aboutsummaryrefslogtreecommitdiff
path: root/llvm/test/CodeGen/AMDGPU/fp64-atomics-gfx90a.ll
AgeCommit message (Expand)AuthorFilesLines
6 days[AMDGPU] Support f64 atomics on gfx1250 (#151172)Changpeng Fang1-0/+799
10 days[AMDGPU] Allocate AVRegClass last (#146606)Jeffrey Byrnes1-120/+120
2025-03-13AMDGPU: Replace ptr undef in tests with poison (#131050)Matt Arsenault1-12/+12
2025-02-13[AMDGPU][NFC] Replace gfx940 and gfx941 with gfx942 in llvm/test (#125711)Fabian Ritter1-583/+583
2025-01-10Revert "[MachineLICM] Use `RegisterClassInfo::getRegPressureSetLimit` (#119826)"Nikita Popov1-6/+6
2025-01-09[MachineLICM] Use `RegisterClassInfo::getRegPressureSetLimit` (#119826)Pengcheng Wang1-6/+6
2024-11-08Reapply "[AMDGPU] Still set up the two SGPRs for queue ptr even it is COV5 (#...Shilei Tian1-296/+296
2024-11-08Revert "[AMDGPU] Still set up the two SGPRs for queue ptr even it is COV5 (#1...Shilei Tian1-296/+296
2024-11-08[AMDGPU] Still set up the two SGPRs for queue ptr even it is COV5 (#112403)Shilei Tian1-296/+296
2024-10-31AMDGPU: Expand flat atomics that may access private memory (#109407)Matt Arsenault1-7/+8
2024-10-09AMDGPU: Remove flat/global fmin/fmax intrinsics (#105642)Matt Arsenault1-360/+4
2024-08-22AMDGPU: Remove global/flat atomic fadd intrinics (#97051)Matt Arsenault1-472/+72
2024-08-02AMDGPU: Handle new atomicrmw metadata for fadd case (#96760)Matt Arsenault1-166/+327
2024-07-23[AMDGPU] Codegen support for constrained multi-dword sloads (#96163)Christudasan Devadasan1-77/+77
2024-07-15Reapply "AMDGPU: Move attributor into optimization pipeline (#83131)" and fol...Matt Arsenault1-630/+372
2024-07-14Revert "AMDGPU: Move attributor into optimization pipeline (#83131)" and foll...dyung1-372/+630
2024-07-14AMDGPU: Move attributor into optimization pipeline (#83131)Matt Arsenault1-630/+372
2024-06-23AMDGPU: Remove ds atomic fadd intrinsics (#95396)Matt Arsenault1-8/+30
2024-06-18AMDGPU: Flat instructions do not have signed offsets gfx7-gfx11 (#95852)Matt Arsenault1-12/+42
2024-06-18AMDGPU: Add some addressing mode tests for flat atomic intrinsicsMatt Arsenault1-0/+228
2024-06-10[RFC][AMDGPU] Remove old llvm.amdgcn.buffer.* and tbuffer intrinsics (#93801)Jay Foad1-136/+52
2024-04-22AMDGPU: Simplify DS atomicrmw fadd handling (#89468)Matt Arsenault1-38/+14
2024-03-22[AMDGPU] Support double type in atomic optimizer. (#84307)Pravin Jagtap1-57/+213
2024-01-16[AMDGPU,test] Change llc -march= to -mtriple= (#75982)Fangrui Song1-2/+2
2023-12-15[AMDGPU][SIInsertWaitcnts] Do not add s_waitcnt when the counters are known t...Pierre van Houtryve1-38/+7
2023-11-20[MachineLICM][AArch64] Hoist COPY instructions with other uses in the loop (#...Rin1-28/+28
2023-10-30[AMDGPU] Select 64-bit imm moves if can be encoded as 32 bit operand (#70395)Stanislav Mekhanoshin1-16/+16
2023-09-25[AMDGPU] Add DAG ISel support for preloaded kernel argumentsAustin Kerbow1-26/+26
2023-06-05[AMDGPU] Add buffer intrinsics that take resources as pointersKrzysztof Drewniak1-24/+528
2023-06-02[AMDGPU] Don't flush vmcnt for loops with use/def pairsAustin Kerbow1-12/+7
2023-05-17[AMDGPU] Regenerate test checks after D149986Jay Foad1-14/+14
2023-05-05[AMDGPU] Also consider global and scratch instructions when flushing vmcnt co...Ronak Chauhan1-7/+12
2023-02-08[AMDGPU] Do not exapnd fp atomics on gfx940Stanislav Mekhanoshin1-156/+24
2023-02-08[AMDGPU] Update atomic tests. NFC.Stanislav Mekhanoshin1-0/+758
2022-12-01AMDGPU: Convert some assorted tests to opaque pointersMatt Arsenault1-103/+103
2022-09-25[AMDGPU] Pattern for flat atomic fadd f64 intrinsic with local addrPetar Avramovic1-2/+32
2021-12-01[AMDGPU] Set most sched model resource's BufferSize to oneAustin Kerbow1-35/+35
2021-11-20[AMDGPU] Do not generate ELF symbols for the local branch target labelsRamNalamothu1-22/+22
2021-10-20[AMDGPU] MachineLICM cannot hoist VALUStanislav Mekhanoshin1-3/+3
2021-09-14[AMDGPU] Switch PostRA sched to MachineSchedJoe Nash1-7/+7
2021-08-10AMDGPU: Add alloc priority to global rangesMatt Arsenault1-6/+6
2021-06-30[AMDGPU] Update gfx90a memory model supportTony Tye1-0/+16
2021-05-17[AMDGPU] Do not check denorm for LDS FP atomic with unsafe flagStanislav Mekhanoshin1-2/+50
2021-05-13[AMDGPU] Only allow global fp atomics with unsafe optionStanislav Mekhanoshin1-10/+68
2021-05-05[AMDGPU] Revise handling of preexisting waitcntAustin Kerbow1-3/+0
2021-04-08[AMDGPU] Allow -amdgpu-unsafe-fp-atomics to ignore denorm modeStanislav Mekhanoshin1-16/+4
2021-04-07[AMDGPU] Update gfx90a memory model supportTony Tye1-32/+10
2021-04-05Copy syncscope when expanding atomicrmw into cmpxchg loopStanislav Mekhanoshin1-10/+9
2021-03-10[AMDGPU] Always expand system scope fp atomics on gfx90aStanislav Mekhanoshin1-13/+258
2021-02-24AMDGPU: Remove special case in shouldCoalesceMatt Arsenault1-11/+9
generated by cgit v1.1 at 2025-08-04 14:06:22 +0000