Nvidia chip at centre of variety of new, high-powered servers

nvidia tesla-v100-nvlink

Chipmaker Nvidia is apparently having a very good year in terms of the adoption of its technology.

The company has released a range of graphics processing units which have found favour in a variety of markets.

Nvidia was always a favourite of the computer games development community, but in recent months it has added cryptocurrency miners to its list of clients.

The company has also become the leading chipmaker for the automotive sector, with many of the largest original equipment manufacturers building their new advanced driver assistance systems around Nvidia chips.

Almost 150 startups in the automotive sector, many of them developing driverless cars which require huge amounts of computing power, are said to be building their systems around Nvidia technologies.

Additionally, Nvidia says the world’s largest server companies are using its Tesla V100 accelerators, based on its Volta architecture, which the company says is the “world’s most advanced data center GPU”.

One of the keys to unlocking so much success in recent months and years is Nvidia’s concentration on developing chips for artificial intelligence applications.

The new Tesla V100 chip, for example, is specifically designed for things such as AI, deep learning, big data analytics, and high-performance computing, and is said to be capable of more than 120 teraflops of performance per GPU.

The company claims that a single Volta GPU offers the equivalent performance of 100 central processing units.

Nvidia says this means computing challenges that were once “impossible” can now be tackled.

Whatever the claims for it, the V100 has found its way into the servers a relatively large number of companies, including the market leaders.

They include IBM, HPE, Dell, EMC – which is part of Dell now, and SuperMicro, who are building a broad range of multi-V100 GPU systems in a variety of configurations, says Nvidia.

Ian Buck, vice president and general manager of accelerated computing at Nvidia, says: “Volta systems built by our partners will ensure that enterprises around the world can access the technology they need to accelerate their AI research and deliver powerful new AI products and services.”

The companies building V100-based systems that Nvidia highlights include:

Dell EMC – the PowerEdge R740 supporting up to three V100 GPUs for PCIe, the PowerEdge R740XD supporting up to three V100 GPUs for PCIe, and the PowerEdge C4130 supporting up to four V100 GPUs for PCIe or four V100 GPUs for NVIDIA NVLink interconnect technology in an SXM2 form factor.

HPE – HPE Apollo 6500 supporting up to eight V100 GPUs for PCIe and HPE ProLiant DL380 systems supporting up to three V100 GPUs for PCIe.

IBM – the next generation of IBM Power Systems servers based on the Power9 processor will incorporate multiple V100 GPUs and take advantage of the latest generation NVLink interconnect technology – featuring fast GPU-to-GPU interconnects and an industry-unique OpenPower CPU-to-GPU design for maximum throughput.

Supermicro – Products supporting the new Volta GPUs include a 7048GR-TR workstation for all-around high-performance GPU computing, 4028GR-TXRT, 4028GR-TRT and 4028GR-TR2 servers designed to handle the most demanding deep learning applications, and 1028GQ-TRT servers built for applications such as advanced analytics.

As well as these partners, Nvidia says some of China’s leading original equipment manufacturers – including Inspur, Lenovo and Huawei – are now using the Volta architecture for accelerated systems for hyperscale data centers.

And the companies which are building servers based on the V100 are positive about their partnership with Nvidia, and apparently have high hopes for the V100.

Brad McCredie, vice president and IBM fellow, cognitive systems development at IBM, says: “IBM’s upcoming Power9 servers will support Nvidia’s Volta GPU, and will be the only one to support the latest generation of NVLink and PCIe 4.0, which will deliver maximum throughput. With accelerators like Volta, IBM will scale deep learning performance to new heights.”

Charles Liang, president and CEO of Supermicro, says: “With our latest innovations incorporating the new Nvidia V100 PCI-E and V100 SXM2 GPUs in performance-optimized 1U and 4U architectures with next-generation NVLink, our customers can accelerate their applications and innovations to help solve the world’s most complex and challenging problems.”

Armughan Ahmad, senior vice president and general manager of hybrid cloud and ready solutions at Dell EMC, says: “We are proud of the work we do with partners like Nvidia to build PowerEdge servers ideal for compute-intensive workloads including data analytics, high-performance computing, machine learning and AI.”

Bill Mannel, vice president and general manager of high performance computing and artificial intelligence at HPE, says: “As deep learning continues to become more pervasive, technology advancements across systems and accelerators need to evolve in order to gain intelligence from large datasets faster than ever before.

“The HPE Apollo 6500 and HPE ProLiant DL380 systems combine the industry-leading GPU performance of Nvidia Tesla V100 GPU accelerators and Volta architecture with HPE unique innovations in system design and manageability to deliver unprecedented levels of performance, scale and efficiency for high performance computing and artificial intelligence applications.”