There’s a major shift happening in server hardware, and it’s emerged from a surprising direction: the humble network card
Eric Hayes, CEO of Fungible, shares predictions for 2022.
Startup Fungible Inc. says it’s set a new world’s record for datacenter storage processing with a component that disaggregates, virtualizes, and then pools solid-state-drive (SSD) flash storage in hyperscale datacenters.
Enterprise infrastructure that supports data center, cloud and edge networks could someday be dominated by one of its tiniest components–the smartNIC or data processing unit (DPU).
Data Processing Units (DPUs) help organisations build denser, faster, more efficient and cost-effective IT infrastructures, with the goal of providing an overall lower total cost of ownership.
Op sommige momenten is het even nodig dat iemand met een frisse blik naar een probleem kijkt. De Amerikaanse startup Fungible lijkt hiervan een voorbeeld te zijn. Datacentra maken gebruik van computersystemen die draaien rond CPU’s (central processing unit) en GPU’s (graphical processing unit). Rond deze twee centrale bouwstenen worden de computers gebouwd. Fungible voegt daar nu een derde component aan toe: de DPU oftewel een data processing unit.
These semiconductor startups are offering novel ways to improve the performance, efficiency, economics and bandwidth of servers and beyond with new takes on CPUs, accelerators and connectivity solutions.
A data processing unit (DPU) is a hardware accelerator usually installed on commodity x86 servers in the form of a generic PCIe card or as part of a SmartNIC (a sophisticated network interface card). Its main function is to offload specialized compute tasks from the general-purpose system CPU, improving overall performance and efficiency of the entire infrastructure.
Fungible Inc., a pioneer in data-centric computing, and the San Diego Supercomputer Center (SDSC), a leader and pioneer in high-performance and data-intensive computing at the University of California San Diego, today announced they have shattered the NVMe over TCP storage initiator performance world record, achieving 10M IOPS.
Fungible has increased its NVMe/TCP storage-to-server bandwidth from 6.55 million to 10 million IOPS by replacing Mellanox NICS with its own Storage Initiator cards, and claimed a world record.
Fungible Inc., a data-centric computing company, and the San Diego Supercomputer Center (SDSC) at the University of California San Diego, today announced they have shattered the NVMe over TCP storage initiator performance world record, achieving 10M IOPS,* beating the old record of 6.55 IOPS.
Fungible Inc., a pioneer in data-centric computing, announced its latest channel ecosystem partner Savex Technologies, one of India’s largest Information and Communication Technology Distributors. Fungible is increasing its investment in India by building out its sales organization and further developing its design center in Bangalore.
The rapid emergence of the Compute Express Link (CXL) specification is an excellent example of heterogenous computing — but not all heterogenous computing is necessarily CXL. Rather, it’s about connecting to whatever mix of compute, memory, and storage will best tackle a given workload, without out the need to over-provision.
Fungible Inc. announced its collaboration with Savex Technologies, one of India’s largest Information and Communication Technology Distributors. Fungible is increasing its investment in India by building out its sales organization and further developing its design center in Bangalore.
welcome to another FUTRtech video podcast today we are talking with Pradeep Sindhu Founder of Fungible, a company that is making Composable infrastructure a reality.
A pioneer of the data processing unit, the team at Fungible is promoting a composable, disaggregated approach
How Fungible is Rethinking Datacenter and Server Architecture by Addressing Inefficiencies and Pioneering Solutions
Founded in 2015 by a team of tech industry veterans, Fungible is trying to revolutionize the datacenter. The company posits that the current datacenter model has reached a tipping point in which too many silos are causing significant stranded capacity.
Unlike traditional infrastructure designs, which are based on servers that have a finite quantity of local resources such CPU, GPU, RAM, network connectivity, and storage, a composable infrastructure is organized in disaggregated resource pools that can be reconfigured quickly depending on momentary application needs
Silicon Valley-based Fungible, a company aiming to revolutionize the performance, economics, reliability and security of scale-out data centers, has expanded its Fungible Storage Cluster product portfolio.
Secure disaggregation of high-performance scale-out flash storage using open standards.
Fungible Inc. is adding new capabilities and products to its Storage Cluster product portfolio.
The Storage Initiator (SI) cards allow standard servers to access NVMe/TCP storage targets using the fastest and most efficient implementation of NVMe/TCP, providing enhancements to the security and usability of the entire data platform, and make deploying NVMe/TCP effortless in existing data centers.
This is one of those interesting announcements. Fungible announced its FC200 DPU adding a dual 100GbE NVMe/TCP adapter. This announcement is helping to scale its NVMe/TCP offerings as that becomes a hotter industry topic.
300 Millionen Dollar Startgeld für ein Startup sind nicht gerade wenig. Vor allem, wenn sie schon in den Anfangsjahren eines jungen Unternehmens investiert worden sind.
Fungible, a start-up pursuing DPU accelerated data center computing, announced new capabilities enabling its Fungible Storage Initiator (SI) cards installed in standard servers to access NVMe over TCP (NVMe/TCP).
Fungible Inc., a pioneer in data-centric computing, today announced it is adding new capabilities and products to its Fungible Storage Cluster product portfolio.
Data processing unit (DPU) startup Fungible has launched a Storage Initiator card supporting NVMe/TCP and says it makes deploying NVMe/TCP effortless in existing datacentres.
Fungible today announced the availability of its Storage Initiator cards, bringing the capabilities of its data processing units (DPUs) to a standard PCIe form factor.
Learn the basics of data processing units: What they are, what they do, who’s making them and who’s adopting them. Then decide whether your data center might use one someday.
Modern cloud-native workloads are more and more being designed as microservices running on servers distributed across data center networks. This article describes what constitutes a SmartNIC while highlighting select SmartNICs from among the market-leaders.
The SmartNIC revolution is going to be a slow-burn one, with Gartner predicting there will only be $1.6 billion of sales in 2026, up from $50 million in 2020.
Fungible has appointed Eric Hayes as its new CEO and member of Fungible’s Board of Directors, succeeding Pradeep Sindhu, who has served as Executive Chairman and CEO since Fungible’s inception. Sindhu will continue his role as Executive Chairman and assume the role of Chief Development Officer, where he will lead the engineering teams responsible for the company’s products and solutions.
DPU startup Fungible recently briefed Blocks & Files on its views regarding Intel’s Infrastructure Processing Unit. Co-founder and CEO Pradeep Sindhu said it was inadequate as a data centre cost saver, lacked imagination, and couldn’t help solve the public cloud’s trillion-dollar paradox, also known as the Hotel California problem.
Pradeep Sindhu, co-founder and Exec Chairman of DPU startup Fungible, has appointed Eric Hayes to replace himself and serve as the new CEO of the company.
After six years, co-founder and Exec Chairman of DPU startup Fungible has replaced himself as CEO with Eric Hayes – a man who grew Broadcom’s switching silicon business from $100 million to more than a billion dollars a year.
Dutch high-performance computing (HPC) researchers have managed to achieve a speed of 6.55 million random read IOPS using a storage node designed by Fungible.
Dutch high-performance computing (HPC) researchers have reported a Fungible storage node delivering 6.55 million random read IOPS to a single server. Fungible claims this is the world’s highest performance between a single server reading data and a single storage target.
The Fungible Data Center enables end users to create bare-metal servers on-demand to address changing application needs. Infrastructure can operate at peak utilization and efficiency by pooling and deploying compute, storage and network resources on demand. This eliminates overprovisioning and offers flexibility for unknown workloads.
It’s time to rethink IT architecture to increase flexibility and utilization
Fungible wants to make hyperscale data centers available for any organization with its turn-key Fungible Data Center solution that is powered by its namesake data processing unit. With the recently launched data center solution, the Santa Clara, Calif.-based startup claims it can easily slice and dice compute, storage, network and GPU resources on demand while providing “performance, scale and cost efficiencies not even achievable by hyperscalers.”
The Fungible data center offers the ability to create infrastructure on the fly, pulling from CPU, GPU, and storage resources as needed. This allows for better utilization and a cloud-like model in terms of consumption. Underpinning the Fungible model is their own data processing unit (DPU), which handles most of the work. In fact, their FS1600 NVMe over TCP storage platforms have no traditional x86 CPU at all running exclusively on the DPU.
Fungible offers data-centric platforms powered by its data processing unit that disaggregates compute and storage recourses across the data center. In March, the company unveiled the Fungible Data Center, a secure offering with a centralized software suite that aims to transform data centers from complex and expensive silos into simple on-demand powerhouses.
Les entretiens : Un format court d’échanges avec une personnalité Française du monde de la Data !
Young storage companies are innovating products that range from storage arrays to mainframe storage management to cloud storage and more.
IT-Abteilungen, die in diesem Jahr die Effizienz und Performance ihrer Speichersysteme steigern wollen oder müssen, sollten diese vier wichtigsten Trends im Auge behalten.
The composable data center platform Fungible unveiled earlier this year has a number of new approaches to computing infrastructure. Its users can scale compute, storage, and network resources independently, for example.
DPUs often run on networking packets to move information in the data center, instead of supporting processing workflows. Get an overview of the technology and the main vendors.
Following on from last month’s launch of Fungible’s data centre processor, IDC has written a report forecasting the rise of composable, disaggregated systems, like Fungible’s.
Fungible wants to bring composable infrastructure to enterprise and service provider data centers with the launch today of its Fungible Data Center platform.
Fungible Inc. today launched Fungible Data Center, a turnkey composable system featuring its own software, networking technology, and DPU chips.
The networking industry has been on an evolutionary path from monolithic systems toward open, disaggregated and virtualized infrastructure. Here, we feature a deep dive discussion on the Fungible Data Center architecture with Srinidhi Varadarajan, SVP Solutions at Fungible, and Pardha Pyla, VP Product Solutions & Design at Fungible.
Fungible’s computational storage anchors a new offering for composable infrastructure. The Fungible Data Center license allows IT teams to consume resources on demand.
The chip startup’s all-in-one solution said to be one of the early signals of an upcoming wave of composable disaggregated infrastructure.
Well-funded data center startup Fungible Inc. today debuted an ambitious combination of hardware and software components that target a market that has been out of vogue recently: the corporate data center.
A look at some of the hottest chip startups and semiconductor giants in 2021 that are making big, bold moves and shaping the future of IT and beyond.
We’re talking about hyperconvergence, disaggregation, composable architecture, GPUs. We’re talking about The Next Generation Data Center all wrapped into one thing. Fungible addresses that we are reaching the cracks in the performance of IO.
Fungible seeks to revolutionize the performance, economics and security of scale-out data centers by enabling the disaggregation of compute and storage resources. The company recently launched Fungible Storage Cluster, dubbing it the world’s fastest all-flash NVMe disaggregated storage platform.
This week’s podcast episode continues the discussion on SmartNICs and DPUs with Fungible, a company that claims to have originally coined the term DPU
C’est une technologie encore méconnue, un monde foisonnant et complexe, mais qui sera surement le moteur de nos futures architectures ! Cette semaine nous vous proposons de découvrir le Computational Storage et les DPU (Data Processing Unit)…
These 10 storage startups are tackling mission-critical business data issues as they build their own momentum.
The DPU is not an entirely novel concept: the architecture evolved from the Smart Network Interface Controller (SmartNIC) that began to appear in servers several years ago. Rather than attempting to load all the functions needed for a cloud application into individual server blades, the emphasis in computer design for data centres is on scaling out.
Launching a data storage startup is always challenging, and the pandemic made it even tougher in 2020. Here are six startups that can change the way enterprises buy storage.
The Tech Tribune staff has compiled the very best tech startups in Santa Clara, California. In doing our research, we considered several factors including but not limited to: revenue potential, leadership team, brand/product traction, and competitive landscape. Additionally, all companies must be independent (unacquired), privately owned, at most 10 years old, and have received at least one round of funding in order to qualify.
Modern data centers are upending the benefits of hyperconverged infrastructure (HCI). Composable disaggregated infrastructure (CDI) is gaining traction but is not realizing its full potential due to bottlenecks in the critical path to and from the network. Fungible democratizes CDI through the invention of the Fungible DPU, realizing the holy grail of Fungible Data Centers.
Fungible’s composable storage includes FS1600 block storage server and Fungible Composer management backplane. Fungible offloads data services to its FS1 Data Processing Unit.
Powered by the Fungible Data Processing Unit (DPU), the Storage Cluster is a high performance, secure, scale-out, disaggregated data storage platform, delivering 15 million IO/s in a 2RU form factor, scaling linearly to 300 million IO/s in a single 40RU rack, and extending further to many racks.
Fungible, the chip startup that says its aim is to put smaller cloud providers on a more equal hardware footing with the likes of Amazon Web Services, has launched its first storage system for data centers, powered by its processors.
Join Fungible CEO Pradeep Sindhu and Bill Kleyman as they discuss how the new Fungible DPU is revolutionizing data centers with a 10X performance increase.
Let us take a look at the Fungible DPU-based storage cluster and the FS1600 DPU-storage node to see why this is something to get excited about.
Fungible aims to make high-performance disaggregated storage attainable for data centers of any size with the launch of the Fungible Storage Cluster, the first in a series of data-centric platforms planned by the company.
Fungible Inc. has launched an FS1600 storage appliance driven by its DPU microprocessor in the next step in its quest to achieve composable data centre domination.
The new Fungible Storage Cluster delivers 15M IOPS in a 2RU form factor, scaling linearly to 300M IOPS in a single 40RU rack, and extending further to many racks. The company says its high-performance design improves $/IOPS by at least 3x compared to existing software-defined storage solutions by consolidating workloads and increasing utilization of storage media.
The startups says its new DPU chips execute data intensive wokloads 10 times faster than CPUs and offers a threefold reduction in total cost of ownership.
In this video, Pradeep Sindhu, Co-Founder and CEO of Fungible, shares observations about scale-out data centers and the key innovations of Fungible’s Data Processing Unit (Fungible DPU™) which has been positioned as the “third socket” in data centers, complementing the CPU and GPU.
The idea of a data-centric era is a message many companies are using these days. For example, the Intel Data-Centric Innovation Summit happened on August 8, 2018 (8 is a lucky number in Chinese influenced cultures.) Pradeep’s view is of servers that are hyperdisaggregated. The view is that there are x86 compute servers, GPU servers, SSD servers, and HDD servers. In any event, these fundamental scale-out server types are designed for a common purpose: to make their most valuable resource available on the network. As that is the goal, the Fungible DPU can serve as the common endpoint.
Fungible today at Hot Chips 2020 announced a new class of microprocessor it calls the Fungible data processing unit (DPU), which won endorsements from Alibaba Cloud, Juniper Networks, and Samsung Electronics.
Optimized for data interchange and data-centric computations, delivers performance, footprint and cost efficiencies for next gen scale-out networking, storage, security and analytics platforms.
Fungible, a California composable systems startup, claims its technology will save $67 out of every $100 of data centre total cost of ownership on network, compute and storage resources. The company this week launched its first product, a data processing unit (DPU) that functions as a super-smart network interface card. Its ambitions are sky-high, namely to front-end every system resource with its DPU microprocessors, offloading security and storage functions from server CPUs.
Well-funded startup Fungible is coming out of stealth with what it calls a data processing unit along with a software stack that will power storage appliances.
Fungible launched today with two versions of its data processing unit (DPU) microprocessors: one for storage systems and one for networking servers. The vendor also developed a TrueFabric network and storage software stack. Founder and CEO Pradeep Sindhu said Fungible will deliver complete storage systems built around its DPUs and TrueFabric by the end of 2020.
Neither Ray nor Keith has met Pradeep before, but Ray was very interested in Fungible’s technology. Turns out Pradeep Sindhu, CEO and Co-founder, Fungible has had a long and varied career in the industry starting at Xerox Parc, then co-founding and becoming chief scientist at Juniper, and now reachitecting the data center with Fungible.
CPUs are being asked to do more than ever, including supporting storage-related tasks, which is why a special purpose CPU may be in your storage future.
Current metrics used to compare the performance of storage systems are inadequate. The industry needs a new storage performance metric that is fair, broadly applicable and intuitive. In this article, Dr. Menon introduces the performance efficiency percentage (PEP). It overcomes current limitations and is applicable to both scale-up and scale-out.
Fungible Inc, a US composable systems startup, wants to front-end every system resource with its DPU microprocessors, offloading security and storage functions from server CPUs.
A new type of storage system is emerging that’s being targeted at cloud data centers. They are being designed to scale out, support NVMe over TCP protocols with remote storage as fast as local storage, provide high-performance networked erasure coding, and support volumes with flexible durability.
Today’s CPUs are 30 times slower than I/O. The core problem is that servers are compute-centric while applications are becoming data-centric. Ready to liberate your data center with an architecture designed for data-centric workloads?