About a-team Marketing Services
The knowledge platform for the financial technology industry
The knowledge platform for the financial technology industry

A-Team Insight Blogs

Q&A: Vikram Mehta of IBM System Networking – One Year In … New Low-Latency Products, OpenFlow, Comparisons to InfiniBand

Subscribe to our newsletter

Remember Blade Network Technologies? Well, a year ago it was snapped up by IBM, and given the charter to network IBM’s enterprise server and storage products, to provide a unified system. Trading firms – and exchanges – were big customers of BNT, so IntelligentTradingTechnology.com chatted to the company’s founder Vikram Mehta, now vice president, System Networking, at IBM to find out how IBM is continuing to focus on that business, and about new collaborations within IBM.

Q: Blade Network Technologies was acquired by IBM a year ago and now the business is called IBM System Networking. What is your focus/mission?

A: IBM System Networking is focused on providing the essential data and storage networking solutions under the IBM brand to connect servers to servers, servers to storage and storage to storage – and provide complete interoperability with core networks. 

Q: And to be clear, you work with companies that are competitors of IBM in areas such as servers and storage. Will this continue?

A: Yes. To complement IBM data and storage networking products, IBM System Networking delivers a broad portfolio of data center switches and routers through IBM’s original equipment manufacturer partnerships.

Q: What products are you specifically focusing on the financial trading space? And what can you tell us about product directions that are relevant to that space?

A: IBM RackSwitch products, including the ultra-low-latency 10 gigabit Ethernet IBM RackSwich 8124, 10/40gE IBM RackSwitch 8264 and the new 40gE IBM 8316, deliver capabilities that are ideally well suited for the needs of financial trading firms. Future products will delivery the lowest possible latency, rich feature support, and support for industry standards required by the world’s leading trading companies.

Q: And what specific performance, functionality or design attributes make those products suitable for the high throughput/low latency/low jitter requirements of the financial markets?

A: IBM RackSwitch products are based on a single chipset design that enables consistent, deterministic latency with no jitter. This enables full multicast, non-blocking performance at line rate across all port combinations. Support for Layer 3 protocols and multicast is implemented in hardware, so implementing these capabilities does not incur a performance hit.

With multiple bandwidth-intensive financial applications per server cluster, trading firms are typically implementing edge networks at 10gE speeds, and today’s servers are shipping with 10gE ports. So, 10gE is a baseline requirement, with strong interest in implementing 40gE aggregation networks.

For firms interested in implementing flat networks for link aggregation, load sharing, redundancy or scalability, IBM RackSwitch products support Virtual Link Aggregation (vLAG) with TRILL support on the horizon.

Q: Pure data communications performance aside, what other factors are important for financial trading environments, such as co-lo centres?

A: Today’s key requirements include fair availability of market data and deterministic trading speeds, which are driving the need for very efficient, low-latency co-location centers that utilise the latest high-power servers, NICs and network interfaces. Co-location centres are putting market data sources as close as possible to matching engines so they can deliver the same speeds to all competitors and run the exchange’s algorithms and issue trades through gateways as fast as possible. Exchanges are seeking to collapse their gateways to make them faster and evaluating delivering more binary market data feeds instead of formatted feeds that have more protocol overhead and slow things down. A great deal of innovation is in the works by exchanges and their vendors are focused on making co-location centres run better and faster, and IBM is at the forefront of these advances.

Q: How is IBM System Networking collaborating with other divisions in IBM to produce the best solutions for financial trading?

A: Support for the emerging OpenFlow protocol is a great example of collaboration within IBM. OpenFlow promises Software-Defined Networking that will enable trading firms to customise their switching and routing environments to meet the specific to the needs of the business. OpenFlow is an exciting new development that will differentiate IBM products moving forward.

Additionally, IBM System Networking products are being integrated across the board with the System x portfolio for what IBM calls “Smarter Computing” through integrated systems that combine servers, storage and networking with unified management to reduce complexity, deliver  greater performance, and improve efficiency.

Q: More generally, how is gigabit Ethernet technology evolving?  Will it ever provide better performance – latency and jitter – than InfiniBand?

A: When people compare Ethernet to InfiniBand, they’re evaluating the baseline characteristics. However, if you architect an Ethernet network so it is not oversubscribed and design the interfaces to deterministically minimise collisions and eliminate packet loss,  you optimise Ethernet to be on a par with InfiniBand and gain the plug-and-play and management advantages afforded by Ethernet. Ethernet is easier to implement and manage and delivers comparable performance.

Q: Should financial trading firms consider muliti-vendor networks?

A: Absolutely. A recent Gartner research report, “Debunking the Myth of the Single-Vendor Network,” concluded that introducing a second networking vendor will reduce total cost of ownership (TCO) for most organisations by at least 15% to 25% over a five-year time frame and that most organisations that introduced a second vendor gained a lasting decrease in network complexity. Gartner did not encounter one example were operational cost savings would offset the equipment cost premium that the primary networking vendor generally charges. For their high-volume edge networking requirements, financial trading firms are gaining significant advantages with IBM System Networking solutions across a range of dimensions including performance, scalability, density, functionality, manageability and total lifecycle costs.

Subscribe to our newsletter

Related content

WEBINAR

Recorded Webinar: Trade the Middle East & North Africa: Connectivity, Data Systems & Processes

In Partnership With As key states across the region seek alternatives to the fossil fuel industries that have driven their economies for decades, pioneering financial centres are emerging in Egypt, United Arab Emirates (UAE), Saudi Arabia and beyond. Exchanges and market intermediaries trading in these centres are adopting cutting-edge technologies to cater to the growing...

BLOG

How TS Imagine is Unlocking the Power of Data with AI and Snowflake

Exclusive Q&A with Thomas Bodenski, Chief Operating Officer, TS Imagine. From trading strategies to risk management and client interactions, financial institutions are continuously exploring how AI can enhance their businesses. Yet despite the hype and noise, many real-world use cases are still more promise than practice. Firms often face challenges in operationalising AI at scale,...

EVENT

ESG Data & Tech Briefing London

The ESG Data & Tech Briefing will explore challenges around assembling and evaluating ESG data for reporting and the impact of regulatory measures and industry collaboration on transparency and standardisation efforts. Expert speakers will address how the evolving market infrastructure is developing and the role of new technologies and alternative data in improving insight and filling data gaps.

GUIDE

AI in Capital Markets: Practical Insight for a Transforming Industry – Free Handbook

AI is no longer on the horizon – it’s embedded in the infrastructure of modern capital markets. But separating real impact from inflated promises requires a grounded, practical understanding. The AI in Capital Markets Handbook 2025 provides exactly that. Designed for data-driven professionals across the trade life-cycle, compliance, infrastructure, and strategy, this handbook goes beyond...