Winbond Electronics Corporation has revealed that its low-power, high-performance LPDDR4X DRAM technology is supporting the latest breakthrough in edge computing from Flex Logix® for demanding AI applications such as object recognition.
The Winbond LPDDR4X chip is being paired with Flex Logix’s InferX™ X1 edge inference accelerator chip, which is based on an innovative architecture that features arrays of reconfigurable Tensor Processors. This provides higher throughput and lower latency at lower cost than existing AI edge computing products when processing complex neural networking algorithms such as YOLOv3 or Full Accuracy Winograd.
To support the InferX X1’s ultra-high speed operation - 7.5 TOPS maximum - while keeping power consumption to a minimum, Flex Logix has paired the accelerator with the W66CQ2NQUAHJ from Winbond, a 4Gb LPDDR4X DRAM which offers a maximum data rate of 4267 Mbps at a maximum clock rate of 2133 MHz. To enable use in battery-powered systems and other power-constrained applications, the W66 series device operates in active mode from 1.8-V/1.1-V power rails, and from a 0.6-V supply in quiescent mode. It offers power-saving features including partial array self-refresh.
“We chose the Flex Logix InferX X1 edge accelerator because it delivered the highest throughput per dollar, which is critical to drive volume mainstream applications,” said Robert Chang, Technology Executive of DRAM Product Marketing Center at Winbond. “The price/performance advantage of using InferX with our LPDDR4X chip has the potential to significantly expand AI applications by finally bringing inference capabilities to the mass market.”