A torrent of data traffic is growing at an exponential rate driven by applications including 5G, AI/ML, video streaming, online gaming, ADAS and more. Handling this data traffic are hyperscale data centers that have grown to over 500 in number worldwide with a third as many in the pipeline. To scale computing resources to the growing data demands, hyperscale data centers deploy fiber optics throughout to provide the needed bandwidth and manage the power. Pluggable small form-factor optical modules have scaled the optical connections from 50G to 400G over the past two decades. With the evolution to 800G Ethernet and beyond, new architectures including co-packaged optics can enable the desired performance while keeping power consumption within the desired envelope.
The MACsec, IPsec and SSL/TLS/DTLS protocols are the primary means of securing data in motion (communicated between connected devices). These protocols can be anchored in hardware or implemented in software as part of an end-to-end security architecture. This white paper provides fundamental information on each of these protocols including their interrelationships and use cases.
Created to support 3D gaming on consoles and PCs, GDDR packs performance that makes it an ideal solution for AI/ML inferencing. As inferencing migrates from the heart of the data center to the network edge, and ultimately to a broad range of AI-powered IoT devices, GDDR memory’s combination of high bandwidth, low latency, power efficiency and suitability for high-volume applications will be increasingly important. The latest iteration of the standard, GDDR6 memory, pushes data rates to 18 gigabits per second and device bandwidths to 72 gigabytes per second.
Dedicated accelerator hardware for artificial intelligence and machine learning (AI/ML) algorithms are increasingly prevalent in data centers and endpoint devices. These accelerators handle valuable data and models, and face a growing threat landscape putting AI/ML assets at risk. Using fundamental cryptographic security techniques performed by a hardware root of trust can safeguard these assets from attack.
For end-to-end security of data and devices, data must be secured both when it as rest (stored on a connected device) and when it is in motion (communicated between connected devices). For data at rest, a hardware root of trust anchored in silicon provides that foundation upon which all device security is built. Similarly, MACsec security anchored in hardware at the foundational communication layer provides that basis of trust for data in motion.
For over 30 years, DRAM has continuously adapted to the needs of each new wave of hardware spanning PCs, game consoles, mobile phones and cloud servers. Each generation of hardware required DRAM to hit new benchmarks in bandwidth, latency, power or capacity. Looking ahead, the 2020s will be the decade of artificial intelligence/machine learning (AI/ML) touching every industry and application space. For DRAM, AI/ML represents the biggest challenge yet with a list of requirements for “all of the above.”