Accelerate HPC at Scale with Achronix FPGAs at Supercomputing 2023! Join Achronix for Generative AI (GenAI), Machine Learning (ML), Conversational AI (CAI), networking, and more. Attend our Chiplets panel and happy hour for exciting short TechTalks and giveaways.
Supercomputing 2023 (SC23) is known for providing a highly regarded technical program that caters to professionals and students in the HPC community. This program is a leader in its impact and adheres to the highest academic and professional standards.
The program's main objective is to facilitate sharing best practices among participants. It covers various topics, including algorithms, applications, architectures and networks, clouds and distributed computing, data analytics, visualization, and storage. Additionally, the program explores the intersection of machine learning and HPC, performance optimization, programming systems, system software, and the current state of large-scale deployment and integration.
By addressing these areas, the program aims to promote knowledge exchange, foster innovation, and drive advancements in the field of HPC. Attendees can expect to gain valuable insights, learn about the latest developments, and engage in discussions with experts and peers.
Engage With Achronix HPC Acceleration Experts at Booth 2019
Meet Achronix at our booth or contact us to arrange a meeting. We will showcase our FPGA technologies built to accelerate Generative AI (GenAI), Conversational AI (CAI), Machine Learning (ML), networking, data center, and other HPC applications. Join us for two demonstrations in our booth:
Accelerated Automatic Speech Recognition (ASR)
Achronix FPGAs accelerate AI performance and, unlike other solutions, can be reprogrammed with new/updated algorithms. This demo shows an automatic speech recognition (ASR) solution running in our Speedster7t FPGA on a VectorPath card. This solution provides low latency real-time speech-to-text solutions that can reduce costs by 90% when using a single server and VectorPath accelerator card to replace 20 standard CPU-based server solutions, which would be required to deliver the same performance. This solution is developed by our partner Myrtle.ai and can be deployed on standard, off-the-shelf hardware. This is a complete solution with a host API exposed, so no RTL or FPGA knowledge is required. It is compatible with all major deep learning frameworks, such as PyTorch.
Accelerated Network Infrastructure Code (ANIC)
The ANIC pipeline network functions with user-selectable building blocks, providing a high-performance Ethernet networking solution. It allows customers to utilize FPGA-powered SmartNIC for accelerated network performance and efficient CPU resource utilization. The ANIC comprises modular logic blocks and leaves additional FPGA logic available for customer applications. The solution eliminates the need for customers to create their own Ethernet functionality and design high performance network applications.
Attend Our Chiplets Panel
Chiplet Ecosystem in High Performance Computing, AI/ML, and Data Acceleration Panel | November 15 at 3:30 pm | Room 201 – 203
Bapi Vinnakota from Open Compute Project Foundation will chair a panel of SMES from Achronix, Ayar Labs, AMD, Columbia University, and Lawrence Berkeley National Laboratory. They will discuss how Chiplets have become a compelling approach to incorporating specialization and massive bandwidth into compute and memory devices used in HPC. But there are many challenges in realizing the vision for affordable, modular HPC applications using advanced packaging technology. We bring together a diverse panel of experts to discuss whether an ecosystem or marketplace of Chiplets will be available for system developers to build next-generation devices and weigh the pros and cons of off-the-shelf Chiplets vs. custom designed Chiplets.
Join Us for Happy Hour at SC23
Achronix will host two Happy Hours during SC23 on Tuesday, November 14, and Wednesday, November 15, at 3:00pm in Booth 2019. Join us for a beer and popcorn, and listen to the latest developments on an array of trending industry topics from our data acceleration experts:
-
Tuesday, November 14th Happy Hour Presentations: SmartNICs & Chiplets
-
Wednesday, November 15 Happy Hour Presentations: Generative AI & Conversational AI
Unlock the Acceleration Power of Achronix FPGAs for Your HPC Projects
Explore the latest FPGA and eFPGA IP solutions for high-bandwidth, compute-intensive, and real-time processing applications:
- Speedster®7t FPGAs: high-performance FPGAs with 2D network on chip, delivering 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 with 400G and 200G Ethernet interfaces and 3.5 Tbps of GDDR6 memory bandwidth.
Schedule a Meeting with a Data Acceleration Expert
Set up a meeting or private demo about your project and how Achronix can help achieve your performance and go-to-market goals.