NEC ExpEther GPU Expansion and NVMe FPGA PCI-E Over Ethernet for Crypto Mining 3D Simulation Virtual Reality IoT AI Low Latency Storage Deep Learning
NEC ExpEther is a technology that can extend PCI Express beyond the confines of a computer chassis via Ethernet without any modification of existing hardware and software. It leverages 40G technology and uses Ethernet infrastructure to help accelerate real-time Big Data processing. The technology enables you to install large number of GPUs and NVMe SSDs without adding new servers every time so you can scale as you grow your computational or storage needs. The GPU / SSD / FPGA expansion box/chassis can be miles away because it uses ethernet technology and also can be shared by multiple servers which lowers your cost of ownership.
This technology is also extremely suitable for Internet of Things (IoT) where you can have remote sensor data processed in almost real time away from the sensor (example – in a large factory automation environment. With the world’s most advanced GPUs populated, this expansion box is particularly suited for maximum acceleration of highly parallel applications like Artificial Intelligence (AI), Deep Learning, Machine Learning, Autonomous Machines, Self-Driving Cars,Big Data Analytics, IoT, Smart Cities, Health Care, Oil & Gas Research,Computer Aided Design (CAD), Virtual/Augmented Reality, HPC, Virtualization, Database Processing, and General IT & Cloud Enterprise Applications.
Plug-n-Play system (No FW/SW installation needed at server!)
Server architecture independent, OS independent, PCIe device type independent.
Can work effectively with low-end servers.
Can perform P2P communication without any server involvement.
Multiple servers having ExpEther HBAs can share remote PCIedevices, leading to efficient utilization of PCIe devices.
Supports & qualified with growing pool of GPUs, FPGA Accelerators and NVMe SSD device models.
Uses NEC proprietary hardware security engine “Twine”for safe & reliable data communication over Ethernet.
Price shown is for ExpEther Server Adapter (N8104-165) and IO Expansion Box (N8141-80F) ready for 2 GPU or another PCI-Express add-on component, NVMe storage etc. For 4 GPU/PCI-E expansion please see option below.
The ExpEther technology enables system expansion by connecting PCI Express devices directly, using an Ethernet infrastructure. As the ExpEther keeps the native PCI Express connectivity, the PCI Express devices can also be operated as a single system, despite being distributed in different locations connected by Ethernet. This process enables standard PCI Express configurations, interruptions, and hot plugging to be remotely performed with an Ethernet LAN, as if they were connected to a virtual single-hop PCI Express switch.
NEC’s ExpEther 40G technology delivers a compelling solution for real-time Big Data processing and other data center workload acceleration. It does so by enabling the connection of GPGPU, NVMe SSD, or FPGA-based accelerators via an Ethernet connection. NEC has closely collaborated with Xilinx, a fellow ExpEther Consortium member, to validate and enable the ExpEther 40G technology as either an IP core or an ExpEther platform leveraging Xilinx UltraScale™ FPGAs. NEC launched the IP core business in January 2016.
ExpEther 40G provides customers with the following advantages:
Since all connections with the computing resources can be dynamically reconfigured, ExpEther40G technology optimizes the utilization rate.
Original software assets can be used without changing the device drivers, even when all resources are connected via Ethernet.
The service platform enables the scalability needed to process Internet of Things (IoT) solutions and big data projects in real time, especially in the area of high-performance servers, which have difficulty in utilizing ExpEther 1G/10G.
Artificial Intelligence and Deep Learning Use Cases
Deep Learning systems constantly require more computational power and adding new servers is always not practical. The ExpEther allows you to keep adding supercomputing power over ethernet and helps save time and money in realizing value from ongoing research.
2Slot:ExpEther I/O Expansion Unit (40G)-2S, N8141-80F 4Slot: ExpEther I/O Expansion Unit (40G)-4S, N8141-81F
PCI Express Slot
PCI Express 3.0
x8 (Mechanical x16)
Number of Slots
Full Height/ Full Length / Double Width size
40Gbps (Single pass) / 80Gbps(Multiple pass)
10 –100Mbps (for Expansion Chassis management)
1000W AC 100 –240V / 7.08AMAX with fan (100V), 12.47A MAX with fan (240V)
142mm x 131mmx 396mm
GPU Power cablex 2
15.6 x 5.6 x 5.1 in
Dihuni was formed to simplify Digital Transformation. The internet has changed everything – from software applications to compute, storage and networking hardware. At Dihuni, we believe every business is transforming to enable digital customer outcomes and our mission is to ensure we can enable you with the right hardware, software and services to make that happen. Believe us, no matter which application you are working on today, you are helping transform the world into a Digital place. Some of the reasons to trust your business to us :
World Class Partners
Dihuni partners with world class companies such as Dell, HPE, Lenovo, Supermicro, Intel, Microsoft and several other top Software and Hardware companies. We carefully select best-in-class technology and business partners and work with them on strategy, product roadmap and solutions development to ensure we not only provide you the best product but also help our partners enhance their offerings. With our deep rooted partnerships and relationships with product teams, we are able to escalate any product issue or provide new requirements based on your feedback directly to our partners. Our partnerships offer you the best in the following areas :
Server, Storage and Networking Hardware
Internet of Things (IoT)
Software Development – Onshore (US) and Offshore
High Quality Manufacturing for Standard Products
We leverage the manufacturing capabilities of our partners and work closely with them to customize your system. Instead of adding more complexity in shipping individual parts, integrating and testing it at facilities that require constant maintenance, we work closely with our OEM partners and use their expertise and operations so they can build a high quality system that is suitable for your exact application. By doing this, we are able to not only control manufacturing costs and pass on the savings to you but also deliver a system directly from our partner to you in any part of the world. At Dihuni, we ensure and select partners who adhere to rigorous design implementation, manufacturing standards and ISO standards to ensure that its products are produced with the highest quality and reliability. Our partners integrate only the best quality parts and components into their system boards, servers, and chassis. To ensure excellent performance even under extreme operating conditions, our products undergo rigorous environmental and intense computational testing. These quality efforts optimize system performance and minimize system downtime for you to have an extremely reliable system from Dihuni.
Focus on Solution, Not Just Hardware
We know you are looking for hardware as part of a solution that you are implementing. With our experience in software as well as real world IT implementation, we help you select the right product that fits your solution. There is huge complexity in implementing a successful solution regardless of whether you are a software developer wanting a fast developer machine or if you are involved in developing an efficient on-premise and cloud back-end infrastructure for your IT or Internet of Things (IoT) applications or setting up the right systems for data, analytics, Machine Learning, Artificial Intelligence (AI) and Digital Applications. We help you through your needs regardless of the size of your project and your budget.
Our leadership has over 20 years of experience in designing, developing, manufacturing and shipping servers and embedded/IoT systems in high volume. With direct experience with companies such as Dell, NEC, Supermicro, Honeywell, BSDi etc, we are experts in effective product management and will help you with every need you may have. We carefully select each product that we carry and understand the target applications for your systems. Utilizing our experience in software, we also provide Digital Transformation and Agile software development consulting services should you need help with any of your projects in IoT, IT etc.
We Really Believe in Customer Service
We believe and have implemented best practices in product design, development and more importantly customer service. This thinking is permeated throughout our company. We offer :
High Quality Products and Consultation on product positioning and suitability
Fast response times
Completely customized systems and services including
Phone and Onsite Support including Manufacturer’s Support
Marketing opportunity for your project and case studies
We appreciate your business! Please call us at 703-436-4721 or email us at firstname.lastname@example.org for any question or information. We respond promptly and you can contact us even during weekends.
To simplify your shopping experience, we continuously add secure and easy transaction methods. You can now save time by using your billing and shipping information already stored in your familiar Amazon account for a simple, fast, easy and secure checkout! Great for both mobile and desktop shopping globally. Powered by Amazon!
We also accept Paypal and all major credit cards e.g. MasterCard, Visa, American Express, Discover etc.
For large orders, please contact us for bank/wire transfer info, checks, Net Terms and other payment methods your company or you prefer.
We proudly serve customers ranging from Fortune Corporations to Universities, Schools, Startups, Small and Medium Businesses, Government and Individual Buyers. Our customers are among :
Top 5 Semiconductor Companies
Top 3 RideShare Companies
Top 5 IT Infrastructure Companies
Ivy League Universities
Top IoT, AI and Deep Learning Startups
Deep Learning Servers with NVIDIA Tesla V100
Dihuni OptiReady Systems are 'Optimized and Ready' for your applications. These are systems that are pre-configured with CPU, memory, SSD etc so you can have peace of mind.
We have the broadest range of 'Ready to Buy' Deep Learning OptiReady Servers with NVVIDIA Tesla V100 32GB and 16GB GPUs.
Deep Learning & AI Software Installation Available : Check on GPU Server Pages!
Promotion on NVIDIA GPUs!!
We're offering Free Ground Shipping on all NVIDIA Tesla GPUs. Please use FREESHIP18 during Checkout to avail this offer.
For higher volumes and special pricing requests on NVIDIA GPUs including the new Tesla V100 32GB, please email/call us with your requirements.
For any product related question, custom quotes, high volume pricing or help with ordering etc please call us at 703-436-4721 or e-mail email@example.com.
Brand New! Dual NVIDIA Tesla V100 32GB GPU Based Deep Learning System
“We purchased a variety of systems for low-power applications from Dihuni. Dihuni engaged with us to ensure we selected the best options for our requirements and gave us access to newly introduced systems. We would recommend Dihuni to other buyers because of the quality of their customer care.”
Strategic Marketing Manager, Top 15 Semiconductor Co.
“We’ve purchased AMD EPYC Servers from Dihuni, and their service and response was top notch. They clarified exactly what we needed, what type of motherboard will fit best our needs, and delivered the servers on time and in tip top condition. Was a pleasure working with them!”
CTO, Tech Co., Tel Aviv, Israel
Popular! Tyan AMD EPYC All NVMe Server
The Tyan B8026T70AE24HR features 24xNVMe drives and delivers top AMD EPYC CPU Performance.
“We ordered the SuperMicro 5019A-FTN4 SuperServer featuring the latest “Denverton” Intel Atom C3758 processor from Dihuni within days of the product being available. Working with Dihuni was an absolute pleasure, they kept us informed/updated on the order process and made sure to get the product shipped in time to meet our tight deadline. We are running several virtual machines on the Windows 2016 Hyper-V platform: Palo Alto Networks VM-100 firewall, Aruba Networks Virtual Mobility Controller, BlueCat DNS/DHCP servers and a few Windows Server 2012 & 2016 servers in our POC lab. We configured our system with 64GB of RAM and it’s easily handled the workload we’ve thrown at it. I highly recommend purchasing all of your SuperMicro server equipment from Dihuni, you won’t be disappointed!”
Robert Tesdall, Sr. Network Engineer, Enterprise Networks Solutions, USA
Can’t Find Your Product?
Our partners carry hundreds and thousands of products and it is possible we don’t have the one you are looking for listed online here. Please contact us with the product name and part number and we will respond with a quote asap.