Chinmay Deshpande 40d5a7d69e

[AMDGPU][UniformityAnalysis] Mark set_inactive and set_inactive_chain_arg as SourceOfDivergence (#190640) ...

`set_inactive` produces a result that varies per-lane based on the EXEC mask, even when both inputs are uniform.

2026-04-06 12:40:22 -07:00

..

deprecated

…

irreducible

[UniformityAnalysis] Jump over reducible cycles when locating join blocks (#174938)

2026-01-13 07:49:58 +05:30

MIR

[UniformityAnalysis] Replace DivergentValues with UniformValues for conservative divergence queries (#180509)

2026-03-27 12:57:17 +05:30

addrspacecast.ll

…

always_uniform.ll

[AMDGPU] Change isSingleLaneExecution to account for WWM enabling lanes even if there's only one workitem (#188316)

2026-04-06 12:51:46 -04:00

atomics.ll

AMDGPU: Drop and upgrade llvm.amdgcn.atomic.csub/cond.sub to atomicrmw (#105553)

2025-12-09 23:13:33 +00:00

b42473-r1-crash.ll

…

branch-after-join.ll

…

control-flow-intrinsics.ll

…

hidden_diverge.ll

…

hidden_loopdiverge.ll

…

inline-asm.ll

…

interp_f16.ll

…

intrinsics.ll

[AMDGPU][UniformityAnalysis] Mark set_inactive and set_inactive_chain_arg as SourceOfDivergence (#190640)

2026-04-06 12:40:22 -07:00

join-at-loop-exit.ll

…

kernel-args.ll

…

lit.local.cfg

…

llvm.amdgcn.buffer.atomic.ll

…

llvm.amdgcn.image.atomic.ll

…

no-return-blocks.ll

…

nodivergencesource.ll

…

phi_div_branch.ll

…

phi_div_loop.ll

…

phi-undef.ll

…

propagate-loop-live-out.ll

…

temporal_diverge.ll

…

trivial-join-at-loop-exit.ll

…

uniform_intrinsic.ll

[AMDGPU][Uniformity][TTI] Make Uniformity Analysis Operand-Aware via Custom Uniformity Checks (#137639)

2026-03-24 22:24:57 +05:30

unreachable-loop-block.ll

…

unstructured-branch.ll

…

workitem-intrinsics.ll

[AMDGPU] Change isSingleLaneExecution to account for WWM enabling lanes even if there's only one workitem (#188316)

2026-04-06 12:51:46 -04:00