Startup Cooks Up Software Sauce for SSDs

By Nicole Hemsoth

June 7, 2011

A small startup emerged from stealth mode today to announce software that improves the read and write performance of SSDs. Although their product won’t appear until later in the year, they claim their solution packs an order of magnitude price-performance improvement for solid-state drives (SSDs) and, for that matter, anything with a block storage interface.

According to Massachusetts-based VeloBit, which just scored an undisclosed round of Series A funding, SSDs can be simpler to deploy without the need for application or existing storage system manipulation.

CEO and founder, Duncan McCallum is no stranger to technology startups. Before he embarked on the VeloBit venture, he served as CEO for Cilk Arts, a multicore software vendor that was swept up by Intel. Before that the MIT and Harvard Business School alum spent a decade in venture capital circles working as a partner at Bessemer Venture Partners and Flagship Ventures.

McCallum’s co-founder, Qing Yang serves as CTO, bringing his 20 years of computer architecture research to bear. His focus has been on securing patents in the areas of memory and storage architectures, disk I/O systems, as well as parallel and distributed computing

McCallum claims that customers who invest in SSD technology are often already plagued with storage problems, but using SSDs still comes bundled with performance limitations. He says that customers who have made the SSD leap are left with two issues. First they have a write problem since it’s much slower to write to an SSD than to read from it. He acknowledges that this can be solved by companies with workarounds like EMC and Fusion-io but these are expensive fixes for a problem that can be handled off the SSD. According to McCallum, the software-only approach VeloBit created means there is no need for heavy investments beyond the SSDs themselves.

In addition to the write issue, McCallum claims that the complexity of using SSDs alone creates a number of challenges since customers are faced with big investments to simplify data management and protection. He says ‘if you look at a dedicated SSD system like Fusion-io, for instances, you’re changing primary storage and you’re left with data on a system that is not part of your legacy infrastructure…what you’re left with is a data island.”

There are other ways to approach these problems, including buying an SSD from one of several system vendors and put it in as a tier, but McCallum says that when you do this, you’re left with data tiering problems. This requires a thorough inventory of data to determine what data is hot and thus suitable to reside on the expensive SSD, with the rest relegated to the cheaper disk storage. Since your “hot” data can change with the times, this means you’re left moving data around accordingly, which adds complexity and cost.

To solve these problems VeloBit’s software-only approach weaves together caching and data compression. He told us that the compression is happening at line speed, creating a large cache that drives performance. The other ingredient in their software sauce is that they are able to use the SSD to expand the cache, and can thus organize the data in such a way that they can make use of the device as a read cache. McCallum says that when you put these capabilities together, it is possible to use less SSDs and on top of that, to use cheaper ones.

The best description he could give was the pyramid example. Imagine that at the top the server running the application needs to be faster. At that bottom of that pyramid is your primary storage—anything with a block interface—and in between those two is VeloBit’s solution. But here’s the catch. Sitting off to the side of that pyramid is the SSD that we use to expand the cache.

In addition to bypassing the write issue, he says that one other benefit to this approach is that in making use of cache, it doesn’t hold the primary copy of the data. Thus the primary data store remains unaltered so there are no concerns about changing how it is managed or backed up. This is what he describes as a complementary technology to SSDs versus something that will reroute how you use them.

McCallum was adamant that despite the fact that it is possible to get data management from an SSD product since the customer already handles her own caching via built-in SSD management tools, read-write manipulation and optimization, there are clear price-performance benefits.

While McCallum focused consistently on the value of their software for SSDs, he claims that this can be used with any type of block interface. When asked where the caching is done his response was clipped since he didn’t wish to give away trade secrets, but he did note that the key is that they’re running the software on the server between the application and the storage—not on top of the SSD itself. From the perspective of the application and storage though, this is all transparent. Suffice to say, McCallum is claiming that if there is a block interface, there is room for his software.

He repeated that VeloBit’s software solution aims to optimize the read and write performance with emphasis on SSD acceleration, although it can speed up a purely disk-based system as well.

One might guess that there could be potential conflicts with running a software-level optimization when there are other manipulations being made to the same storage medium. He says that since they are sitting above the storage medium this is not an issue

This might lead one to believe that this is the part where he announces that to get these price-performance increases means you need to be tied to their own supplied SSDs. His answer to this was somewhat evasive on the partnership front since he admitted that indeed, they would branch into the hardware sphere, but he was adamant that they were not a hardware vendor and were not going to be selling SSDs or other storage devices.

MaCallum couldn’t offer benchmark data to give us a sense of the kind of price-performance improvements, but said they would be publishing figures at some point. However, he says, even though we are lacking some numbers to verify these claims, in their comparisons against the industry-leading SSD and less expensive ones, the results were a combination of price and performance improvements of an order of magnitude.

This leads to the question of whether or not this is a bid to replace a Fusion-io system for example. He says that is one option but even still, if you use the VeloBit solution on top of a high-performance SSD the order of magnitude improvements on price and performance can still be realized but it makes more cost sense to simply use cheaper SSD options.

With Fusion-io, Virident, Texas Memory Systems, and Micron all boasting faster read performance McCallum claims that their VeloBit technology will still prevail. This is because they are operating a different layer, he says. “Look at a traditional storage systems; anytime you can put a cache in front of it, it goes faster—it doesn’t matter what the storage is. The other part, with any SSD, is that it will always be faster with reading than writing. If you use it for read mostly, it will simply be faster.”

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!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues 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 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…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion 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…

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