Intensivate uses SiFive’s RISC-V to develop accelerator

101

SiFive, the provider of commercial RISC-V processor IP and silicon solutions, has announced that Intensivate is implementing SiFive Tilelink and cache technologies to provide a chip-scale fabric as part of a new, high-performance PCIe Card.

Intensivate is a provider of acceleration for clustered computing within data centres and edge deployments and its latest accelerator card is able to provides more compute on platforms such as Hadoop, Kafka, Spark, NoSQL databases and other custom applications running on clusters. These significant performance increases will enable more rapid, agile decision making while improving the efficiency of data centres and lowering TCO.

“The era of the general-purpose processor for all workloads is fading,” said Peter Rutten, IDC’s research director for its Infrastructure Systems, Platforms and Technologies Group. “Instead new processors and co-processors – or accelerators – have started to take over specific compute tasks for greater performance and efficiency.

“Our research shows that the worldwide accelerated server market, for example, will rapidly grow to $ 25.6bn by 2022. If successful, the technology that Intensivate is developing could address a large class of applications that are currently not well served by existing accelerators, expanding the opportunities for server consolidation.”

The Intensivate accelerator card focuses on compute performance improvements for the business operations software key to modern business. AI accelerators, GPUs, FPGAs, and Custom ASICs are focused on deep learning or narrow function accelerations. Intensivate is looking beyond this by addressing applications that run on clusters and imposing no specialised software requirements typically seen with accelerator technologies.

Leveraging RISC-V ISA tools, software, and industry ecosystem, Intensivate, in partnership with SiFive, has created a high performance, high-efficiency chip that consumes only 14W.

A high-speed 120Gbps chip-to-chip mesh network allows the twenty-one chips on the accelerator to support network-intensive scale-out applications. Each chip is combined with 32GB of quad-channel LP-DDR4 to feed data into the 16 Intensivate designed cores inside. Each combination of chip and memory is equivalent to a 1U server node, providing twenty-one server nodes on a single PCIe card.

The high-speed, compute-dense accelerator card offers ROI savings, with a 1000-Node Hadoop cluster said to be able to be matched in performance by just 84-Nodes when equipped with Intensivate accelerator cards, delivering over $ 1m in CapEx and power savings over a 3-year period.

“Our product development strategy is aimed at bringing a product up relatively quickly and cost effectively while tapping into the fast-growing ecosystem of RISC-V,” said Sam Sirisena, chief strategy officer and co-founder of Intensivate. “We intend to build our alliances using the RISC-V ecosystem while contributing towards it. This is a winning situation for everyone involved: our end users, channel partners and the open source community at large.”

Author
Neil Tyler

Let’s block ads! (Why?)

Read more here: New Electronics News

Get real time updates directly on you device, subscribe now.

Subscribe to our newsletter
Sign up here to get the latest news, updates and special offers delivered directly to your inbox.
You can unsubscribe at any time
You might also like

Leave A Reply

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More