Ultrafast CPU/GPU Kernels for Density Accumulation in Placement

Density accumulation is a widely-used primitive operation in physical design, especially for placement. Iterative invocation in the optimization flow makes it one of the runtime bottlenecks. Accelerating density accumulation is challenging due to data dependency and workload imbalance. In this paper...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	2021 58th ACM/IEEE Design Automation Conference (DAC) s. 1123 - 1128
Hlavní autoři:	Guo, Zizheng, Mai, Jing, Lin, Yibo
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	IEEE 05.12.2021
Témata:	Design automation Graphics processing units Kernel Optimization Physical design Runtime Task analysis
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Density accumulation is a widely-used primitive operation in physical design, especially for placement. Iterative invocation in the optimization flow makes it one of the runtime bottlenecks. Accelerating density accumulation is challenging due to data dependency and workload imbalance. In this paper, we propose efficient CPU/GPU kernels for density accumulation by decomposing the problem into two phases: constant-time density collection for each instance and a linear-time prefix sum. We develop CPU and GPU dedicated implementations, and demonstrate promising efficiency benefits on tasks from large-scale placement problems.
DOI:	10.1109/DAC18074.2021.9586149