معرفی
Peter Milder is an Associate Professor in the Department of Electrical and Computer Engineering at Stony Brook University. His research focuses on hardware acceleration, FPGA-based systems, and domain-specific compilers for applications in machine learning, signal processing, and networking. He leads projects on automatic hardware generation tools like Argus for CNNs and FFT Gen for signal processing transforms.
Education details are not explicitly provided in the text, but his work spans multiple interdisciplinary areas including formal verification (e.g., model checking on FPGAs), wireless edge computing (OPSEL protocol), and high-performance sorting algorithms. He has advised numerous PhD students and collaborates with researchers across academia and industry.
Research Highlights:
- Developed voltage-scaling techniques for DNN accelerators.
- Created Waverunner, an FPGA-accelerated state machine replication system.
- Organized IEEE Transactions special issues and NSF-funded projects on edge computing and machine learning hardware.
Awards:
- ACM TODAES Best Paper Award (2014).
- NSF grants for sparse transformer acceleration and FPGA-based spectrum sensing.
Grants & Funding:
- NSF XPS Program (2015): Cloud FPGA deep learning.
- NSF ECCS (2020): Sparsity-aware NLP hardware.
Lab/Collaborations: Collaborates with Professors Michael Ferdman, Fan Ye, and others on FPGA, edge computing, and embedded systems. His work often bridges hardware design with software frameworks.
