cavium, inc., a leading provider of semiconductor products that enable secure and intelligent processing for enterprise, data center, wired and wireless networking, announced that it is collaborating with hewlett packard enterprise (hpe), to bring hyperscale-inspired designs based on open compute project into mainstream enterprise it.
the introduction of cavium fastlinq® 41000 series 10/25gbe nics in ocp 2.0 form factor for hpe's cloudline servers and broad collaboration on driving the emerging ocp nic 3.0 standard will enable mainstream delivery of the most efficient designs for scalable computing to cavium and hpe's enterprise and cloud service provider customers.
tier-1 hyperscale buyers define leading-edge operational efficiency and have the skill set along with the purchasing power to request or design custom and semi-custom hardware, which enables operational cost savings and performance benefits to enable their businesses to run more efficiently. enterprise it organizations and cloud service providers outside the hyperscale category often lack the scale and skill set for custom hardware design but are increasingly under more pressure to improve efficiency and provide competitive differentiation for their business.
as a result, minimizing capital expenses and operating expenses is a key priority for enterprise it as they seek disruptive innovations or new business models to achieve their goals. these organizations are closely tracking hyperscale buyers' actions and are looking for ways to leverage hyperscale best practices in their own it environments.
to optimize visibility, improve efficiencies, and achieve collaborative design opportunities with the enterprise datacenter supply chain, cio and ctos are demanding technologies that are considered "open."
one such "open" technology that brings efficient designs for scalable computing is open compute project (ocp), initiated by facebook and now a truly open and collaborative community spanning hyperscale, enterprise and cloud service providers. with the aim to facilitate the open development of compute, storage and network hardware – together with trusted project validation - the ocp standard has the potential to minimize capex and opex by bringing the economies of scale within reach of enterprise it.
the ocp nic standard, now in its third generation (ocp nic 3.0) proposes to further enhance server networking i/o options with expanded provisions for thermal footprints, pcie gen 4 and smartnics while reducing overall downtime by simplifying nic installation and removal.
cavium and hpe were both quick to recognize the value that the ocp standard can bring to customers and have been committed to ocp's vision since its inception. hpe cloudline uses standardized and custom servers that leverage ocp mezzanine adapters, such as the cavium fastlinq 41000 series 10/25gbe nics.
currently available from hpe in ocp 2.0 form factors, cavium fastlinq adapters enable easier adaptability, scalability, and integration with support for key features such as network virtualization offload and universal rdma.
further extending their leadership in ocp, cavium and hpe are collaborating to jointly drive, evangelize and embrace the open compute project nic 3.0 standard across the server and networking community worldwide.
"cavium has a decade-old relationship with hewlett packard enterprise (hpe) and provides differentiated i/o technology for hpe servers, storage and networking," said rajneesh gaur, vice president and general manager of ethernet adapter group, cavium.
"as technology pioneers and innovators of open standards, i am proud to announce that cavium and hpe are aligning their strategy and investments to enable enterprise and cloud it to leverage the economics of scale by driving the ocp nic 3.0 standard."
"hpe is committed to decreasing data center tco while improving performance and availability by enabling an open infrastructure," said kara long, vice president and general manager for cloudline portfolio at hpe.
"with the introduction of cavium fastlinq ocp 2.0 nics in cloudline servers and collaboration with cavium on the ocp nic 3.0 standard development, joint customers will have the ability to transform their infrastructure for modern workloads and cloud initiatives while optimizing infrastructure costs."
purpose-built to accelerate and simplify data center networking, cavium fastlinq ethernet ocp nic technology in hpe cloudline servers delivers:
- universal rdma – industry's only network adapter that offers customers a choice of rdma technology and investment protection with concurrent support for roce, rocev2 and iwarp.
- network virtualization offloads – acceleration for network virtualization by offloading protocol processing for vxlan, nvgre, gre and geneve, enabling customers to build and scale virtualized networks without impacting network performance.
- server virtualization – optimizes infrastructure costs and increases virtual machine density by leveraging built-in technologies like sr-iov and nic partitioning (npar) that deliver acceleration and qos for workloads and infrastructure traffic.
- network function virtualization (nfv) – enables telcos and nfv application vendors to seamlessly deploy, manage and accelerate the most demanding nfv workloads by delivering leading small packet performance and integration with dpdk and openstack.
for more information, visit and www.cavium.com and www.cavium.com/hpe.