Accelerate Your Workloads at Massive Scale
Built for HPC and Big Data applications, the Alveo U55C accelerator is the most powerful AMD Alveo card.
The U55C harnesses the power of AMD Adaptive Computing to deliver extraordinary performance unmatched by competing architectures.
High performance, low power HBM
Highest performance per watt
Fast and easy clustering
HPC Clustering for Every Data Center
Scale out across hundreds of Alveo U55C cards over existing infrastructure and network with standards-based, API-driven HPC clustering solution from AMD. No proprietary hardware, no vendor locks.
Optimized Data Movement
Scale Out Architecture on RoCE v2 and DCBx with existing data center server infrastructure
Superior Memory Management
Shared workload and shared memory across multiple cards
Data Pipeline Hyperparallelism
MPI enables hyper-parallelism of AMD Adaptive Compute across nodes
Resources
Vitis HPC Libraries
High Level Programmability That’s Scalable. Flexible.
Software developers and data scientists can unlock the benefits of Alveo and adaptive computing through high-level programmability of both the application and cluster utilizing the Vitis™ platform.
AMD Vitis™ Unified Software Platform includes an extensive set of open-source, performance-optimized libraries that offer out-of-the-box acceleration with minimal to zero-code changes to your existing applications.
Vitis HPC Clustering Libraries
- Ease of programming
- Custom data movement
- Write your application in C/C++
Acceleration in Action
Real-Time Results on Graph Databases
When TigerGraph, the world’s most scalable graph database, needed to accelerate their graph database analytics solution, they turned to AMD.
Unlocking the Mysteries of the Universe
Find out how the Alveo U55C’s powerful HPC clustering are generating real-time streaming signal arrays for the world’s largest radio telescope.
Graph Database Analytics Acceleration
Graph databases are great for connecting siloed data to gain valuable insights. If you have a graph database, you know the best way to get your answers fast, is through acceleration.
The Alveo U55C card is able to accelerate query times and predictions for recommendation engines from minutes down to milliseconds. The U55C’s superior computational power and memory bandwidth enable graph query speeds up to 96x faster compared to CPU-based clusters, while increasing the quality of scores by up to 35%.
This improvement results in greater confidence, dramatically lowering false positives to low single digits.
TigerGraph, the world’s most scalable graph database, turned to AMD to accelerate their software-based graph analytics solution.
Utilizing multiple Alveo U55C cards, TigerGraph tapped into AMD massive clustering ability to accelerate the two most prolific algorithms that drive graph-based recommendation engines: Cosine Similarity and Louvain Modularity.
Product Recommendation
Real-time Personalized Patient Care. 96x Faster on AMD.
In this test, the Alveo U55C card performed 96x faster than a CPU running the TigerGraph Cosine Similarity recommendation engine across millions of patient records to deliver results in milliseconds.
Fraud Detection
Real-Time Fraud Detection. 45X Faster on AMD.
With TigerGraph’s Graph analytics database running on the Alveo U55C card, the Louvain clustering algorithm detected fraudulent attempts across hundreds of bank accounts 45x faster.
Real-Time Signal Processing Acceleration
The Alveo U55C card is ideally suited for processing terabytes of sensor data in real time, via distributed processing across hundreds of Alveo accelerator cards.
Radio Astronomy
Cataloging the origins of the universe requires terabits of sensor data to be processed in real time.
The Commonwealth Scientific and Industrial Research Organization’s (CSIRO) Square Kilometer Array (SKA) - the world’s largest radio astronomy antenna array – depends on Alveo U55C cards to perform end-to-end signal packet processing on incoming data at 15Tbps for real-time data flow.
The Alveo card-based cluster allows CSIRO to tackle the massive compute task of aggregating, filtering, preparing and processing data from 131,000 antennae in real time. The 460GBs of HBM2 bandwidth across the signal processing cluster is served by 420 Alveo U55C cards fully networked together across P4-enabled 100Gbs switches.
Up to 50x Lower in Price, Area & Power Efficiency vs GPU Benchmark
The explosion of sensors at the Edge has accelerated the need to process data in real-time.
Commodity GPUs running streaming sensor data clusters simply can’t keep up with the price, performance and power that Alveo U55C cards deliver.
Test Drive the Alveo U55C Card
Easy Evaluation on the Cloud or On-Premises
Cloud FPGAaaS
Co-Location
How to Buy
Get started today with the Alveo U55C accelerator card.
Available now from AMD and authorized distributors.
