There is growing interest in some corners of the government to be more like Silicon Valley when acquiring and developing new computer systems. A recent New York Times article noted the high-level interest former Google CEO Eric Schmidt is getting to revamp America’s defense forces with more engineers, more software, and more artificial intelligence (AI).

The gist of Schmidt’s argument is that the government (and private industry for that matter) could get higher performance without proprietary restraints by applying Silicon Valley expertise when replacing and updating computer systems.

Many point to the benefits of using this approach. For more than a decade, Amazon, Facebook, and Google have built their data centers from scratch with non-proprietary solutions. They developed their own server hardware, stripping out all unnecessary features and functions. The goal has been and is to use systems that deliver the best performance per dollar.

These companies and others have taken a similar approach to software. They opted for open-source solutions or developed the software in-house. Certainly, the government and private businesses do not want to undertake expansive software development projects. Fortunately, much of the work done by these companies and others is available via open-source programs, including numerous projects from Amazon, Facebook, and Google.

In addition to traditional HPC hardware and software, Schmidt and others rightly point out how critical the adoption of AI is to improve services, retain competitive advantages, and deliver innovation. Mandates for AI start at the top with last year’s Executive Order announcing the American AI Initiative — the United States’ national strategy on artificial intelligence.

Here again, the big technology companies are opting for more cost-effective computing hardware and open-source software solutions rather than buying proprietary platforms. For example, Amazon, Facebook, and Google are building their AI solutions on the best available hardware, while also developing their own AI acceleration chips.

Why Wait?

Many high-level government initiatives will take years to develop new HPC purchasing strategies and have that reflected in purchasing mandates. That should not prevent government entities from adopting the approach on their own. This is an area where PSSC Labs can help.

We offer HPC, Big Data an AI systems using best of breed technology. Components, sub-systems, and software choices are made based on cost/performance factors, not because it is a particular vendor’s brand.

Using this approach, PSSC Labs systems are ideal for HPC applications and AI offering high performance, scalability, and lower total cost of ownership (TCO).  In additionl this prevents vendor “lock-in” which significantly increase cost while limiting growth options.

An example is our PowerWulf ZXR1+ HPC Clusters, which are application-optimized, scalable, and delivered production-ready. We’ve deployed more than 2,000 PowerWulf ZXR1+ HPC Clusters to a wide range of companies across 36 countries including many to government agencies such as NASA, US DOD, NIH, USDA, NOAA. They are used to support work in a wide range of applications, from bioinformatics to weather modeling. Systems are developed using elements selected to deliver the highest performance at cost for an organization’s specific compute requirements. Compared to a single vendor proprietary solution, the PowerWulf HPC clusters use best in breed components including:

• Intel^® and AMD^® CPUs
• Nvidia^® and AMD^® GPUs
• Intel Omnipath^® and Mellanox^® High Speed Network Interconnects
• High Performance Flash and NVME based Parallel Storage

Given the volumes of data that are now routinely analyzed in HPC and mainstream applications, storage becomes critical in any application. There also are PSSC Labs storage systems that take the same best performance for cost approach. For example, our Parallux High Performance Storage Clusters are cost-effective and highly-scalable to meet today’s HPC application storage requirements. They scale to tens of petabytes of capacity. They deliver extreme performance exceeding 20GB/sec sustained IO. And they are compatible with POSIX file systems, allowing organizations to leverage the rich POSIX ecosystem of utilities and tools.

Similar to the PowerWulf ZXR1+ HPC Clusters, Parallux High Performance Storage Clusters use best of breed elements to deliver high performance with costs in mind. The solutions are customized based on an organization’s workloads. Elements can include:

• High Performance Flash and NVME Storage Media or Traditional Spinning Hard Drives
• Intel Omnipath^® and Mellanox^® High Speed Network Interconnects
• Ceph, Gluster Parallel File Systems

All PSSC Labs solutions are tightly integrated and optimized. They are delivered as turnkey solutions with easy to use management systems.

The bottom line: Instead of waiting years for high-level mandates that dictate the use of systems that maximize performance at a lower TCO, there are options available today. As such, government departments, groups, and entities using such systems can embrace Silicon Valley methodologies and reap the benefits enabling new and better services, while being more responsive.

“What was the name of that client we worked with two years ago?” “Which folder has the files with last year’s marketing campaigns?” Such questions are typical in most businesses. Unfortunately, the constant hunt for information within organizations consumes enormous amounts of time. In fact, it is estimated that knowledge workers spend almost 20% of their time searching for and gathering information. That’s roughly 10 hours a week, or a quarter of their time in the office. 

For years, businesses have tried to make the information search process easier in one of two ways. They have either used rudimentary systems based on keyword search queries. Or, they have employed monolithic content management systems with better search capabilities, but typically exclude data stored outside of the system.

Unfortunately, these traditional enterprise search tools are not enough in today’s fast-paced, data-driven business environments. Exasperating the issue is COVID-19. It’s a good bet the time dedicated to search is even greater now with most people working from home during the pandemic. Workers have lost their in-office network where they can turn around and ask an office mate for help.

Such conditions have given rise to the need for intelligent enterprise search. Ideally, an intelligent enterprise search solution would extend search to data from all sources (applications, email, network shares, intranets, websites, databases, social media, and more). And would use artificial intelligence (AI) powered search techniques to deliver insightful information to every query.

Characteristics of Intelligent Search

What makes a search intelligent? Traditional enterprise search has always been based on entering keywords and getting a long list of results the user had to wade through. Intelligent search uses AI to help with content classification and to personalize search results based on a user’s previous searches. For instance, an AI-based intelligent search solution might analyze a person’s past queries, spot patterns, and suggest customized keywords or search terms.

Combining AI and search also allows for new and expanded search capabilities. For example, Natural Language Processing, as well as intelligence image and video analysis technology, can extend search to images, videos, audio, and multimedia content. Such functionality was never available with old-style keyword search.

Even higher-level capabilities are possible. For instance, solutions could leverage AI and machine learning techniques that enable a system to become self-learning. So, each time a user searches, results are refined and improved based on what the user considered valuable from previous searches. In this way, delivered information is personalized and optimized to meet a user’s needs.

Systems Requirements Grow

Intelligent enterprise search requires lots of processing power (supplied by high-performance CPUs and GPUS), massive amounts of storage, and superior data management capabilities. Systems also must be optimized for AI workloads.

This is an area where PSSC Labs can help. PSSC Labs has a more than 30 years history of delivering systems that meet the most demanding workloads across industries, government, and academia.

It offers a wide range of systems ideally suited for AI applications. To achieve the necessary performance, its AI deployments typically make use of GPU processing arrays. For workloads to run cost-effectively, the solutions support high data rates to keep the processors satiated. That, in turn, dictates the use of ultrafast interconnect technology and tightly coupled high-performance storage.  

The challenge for most companies is that they might have system expertise in HPC, but often not in AI. As such, there may be a skills gap that makes it hard to bring together the essential elements and fine-tune the system’s performance for critical enterprise intelligent search workloads.

To overcome such issues, many companies are looking for turnkey solutions that combine the needed processing, storage, memory, and interconnect technologies for AI into a tightly integrated system.

Delivering such a solution requires expertise and real-world best practices across both HPC and AI domains, plus deep industry knowledge about the specific data sources and search applications.

Beyond general systems for AI workloads, PSSC Labs also offers a solution specifically designed for intelligent search. The Daedalus Enterprise Search Appliance is a turnkey, high-performance computing platform powered by Elastic and certified compatible with Elastic Cloud Enterprise (ECE), which allows users to centrally manage and monitor their Elasticsearch deployments for use cases like search, observability, and security. The system includes all necessary hardware, networking, support, and software for a simple, one-step deployment.

Such solutions are increasingly important as the volumes of data companies use grows, and the need to find information quickly becomes critical to success. Get in touch with a Solutions Architect today to learn how the Daedalus Enterprise Search Appliance can simplify your business processes and streamline your work objectives. 

Improving the performance of compute workloads has always been a case of dealing with a changing landscape. The introduction of every new CPU, storage, or I/O technology boosted one aspect of performance but shifted the bottleneck to another.

Of late, most of the action has focused on increasing processing and storage performance. High-end systems now routinely use the latest generate CPUs, and many workloads are accelerated using GPUs. Storage solutions have benefited from lower-cost SSDs and innovative high-performance distributed file systems.

Now, there is a relatively new development for boosting I/O. Mellanox BlueField-2 is being integrated into high-performance computing (HPC) systems to eliminate common issues that degrade the overall performance of job execution.

The concept behind Mellanox BlueField-2 is that heavy compute and storage workloads consume valuable CPU cores for processing and steering network traffic. Such resources could be used for critical application processing. The way to reduce these demands is to handle these processing chores with an I/O Processing Unit (IPU), which brings programmable intelligence and accelerations to the network. 

Specifically, the Mellanox BlueField-2 IPU offloads critical network, security, and storage tasks from the CPU, making it ideal for addressing performance, networking efficiency, and cybersecurity concerns in a modern data- center.

Drilling Down into the Technology

Powered by industry-leading 50Gb/s PAM4 SerDes technology and PCIe Gen 4.0, BlueField-2 provides up to two ports of 25, 50, or 100Gb/s, or a single port of 200Gb/s Ethernet and InfiniBand connectivity. BlueField-2 combines the advanced capabilities of the ConnectX-6 Dx ASIC network adapter with an array of Arm processors and a high-speed memory controller, which enables enhanced and flexible software programmability.

BlueField-2 storage capabilities include NVMe-oF offload and NVMe emulation, which can be used for both the storage target and the storage client. The IPU is available as both a controller card that delivers the performance-boosting features in a PCIe standard form factor and as a software-programmable SmartNIC.

Beyond performance acceleration, one particularly useful benefit of using the SmartNic is that it can deliver isolation, hardware root-of-trust, and IPsec and TLS cryptography accelerations, allowing data center security at the end-point with best-in-class performance.

Mellanox SmartNICs and BlueField IPUs thus provide in-hardware security policy enforcement and connection tracking at full wire-speed with up to 100X performance gains compared to non-accelerated solutions – making them ideal to boost next-generation firewalls in bare-metal, virtualized, and containerized cloud environments.

Additionally, as an IPU, BlueField-2 provides in-hardware security capabilities, including agentless micro-segmentation, advanced malware detection, deep packet inspection, and application recognition, that far outperform software-only solutions.

These capabilities and features make the solution ideal for Department of Defense applications that require enhanced security extended to the edge and high performance.

Selecting the right technology solution

Integrating new technologies into HPC systems and optimizing those systems requires a great amount of time and special skill sets. Deploying such systems that deliver the requisite compute performance is a fine art. Employing such systems so that they also can support enhanced end-point security without impacting performance is even more challenging.  Many companies opt to team with a technology partner to benefit from real-world experience best practices and free their staff up for other jobs. PSSC Labs is a long-time partner with Mellanox, using its high-performance I/O solutions in the most demanding HPC applications.

PSSC Labs has a more than 30 years history of delivering systems that meet the most demanding workloads across industries, government, and academia. In particular, it has a long history working with federal agencies – from the Department of Defense and NASA to the National Oceanic and Atmospheric Administration and the National Institutes of Health. Through this experience, PSSC Labs understand the ever-increasing need for improving compute, storage, and security capabilities to meet the wide range of use cases across diverse agency missions. PSSC Labs HPC and Big Data products are available on a variety of government contract vehicles. These widely accepted contracting vehicles expedite the purchasing process while satisfying government purchasing regulations.

To learn more about I/O acceleration, visit www.site-a.com.

Our nation and world is facing the battle of a lifetime. COVID-19 has forced the shutdown of schools and business, not just in the United States but worldwide. Many businesses have been asked to implement emergency work-from-home protocols to limit and if possible, avoid exposure in the workplace. Even some of the world’s largest organizations like Google, Facebook, and Amazon are limiting exposure for their employees by implementing work-from-home policies indefinitely. 

With so many employees being asked to work-from-home, the structure of businesses and how we do business with others is changing drastically. While these adjustments can be difficult, there are a few technologies you and your team can adopt to make the transition a bit easier. 

Video Conferencing

Chances are you already have access to some kind of video conference platform, like Google Hangouts or Zoom. Using video conferencing might feel awkward or uncomfortable at first, but it can add an extra layer of communication and understanding to your meetings. Video conferencing software will also typically include screen-sharing capabilities, which most companies will find to be useful when sharing or reviewing documents, purchase orders, presentations, etc. 

Chat

Communication can feel significantly different with a work-from-home culture, especially if you’re used to communicating in-person with your team members. Chat software like Slack can significantly speed up communication processes. Even better, Slack allows for communication between individual team members, entire departments, and the entire company — or any subset of employees. Each group can have their own channel that allows for constant communication and brainstorming without disrupting other team members that are not a part of that conversation or project. 

Project Management

Not everyone is great at time or project management, and keeping your employees on track and monitoring their progress can be even more difficult when done remotely. That’s where project management tools like Trello, Asana, and Basecamp come in. Tasks related to specific projects can be assigned to team members, making it easier to quickly view progress and identify what still needs to be done as deadlines approach. 

File Sharing Applications

Web-based applications like Box and Dropbox make file and document sharing easier than ever. In fact, this is actually how PSSC Labs shares their own files whether working remotely or in-house. By moving files over to Box or Dropbox, your team is given uninterrupted access to documents, spreadsheets, presentations, and more. It’s also easier to collaborate on these docs in real time without the risk of sending edited or incorrect versions back and forth. 

As we’re all adjusting to a new normal, it’s important to note that you and your team members will need to adjust to a new workflow that works for your company and that might not look exactly as you thought. Don’t be afraid to try new things or technologies for working remotely to find what works best for your business processes — and most importantly, stay healthy!