Alexis Bjorlin
A5016973085- Stochastic Gradient Optimization Techniques
- Parallel Computing and Optimization Techniques
- Photonic and Optical Devices
- Optical Network Technologies
- Image and Video Quality Assessment
- Low-power high-performance VLSI design
- Video Coding and Compression Technologies
- Advanced Data Compression Techniques
- Neural Networks and Reservoir Computing
Meta (United States)
2023
Broadcom (United States)
2021
Silicon photonics is advancing rapidly in performance and capability with multiple fabrication facilities foundries having advanced passive active devices, including modulators, photodetectors, lasers. Integration of electronics has been key to increasing the speed aggregate bandwidth silicon based assemblies, approaches achieving transceivers capacities 1.6 Tbps higher. Progress rapid as well, state-of-the-art chips switches many tens billions transistors. However, electronic system often...
Meta has traditionally relied on using CPU-based servers for running inference workloads, specifically Deep Learning Recommendation Models (DLRM), but the increasing compute and memory requirements of these models have pushed company towards specialized solutions such as GPUs or other hardware accelerators. This paper describes company's effort in constructing its first silicon designed recommendation systems; it accelerator architecture platform design, software stack enabling optimizing...
Videos uploaded to Meta's Family-of-Apps are transcoded into multiple bitstreams of various codec formats, resolutions and quality provide the best video across wide variety devices connection bandwidth constraints. On Facebook alone, there more than 4 billion views per day address processing at this scale, we needed a solution that can deliver possible, with shortest amount encoding time — all while being energy efficient, programmable, scalable. In paper, present, Meta Scalable Video...