AMD Announces New Records Accelerating Ecosystems With Xilinx

Today at the Xilinx Developer Forum, Xilinx CEO Victor Peng and AMD CTO Mark Papermaster revealed a special moment, a new world-record for inference throughput of 30,000 images per-second.

The companies revealed the AMD and Xilinx have been jointly working to connect AMD EPYC CPUs and the new Xilinx Alveo line of acceleration cards for high-performance, real-time AI inference processing. To back it up, they revealed a world-record* 30,000 images per-second inference throughput!

The impressive system, which will be featured in the Alveo ecosystem zone at XDF today, leverages two AMD EPYC 7551 server CPUs with its industry-leading PCIe connectivity, along with eight of the freshly-announced Xilinx Alveo U250 acceleration cards. The inference performance is powered by Xilinx ML Suite, which allows developers to optimize and deploy accelerated inference and supports numerous machine learning frameworks such as TensorFlow. The benchmark was performed on GoogLeNet*, a widely used convolutional neural network.

This was done on a system using two AMD EPYC 7551server CPUs along with eight newly announced Xilinx Alveo U250 acceleration cards. The benchmark was performed on GoogLeNet (running a batch size of 1 and Int8 precision), a widely used convolutional neural network. AMD and Xilinx share a common vision around the evolution of computing to heterogeneous system architectures at the event.

AMD’s GPUs for the cloud have been purpose-built to optimally virtualize and deliver these workloads. Using a built-in virtualization engine, based on the PCI spec SR-IOV (Single Root IO Virtualization), the GPUs deliver persistent quality of service making it easier to deploy and manage. With up to 32 cores and 64 threads, 8 memory channels with up to 2 TB of memory per socket, and 128 PCIe lanes, AMD EPYC CPU is designed to deliver the connectivity, memory capacity and VM density for GPU accelerated workloads.

ZT Systems, known for their work in the hyperscale datacenter space, announced a new system based upon the Microsoft Project Olympus platform. The new system supports AMD EPYC and AMD Radeon Instinct together for outstanding flexibility and performance in virtualized desktop (VDI) environments, or for executing AI and deep learning workloads. You can read more in the ZT Systems press release here and the AMD blog here.