2020.11.12

Rejuvenating our performance tuning team

Share:

Intel Select Solutions for uCPE is a project we’ve undertaken earlier this year and have recently gone live with the PR. (Please read more about ISS if you’re interested (https://www.intel.com/content/www/us/en/architecture-and-technology/intel-select-solutions-overview.html ). Intel Select Solutions is billed as “workload optimized” and “simplifies deployment.” This has shined a spotlight on where we could improve our process. While we started the project for the marketing potential of such verification, but it becomes apparent to us through the testing process that we could better integrate performance testing and the workloads our customers may run on their system.

This is a departure from our previous benchmarking focused test workflow and exactly what we needed to elevate above being “another ODM.” We have to understand customer workloads and know how to optimize systems for that. Customers’ requirements come in all shape and sizes, and they will all need to be able to deploy quickly. We see this as the key differentiator above and beyond providing a solution. This is the rebirth of our NFVI performance team.

team2-1

So here is a belated introduction of our team. As mentioned above, our focus is NFVI and performance optimization. We have integrated many experts in different fields into a multidisciplinary optimization workflow. We’re tasked with many exciting projects that we hope that can be announced in the near future, as well as optimizing our hardware platform against a variety of infrastructure software. Playing with these software gives us new avenues to fine tune our systems and apply these experiences for our increasingly diverse customer requirements.

We have learned a few new tricks about tuning BIOS & DPDK compiler tuning through repeated testing and tweaking. If you read our previous blog regarding tuning GPU servers for better performance, that project benefitted from our improved process. Even when we aren’t working on projects that directly translate to customer software stack, we’re building a library of tweaks into our organizational knowledge that can be leveraged by all our customers. For customers wanting to use software we’ve optimized for, we can offer a quick path to get the systems up and ready to be put into service.

We are genuinely excited about the projects we’re currently working on and we hope you’ll stick around and follow our progress.

Related News

Enabling Agentic AI in Cybersecurity with On-Prem Infrastructure
2026.04.08

Enabling Agentic AI in Cybersecurity with On-Prem Infrastructure

Agentic AI in cybersecurity is rapidly transforming traditional defense into an autonomous, real-time defense solution. As security systems gain the ability to independently detect and respond to threats, infrastructure must evolve to support instant data processing and decision-making. This shift is driving the need for on-prem AI infrastructure, positioning edge servers, and network appliances as critical enablers of next-generation cybersecurity.

AEWIN Has Completed 2025 Carbon Footprint Verification
2026.03.18

AEWIN Has Completed 2025 Carbon Footprint Verification

As sustainability becomes a global priority, organizations are expected to better understand and manage their greenhouse gas (GHG) emissions. Carbon footprint verification helps quantify emissions, identify key sources, and support long-term reduction planning. As part of its ESG commitment, AEWIN conducts annual carbon footprint verification to ensure transparent reporting and responsible environmental management.

Scalable Storage Infrastructure for AI-Driven Data Management
2026.03.04

Scalable Storage Infrastructure for AI-Driven Data Management

As data grows exponentially and AI adoption accelerates across enterprise, cloud, and edge environments, massive datasets must be processed, moved, and retained efficiently. Training, inference, and real-time analytics require storage infrastructure that delivers performance consistency, excellent efficiency, and scalability. To support AI-driven data management, storage servers must be architected not only for capacity expansion, but for throughput stability, system resilience, and overall reliability across dynamic data environments.

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.