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:20260730T152639Z
LOCATION:DAC Pavilion\, Exhibit Floor
DTSTART;TZID=America/Los_Angeles:20260728T170000
DTEND;TZID=America/Los_Angeles:20260728T180000
UID:dac_DAC 2026_sess295_ENGPRES422@linklings.com
SUMMARY:BIMEM-RAG: Reinforced Dual Memory Retrieval with Bidirectional Rea
 soning for RTL Synthesis and Summarization
DESCRIPTION:Prashanth Vijayaraghavan, Luyao Shi, Apoorva Nitsure, David Be
 ymer, Ehsan Degan, and Vandana Mukherjee (IBM Research)\n\nAutomating Regi
 ster-Transfer Level (RTL) code generation and summarization is critical fo
 r improving hardware design productivity and reducing time-to-market. Howe
 ver, existing approaches struggle due to limited Verilog and VHDL training
  data and the structural concurrency inherent in hardware description lang
 uages (HDLs). We propose BiMem-RAG, a dual-memory retrieval and bidirectio
 nal reasoning framework for HDL synthesis and documentation. BiMem-RAG com
 bines (i) an exemplar memory of specification-to-code and code-to-summary 
 pairs indexed using joint code and abstract syntax tree embeddings, and (i
 i) an analogical memory capturing reusable hardware design patterns such a
 s sequential and combinational logic. The system employs modular decomposi
 tion, reinforcement-guided retrieval, and backward verification to improve
  semantic fidelity and reduce hallucinations. Experiments on Verilog and V
 HDL benchmarks demonstrate up to 19 percentage-point improvements in Pass@
 1 and 9-point gains in ROUGE-L over strong baselines. These results show t
 hat structured retrieval and verification significantly improve RTL genera
 tion and summarization, enabling more reliable hardware design automation.
 \n\nTopics: AI, Chiplet, Design, EDA, Quantum, Security, Systems\n\n
END:VEVENT
END:VCALENDAR
