Push the Boundaries of AI Processing at the Edge
|
|
New Terasic Agilex® SOM Accelerates AI Edge Applications
The Terasic Apollo Agilex® SoC System-on-Module (SoM) incorporates the latest Intel® Agilex® SoC FPGA. With 1.4M FPGA logic elements, an integrated quad-core ARM Cortex-A53 hard processor system, two DDR4 SODIMM memory sockets, and multiple on-board high-speed connectivity interfaces, the Apollo Agilex® SoM is designed for high-performance AI edge and HPC applications such as AI-accelerated video and image processing.
|
|
The Apollo SoM’s on-board interfaces enable OS and applications development. On the bottom-side of the SoM, two FMC connectors provide connectivity to industry-standard FMC mezzanine cards or to a custom carrier board for application-specific devices and interfaces. High-level FPGA development tools and IP libraries are available to reduce the development time of implementing sophisticated AI processing algorithms. This SoM enables AI edge applications to have unrivaled performance while having the best real-time compute/watts.
Key Features
- Agilex® 1.4MLE FPGA with an integrated 1.4GHz quad-core ARM Cortex-A53 processor system
- Two 72-bit DDR4 ECC SODIMM sockets, microSD card socket, 1Gbits of QSPI configuration flash
- On-board power regulators and board management system
- On-board high-speed Interfaces: FMC/FMC+, QSFP28, GigE, USB2, USB-UART, USB Blaster II
- PCIe Gen4 x16 interface via the FMC+ connector
Target Applications
- Video and Imaging Processing
- HPC Processing and Computing
- Video Broadcast
|
|
Ambarella Focuses on Edge AI Perception
|
The CV5 AI Vision SoC features 8K video or 4K video processing along with video encoding/decoding, and CVflow computer vision processing in a single, low-power design. The SoC can function below 2W for 8K video recording at 30 fps, and below 5W for 8K video recording at 60 fps. The CV5 combines Ambarella’s powerful CVflow AI engine with dual Arm A76 CPUs to provide the performance necessary for a wide range of AI-based algorithms used in security, automotive and consumer applications. If using customized neural networks for dedicated use cases on the CV5 SoC, Ambarella’s SDK offers a complete set of tools for software and AI implementation that includes a compiler, debugger, and support for various ML frameworks, such as PyTorch, ONNX, Caffe, and TensorFlow.
Key Features
- High-Efficiency Video Encoding with H.265 and H.264 video compression
- Flexible multi-streaming capability and 8KP60 video performance
- Multiple CBR and VBR bit rate control modes for encoding
- CNN / DNN-based processing for detection and classification
- Computer Vision engine for conventional CV operations
- CNN toolkit for easy porting of neural networks implemented in Caffe, TensorFlow, PyTorch, or ONNX frameworks
- Advanced image processing includes multi-exposure HDR and EIS
- LED flicker mitigation and 3D motion-compensated temporal filtering (MCTF)
- RGGB / RCCB / RCCC / RGB-IR / monochrome sensor support
|
|
iBase Brings AI Accelerated Performance to a Rugged Compact Edge Solution Running Intel® 11th Gen Core™ U-Series CPU’s
|
|
As a leading supplier of computing solutions, iBase offers a significant portfolio of edge computing rugged and compact options. A particularly impressive model is featured here based on Intel®’s powerful Core™ U-Series (11th gen) CPU paired with the Hailo-8™ AI accelerator (M.2 slot). This brings efficient computing to 26 Tera-Operations Per Second (TOPS) performance! Customization possible.
Features
-
AI Acceleration via Hailo-8™ up to 26 TOPS
-
Intel® Core™ U-Series 11th gen CPU
- 2x M.2 sockets (B-Key/E-Key)
- External GPIO, 2x DisplayPort, TPM (2.0)
- 3x USB 3.1, 1x USB 2.0, 2x Intel® GbE, 1x COM
- 12V (-10%) ~ 24V (+10%) DC-in power input
- Operating temp: 0 to 45 C
- Rugged housing: 180mm x 150mm x 72mm, 1.5 Kg (Optional VESA mounting kit)
|
|
New Groundbreaking Intel© FPGA Families Announced
Midrange Intel® Agilex™ 5 FPGA and SoC FPGAs are optimized for applications requiring high performance, lower power, and smaller sizes.
|
|
Based on Intel© 7 technology, these families leap to the forefront of the FPGA space for low power, footprint and performance. All from U.S. ON SHORE FABS with lead times anticipated to be a fraction of today’s classic semiconductor lead times!
Contact Macnica for further details.
|
|
Macnica - Empowering Efficient Innovation
|
|
|
Macnica Americas, Inc. is the North America division of Macnica Fuji Electronics Holdings, Inc., a $7.5B global leader in technology product distribution, technical support, and design services.
To sign up for our monthly newsletter, please click here .
For other inquiries, contact us here .
|
|
|
|
|
|
|