David vs. Goliath: Can Small Models Win Big with Agentic AI in Hardware Design?
By Shashwat Shankar 1, Subhranshu Pandey 1, Innocent Dengkhw Mochahari 1, Bhabesh Mali 1, Animesh Basak Chowdhury 2, Sukanta Bhattacharjee 1, Chandan Karfa 1
1 Indian Institute of Technology, Guwahati, India
2 NXP USA, Inc.
Abstract
Large Language Model(LLM) inference demands massive compute and energy, making domain-specific tasks expensive and unsustainable. As foundation models keep scaling, we ask: Is bigger always better for hardware design? Our work tests this by evaluating Small Language Models coupled with a curated agentic AI framework on NVIDIA's Comprehensive Verilog Design Problems(CVDP) benchmark. Results show that agentic workflows: through task decomposition, iterative feedback, and correction - not only unlock near-LLM performance at a fraction of the cost but also create learning opportunities for agents, paving the way for efficient, adaptive solutions in complex design tasks.
Keywords: AI assisted Hardware Design, Agentic AI, Large Language Model, Small Language Model, Benchmarking
To read the full article, click here
Related Semiconductor IP
- SMC 2nm 1V8 ESD Power Clamp – Low Leakage
- TSMC 2nm 1V8 ESD Local Clamp – Low Leakage
- Zigbee Transceiver PHY
- Data Flow Architecture IP
- AMBA SPI Controller MRAM Controller
Related Articles
- Optimizing Electronics Design With AI Co-Pilots
- The role of cache in AI processor design
- New PCIe Gen6 CXL3.0 retimer: a small chip for big next-gen AI
- Scaling AI Chip Design With NoC Soft Tiling
Latest Articles
- HyNoC: A Hybrid Circuit-Switch/Wormhole Network-on-Chip for Distributed VLIW Computing on FPGA
- Hybrid ASIC-FPAA Fabric for Performance Security Trade-off
- A Centralized Performance Monitoring Architecture for Heterogeneous Multicore SoCs
- A Low-Latency ASIC Architecture for Real-Time Line Segment Detection
- BitFair: A 12nm Bit-Serial CNN Accelerator with Learnable Early Termination and Adaptive Bit Ordering for Ultra-Low-Power XR Vision