KALRAY
21.1.2021 17:47:13 CET | Business Wire | Press release
Wistron, a leader in ICT (Information and communications technology) products, and Kalray (Paris:ALKAL) (Euronext Growth Paris: ALKAL), a leading provider in new generation of processors specialized in Intelligent Data Processing from Cloud to Edge, announce the availability of FURIO1200™, a 24-Flash-Drive NVMe-oF based storage node appliance, integrating Kalray’s NVMe-oF K200™ smart storage adapter, powered by its MPPA® Coolidge™ intelligent processor, and Wistron LYMMA chassis. FURIO1200™ is a new type of hyper-fast disaggregated storage solution delivering ultra-high throughput and reliability. It is the ideal solution for Cloud Service Providers and Enterprises running applications with intensive AI and Data Analytics workloads as well as to optimize their next generation storage.
Data Centers are undergoing a very important revolution due to the explosion of usages, the surge of data to be processed and the exponential growth of the number of machines to be managed to support this growth. Storage is one major bottleneck of the increasing performance needs in Data Centers, driving the introduction of flash technology-based drives (“Solid-State Drive” or SSD) with hyper-fast communication protocols such as NVMe® and NVMe-oF™.
FURIO1200™, as an NVMe-oF all flash JBOF (“Just Bunch of Flash”) appliance, offers a breakthrough solution for the industry to massively scale up and increase performance of existing data centers. In addition, FURIO1200™ makes disaggregation a reality, by allowing compute resources to be separated from storage resources while optimizing performance of the overall system and re-use.
Eric Baissus, President and CEO of Kalray , has declared: “Together with WISTRON, one of the world’s largest manufacturers of data center servers, we are very proud of our contribution to development of the FURIO1200™ solution. We expect this solution to become a game changer in the industry .”
William Lin, President of Enterprise Business Group of Wistron Technologies, Wistron Corporation, has declared: “We are enthused about FURIO1200™ availability. There is a strong need for more efficient and scalable storage solutions in the market. It’s the perfect fit for data intensive applications such as AI, data analytics or IoT, for increasing performance of existing datacenters as well as addressing the growing markets of hyper converged infrastructure and on-premises enterprise data centers.”
Whereas most storage platforms run standard x86 processor, FURIO1200™ is powered by Kalray MPPA® Coolidge™ Intelligent Processor. The MPPA® processor has been designed to manage in parallel a huge flow of data in real time and removes the traditional bottleneck in running intensive data services such as data protection on intense workloads. This results in unique performance improvements and a reduction of the workload on the servers connected to FURIO1200™, freeing expensive resources for data center users.
FURIO1200™ will be available for Proof of Concept (PoC) first quarter of this year, and targets volume production by mid 2021, first customer trials being planned in the coming weeks.
FURIO1200™ is a 2U chassis using Gen3 PCIe fabric, featuring comprehensive chassis management with redundant and efficient power provision and is able to host 24 U.2 NVMe SSDs and multiple PCIe K200™ Coolidge™- based smart storage adapter solutions. FURIO1200™ delivers more than 12 million IOPS (Input/Output Operations per second) within a range of 20 to 50us latency and a global throughput of up to 72GB/s whilst supporting in parallel data protection services such as Erasure Coding.
FURIO1200™ integrates Kalray K200™ cards running NVMe-oF Kalray software, which has been certified by the University of New Hampshire InterOperability Laboratory (UNH-IOL), an independent testing provider of standard conformance solutions and multi-vendor interoperability.
One additional specialty of FURIO1200™ is the seamless support of the NVMe-over Fabric (“NVMe-oF”) over RDMA (“RDMA over Converged Ethernet” or RoCE) or over TCP protocol standards. This dual-persona capability brings the flexibility required in evolving data centers, minimizing investment while maximizing the return and lifetime of the FURIO1200™-based infrastructure.
In addition, the Intelligent Processors integrated into Kalray cards are fully programmable and are provided with an open SDK. This makes FURIO1200™ an evolving, customizable and future proof solution. New software releases are planned with additional features such as KVS, in-line security services offloading (e.g. SSL-TLS or IPSEC), computational storage, and AI analytics as well cluster storage support.
About Wistron
Wistron Corporation is a Fortune® Global 500™company supplying the design, manufacturing and after-sales services on various ICT (information and communication technology) products to top branded companies worldwide. Wistron’s product and service lines include PCs, server and networking systems, enterprise storage solutions, professional display products, communication devices, after-sales services, and electronics scrap recycling, as well as cloud and display vertical integration solutions. With the development of cloud computing, Wistron combines hardware devices and cloud data systems through software services to provide technical service platforms and solutions to our customers. In addition, Wistron has been dedicated to building value chain in ICT industry and innovation platforms in the new era of education and enterprise services, IOT, and medical services. For more information, please visit: www.wistron.com .
About Kalray
Kalray (Euronext Growth Paris - FR0010722819 - ALKAL) is a fabless semiconductor company, leading provider in a new generation of processors specialized in Intelligent Data Processing from Cloud to Edge. Kalray MPPA® Intelligent Processors are able to capture and analyze on the fly massive data flows, and interact in real time with the outside world. These processors are capable of running demanding AI algorithms and simultaneously a wide set of different processing and control tasks such as intensive mathematical algorithms, signal processing, network or storage software stacks. Kalray’s Intelligent Processors can be deployed in fast-growing sectors from Cloud to Edge: modern data centers, 5G telecom networks, autonomous vehicles, healthcare equipment, industry 4.0, drones and robots… Kalray’s offering includes processors, acceleration cards and a software suite, for a broad spectrum of customers such as next generation data center equipment manufacturers and service providers, system integrators and consumer product manufacturers such as car makers. Founded in 2008 as a spin-off of CEA French lab, Kalray counts among its investors: Alliance Venture (Renault-Nissan-Mitsubishi), Safran, NXP Semiconductors, CEA and Bpifrance.
Read more at: www.kalrayinc.com
View source version on businesswire.com: https://www.businesswire.com/news/home/20210121005644/en/
Link:
About Business Wire
Subscribe to releases from Business Wire
Subscribe to all the latest releases from Business Wire by registering your e-mail address below. You can unsubscribe at any time.
Latest releases from Business Wire
30 Years of Restylane®: Reshaping the Aesthetics Field Through Science-Led, Patient-Centric Innovation6.10.2026 07:00:00 CEST | Press release
Galderma celebrates the 30th anniversary of Restylane, its pioneering range of hyaluronic acid (HA) injectables that established the category as the first to market1 With three decades of innovation across technology, packaging, and treatment areas, Restylane continues to meet growing aesthetic needs, including emerging areas such as medication-driven weight loss, skin quality and menopause1-11 This year’s milestones include the approvals of Restylane Shaype™ in the European Union (EU) for enhancement of the chin region, the new state-of-the-art Restylane syringe in the EU, United States (U.S.), and Canada, and Restylane Volyme™* in the U.S. for temple hollowing, with a dual-layer patent-pending technique leveraging both needle and cannula12-18 With more than 80 clinical trials, 180 publications, around 407,000 patients evaluated for safety, and 77 million treatments administered worldwide, Restylane remains a pioneer in science-backed aesthetic innovation and continues to shape the fu
Posiflex Unveils AI-Powered SCO Series Kiosk to Accelerate the Future of Self-Service Retail6.10.2026 04:33:00 CEST | Press release
A modular, smarter self-checkout platform engineered for weighing, RFID, and loss-prevention automation across diverse retail environments Posiflex Technology, Inc., a global leader in Point of Sale (POS) systems and Online-to-Offline (O2O) solutions, proudly introduces the SCO Series Self-Service Kiosks, an AI-powered platform designed to redefine self-service retail by offering flexible system configurations that support either precise weighing-scale transactions or RFID-enabled automated checkout. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20261004628458/en/ Posiflex Unveils AI-Powered SCO Series Kiosk to Accelerate the Future of Self-Service Retail Built to address the evolving needs of both traditional fresh-goods environments and modern RFID-driven retail concepts, the SCO Series enables retailers to elevate operational accuracy, accelerate checkout processes, and future-proof store deployments through modular archit
Cities Integrating AI Into Public Services With No Common Framework for Assessing Readiness, Oxford Insights Finds6.10.2026 04:00:00 CEST | Press release
Organisation behind the Government AI Readiness Index proposes a City AI Readiness Index, based on a new study of Abu Dhabi Cities are integrating artificial intelligence into public services and operations with no shared framework for measuring or comparing how prepared they are to do so safely, effectively or accountably. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20261005281462/en/ Cover of Oxford Insights' latest report on City AI Readiness. (Graphic: AETOSWire) Existing global indices compare countries on legislation, investment and research output, but the AI efforts happening at city level – the level of government where the technology most directly shapes daily life – are not systematically captured. To start closing that gap, Oxford Insights researchers studied AI readiness across six cities. They found that all share the same core priorities, from governance and funding to talent and infrastructure, but take dist
NEG Develops “BDX-3,” a New Starveil™ Ultra-thin Cover Glass for a Wider Range of Space Environments6.10.2026 03:00:00 CEST | Press release
Nippon Electric Glass Co., Ltd. (NEG) (TOKYO: 5214) has developed “BDX-3,” a new Starveil™ ultra-thin cover glass for space applications. BDX-3 is designed to reduce radiation-induced discoloration while providing greater ultraviolet (UV) shielding performance than BDX-2. While primarily intended for low Earth orbit (LEO), it can also be used in medium Earth orbit (MEO) and high Earth orbit, making it suitable for a wider range of space environments. Samples are now available for purchase, and NEG aims to achieve commercial adoption of BDX-3 in satellites and other spaceborne equipment. About BDX-3 Satellites and other equipment operating in space are exposed to intense UV radiation and other forms of radiation. Low Earth orbit is widely used for Earth observation and communications, medium Earth orbit for positioning systems, and high Earth orbit for communications and weather observation. Cover glass used in these environments must not only protect precision equipment from harsh cond
AM Intelligence Expands NVIDIA Vera Rubin AI Factory Buildout in India and Malaysia5.10.2026 20:16:00 CEST | Press release
Two further binding orders of ~20,000 NVIDIA GPUs take AMI's committed NVIDIA Vera Rubin capacity to approximately ~29,000 GPUs and close to 100 MW, part of its global development pipeline of ~400 MW AM Intelligence (“AMI”), the AI infrastructure platform set up by Promoters of Greenko, today announced two further firm and binding orders for 20,000 NVIDIA Rubin GPUs, to be deployed as NVIDIA Vera Rubin NVL72 rack-scale systems. Building on its first AI factory in Hyderabad, the expansion is designed to give cloud providers, enterprises and AI developers access to large-scale computing capacity closer to where they build and deploy AI. These orders are in addition to the AMI's inaugural commitment announced on August 25, 2026, for 9,000 NVIDIA Rubin GPUs at its first AI Factory in Hyderabad. This follow-on capacity totalling ~70 megawatts (MW) will be deployed at Malaysia and India with delivery scheduled for Q2 2027. Taken together, the three orders bring AMI's committed frontier compu
In our pressroom you can read all our latest releases, find our press contacts, images, documents and other relevant information about us.
Visit our pressroom