5 papers
The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution
Deepak Panigrahy, Aakash Tyagi
Agentic AI workloads - where a single user goal triggers multi-step orchestration, tool calls, retries, and failure recovery - are being targeted for edge deployment, with NVIDIA,…
Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems
Deepak Panigrahy, Aakash Tyagi
Current AI energy benchmarks measure consumption at the granularity of a single model invocation or training run. For classical single-turn workloads this unit remains coherent. Fo…
VCDiag: Classifying Erroneous Waveforms for Failure Triage Acceleration
Minh Luu, Surya Jasper, Khoi Le +4
Failure triage in design functional verification is critical but time-intensive, relying on manual specification reviews, log inspections, and waveform analyses. While machine lear…
BugGen: A Self-Correcting Multi-Agent LLM Pipeline for Realistic RTL Bug Synthesis
Surya Jasper, Minh Luu, Evan Pan +4
Hardware complexity continues to strain verification resources, motivating the adoption of machine learning (ML) methods to improve debug efficiency. However, ML-assisted debugging…
Spec2Assertion: Automatic Pre-RTL Assertion Generation using Large Language Models with Progressive Regularization
Fenghua Wu, Evan Pan, Rahul Kande +5
SystemVerilog Assertions (SVAs) play a critical role in detecting and debugging functional bugs in digital chip design. However, generating SVAs has traditionally been a manual, la…