Traditional Cloud vs. Owned Cloud

By marketing@site-a.com

Introduction

We are now in our second decade of Cloud Computing. The promise of unlimited computing power combined with the outsourcing the care and feeding of the systems is very appealing.  These benefits, however, do not come without significant costs and risks.  Losing control of the budget, security standards, performance benchmarks and even intellectual property have given companies a reason to pause and consider why they went to the cloud in the first place.  High-performance computing and storage are the foundation and critical core ingredient for companies that need computational muscle and big-data protection. Making this infrastructure the best it can be is essential to your company’s success. At the end of the day, any enterprise positioned for growth and success is dependent upon the efficiency and speed of its computing power and the ability to store critical data securely. Let’s look two ways companies host their computer power and data storage/access: Traditional Cloud and Owned Cloud. And let’s compare both to see how much control they have.

Traditional Cloud

Traditional Cloud is the choice by companies that see value in moving away from on-premises hosting (where all equipment is company owned and maintained by their own IT department). This method relies on an outside service provider to do everything to ensure the vital data needs of your company. They procure, install and maintain all hardware, software, and other supporting infrastructure in their data centers. Companies pay for these services, and access and manage their accounts through the provider’s applications. But companies have little control of performance, security and cost.

Performance

While it’s every traditional cloud host’s intention to provide ultimate performance, their host infrastructures need to provide for multiple clients, all vying for precious processing power, bandwidth, and storage. Bandwidth in particular can be the source of problematic bottlenecks and diminished performance.

Security

Security is a major concern on two fronts: hardware infrastructure and the data itself.  Because of the mass of data hosted by a traditional provider, infrastructure and the data the resides on it must be protected at all costs. Traditional Cloud providers, in general, make sure their physical servers are environmentally protected and secure from outside intruders. The data itself, on the other hand, may not be as safe. Your precious data sits on someone else’s hardware. Providers struggle daily with security breaches to protect critical data from outside intrusion.

Cost

Once companies lock into Traditional Cloud, they are at the mercy of incremental cost increases. As infrastructure complexities grow, costs to support them can be astronomical.  The initial investment to save money starts to become less and less obvious.

 

Owned Cloud

Some companies are bucking the traditional cloud companies by moving to a new type of cloud environment called “Owned Cloud”.  This method enables companies to regain better control of performance, security and costs. This owned cloud solution involves purchasing IT infrastructure then fortifying it with a third-party provider that offers manufacturing, integration, testing, application installation, basic logistics and fine-tuning systems requirements. Instead of this system being packaged up and shipped, the infrastructure resides and is maintained by the third party. Owned Cloud offers all the benefits of the traditional cloud providers combined with the performance, security and cost controls organizations need to ensure business continuity.

Performance

Customers have better control over their infrastructure when it’s dedicated to just their needs.  They don’t need to compete with other hosted clients for precious processing power, bandwidth and storage.

Security

Security can be better maintained on a system that is not shared amongst multiple organization / individuals that need only a credit card number to gain access. Customized security and stronger encryption are allowable only if the infrastructure is dedicated to you rather than part of a behemoth environment where hackers and malicious actors prey on day to day.

Cost

The idea of having a fixed monthly expense rather than an ever-increasing credit card bill is the cost control companies need to ensure success.  Although the initial spend on hardware infrastructure may cost more upfront, companies have better visibility to what the consistent spend will be. After that, third-party services that host and maintain a company’s infrastructure can oftentimes cost much less than traditional cloud hosting. The initial investment becomes a better total-cost-of-ownership in the long run. The following table gives more comparison on the control you get with traditional cloud hosting vs. owned cloud hosting.

Traditional Cloud vs. Owned Cloud

Considerations
Traditional Cloud
 
Owned Cloud
Development and Design
Development and infrastructure design controlled by provider and out of user’s hands.
 
Full knowledge and control of incremental development and software.
Hardware
Host provides rent servers and data storage that is all hardware housed at their data centers.
 
You own servers and data storage that are designed to your specifications.
Software
Host provides and programs all software and may not support some application software
 
You can customize your own software environment because it is your own machine.
Migration
Can be difficult and costly.
 
Migration not needed. It is your own infrastructure. 
Environment
Hosting company provides secure, climate-controlled environment that host many other companies.
 
Your equipment is housed in a third party secure, climate-controlled environment to ensure date security and proper operation.
Bandwidth
Bandwidth is shared and allocated as host determines. It can be subject to slow downs based on their entire infrastructure traffic.
 
Owned Cloud data pipelines are more exclusive and can maintain optimum bandwidth better.  Bandwidth costs can be less expensive.
Infrastructure Security
Relatively secure as determined by the cloud host.
 
Security determined by user and their third-party choice.
Data Security
Your data sits on someone else’s hardware. It’s part of a much larger infrastructure that gets general service. It can be more prone to external and internal breaches – and you may not even know it. Some providers have been known to scrape client data for their own use.
 
Your data sits on your hardware and is as secure as you make it. You can use security to provide the best protection, tailored to your specific data. Data access can be much more tightly controlled. This is a huge advantage to companies that need the ultimate data protection.
Resources
Once you pick your provider, additional resources are out of your control.
 
Resources can be the right combination of third-party builder / offsite host for your hardware and your company’s IT team.
Costs
Lower cost of entry quickly becomes exorbitantly more expensive with almost no ability to control those incremental increases.  Companies are penalized for testing, development and accidentally leaving processes running.
 
Fixed monthly cost with no surprise upcharges.  Makes budgeting simple and straightforward.  Companies can use the resources as they need since it is not charged on a usage basis. No penalty for any development, testing or accidentally leaving processes running.

 

PSSC Labs and Owned Cloud Hosting

PSSC Labs architects and builds high-performance computing and storage solutions for companies requiring the fastest computational capabilities and maximum data storage. These systems go far beyond typical systems.  We have decades of experience providing high-performance computing clusters (HPCs) and storage solutions that continue to exceed requirements.  In addition to its renowned on-premises solutions, PSSC Labs is working on infrastructure designs that help provide owned cloud hosting. We work with your internal teams to architect and build your data processing and storage solutions to your exact requirements. You can purchase our high-performance systems then house and maintain them at your chosen secure, environmentally controlled offsite facility. PSSC Labs is now building its own data center to host customer cloud infrastructure offering a full vertical integration from design, development, manufacturing, integration, hosting, support, and managed services all in one roof.  This unique model provides all the benefits of traditional cloud environment and allows companies to take back control of costs, performance, and security. We will remain your partner to make sure your system provides long-term, secure operation and long-term product lifecycle.

Contact Us Today to Learn More

At PSSC Labs, we recognize every application has its distinct requirements.  Contact us today at 4sales@site-a.com / tel: 949-380-7288 to learn how our engineers can work with your third-part teams to fine-tune our HPC and storage cluster products with our CBeST Manager Software Suite and work with your third-party provider to house and maintain your data infrastructure to ensure your company’s future success.

The Dangers of Allowing The Cloud to Own Your Data

By marketing@site-a.com

When it comes to the cloud and cloud data ownership, we feel that your data should remain your own digital property.  But before explaining our viewpoint, we feel it’s important to state that our intentions behind this article are not to analyze or evaluate the political viewpoints or actions of any political party. We merely seek to analyze what many cloud service providers seem to have been denying for years.  Sadly, we’ve seen that when you host your data with a third-party, you potentially sacrifice control of your content, and at worst, your business.

We saw a potential example of this happen in early 2021 when a major cloud provider cut off hosting services for a conservative social media alternative to Twitter, amid concerns that the platform could be promoting violence in the wake of the attack on the U.S. Capitol. This move by the cloud provider appeared to follow the decisions of tech giants Apple and Google to stop distributing the social network’s mobile apps.

This news hit the technology community with force, as it appeared to raise concerns from many companies who choose to host their application with cloud service providers. Could these companies, too, potentially lose their data at the drop of a hat (or perhaps say…little recourse)? If so, would the powers of big tech stop there?

While we recognize that this is an extreme scenario, our main message here is that many companies are now beginning to see the value in maintaining full-ownership and control of their data with dedicated High Performance Computing solutions that they own. Hosting data in a privately owned server as opposed to the Cloud not only provides potentially greater reliability and reduced costs, but perhaps better security. Your data is not privy to the decisions of third parties when privately hosted.

PSSC Labs builds systems just for companies like that – companies that want to keep sole control over their own technology. Our storage servers, AI/HPC servers, and more are built with security, performance, reliability, and the lowest total cost of ownership front of mind. To learn more about our products or our work to help our clients protect their data, please contact us at 4sales@site-a.com or (949) 380-7288.

Technology Grants – PSSC Labs Can Help

By marketing@site-a.com

Over the past 25 years, PSSC Labs has helped researchers, scientists, network administrators, department heads, and others prepare grant proposals.

PSSC Labs has been working with researchers, scientists, and others prepare technology grant proposals for more than 25 years and we can help you. We can help you to prepare your grant proposal for a wide variety of grant programs, including the NSF and many other sources of HPC grant funding.

We will do everything we can to help you with the grant proposal process, including answering the following vital questions:

1.) Audience:  Who will be using the system and what are the specific needs that the system will address.  We will assist you in determining the best configuration for your needs and goals. You will save yourself headaches later on if you define the ideal HPC system during the grant-writing phase. Just imagine getting an HPC system that doesn’t meet all your needs. Or having to reissue an RFP simply because the system you described is not what you really need. Or missing out on the optimal technologies for your organization.

2.) Technology Specifications:  What are the latest HPC technologies and trends that I should consider for AI and Deep Learning. PSSC Labs works with all of the major providers of high performance computing including processors, motherboards, GPUs, and overall networking performance. PSSC Labs is knowledgeable about the latest technologies and can advise you as to the best configuration to meet your current and future needs.

3) Financial: I want to know how far my budget should go or how much I should specify in my grant proposal.  Can you give me an idea of a realistic grant request for my proposed HPC system?  While some providers will provide you with generic price lists the PSSC Labs team will discuss your specific needs and objectives and then work with you to determine what system will realistically meet your unique needs. Click here to start this process.  

4.) Grant Writing:  I need help with my grant request and knowing exactly how to communicate my High Performance Computing needs.  This is perhaps the biggest challenge when facing a grant proposal with an HPC component.  The PSSC Labs team has worked with numerous organizations that have been through this same process and we can help you create a system that effectively reaches your goals and objectives and then discuss how best to communicate this system in your grant proposal.

To start the grant process PSSC Labs team will provide a detailed quote detailing all the aspects of the HPC system including system options that we would recommend. Our quotes include all the key points you’ll need for your grant proposal including the physical details of the HPC system such as power and cooling requirements as well as hardware recommendations that will meet the stated goals of the grant proposal.

PSSC Labs is completely committed to the consultative process and will work with you to understand your unique needs and objectives and then we will work with you to determine the best HPC and HPC Cluster configuration for you. Determining the best system now will save you countless headaches in the future. Imagine not getting the system that meets all user needs. Or having to re-issue an RFP because the system you described is not, as it turns out, what you really need. Or missing out on the optimal technologies with options that will save you time, space, and budget.

To learn more about PSSC Labs and our grant assistance program please click here.

Understanding Diskless HPC Clusters

By marketing@site-a.com

Understanding “Diskless” HPC Clusters

We have manufactured a lot of HPC Clusters over more than 25+ years.  One of our key goals is to deliver a fully functioning system that meets your unique needs and that remains fully operational for as long as possible.  We understand that capital expense budgets are tight and systems may be in operation well beyond the normal three-year warranty period. In fact, we have seen many clusters that are in production for nearly ten years since the initial delivery date.  Seeing these legacy HPC clusters still in operation for nearly a decade gives us and our clients great pride in knowing that these HPC cluster platforms are some of the most reliable in the industry.

Preparing for the Unexpected

What we typically tell our clients is that any technical component with a moving part will eventually need to be replaced over time.  So what components inside of a server have moving parts?  Luckily there aren’t many.  Power supplies, fans, and hard drives are the most obvious ones.  Obviously, a system needs a power supply and fans for operation; but what about a hard drive? 

The PowerWulf HPC Clusters are configured in a very traditional manner with a Head Node and Compute Nodes networked together with a high-speed backplane.  The Head Node contains the basic operating system and HPC software tools (our toolset is called CBeST). For protection, we configure our Head Node with two hard drives configured in a RAID 1 mirror.  This is a very inexpensive way to add system protection as well as adding an easy OS upgrade path.  It is probably not possible to remove the Head Node hard drives and still have a functioning HPC Cluster.  But what about the hard drives on the Compute Nodes?  Are they really necessary?  The answer is no.  Compute Nodes really just need a small Operating System kernel that can be loaded into memory on boot.  Our latest version of CBeST Cluster Management Toolkit allows for this diskless Compute Node configuration.  Operation is very simple.  Just boot up the Head Node and then boot the Compute Nodes which will connect via PXE boot to the Head Node.  The Head Node then pushes a small OS kernel down to each Compute Node which stores the image in memory.  The great thing is that this process is seamless to the end-user.

What are the benefits and drawbacks of a “Diskless” HPC Cluster?  As we discussed the most obvious benefit is reduced support cost and downtime in the event of Compute Node disk failure.  Now no one needs to go into the data center to swap a disk and reimage that drive, configure the network settings and configure the OS.  The other benefit is regarding security.  Many government agencies we work with required “hardened” systems.  Removing the hard drives on the Compute Nodes ensures that there isn’t any data that exists on the Nodes that can be extracted by accessing and removing the hard drive. In terms of drawbacks, the only possible issue may be a slower time to boot.  Our engineers would argue that this is not really an issue with our latest version of CBeST.

All in all, removing the disks from our PowerWulf HPC Cluster should help extend the longevity even more.  Who knows maybe one day we will see our cluster reaching a 20-year lifespan!

To learn more about our PowerWulf HPC Cluster and the “Diskless” HPC Cluster email us at 4sales@site-a.com to learn more.

Understanding HPC and HPC Cluster Management

By marketing@site-a.com

Many of the most significant challenges today in diverse fields such as weather modeling, the federal government, financial services, higher education, life sciences, healthcare, manufacturing, and more are using the power of High Performance Computing (HPC) to create more optimized products and to understand the physical world around us.

Connect With Us

What is the Scope of HPC

HPC has become interwoven into many organizations’ workflows and is only expected to grow over time. With such a wide range of industries using HPC today, designing and implementing an efficient infrastructure requires knowledge of the applications that will be used as well as planning for future growth as well as finding partners that can work with you to determine the ideal solution for your organization. Many organizations may be using HPC in more than one application, which requires the HPC solution to be flexible for different computing, storage, and networking requirements. According to the industry experts at MarketWatch and other sources, the market for HPC servers, storage, middleware, applications, and service is only expected to grow exponentially year over year.

HPC System Components

HPC systems infrastructures contain several subsystems that all must work together efficiently and scale together. The main subsystems of an HPC system are:

  • Compute – This part runs the application, takes the data passed to it, and outputs an answer. Over the past two decades, most algorithms have been parallelized, where parts of a problem are run on separate computers or multiple cores. Each time the results are generated or partial results are generated, they need to be communicated with the other calculations or stored on a storage device. Modern servers contain two to four sockets (chips), each with up to 64 cores. Since each of these cores may need to store recently computed information, the demands on the storage device may increase as core counts increase. Many modern applications now take advantage of accelerators that are tightly connected with the main CPU that can accelerate certain portions of the application. Usually referred to as GPGPUs, these accelerators can speed up specific applications and can place their demands on the storage or networking infrastructure.
  • Storage – During or at the beginning of a long-running simulation, a great deal of data is required to get the simulation going. As the application runs, more data may also be required based on the algorithm. The complexity of storage solutions can quickly grow with the complexity of your application so the PSSC Labs team works with you to make sure the storage is customized to meet your unique needs. The key point is that HPC storage is a key component for the smooth and efficient running of any HPC cluster.
  • Networking – The communication between servers and storage devices should not slow down the performance of the entire system. Each core that is performing the computations may need to communicate with numerous other cores, and request information from other nodes in the process. The network needs to be designed to handle server-to-server communication as well as multiple servers concurrently communicating to the storage system.
  • Application Software – Typically, sophisticated software simulates physical processes and runs across many cores. HPC application simulators are not just complex because of the mathematics behind them, but also because highly tuned libraries are used to manage networking, work distribution, and storage processes. The HPC application software needs to be architected to keep the overall system busy to maximize the investment for an HPC infrastructure.  To learn more about HPC application software click here.
  • Orchestration – Organizing a large cluster can be challenging for network administrators.  Rarely will the entire system of a large supercomputer be dedicated to a single application. Therefore, application software is needed to allow a network engineer to allocate a certain number of servers, GPUs, network bandwidth, and storage capacities. All of these sub-systems, as well as the installation of an Operating System and the associated software on the allocated system need to be handled seamlessly and effortlessly. For applications that require rapid access to data, it is absolutely crucial to correctly set up the software for HPC storage.

What is HPC Cluster Management?

HPC Clusters are composed of components that enable applications to be executed. Therefore, the HPC cluster software will typically run across many nodes and access storage both for reading and writing data. All of this, including the communication between nodes and the storage system, needs seamless communication. According to the European Grid Infrastructure, “High Performance Computing” (HPC) requires distributed computing between many nodes to deliver efficient computational performance, which is typically described as HPC Clusters. Typically, several different types of nodes comprise an HPC Cluster. HPC cluster components will include:

  • Head Node (i.e. the login node) – Often, a head node is nothing more than a simple setup designed to act as a bridge between the cluster and an external network.
  • Compute Nodes – These nodes perform the numerical computations and will probably contain the highest clock rates available with the maximum number of cores at the given clock rate. According to Alex Lesser, a VP at PSSC Labs, “the persistent storage on these nodes may be minimal, while the DRAM memory will be high.”
  • Accelerator Nodes – Some nodes may include one or more accelerators since not all applications can take advantage of these accelerators. In addition, smaller HPC clusters, designed for a specific application may be set up where all the nodes contain an accelerator
  • Storage Nodes (i.e. storage system) – An efficient HPC cluster will need to contain a high performance, parallel file system or PFS. Parallel file systems allow all nodes to communicate with storage drives in parallel. HPC storage enables the compute nodes to operate with minimal wait times.
  • Network Fabric – In HPC clusters, typically, an Infiniband or another high performing Ethernet network switch will be used, due to the requirement of low latency and high bandwidth features.
  • Software – Cluster management software is required to control the underlying infrastructure, as well as the applications to run on the cluster. Managing the multiple I/O streams that are inherent to HPC applications requires the appropriate cluster management software for an optimal HPC cluster.  Parallel transfer of data from the large number of CPUs to the storage system (on the HPC servers or externally) is critical and must not be overlooked.

To learn more about HPC cluster management and HPC servers built for the highest possible performance and reliability including support for Intel Xeon, AMD Epyc, NVIDIA GPU, and Mellanox Infiniband click here https://pssclabs.losangeles.dev.buckupstudio.com/products/ai-hpc-servers/

Keys to Providing the Federal Government with Customized HPC and AI Solutions

By marketing@site-a.com

In order to achieve maximum performance at the lowest possible investment, the PSSC Labs team has been working with federal government agencies to develop a deeper understanding of what is important as well as their technical specifications.  This consultative approach is the key to exceeding the needs of the federal government.

Connect With Us

“Over our 20+ years working with federal agencies, we understand that a one-size-fits-all approach simply does not work. Each organization and group has a specific mission requiring specific computing and storage needs.  We work closely with the end users to ensure they receive the right platform,” said Alex Lesser, VP for PSSC Labs.

PSSC Labs is trusted as a proven HPC and AI/DL technology partner – with the Department of Defense, NASA, the National Oceanic and Atmospheric Administration (NOAA), and the National Institutes of Health (NIH). PSSC Labs is uniquely qualified to help federal agencies embrace HPC / AI technologies. We have deep expertise with federal agencies in these HPC and AI systems, which are rapidly becoming the solutions for agency computing needs.

PSSC Labs HPC / AI solutions are TAA compliant and innovative, while being cost-effective and delivered on time.

Contract Vehicles

PSSC Labs offers HPC and AI products through a variety of government contract vehicles. These widely accepted contracting vehicles expedite the purchasing process while satisfying government purchasing regulations. In addition, PSSC Labs is classified as a small, woman-owned business.

Federal Government Contract Vehicles

GSA Schedule # GS-35F-0598R
US Army Chess
CMAS (California Multiple Award Schedule)
NASA SEWP
NIH NITAAC