Anzeige
Anzeige
Anzeige

Heterogeneous Acceleration Platform for AI Applications

No programmable logic experience is required to get started with ACAP, but designers can design their own IP or add from the Xilinx ecosystem. (Bild: Xilinx Ltd)

Can you tell me a little bit about the use of ACAPs for artificial intelligence applications?

Among Versal’s intelligent engines is the AI engine, a key enabler for many of Versal’s target markets. The software programmable, hardware adaptable AI Engine addresses both the compute density and the memory bandwidth needed for high throughput and low latency machine learning. The massive array of interconnected VLIW SIMD high-performance processors with local memory offer up to 8X compute density for vector-based algorithms vs. programmable logic and at half the power. These engines are optimized for deterministic, real-time DSP and AI/ML computation and suited for applications from cloud, to network, to edge and endpoint. AI Engine is tightly coupled with adaptable hardware for custom compute and flexible memory hierarchy to maximize performance. Alongside these adaptable hardware engines and scalar engines, the AI engine is part of a complete heterogeneous compute platform where deep learning can be infused as an element of a larger application that has other pre/post processing requirements.

Are there already benchmarks available, to compare Versal with other devices?

Multiple performance projections for machine learning inference throughput for Versal VC1902 can be found in the media presentation delivered at XDF San Jose 2018. Xilinx’s initial benchmark ratings show the Versal VC1902 delivering 3.5X low-latency CNN throughput against Nvidia T4 in a 75W power envelope, and 4.2X low-latency CNN throughput against a high-end Volta V100 GPU. These Versal performance numbers assume 60 percent of the VC1902 device is reserved for user functions, such as network attach or video processing. 5X wireless compute versus UltraScale+ is also cited in the presentation. From the technology announcement in March 2018, 20X AI Compute performance is cited in a comparison to Virtex UltraScale+ (VU9P) for Machine Learning inference for image recognition.

 What about ACAPs in the classic machine vision application?

Xilinx will be announcing Versal devices for edge applications such as machine vision some time in the future. These will leverage Versal’s scalar engines, adaptable engines, intelligence engines, and high-throughput connectivity from highest-resolution image sensors to frame grabber cards or industrial networks. Versal will excel in enabling the next generation of smart machine vision for the most compact and capable solution on the market.

Which devices of the Versal series are already available, which will be added in the future?

Versal is comprised of multiple device series, including AI Core Series, AI RF series, AI Edge series, Prime, Premium, and HBM. Product details of AI Core and Prime have been announced. Details of other device series will be disclosed at a later date.

Anzeige

Empfehlungen der Redaktion

Das könnte Sie auch interessieren

The Omnitek DPU (Deep Learning Processing Unit) is a configurable IP core built from a suite of FPGA IP comprising the key components needed to construct inference engines suitable for running DNNs used for a wide range of Machine Learning applications, plus an SDK supporting the development of applications which integrate the DPU functionality.‣ weiterlesen

www.omnitek.tv

Anzeige

Moonvision automatisiert dank AI die Oberflächenerkennung unterschiedlichster Materialien. Was bislang über 50 Bilder erfordert hat, gelingt dem Wiener Startup mit nur elf Bildern. ‣ weiterlesen

www.moonvision.io

Anzeige

Preiswerte Einplatinencomputer haben ihr Bastler-Image längst abgelegt und werden bereits zur Maschinensteuerung eingesetzt. Im Rahmen einer Masterarbeit an der TH Deggendorf wurde nun ein kostengünstiges Smart-Kamera-System auf Basis eines Einplatinencomputers (Raspberry PI 3) als Labormuster entwickelt.‣ weiterlesen

www.th-deg.de

Anzeige

Der neuromorphe System-on-Chip-Baustein (NSoC) Akida ermöglicht erstmals eine gepulste neuronale Netzwerk-Architektur (SNN: Spiking Neural Network) in Serie.‣ weiterlesen

www.brainchipinc.com

Embedded Deep Learning soll künstliche Intelligenz von der Cloud in das Gerät oder die Maschine bringen. Der erste Schritt zur Verkleinerung einer Serverfarm besteht laut Imago darin, ein leistungsstarkes GPU-Board in einer kompakten VisionBox einzusetzen.‣ weiterlesen

www.imago-technologies.com

Die VisionCam ist eine frei unter Linux programmierbare, intelligente Kamera. Die hohen Datenraten werden durch den mit 1,5GHz getakteten Dual-ARM Cortex-A15-Prozessor verarbeitet.‣ weiterlesen

www.imago-technologies.com

Anzeige
Anzeige
Anzeige