fbpx

Imagination Technologies

www.imgtec.com

Imagination Technologies, a global leader in multimedia, processor, communication and cloud technologies, creates and licenses market-leading processor solutions including graphics, video, vision, CPU and embedded processing, multi-standard communications, cross-platform V.VoIP and VoLTE, and cloud connectivity. These silicon and software intellectual property (IP) solutions for systems-on-chip (SoC) are complemented by an extensive portfolio of software, tools and ecosystems. Target markets include mobile phone, connected home consumer, mobile and tablet computing, in-car electronics, networking, telecoms, health, smart energy and connected sensors. Imagination’s licensees include many of the world’s leading semiconductor manufacturers, network operators and OEM/ODMs. Corporate headquarters are located in the United Kingdom, with sales and R&D offices worldwide.

Recent Content by Company

Imagination and Apple Sign New Agreement

London, UK; 2nd January 2020 – Imagination Technologies (“Imagination”) announces that it has replaced the multi-year, multi-use license agreement with Apple, first announced on February 6, 2014, with a new multi-year license agreement under which Apple has access to a wider range of Imagination’s intellectual property in exchange for license fees. About Imagination Technologies Imagination is a …

Imagination and Apple Sign New Agreement Read More +

imglogo2013

UNISOC and Imagination Carry Out Strategic Cooperation on AI Based on IMG Series3NX Neural Network Accelerator

LONDON, UK and Beijing, China; 3rd  December 2019 – Imagination Technologies announces that UNISOC, a leading fabless semiconductor company, has licenced its latest generation of neural network accelerator (NNA), IMG Series3NX for use in future system-on-chips (SoCs) targeting mid-high range mobile devices, TV and other markets. UNISOC previously integrated Imagination’s Series2NX AI core into its …

UNISOC and Imagination Carry Out Strategic Cooperation on AI Based on IMG Series3NX Neural Network Accelerator Read More +

PowerVR-GPU-Slides6_678x452

Imagination Launches IMG A-Series: “The GPU of Everything”

The fastest GPU IP ever Shanghai, China; 3rd December 2019 – Imagination Technologies announces the tenth generation of its PowerVR graphics architecture, the IMG A-Series. The fastest GPU IP ever released, IMG A-Series evolves the PowerVR GPU architecture to fulfil the graphics and compute needs of the full spectrum of next-generation devices. Designed to be …

Imagination Launches IMG A-Series: “The GPU of Everything” Read More +

Infographic-Smart-City

Cloud and Edge Vision Processing Options for Deep Learning Inference

Should deep learning-based computer vision processing take place in the cloud, at the edge, or both? This seemingly simple question has a complicated answer: "it depends." This article provides perspectives on the various factors you should consider, and with what priorities, when making this implementation decision for your particular project's requirements. THe Edge-Centric Inference Evolution …

Cloud and Edge Vision Processing Options for Deep Learning Inference Read More +

“Object Detection for Embedded Markets,” a Presentation from Imagination Technologies

Paul Brasnett, PowerVR Business Development Director for Vision and AI at Imagination Technologies, presents the “Object Detection for Embedded Markets” tutorial at the May 2019 Embedded Vision Summit. While image classification was the breakthrough use case for deep learning-based computer vision, today it has a limited number of real-world applications.… “Object Detection for Embedded Markets,” …

“Object Detection for Embedded Markets,” a Presentation from Imagination Technologies Read More +

“Mining Site Data Extraction Using 3D Machine Learning,” a Presentation from Strayos

Ravi Sahu, Founder and CEO of Strayos, presents the "Mining Site Data Extraction Using 3D Machine Learning" tutorial at the May 2019 Embedded Vision Summit. This talk focuses on extracting invariant features for segmentation of 3D models of mining sites. The image data is generated by stitching together geo-tagged images from a drone. The 3D …

“Mining Site Data Extraction Using 3D Machine Learning,” a Presentation from Strayos Read More +

imglogo2013

PowerVR GPU and NNA Available On SiFive Platform

Imagination Technologies joins SiFive’s DesignShare Ecosystem, Enabling RISC-V users to access industry-leading IP London, UK; and San Mateo, California; 13th May 2019 – Imagination Technologies announces that it has joined SiFive’s DesignShare ecosystem, giving system designers easy access to its industry-leading PowerVR GPU and neural network accelerator (NNA) IP cores. The PowerVR GPU will be …

PowerVR GPU and NNA Available On SiFive Platform Read More +

Figure5

Combining an ISP and Vision Processor to Implement Computer Vision

An ISP (image signal processor) in combination with one or several vision processors can collaboratively deliver more robust computer vision processing capabilities than vision processing is capable of providing standalone. However, an ISP operating in a computer vision-optimized configuration may differ from one functioning under the historical assumption that its outputs would be intended for …

Combining an ISP and Vision Processor to Implement Computer Vision Read More +

“Improving and Implementing Traditional Computer Vision Algorithms Using DNN Techniques,” a Presentation from Imagination Technologies

Paul Brasnett, Senior Research Manager for Vision and AI in the PowerVR Division at Imagination Technologies, presents the “Improving and Implementing Traditional Computer Vision Algorithms Using DNN Techniques” tutorial at the May 2018 Embedded Vision Summit. There has been a very significant shift in the computer vision industry over the past few years, from traditional …

“Improving and Implementing Traditional Computer Vision Algorithms Using DNN Techniques,” a Presentation from Imagination Technologies Read More +

“Training CNNs for Efficient Inference,” a Presentation from Imagination Technologies

Paul Brasnett, Principal Research Engineer at Imagination Technologies, presents the "Training CNNs for Efficient Inference" tutorial at the May 2017 Embedded Vision Summit. Key challenges to the successful deployment of CNNs in embedded markets are in addressing the compute, bandwidth and power requirements. Typically, for mobile devices, the problem lies in the inference, since the …

“Training CNNs for Efficient Inference,” a Presentation from Imagination Technologies Read More +

“Training CNNs for Efficient Inference,” a Presentation from Imagination Technologies

Paul Brasnett, Principal Research Engineer at Imagination Technologies, presents the "Training CNNs for Efficient Inference" tutorial at the May 2017 Embedded Vision Summit. Key challenges to the successful deployment of CNNs in embedded markets are in addressing the compute, bandwidth and power requirements. Typically, for mobile devices, the problem lies in the inference, since the …

“Training CNNs for Efficient Inference,” a Presentation from Imagination Technologies Read More +

2015-openvx-release-graphic-3

Imagination’s Smart, Efficient Approach to Mobile Compute

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. Imagination designed its PowerVR Tile-Based Deferred Rendering (TBDR) graphics architecture more than 20 years ago with a focus on efficiency across performance, power consumption and system level …

Imagination’s Smart, Efficient Approach to Mobile Compute Read More +

20-Parallel-versus-serial-execution-of-a-statement-in-a-warp

Measuring GPU Compute Performance

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. After exploring a quick guide to writing OpenCL kernels for PowerVR Rogue GPUs and analyzing a heterogeneous compute case study focused on image convolution filtering, I am …

Measuring GPU Compute Performance Read More +

22-Zero-copy-YUV-semi-planar-native-flow-between-hardware-and-GPU-768x421

Supported Zero-copy Flows Inside the PowerVR Imaging Framework

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. In a previous article we described our PowerVR Imaging Framework, a set of extensions to the OpenCL and EGL APIs that enable efficient zero-copy sharing of memory …

Supported Zero-copy Flows Inside the PowerVR Imaging Framework Read More +

25-Integrating-zero-copy-flow-with-Android-Camera-HAL-698x500

The PowerVR Imaging Framework Camera Demo

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. Writing and optimizing code for heterogeneous computing can be difficult, especially if you are starting from scratch. Imagination has set up a new page where developers can …

The PowerVR Imaging Framework Camera Demo Read More +

12-Block-level-implementation-of-face-detection-on-CPU-and-GPU

Deep Dive: Implementing Computer Vision with PowerVR (Part 3: OpenCL Face Detection)

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. Imagination’s R&D group has developed a face detection algorithm, which is based on a classifier cascade and is optimized to run on mobile devices comprising a CPU …

Deep Dive: Implementing Computer Vision with PowerVR (Part 3: OpenCL Face Detection) Read More +

“Efficient Convolutional Neural Network Inference on Mobile GPUs,” a Presentation from Imagination Technologies

Paul Brasnett, Principal Research Engineer at Imagination Technologies, presents the "Efficient Convolutional Neural Network Inference on Mobile GPUs" tutorial at the May 2016 Embedded Vision Summit. GPUs have become established as a key tool for training of deep learning algorithms. Deploying those algorithms on end devices is a key enabler to their commercial success and …

“Efficient Convolutional Neural Network Inference on Mobile GPUs,” a Presentation from Imagination Technologies Read More +

Optimizing Computer Vision Applications Using OpenCL and GPUs

The substantial parallel processing resources available in modern graphics processors makes them a natural choice for implementing vision-processing functions. The rapidly maturing OpenCL framework enables the rapid and efficient development of programs that execute across GPUs and other heterogeneous processing elements within a system. In this article, we briefly review parallelism in computer vision applications, …

Optimizing Computer Vision Applications Using OpenCL and GPUs Read More +

Embedded-Vision-Summit-PowerVR-GPUs-running-CNN-demo-768x410

Deep Learning on Mobile Devices at the Embedded Vision Summit 2016

This article was originally published at Imagination Technologies' website. It is reprinted here with the permission of Imagination Technologies. It was clear last week at the annual Embedded Vision Summit in Santa Clara that the time of computer vision and deep learning on mobile had finally arrived. Interest in the area is growing noticeably – …

Deep Learning on Mobile Devices at the Embedded Vision Summit 2016 Read More +

11-Components-of-a-modern-vision-processor-1024x720

Deep Dive: Implementing Computer Vision with PowerVR (Part 2: Hardware IP for Computer Vision)

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. Modern mobile application processors are highly heterogeneous, combing a variety of different hardware components optimized for different tasks. As shown in the figure below, a processor designed …

Deep Dive: Implementing Computer Vision with PowerVR (Part 2: Hardware IP for Computer Vision) Read More +

Deep Dive: Implementing Computer Vision with PowerVR (Part 1: Computer Vision Algorithms)

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. Computer vision is the use of computers to extract useful meaning from images, such as those that arise from photographs, video and real-time camera feeds. Thanks to …

Deep Dive: Implementing Computer Vision with PowerVR (Part 1: Computer Vision Algorithms) Read More +

15-Example-of-image-filtering-by-means-of-convolution_v2

Heterogeneous Compute Case Study: Image Convolution Filtering

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. In a previously published article, I offered a quick guide to writing OpenCL kernels for PowerVR Rogue GPUs; this sets the scene for what follows next: a …

Heterogeneous Compute Case Study: Image Convolution Filtering Read More +

04-Example-zero-copy-flow-between-ISP-and-GPU

The PowerVR Imaging Framework for Android

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. In a previous article about heterogeneous architectures, I identified memory bandwidth as the main bottleneck for implementing power-efficient algorithms for computer vision. Luckily, Imagination has created an …

The PowerVR Imaging Framework for Android Read More +

03-Vision-software-pipeline-implemented-on-top-of-hardware

Increasing Performance and Power Efficiency in Heterogeneous Software

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. Heterogeneous architectures in embedded computing are fast becoming a reality – we indeed see many leading IP and semiconductor companies today building heterogeneous computing hardware. In the …

Increasing Performance and Power Efficiency in Heterogeneous Software Read More +

A Quick Guide to Writing OpenCL Kernels for PowerVR Rogue GPUs

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. Firstly, I’d like to give you an overview of OpenCL programming fundamentals using a basic program, followed by an explanation of OpenCL execution on Rogue GPUs. This …

A Quick Guide to Writing OpenCL Kernels for PowerVR Rogue GPUs Read More +

01-SoC-architecture

A Primer on Mobile Systems Used for Heterogeneous Computing

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. In the mobile and embedded market, the design constraints of electronic products can sometimes be seen as tight and contradictory: the market demands higher performance yet lower …

A Primer on Mobile Systems Used for Heterogeneous Computing Read More +

GPU-compute_memory-hierarchy-in-OpenCL

The Complete Glossary to Heterogeneous Compute

This article was originally published at Imagination Technologies' website, where it is one of a series of articles. It is reprinted here with the permission of Imagination Technologies. For the last decade, Imagination has been at the forefront of heterogeneous compute, becoming a founding member of the HSA Foundation and a contributor to many open …

The Complete Glossary to Heterogeneous Compute Read More +

OpenCL Eases Development of Computer Vision Software for Heterogeneous Processors

OpenCL™, a maturing set of programming languages and APIs from the Khronos Group, enables software developers to efficiently harness the profusion of diverse processing resources in modern SoCs, in an abundance of applications including embedded vision. Computer scientists describe computer vision, the use of digital processing and intelligent algorithms to interpret meaning from still and …

OpenCL Eases Development of Computer Vision Software for Heterogeneous Processors Read More +

OpenCLLogo_678x452

OpenCL Eases Development of Computer Vision Software for Heterogeneous Processors

OpenCL™, a maturing set of programming languages and APIs from the Khronos Group, enables software developers to efficiently harness the profusion of diverse processing resources in modern SoCs, in an abundance of applications including embedded vision. Computer scientists describe computer vision, the use of digital processing and intelligent algorithms to interpret meaning from still and …

OpenCL Eases Development of Computer Vision Software for Heterogeneous Processors Read More +

logo_2020

May 18 - 21, Santa Clara, California

The preeminent event for practical, deployable computer vision and visual AI, for product creators who want to bring visual intelligence to products.

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.

Contact

Address

1646 North California Blvd.,
Suite 360
Walnut Creek, CA 94596 USA

Phone
Phone: +1 (925) 954-1411
Scroll to Top //