Exxact Announces Xilinx Alveo Accelerator-Powered Servers & Workstations: Now Shipping Worldwide
Exxact Corporation, a leading provider of high performance computing solutions (HPC), announced that their Xilinx Alveo Accelerator Powered Workstations & Servers are now shipping worldwide.
The Xilinx Alveo accelerator-powered workstations and servers from Exxact are designed to meet the constantly changing needs of the modern data center, providing up to 90X performance increase over CPUs for computationally intensive workloads and perform up to 90X higher than CPUs on key workloads at 1/3 the cost.
“Exxact systems paired with Xilinx Alveo accelerator cards give our customers unique options for maximum flexibility, performance, and cost saving solutions for HPC, networking, and computational storage,” said Jason Chen, Vice President of Exxact Corporation. “Alveo accelerators offers the hardware adaptability of the FPGA with simple high-level development tools as well as containerized deployment options you’ll find with mainstream applications.”
Exxact systems with Xilinx Alveo accelerators can perform multiple tasks from machine learning inference, to video processing, to any workload using the same accelerator card. Systems come preinstalled with the Xilinx ML Suite including the Anaconda development environment for implementing ML software (TensorFlow, Keras, MXNET, Caffe, etc) to run on Alveo accelerator cards.
Exxact is offering various Xilinx Alveo accelerator-powered workstations and servers including:
- Entry-Level TensorEX Workstation: Featuring 4x Alveo U200 or U250 Accelerator Cards, 2x Intel Xeon Scalable (Silver), 4x 16GB Memory
- Mid-Range TensorEX Workstation: Featuring 4x Alveo U200 or U250 Accelerator Cards, 2x Intel Xeon Scalable (Silver), 12x 16GB Memory
- High-End TensorEX 4U Server: Featuring 8x Alveo U200 or U250 Accelerator Cards, 2x Intel Xeon Scalable (Gold), 12x 16GB Memory
Deploy Xilinx Alveo solutions in the cloud or on-premises interchangeably as it is scalable to specific application requirements. Take existing pre-trained machine learning models and optimize them for the Xilinx Alveo accelerators, with no re-training needed.
Read More: AI Brings New Energy to Oil and Gas