With reports circulating last week that Samsung may build as many as 11 new chip fabs in Texas, it was easy to miss another significant piece of news the company announced last week: Samsung has developed a second generation SmartSSD that processes data directly on the SSD, drastically cutting CPU utilization, energy consumption and processing time.
Over the last two years, Samsung has worked with Xilinx and then AMD after the latter acquired the former to develop technology that minimizes the need for data transfers between the CPU, GPU and RAM. The SSD uses AMD’s Versal Adaptive system-on-a-chip technology.
As 5G, AI and machine learning capabilities move into devices and applications, transfers between storage and CPU increasingly could cause bottlenecks that would limit systems performance. Compared to conventional data center solid-state drives, Samsung said its second-generation SmartSSD can slash processing time for scan-heavy database queries by more than 50%, energy consumption by up to 70% and CPU utilization by up to 97%.
“Commercialization of the first-generation SmartSSD, in collaboration with AMD, established that the computational storage market has great potential,” said Jin-Hyeok Choi, Executive Vice President and Head of Memory Solution Product & Development at Samsung Electronics. “With the upgraded processing functionality of the second-generation SmartSSD, Samsung will be able to easily address increasing customer needs in the database and video transcoding sectors, as we expand the boundaries of the next-generation storage market.”
Sina Soltani, Corporate Vice President of Sales, AECG, Data Center and Communication Group at AMD, added, “As data-intensive applications continue to grow, second-generation Samsung SmartSSDs will deliver the superior performance and efficiency required for this expanding market.”