English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Despite the great success of High-Level Synthesis (HLS) tools, we observeseveral unresolved challenges: 1) the high-level abstraction of programmingstyles in HLS sometimes conceals optimization opportunities; 2) existing HLStools do not provide flexible trade-off (Pareto) solutions among differentobjectives and constraints; 3) the actual quality of the resulting RTL designsis hard to predict. To address these challenges, we propose an end-to-endframework, namelyIronMan. The primary goal is to enable a flexible andautomated design space exploration (DSE), to provide either optimal solutionsunder user-specified constraints, or various trade-offs among differentobjectives (such as different types of resources, area, and latency). Such DSEeither requires tedious manual efforts or is not achievable to attain thesegoals through existing HLS tools. There are three components in IronMan: 1)GPP, a highly accurate graph-neural-network-based performance and resourcepredictor; 2) RLMD, a reinforcement-learning-based multi-objective DSE enginethat explores the optimal resource allocation strategy, to provide Paretosolutions between different objectives; 3) CT, a code transformer to assistRLMD and GPP, which extracts the data flow graph from original HLS C/C++ andautomatically generates synthesizable code with HLS directives. Theexperimental results show that: 1) GPP achieves high prediction accuracy,reducing prediction errors of HLS tools by 10.9x in resource utilization and5.7x in timing; 2) RLMD obtains optimal or Pareto solutions that outperform thegenetic algorithm and simulated annealing by 12.7% and 12.9%, respectively; 3)IronMan is able to find optimized solutions perfectly matching various DSPconstraints, with 2.54x fewer DSPs and up to 6x shorter latency than those ofHLS tools while being up to 400x faster than the heuristic algorithms and HLStools.

IronMan: GNN-assisted Design Space Exploration in High-Level Synthesis via Reinforcement Learning