Do you require high-density and high efficiency for vision analytics in edge computing environments? The HPE Edgeline VPU Module with Myriad™ X seamlessly integrates vision processing unit (VPU) computing with HPE Edgeline. VPU technology delivers high performance, high density, and high power efficiency for deep neural networking running imaging and video inference applications.
Ultra High Performance for Imaging and Vision Analytic Applications
HPE Edgeline VPU Module with Myriad™ X features a neural compute engine for running on-device deep neural network applications, and delivers ultra high performance per watt. It is well suited for video analytic and surveillance applications with smaller numbers of cameras and sensors.
Sixteen programmable SHAVE Cores delivering more compute for neural compute engine computation.
HPE Edgeline VPU Module includes four Myriad™ X VPUs on a single M.2 form factor adapter. Each VPU can handle two 1080p30 streams or four 1080p15 streams. The HPE Edgeline VPU module is an optional feature on HPE ProLiant m510 Server Blade and HPE ProLiant m710x Server Blade.
VPU Neural Network Frameworks Supported Through Intel® OpenVINO
HPE Edgeline VPU Module with Myriad X leverages Intel® OpenVINO and frameworks including Caffe, TensorFlow, mxNet, and nGraph.
HPE Edgeline VPU Module with Myriad X supports a wide range of deep neural networks (DNNs) including GoogleNet, ResNet-18, and TIny Yolo V1.
- Intel is a trademark of Intel Corporation in the U.S. and other countries. All other third-party marks are property of their respective owners.