGPU][Scheduler] Refactor ArchVGPR rematerialization during sched...Lucas Ramirez1-314/+550
2025-05-09Revert "[AMDGPU][Scheduler] Refactor ArchVGPR rematerialization during schedu...Vitaly Buka1-550/+314
2025-05-08[AMDGPU][Scheduler] Refactor ArchVGPR rematerialization during scheduling (#1...Lucas Ramirez1-314/+550
2025-04-11[AMDGPU] Teach iterative schedulers about IGLP (#134953)Jeffrey Byrnes1-9/+5
2025-03-20[Target] Use *Set::insert_range (NFC) (#132140)Kazu Hirata1-1/+1
2025-03-19[AMDGPU] Fix a crash by skipping DBG instrs at start of sched region (#131167)Emma Pilkington1-0/+2
2025-03-19[AMDGPU] Update target helpers & GCNSchedStrategy for dynamic VGPRs (#130047)Diana Picus1-0/+10
2025-03-18[AMDGCN] Allow unscheduling of bundled insnsJulian Brown1-2/+1
2025-03-04[MachineScheduler] Optional scheduling of single-MI regions (#129704)Lucas Ramirez1-0/+4
2025-02-06[AMDGPU] Allow rematerialization of instructions with virtual register uses (...Jeffrey Byrnes1-9/+136
2025-01-27[AMDGPU] Do not remat instructions with PhysReg uses (#124366)Jeffrey Byrnes1-2/+10
2025-01-23[AMDGPU] Occupancy w.r.t. workgroup size range is also a range (#123748)Lucas Ramirez1-5/+4
2025-01-11[AMDGPU] Add target hook to isGlobalMemoryObject (#112781)Austin Kerbow1-4/+8
2024-12-09[AMDGPU] Add MaxMemoryClauseSchedStrategy (#114957)Ruiling, Song1-1/+145
2024-10-09[AMDGPU] Fix expensive checkJeffrey Byrnes1-1/+1
2024-10-09[AMDGPU] Optionally Use GCNRPTrackers during scheduling (#93090)Jeffrey Byrnes1-23/+125
2024-08-13[AMDGPU] Use llvm::any_of, llvm::all_of, and llvm::none_of (NFC) (#103007)Kazu Hirata1-5/+4
2024-06-14[NFCI][AMDGPU] Try to use PressureDiff to Calculate RegPressure. (#94221)Pierre van Houtryve1-21/+108
2024-03-25[AMDGPU] Use correct VGPR threshold for flagging ExcessRP regions in unified ...Jeffrey Byrnes1-3/+8
2024-02-27[AMDGPU] Do not attempt to fallback to default mutations (#83208)Jeffrey Byrnes1-6/+4
2024-02-26[AMDGPU] Prefer lower total register usage in regions with spillingJeffrey Byrnes1-3/+3
2024-02-23[AMDGPU] Introduce iglp_opt(2): Generalized exp/mfma interleaving for select ...Jeffrey Byrnes1-3/+8
2024-01-26[AMDGPU] Fix typos. NFCDiana Picus1-1/+1
2023-12-07[AMDGPU] [IGLP]: Fix assert (#73710)Jeffrey Byrnes1-2/+4
2023-11-21[AMDGPU] NFC: Add flag to disable clustered low occupancy phase (#73025)Jeffrey Byrnes1-0/+10
2023-10-06[AMDGPU][IGLP] SingleWaveOpt: Cache DSW Counters from PreRA (#67759)Jeffrey Byrnes1-3/+3
2023-09-28[AMDGPU] Fix typo in scheduler option name (#67661)Jay Foad1-7/+6
2023-06-28[AMDGPU] NFC: Add schedule-relaxed-occupancy to relax occupancy targets for w...Jeffrey Byrnes1-1/+17
2023-06-05[AMDGPU] Make use of MachineInstr::all_defs and all_uses. NFCI.Jay Foad1-5/+4
2023-04-27[AMDGPU] Track liveins for max-ilp-sched-strategyJeffrey Byrnes1-1/+2
generated by cgit v1.2.3 (git 2.39.1) at 2026-05-20 12:34:41 +0000