Samsung previews FPGA-powered SSDs for accelerated data

At a Tech Day event in San Jose, Samsung Electronics previewed a FPGA-powered SSD featured accelerated data processing and the ability to bypass current generation server CPU limits.

Samsung's forthcoming SmartSSD leverages quad-level cell (QLC)-SSD technology and an FPGA accelerator in the SSD unit for higher processing performance, improved time-to-insight, more virtual machines (VM), scalable performance, better de-duplication and compression, lower power usage and fewer CPUs per system.


At the event, Samsung also highlighted 7nm EUV process node technology from it foundry business unit.  This promises significant improvements in power, performance and area. Initial wafer production of Samsung’s 7nm LPP (Low Power Plus) EUV process node is expected to deliver a respective maximum of 40-percent area reduction, 50-percent dynamic power reduction and 20-percent performance increase over 10nm processes. EUV uses 13.5nm wavelength light to expose silicon wafers as opposed to conventional argon fluoride (ArF) immersion technologies that are only able to achieve 193nm wavelengths and require expensive multi-patterning mask sets.

Samsung said the advancement of its 7LPP process also puts it forward  on a direct path forward to 3nm.

“With the introduction of its EUV process node, Samsung has led a quiet revolution in the semiconductor industry,” said Charlie Bae, executive vice president of foundry sales and marketing team at Samsung Electronics. “This fundamental shift in how wafers are manufactured gives our customers the opportunity to significantly improve their products’ time to market with superior throughput, reduced layers, and better yields. We’re confident that 7LPP will be an optimal choice not only for mobile and HPC, but also for a wide range of cutting-edge applications.”
Samsung also previewed a 256-gigabyte (GB) 3DS (3-dimensional stacking) RDIMM (registered dual in-line memory module), based on 10nm-class 16-gigabit (Gb) DDR4 DRAM.  This will double current maximum DRAM capacity to deliver higher performance and lower power consumption.