BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260730T152727Z
LOCATION:Exhibitor Forum\, Exhibit Floor
DTSTART;TZID=America/Los_Angeles:20260727T134500
DTEND;TZID=America/Los_Angeles:20260727T141500
UID:dac_DAC 2026_sess229_EF102@linklings.com
SUMMARY:CHIPAGENTS AI: Autonomous Root Cause Analysis: Agentic AI for Debu
 gging at Commercial Scale
DESCRIPTION:Zackary Glazewski and Mehir Arora (ChipAgentsAI) and Alon Shte
 pel (Senior Director, ASIC verification and emulation, Micron)\n\nOver hal
 f of frontend ASIC engineering time is spent on debugging and root cause a
 nalysis, navigating millions of lines of HDL and terabytes of waveform dat
 a. Despite this cost, hardware debugging remains almost entirely manual. T
 his presentation introduces ChipAgents RCA, the first autonomous, agentic 
 AI system for end-to-end ASIC root cause analysis using both code and wave
 form data at commercial scale.\n\nChipAgents RCA treats debugging as a str
 uctured search problem. The system combines three core innovations: (1) a 
 waveform understanding engine purpose-built for AI agents that enables sym
 bolic, query-based reasoning over massive waveform databases; (2) a novel 
 multi-agent prover-verifier architecture that explores debugging hypothese
 s in parallel while enforcing skepticism and verification; and (3) a self-
 consistency ranking layer that calibrates confidence and surfaces the most
  reliable explanations to engineers.\n\nThe system has been evaluated acro
 ss a diverse dataset of commercial-scale IPs, including bus fabrics, RISC-
 V cores, and complex protocols such as PCIe and DDR, spanning bug classes 
 like backpressure, data corruption, protocol violations, and clock-domain 
 issues. ChipAgents RCA achieves over 3x higher pass-at-one accuracy than s
 tate-of-the-art generic AI agents. In a representative PCIe 3.0 case study
  (36k lines of code, multi-level indirection), ChipAgents RCA isolated the
  exact root cause and patch in 10 minutes, compared to 4–8 hours of projec
 ted human effort, representing a 12x speedup.\n\nThis talk will present th
 e system architecture, evaluation results, and lessons learned deploying a
 utonomous debugging agents in real verification flows, highlighting how ag
 entic AI can fundamentally change how hardware teams approach debug and ve
 rification closure.\n\n
END:VEVENT
END:VCALENDAR