SiTime Corporation announces that AMD is using SiTime MEMS precision timing solutions for its Alveo™ X3 series, the first AMD network cards designed with screened FPGAs and optimized specifically for low-latency electronic trading. Designed for the fintech industry, AMD’s first network interface card (NIC) platform is optimized for electronic trading systems that require lower latency and security in every transaction. The SiTime SiT95145 Cascade™ clock system on a chip (ClkSoC™) is a unique single chip solution that generates all the clocks in the Alveo X3 NIC and delivers performance required by high-speed networks, and data centers that are the backbone of stock exchanges.

“Electronic trading continues to evolve and the race to the lowest latency trade execution is critical to how financial firms operate,” said Hamid Salehi, director of product marketing, Fintech and Blockchain Technologies, AMD. “The Alveo X3 series brings low-latency and adaptive computing onto a single platform to give our customers a competitive advantage for today and tomorrow. In this system, we used the SiTime SiT95145 Cascade clock system on a chip to supply all critical clocks. This precision timing device replaced multiple oscillators and resonators, simplified our clock tree design, and helped us save verification time, accelerating our time to market.” 

Related Resources

SDS7000A 4 Channel 12-Bit 4GHz MSO Oscilloscope Series
Keysight Introduces Optimized In-Line High Density In-Circuit Test System for Printed Circuit Board Assemblies
Renesas Develops Circuit Technologies for 22-nm Embedded STT-MRAM with Faster Read and Write Performance for MCUs in IoT Applications

Leading financial trading firms, quants, hedge fund managers, and exchanges demand near instantaneous, ultra-low-latency trade execution, and risk management to maintain competitive advantage and outperform the market in today’s volatile environment. High-performance NICs built with precision timing components are critical to the speed and accuracy of automated trading systems designed to complete transactions within milliseconds.

“Higher speeds and lower latency are the two major requirements of new communications networks as they enable new services. Precision timing plays a crucial role in fulfilling these requirements by delivering higher performance for modern communications deployment. SiTime has a complete portfolio of oscillators and clocks that offer compelling benefits, whether it be in performance, robustness, reliability, integration, size, or power. These benefits enable unique capabilities, simplify customer’s designs, save verification time, and accelerate our customers’ time to revenue.”

AMD’s FPGA-based platform delivers low-latency performance benefits through turnkey networking IP, state-of-the-art connectivity and timing technology, and hardware adaptability for evolving use cases and future electronic trading requirements. The Alveo X3 low-latency data center accelerator card can serve as a plug-and-play NIC, providing deterministic response time for rapid, reliable trade execution.

Cascade, with SiTime’s MEMS technology combined with a low noise and feature-rich on-chip PLL IC, enables more robust system timing. This ClkSoC precision timing solution is designed to deliver ultra-low jitter even in the presence of noise, always-accurate frequency synthesis without crystal capacitive mismatching, 10x greater vibration resistance, always-reliable startup in harsh environments and fast hitless switching to ensure redundancy.