- Notifications
You must be signed in to change notification settings - Fork 15.3k
Pull requests: llvm/llvm-project
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Reland "[LICM] Sink unused l-invariant loads in preheader #157559" backend:AMDGPU backend:PowerPC llvm:transforms
#170204 opened Dec 1, 2025 by VigneshwarJ Loading…
Avoid maxnum(sNaN, x) optimizations / folds backend:AMDGPU backend:ARM backend:X86 llvm:analysis Includes value tracking, cost tables and constant folding llvm:globalisel llvm:instcombine Covers the InstCombine, InstSimplify and AggressiveInstCombine passes llvm:SelectionDAG SelectionDAGISel as well llvm:transforms
#170181 opened Dec 1, 2025 by LewisCrawford Loading…
[OpenCL][NVPTX] Don't set calling convention for OpenCL kernel backend:AMDGPU clang:codegen IR generation bugs: mangling, exceptions, etc. clang Clang issues not falling into any other category
#170170 opened Dec 1, 2025 by XChy Loading…
[AMDGPU] Add scheduling DAG mutation for hazard latencies backend:AMDGPU llvm:globalisel
#170075 opened Dec 1, 2025 by perlfu Loading…
[mlir][amdgpu] Add lowering for make_dma_descriptor backend:AMDGPU mlir:amdgpu mlir:gpu mlir
#169955 opened Nov 28, 2025 by amd-eochoalo Loading…
[LoadStoreVectorizer] Allow redundant stores backend:AMDGPU llvm:globalisel llvm:transforms vectorizers
#169946 opened Nov 28, 2025 by cmc-rep Loading…
AMDGPU/GlobalISel: Report RegBankLegalize errors using reportGISelFailure backend:AMDGPU
#169918 opened Nov 28, 2025 by petar-avramovic Loading…
[Codegen][NewPM] Explicitly Nest Passes in CodegenPassBuilder backend:AMDGPU backend:X86
#169867 opened Nov 28, 2025 by boomanaiden154 Loading…
[SPIRV] Use AMDGPU ABI for AMDGCN flavoured SPIRV backend:AMDGPU backend:SPIR-V clang:codegen IR generation bugs: mangling, exceptions, etc.
#169865 opened Nov 28, 2025 by AlexVlx Loading…
[mlir][AMDGPU] Add scaled wmma ops for gfx1250 backend:AMDGPU mlir:amdgpu mlir:gpu mlir
#169854 opened Nov 27, 2025 by justinrosner Loading…
[AMDGPU] Emit amdgpu.max_num_named_barrier resource symbol backend:AMDGPU
#169851 opened Nov 27, 2025 by PMylon Loading…
[mlir][amdgpu] Lower amdgpu.make_dma_base backend:AMDGPU mlir:amdgpu mlir:gpu mlir
#169817 opened Nov 27, 2025 by amd-eochoalo Loading…
[AMDGPU] Relax restrictions on amdgcn.cs.chain intrinsic backend:AMDGPU llvm:ir
#169785 opened Nov 27, 2025 by rovka Loading…
[AMDGPU][DAGCombiner][GlobalISel] Prevent FMA contraction when multiply cannot be eliminated backend:AMDGPU llvm:globalisel llvm:SelectionDAG SelectionDAGISel as well
#169735 opened Nov 26, 2025 by adelejjeh Loading…
[PHIElimination] Declare MachineLoopInfo dependency for Legacy PM backend:AMDGPU llvm:codegen llvm:regalloc
#169693 opened Nov 26, 2025 by PrasoonMishra Loading…
[AMDGPU][InsertWaitCnts] Optimize loadcnt insertion at function boundaries backend:AMDGPU llvm:globalisel
#169647 opened Nov 26, 2025 by PankajDwivedi-25 Loading…
Reland "Redesign Straight-Line Strength Reduction (SLSR) (#162930)" backend:AMDGPU backend:NVPTX llvm:transforms
#169614 opened Nov 26, 2025 by fiigii Loading…
AMDGPU/GlobalISel: Report RegBankLegalize errors using reportGISelFailure backend:AMDGPU llvm:globalisel
#169511 opened Nov 25, 2025 by petar-avramovic Loading…
[AMDGPU] Insert inliner anchor earlier backend:AMDGPU llvm:codegen
#169478 opened Nov 25, 2025 by rovka Loading…
[AMDGPU] Update machine frame info during inlining backend:AMDGPU
#169477 opened Nov 25, 2025 by rovka Loading…
[AMDGPU] Add machine-level inliner pass backend:AMDGPU testing-tools
#169476 opened Nov 25, 2025 by rovka Loading…
[AMDGPU] Reland "Remove leftover implicit operands from SI_SPILL/SI_RESTORE" backend:AMDGPU
#169449 opened Nov 25, 2025 by LU-JOHN Loading…
[AMDGPU][GISel] Add RegBankLegalize support for G_STRICT_{FADD|FMUL} backend:AMDGPU llvm:globalisel
#169406 opened Nov 24, 2025 by chinmaydd Loading…
optimize SelectionDAGISel as well
is_finite assembly backend:AArch64 backend:AMDGPU backend:PowerPC backend:RISC-V backend:X86 llvm:SelectionDAG #169402 opened Nov 24, 2025 by folkertdev Loading…
[LICM] Improve LICM when calls only change Inaccessible memory backend:AMDGPU llvm:analysis Includes value tracking, cost tables and constant folding llvm:globalisel llvm:ir llvm:transforms
#169379 opened Nov 24, 2025 by CarolineConcatto Loading…
Previous Next
ProTip! What’s not been updated in a month: updated:<2025-11-01.