hailo News - Page 2 of 2 - CNX Software

October 17, 2023October 17, 2023 by Jean-Luc Aufranc (CNXSoft) - 2 Comments

Hummingboard 8P Edge AI SBC combines NXP i.MX 8M Plus SoC with Hailo-8 AI accelerator

Hummingboard 8P Edge AI Pico-ITX SBC combines an NXP i.MX 8M Plus processor – itself with a 2.3 TOPS NPU – with the 26 TOPS Hailo-8 AI accelerator for edge AI applications such as smart cameras and automated optical inspection. The compact board comes with up to 8GB RAM, up to 128GB eMMC flash, two gigabit Ethernet ports including one with PoE, WiFi 5, a MIPI camera interface, HDMI and micro HDMI ports, two USB 3.0 ports, and more. Hummingboard 8P Edge AI specifications: SoC – NXP i.MX 8M Plus quad-core Cortex-A53 @ up to 1.8 GHz with Arm Cortex-M7 @ up to 800 MHz, Vivante GC7000UL 3D GPU, Vivante GC520L 2D GPU, 2.3 TOPS NPU System Memory – Up to 8GB LPDDR4 Storage – Up to 128GB eMMC flash, microSD card slot AI accelerator – M.2 Hailo-8 module delivering up to 26 TOPS Video Output – HDMI and Micro […]

August 4, 2023 by Jean-Luc Aufranc (CNXSoft) - No Comments

Hailo-8L 13 TOPS AI accelerator targets entry-level edge devices

Hailo introduced the Hailo-8 AI accelerator offering up to 26 TOPS in 2020, and we’ve found it integrated into many designs since then. The company has now launched a cost-down version with the Hailo-8L AI accelerator delivering up to 13 TOPS for more cost-sensitive entry-level edge devices, or workloads that do not require the more powerful Hailo-8. Hailo says the Hailo-8L offers low-latency, high-efficiency processing, and is capable of handling pipelines with multiple real-time streams and concurrent processing of multiple models and AI tasks. The new Hailo-8L is compatible with the Hailo-8 and relies on the same Hailo-8 software suite, so they could be integrated into existing designs for cost savings. Hailo-8L key features and specifications: 13 Tera-Operations Per Second (TOPS) Real-time, low latency & high-efficiency AI inferencing on edge devices No external memory required Scalable with simultaneous processing of multi-streams & multi-models Typical power consumption – 1.5W Commercial & […]

March 12, 2023March 12, 2023 by Jean-Luc Aufranc (CNXSoft) - No Comments

Hailo-15 quad-core AI Vision processor delivers up to 20 TOPS for Smart Cameras

Hailo-15 is a family of AI Vision processors for smart cameras that deliver up to 20 TOPS of AI inference and are able to process deep-learning AI applications such as video analytics. The Hailo-15 appears to build upon the earlier Hailo-8 AI processor with up to 26 TOPS and more limited computer vision capability. The new AI vision processor integrates a quad-core Cortex-A53 CPU sub-system, can handle 4K video streams, and features “advanced computer vision engines”. So the main differences are that the Hailo-15 is a complete SoC / standalone processor and is specifically designed for AI cameras. Hailo-15 highlights: CPU – Quad-core Arm Cortex-A53 processor up to 1.3 GHz or 1.1 GHz (Hailo-15L) DSP – Vector DSP, 256 MACs @ 700 MHz supports up to 350 GOPs AI accelerator / NN core sub-system with dataflow architecture Hailo-15H – Up to 20 TOPS Hailo-15M – Up to 11 TOPS Hailo-15L […]

October 5, 2021February 10, 2023 by Jean-Luc Aufranc (CNXSoft) - 3 Comments

miriac AIP-LX2160A 16-core embedded platform delivers up to 130 TOPS with 5 Hailo-8 modules

MicroSys Electronics miriac AIP-LX2160A embedded platform combines a 16-core Cortex-A72 NXP LX2160A networking processor with up to five Hailo-8 AI accelerator modules delivering up to 130 TOPS of AI inference performance. The board supports up to 128 GB RAM, up to 4x SATA hard drives, up to 100GbE connectivity, and appears to be especially suited to applications with multiple IP video streams requiring real-time video analytics. miriac AIP-LX2160A specifications: SoC – NXP Layerscape LX2160A with 16 Arm Cortex-A72 cores @ up to 2.2 GHz AI accelerators – 2x Hailo-8 M.2 AI Acceleration Modules, upgradeable to up to 5 Modules via NGFF M.2 Key M card System Memory – Up to 128 GB DDR4 RAM & optional ECC, up to 3200MT/sec, up to 4 ranks (combined design: 2x discrete & 2x SODIMM) Storage 4x SATA III ports Up to 256 GB eMMC 5.1 flash, additional eMMC device on carrier board Up […]

July 1, 2021July 1, 2021 by Jean-Luc Aufranc (CNXSoft) - No Comments

Vecow ABP-3000 AI Edge gateway combines Hailo-8 AI accelerator with Intel Whiskey Lake processor

We first discovered Hailo-8 AI accelerator with claims of up to 26 TOPS performance and 3TOPS/W efficiency in October 2020. Since then, we’ve seen several integrate an Hailo-8 M.2 module into their design including EdgeTuring Edge AI camera and Vecow VAC-1000 gateway with a 24-core Foxconn processor. Vecow has now integrated the Hailo-8 AI accelerator into another gateway, but instead of relying on an Arm processor, the Vecow ABP-3000 AI computing system features an 8th generation Intel Core Whiskey Lake processor. Vecow ABP-3000 specifications: SoC – Intel Core i7-8665UE or i3-8145UE quad-core Whiskey Lake processor with Intel UHD Graphics 620; 15W TDP System Memory – 2x DDR4 2400MHz SO-DIMM, up to 64GB Storage – 1x M.2 Key B Socket (PCIe x2/SATA) AI Accelerator – Hailo-8 AI Processor, up to 26 TOPS with TensorFlow, ONNX frameworks support System IO chip – IT8786E Video Output – 2x DisplayPort up to 4096 x […]

October 7, 2020October 8, 2020 by Jean-Luc Aufranc (CNXSoft) - 9 Comments

Learn more about Hailo-8 AI accelerator and understanding AI benchmarks

Last week we wrote about Hailo-8 M.2 card delivering up to 26 TOPS of AI performance, and comparing well against Google Edge TPU and Intel Movidius Myriad X both in terms of footprint, performance, and efficiency. I’ve since then had a conference call with Liran Bar, VP of Business Development for Hailo, where we had time to discuss more about Hailo’s AI solutions, and how to interpret & understand AI benchmarks that may be misleading in many instances. Hailo-8 Architecture In the first post, we noted the chip managed to get the extra performance and efficiency thanks to a “proprietary novel structure-driven Data Flow architecture instead of the usual Von Neumann architecture”. But that’s a bit abstract, so Liran told me one of the key reasons for the performance improvement is that RAM is self-contained without the need for external DRAM like other solutions. This decreases latency a lot and […]