Replacing GNU OpenMP's lock-based task queue and centralized barrier with lockless structures yields up to 1522.8x speedups on fine-grained task benchmarks, plus NUMA-aware load balancing.
Welcome to the documentation of OpenMP in LLVM! — LLVM/OpenMP 20.0.0git documentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Optimizing Fine-Grained Parallelism Through Dynamic Load Balancing on Multi-Socket Many-Core Systems
Replacing GNU OpenMP's lock-based task queue and centralized barrier with lockless structures yields up to 1522.8x speedups on fine-grained task benchmarks, plus NUMA-aware load balancing.