Texas Memory Systems Pushes SSD Envelope

By Michael Feldman

May 18, 2011

Enterprise SSD maker Texas Memory Systems (TMS) has been kicking up some dust lately, announcing record-breaking performance results with its RamSan-630 product and launching its latest PCIe flash offering. Specifically, TMS recently put up some rather impressive numbers in two key benchmarks established by the Storage Performance Council (SPC). And then this week, the company introduced its next-generation PCIe flash memory product, the RamSan-70, which incorporates the latest NAND technology from Toshiba.

First to the SPC results. The TMS RamSan-630, a network-attached 3U enclosure that can hold up to 10 TB of flash memory, was able to deliver a record-setting 400,503 IOPS on the SPC-1 benchmark at a price performance of $1.05/IOPS. That beat the SPC competition by a wide margin, specifically, two disk-based IBM systems that approached the TMS gear in total IOPS, but were far behind in price-performance. In the first case, a 6-node IBM System Storage SAN Volume Controller v5.1 hit 380,489 total IOPS, but at $18.83/IOPS, a far cry from the RamSan-630. The less expensive IBM Power 595 with PowerVM delivered 300,993 IOPS, but still at a cost of $10.77/IOPS.

The SPC-1 benchmark is geared for random I/O, so plays into the strength of flash memory, but it’s still a rather grueling test for SSD technology. The workload uses about 60 percent writes and is sustained for eight hours. Also, the device needs to be prefilled with data at the start. That kind of environment is not very SSD-friendly. To get a sense of that, the RamSan-630 SPC-1 result is less than half the peak performance of the 1,000,000 IOPS that TMS claims for the solution.

The SPC-2 benchmark, on the other hand, is geared for sequential I/O workloads like online transaction processing (OLTP), so one wouldn’t expect great results from an SSD setup. (In fact, the RamSan-630 is the first SSD-based system submitted for this SPC benchmark). But the TMS system managed a respectable 8.3 GB/second average over the three SPC-2 workloads: large file processing, large database query and video-on-demand.

That wasn’t as fast as the top-rated IBM System Storage DS8800 system at 9.7 GB/second, but the RamSan-630’s price-performance of $49.37 undercut the $270.38 result for the IBM system rather handily. An HP and Hitachi storage system both delivered about 8.7 GB/second, but at a price-performance of around $187 they were still considerably more expensive that the RamSan box.

According to Jamon Bowen, TMS’s director of sales engineering, the SPC-2 results point to a new use case for enterprise SSD offerings. Whereas before, flash-based systems were only seen as a way to optimize storage IOPS, Bowen says we’re now beginning to see their utility for traditional bandwidth-sensitive workloads, as found in high performance computing and other applications suffering from the data deluge.

Bowen does admit that their SSD box is still going to be about three or four times as expensive as a typical JBOD array built for low cost and MB/second-level bandwidth. But according the him, when you start needing 7 or 8 GB/second for relatively modest-sized storage systems, it’s just cheaper to go the SSD route. “You can now build high bandwidth systems out of SSDs at a lower price than you can disk systems,” he says. “You don’t get the same amount of capacity, but it’s not that far behind.”

Currently there are only a few submissions from SSD vendors to the Storage Performance Council, but at least half of the new members to the group are using flash technology. “I would not be surprised if this becomes the de facto SSD proving ground,” says Bowen.

Besides the network-attached SSD arrays like the RamSan-630, TMS also offers direct-attached flash via its enterprise-class PCIe products like the 450 GB RamSan-20. Those cards are meant to be plugged into workstations and servers for applications that can make use of very fast local storage. For cluster setups, it offers a high performance I/O without the overhead imposed by a network storage solution.

In particular, for large clusters using a shared nothing architecture, the PCIe SSD offer maximum scalability, minimum I/O latency, and the best price-performance. In HPC, these apply to Hadoop-type analytics applications and direct-attached Lustre nodes. In general, any highly parallel application that can partition data along with the computation is ideal for PCIe-based SSDs says Bowen.

This week, the TMS came out with its next-generation PCIe flash card, the RamSan-70. It incorporates Toshiba’s latest 32nm SLC NAND flash chip (which has already been incorporated into the RamSan-630). Compared to the older RamSan-20, the new card delivers about 3 times the performance (330,000 sustained IOPS), twice the usable capacity (900 GB, although a 450 GB version is available too). And because of the smaller NAND geometries, the RamSan-70 takes up half the space of its predecessor and costs about 15 to 20 percent less per GB.

Like many of the latest enterprise-class SSD devices on the market, the RamSan-70 is upping its game in flash longevity and robustness. According to TMS, at 15 percent of the device’s maximum bandwidth (18 TB/day), the RamSan-70 can be expected to last 30 years. Unlike some of its competition, however, all TMS flash management is done with in-house technology. In the case of the RamSan-70, the TMS-developed flash controller logic is implemented with an on-board Virtex-6 FPGA. Bowen says the advantage of such a setup is that the FPGA can be easily reprogrammed — relative to spinning a new ASIC — when new NAND technology is adopted or if new management features are added.

TMS intends to sell the RamSan-70 through an OEM model. In truth, the sales approach is somewhat more loosely defined. According to Bowen, they’ll deal with anyone who can commit to at least 100 cards year. As mentioned before, pricing will be 15 to 20 percent less per GB than the now obsolete 450 GB RamSan-20, which sold for around $18,000. TMS has yet not announced any OEM partners.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire