2025.10.22

AEWIN Expands NIC Portfolio with Intel Ethernet Controllers for Flexible, Performant Data Solutions

Share:

Introduction
As data volume explodes from edge to cloud, the demand for ultra-fast and reliable data transmission becomes critical. From AI inference at the edge to high-bandwidth storage backends and core networking infrastructure, efficient packet processing and scalable bandwidth are the foundations of modern digital architecture. AEWIN expands its NIC portfolio with cutting-edge Intel Ethernet Controllers including the latest E830 series controllers that power up to 200G throughput to offer flexible solutions for diverse workloads across Networking, Storage, and Edge Computing.

AEWIN NIC Portfolio Powered by Intel Ethernet Controllers
AEWIN leverage a comprehensive list of Intel Ethernet Controllers ranging from the entry-level I350 to the high-end E830 to build a broad NIC portfolio. These NICs are available in AEWIN’s proprietary form factors for seamless integration into AEWIN network appliances. AEWIN also offer options of standard PCIe add-in cards for broader off-the-shelf platform compatibility.

NIC-02

1. Intel E830-CCAM1 does not support RDMA. NICs based on Intel E835 controller with native RDMA support (RoCEv2 / iWARP) will be available in 2026 for storage and enterprise HPC needs.
2. With 1 Pair Bypass;   3. With 2 Pair Bypass;   4. With 4 Pair Bypass
5: The throughput limitation of 120G is due to Intel E810-CAM2.
6: The throughput limitation is due to PCIe Gen3 x8.

 

Feature Support Across Controllers
The wide range of NIC offerings covers options of RJ-45 and Fiber with speeds ranging from 1G to 200G. The rich options are offered for customers to scale up their appliance based on specific scenarios required. There are further features listed below, and they may vary according to different controllers:
● DPDK (Data Plane Development Kit) for high-speed packet processing
● SR-IOV (Single Root I/O Virtualization) for cloud-native virtualization
● RDMA (Remote Direct Memory Access) for ultra-low latency in storage and HPC
● DDP (Dynamic Device Personalization) for programmable packet processing
● VMDq (Virtual Machine Device Queues) to accelerate VM traffic steering
● TSN (Time-Sensitive Networking) for deterministic edge communication

Customization and Verification
AEWIN designs NICs in both proprietary and standard PCIe form factors, with fast customization services available to meet specific customer requirements. All NICs undergo rigorous verification, including DPDK L3 Forwarding tests, to ensure optimized performance. In addition, AEWIN offers pre-test service for AEWIN platforms and NICs based on customers’ requirements to figure out the most suitable configuration with the best TCO.

Summary
AEWIN delivers a comprehensive and adaptable NIC portfolio to address the growing demands of modern data-driven infrastructures. With flexible configurations across PCIe generations up to Gen5, robust customization services, and full verification support, AEWIN’s Ethernet expansion solutions provide the performance, reliability, and scalability enterprises need to thrive in today’s data-driven world.

 

 

Related News

High-Density AI Infrastructure: Scaling Performance with Advanced Cooling Solutions
2026.09.02

High-Density AI Infrastructure: Scaling Performance with Advanced Cooling Solutions

As AI workloads demand greater processing power, data centers must achieve higher compute density and superior thermal efficiency while minimizing space and energy footprints. Integrating high-power CPUs and GPUs into compact server platforms makes advanced thermal management a critical factor in sustaining performance and optimizing infrastructure efficiency.

Building High-Performance Data Pipelines for Next-Generation AI Workloads
2026.08.25

Building High-Performance Data Pipelines for Next-Generation AI Workloads

AI infrastructure has traditionally focused on accelerating compute with powerful CPUs, GPUs, and AI accelerators. As AI workloads continue to process increasingly large and diverse datasets, compute alone is no longer sufficient. Next-generation AI infrastructure must extend from compute to data, featuring high-performance data pipelines that keep AI workloads running efficiently and seamlessly.

Empowering Agentic AI with High-Performance AI Servers
2026.08.18

Empowering Agentic AI with High-Performance AI Servers

Artificial Intelligence is rapidly evolving beyond content generation into autonomous decision-making. While Generative AI has transformed how organizations create text, images, and code, the next wave of AI innovation is driven by Agentic AI—intelligent systems capable of reasoning, planning, acting, and continuously improving with minimal human intervention. AI agents require significantly more computational resources than traditional AI applications, making modern high-performance servers the foundation for scalable, secure, and efficient Agentic AI infrastructure.

Inquiry Cart

total 0 items

Compare

total 0 items

Email Subscribe

Verification

Click the numbers from smallest to largest.

We use cookies to allow our website to work properly, personalize content and advertising, provide social media features and analyze traffic. We also share information about your use of our site with our social media, advertising and analytics partners

Manage Cookies

Privacy Settings

We use cookies to allow our website to work properly, personalize content and advertising, provide social media features and analyze traffic. We also share information about your use of our site with our social media, advertising and analytics partners

Privacy Policy

Manage Consent Settings

Essential Cookies

Accept All

The website cannot function without these cookies and you cannot switch them off on your system.

These cookies are typically set only in response to an action you perform (i.e. a service request), such as setting privacy preferences, logging in, or filling in a form.

You can set your browser to block or prompt you for these cookies, but this may prevent some site features from working.