Scale-out I/O Solutions in a PCIe Gen5 World

February 21, 2023 1 Comment

Scale-out I/O Solutions in a PCIe Gen5 World

By Jeff Sigua, Product Manager

As the world is on the brink of a tech refresh, scale-out solutions will get a significant boost in both TDP and PCIe transfer speeds. Our CPUs jump from 250w up to 400w in Gen5. Our PCIe lane architecture increases from ~32 GB/s to ~64 GB/s - in each direction. The extra watts will push the boundary of I/O solutions and speeds. Scale out I/O is expanding capacity of new hardware resources instead of increased capacity of old hardware. 

Over the past two decades, One Stop Systems has been specializing in cable PCIe expansion using passive PCB routing expertise, or switch architecture, to drive the tech roadmaps into the future. Recently, we have developed PCIe5 Host Interface Boards (HIB) to work up to 2 meters over copper cables and connecting to the latest Gen5 PCIe expansion backplanes or rack mount enclosures. 

As next Gen motherboards become available, it seems the common theme among them is fewer native x16 PCIe5 slots coming from the CPU chips. Those extra PCIe5 lanes from the CPU have been routed to internal network or storage options built into the PCIe5 motherboards and connectors. This highlights the importance of using PCIe5 over cable, to allow for more scaled-out array of I/O cards, such as NVIDIA’s H100 GPU and other high data capture card options in development from multiple third-party companies. At the hub of the scale-out will be One Stop Systems' new Gen5 Short Depth Server (SDS). This server appliance can host up to 16x NVMe U.2 storage with removeable drive canister feature + GPU node + PCIe5 cable expansion to our sister product, the 4U Pro or our Centauri storage expansion solution.

Scale-out Solutions

We’re seeing full scale-out I/O rack deployments running off One Stop Systems' SDS or EOS server. The SDS or EOS can handle up to 128 end point devices, with the help of custom motherboard BIOS optimized for PCIe enumeration. As we move into PCIe Gen5, the rate of the sensor and data ingestion doubles in speeds talking back to the host server to the scaled out I/O devices. These speeds become a critical path with AI on the Edge and/or machine learning software packet sizes. NVIDIA talks about the increased tensor cores AI benefits here, as it also gets a power bump to 350w TDP per PCIe5 GPU. 

Scale-out I/O with Gen5 opens the tech boundaries for our future as a society by doubling its performance. We should see a rapid growth in autonomous cars/trucks/machines and in our infrastructure around use with smart city. Increasing the edge technologies of radar, lidar, 4k/8k camera capture systems with enough processing speeds to get near real time results using machine learning.  

Click the buttons below to share this blog post!

Return to the main Blog page

1 Response

Chana Small
Chana Small

March 03, 2023

Dear admin, Your posts are always well-supported by facts and figures.

Leave a comment

Comments will be approved before showing up.

Also in One Stop Systems Blog

Vibration Mitigation for Enterprise Electronics in Edge Environments
Vibration Mitigation for Enterprise Electronics in Edge Environments

March 21, 2023

Edge computing is loosely defined as enterprise or industrial computing outside of a datacenter. The environments which encompass edge computing pose a unique set of challenges, requiring hardware to be designed to have a broad set of thermal and structural characteristics. For example, an edge computing device designed for an outdoor telecommunications application may be exposed to an extensive range of operating ambient temperatures, but it will experience little to no structural vibration or shock forces. 

Continue Reading

AFSEA West 2023 Booth Tour
[VIDEO] AFCEA West 2023: Rugged Edge AI Transportables

March 14, 2023

In this video, Braden Cooper presents a tour of the OSS booth at AFCEA West 2023 in San Diego, which took place from February 14th-16th. Braden discusses the products OSS showcased, including a few new products. OSS' Rugged Edge AI Transportable products provide GPU acceleration, FPGA data ingest, and NVMe storage for Edge AI Military Applications on land, on the sea and in the air.  

Continue Reading

Artificial Intelligence in Maritime Applications
Artificial Intelligence in Maritime Applications

March 07, 2023

The use of Artificial Intelligence (AI) in maritime applications is quickly becoming an integral part of the shipping industry. As technology advances, so does the potential of AI to help ships better navigate their routes, identify potential hazards, and make more informed decisions. Of course, AI can be used to support a wide variety of applications in traditional manned marine vessels, but the gold standard that is being developed in maritime settings is fully autonomous vessels. This blog post will explore some of the most promising use cases for AI in maritime applications, for both manned and unmanned vessels.

Continue Reading

You are now leaving the OSS website