Achronix will sponsor EE Times’ AI Everywhere Forum, a virtual event covering artificial intelligence (AI) that touch every aspect of electronics today. Taking place on December 12–15, the AI Everywhere virtual conference will provide insights on AI chips, systems, and design tools/software. The conference will answer questions such as how to design for a constantly shifting workload, the most significant challenges AI systems face today, how new accelerators will require new software stacks, and much more.
Visit Achronix Online at AI Everywhere
Achronix will present “Unlocking the Full Potential of FPGAs for Real-Time ML Inference – Tuning an Overlay to an Architecture” on December 13th from 11:50 am – 12:10 pm EST. The presentation will demonstrate how FPGAs are attractive for many machine learning (ML) inference applications by using automatic speech recognition (ASR) as an example. We will explore how FPGAs can accelerate conversational AI and natural language processing applications. We will review the key components in the Achronix FPGAs architecture, such as a 2D network on chip (NoC), high-speed external memory, and optimized machine learning processor (MLP) blocks, and how our symmetrical architecture can make scaling solutions in the FGPA transparent and quick to deploy. Using standard benchmarks, we demonstrate an ASR appliance that can reduce costs by as much as 90% compared with alternative approaches.
Visitors can also check out our virtual booth where we will show the latest FPGA and eFPGA IP solutions for high-bandwidth, compute-intensive, and real-time processing applications built for AI:
- Speedster®7t FPGAs: high-performance FPGAs with 2D network on chip deliver ASIC-level performance with the full programmability of FPGAs.
- Speedcore™ eFPGA IP: 15+ million eFPGA IP cores shipped, offering the performance and flexibility of programmable logic to ASICs and SoCs.
- VectorPath® Accelerator Cards: PCIe accelerator cards for rapid prototyping and production offer 400G and 200G Ethernet interfaces and 4 Tbps of GDDR6 memory bandwidth.
Meet with Achronix
Contact us to arrange a meeting or private demo. We are happy to discuss your project and how Achronix can help achieve your performance and go-to-market goals. Schedule an appointment by visiting https://www.achronix.com/contact-us.