Anil Rao, VP & GM Systems Architecture & Engineering, Intel: Pushing the envelope with optical I/O.

Anil Rao, VP & GM Systems Architecture & Engineering, Intel: Pushing the envelope with optical I/O.
Generative AI is enabling transformative outcomes, but model complexity is growing exponentially. Traditional interconnects create a bottleneck for data, forcing GPUs to remain idle a majority of the time.
Sergey Shumarayev, Intel senior principal engineer/distinguished architect, shares how optical FPGA technology addresses socket power challenges for data-intensive applications like generative AI.
Anil Rao, VP & GM Systems Architecture & Engineering, Intel: Pushing the envelope with optical I/O.
Generative AI is enabling transformative outcomes, but model complexity is growing exponentially. Traditional interconnects create a bottleneck for data, forcing GPUs to remain idle a majority of the time.
Sergey Shumarayev, Intel senior principal engineer/distinguished architect, shares how optical FPGA technology addresses socket power challenges for data-intensive applications like generative AI.
Experience unmatched data transmission speeds. Intel’s optical FPGA integrated with Ayar Labs’ in-package optical I/O solution. See it at ERI and HOT CHIPS.
The future of interconnected military communication and the advantages of converged-aperture sensor platforms.
This webinar discusses the push toward disaggregated resources and optical interconnect technologies to enable the next generation of HPC and AI infrastructure.
Dr. Anthony J. Yu, VP, silicon photonics product management, GlobalFoundries, examines Ayar Labs’ and GlobalFoundries’ long-term partnership and optical I/O product roadmap. Dr. Yu also addresses how Ayar Labs’ optical technology unlocks the compute power necessary for data-intensive applications like artificial intelligence and machine learning.
Here’s a peek at our 4-Tbps optical I/O solution demo as well as real customer assessment data comparing the commercial state-of-the art to Ayar Labs’ in-package optical I/O solution in terms of data throughput, power consumption, and footprint.
In artificial intelligence (AI), increasingly complex algorithms, larger datasets, and process-intensive workloads lend to an insatiable demand for compute, memory, and storage, as well as higher-bandwidth, lower-latency communication between these components.