Vivante Corporation announces milestones that prove its combination of high performance graphics technology and vision capabilities make for a perfect IP choice for leading automotive semiconductor suppliers. Already a recognized industry leader in GPU solutions for automotive display, visualization and vision processing Vivante now adds two milestones – the addition of a leading automotive SoC partner and Vivante GPU design wins with existing SoC partners at seven of the top ten automotive vehicle manufacturers (OEMs). These design wins are the result of Vivante's industry-leading PPA, commitment to the automotive industry, and rapid adoption of cutting-edge API standards and safety-certifiable (ISO 26262 / ASIL-B) solutions. The recent addition of a top three 2014 OE Automotive Semiconductor Vendor as a Vivante GPU licensee and silicon partner adds to the breadth of automotive SoC solutions offered by Vivante partners and creates additional economies of scale for Vivante solution integrators and Vivante ecosystem partners.
Next generation in-car electronics have moved well beyond navigation, entertainment and HMI (human-machine interface) display to include intelligent safety monitoring, occupant protection systems and a path to ubiquitous partial and fully autonomous driving systems. The automotive OEMs that build compelling consumer centric HMI / entertainment IVI (in-vehicle infotainment) and advanced safety and autonomous driving features will be the ones enjoying higher automobile profitability, and the best selling models will be the ones that create the most immersive in-car automation experience in a safe environment where the vehicle is "aware" of its surroundings. Vivante GPU technologies enable automotive OEMs to realize both types of technologies with 3D graphics for visual eye candy and Vision Processing using industry standard compute APIs OpenVX and OpenCL for safety applications.
3D, Composition and Vector Graphics
The migration towards a visual-centric automobile console shows the importance of the GPU and how it has changed from a nice-to-have feature to a must-have requirement that sways technology decisions in the automotive ecosystem. The next generation of automotive GPU requirements goes well beyond what is available in today's showrooms to vehicles on the drawing board for the upcoming decade. Vivante Corporation burst onto the automotive scene in 2010 with silicon partner integrations demonstrating a differentiated approach to rendering and a set of GPU solutions that were optimized for the automotive market with breakthrough capabilities.
"Vivante has focused the full energy of the company to meet the requirements of the automotive market and the effort has paid dividends in both differentiated products and increasing volumes as designs reach mass production," said Wei-Jin Dai, President and CEO of Vivante. "Over the past seven years, Vivante has been collaborating closely with silicon partners, OEMs and their leading tier one platform suppliers as well a broad range of software and services suppliers to enhance the user experience and to lower the cost and complexity of adding advanced graphics to broaden the adoption to the mainstream of graphics rich instrument clusters, information and safety heads up displays (HUD), and center console radio/HMI/IVI/ADAS displays. Today Vivante silicon partners and their customers are delivering the broadest set of GPU capabilities in the market from model years in the 2020s and beyond – including ultra high performance multi-cluster secure virtualization (MCSV) ultra high definition GPUs and ultra-efficient DDR-less vector graphics and composition CPC solutions."
Vivante has been leading the industry in a number of key areas as our GPU solutions have become pervasive in automotive SoC products with differentiated features including:
Industry Leading PPA – In generation after generation Vivante is the clear leader in GPU rendering as measured by the performance delivered per square millimeter, or per milliwatt of power consumption, which enables Vivante silicon partners to offer the widest range of cost and power effective solutions.
Advanced Desktop GPU Features - Vivante was the first GPU vendor to deliver silicon partner integration ready state of the art rendering pipeline including hardware tessellation and geometry shaders now defined in the OpenGL ES 3.2 API standard. Automotive OEMs have welcomed these advanced capabilities to enable differentiated user experiences for future platforms in definition today.
Vulkan API - Vulkan is a new close to the metal graphics and compute API that improves performance by providing direct access to Vivante GPU hardware. Vulkan is ideally suited to automotive applications, allowing the application developer and ecosystem partners to manage memory and multiple threads to squeeze the most out available GPU resources in both future and current generation Vivante powered automotive SoCs.
GPU Virtualization – Starting with the GC7000 series, Vivante offers true hardware virtualization of the GPU cluster with the multi-cluster secure virtualization (MCSV) option. MCSV enables the GPU to be physically subdivided as independent hardware resources with independent software contexts and secure hardware memory management enabling secure and non-trusted operating systems to operate in parallel with separate resources and guaranteed quality of service.
Dynamic Rendering – Automotive display rendering poses unique challenges for efficient rendering that are fundamentally different from 3D games and most game oriented GPU benchmarks. Vivante's patented Dynamic Rendering technology enables very small changes to an HMI, safety or instrument cluster display to be accomplished with minimal CPU overhead and DDR resources and without the large driver footprint and initialization times associated with game content optimized chunking techniques.
DDR-less Rendering – Small displays and new categories of informational and safety display are increasingly moving to more complex rendering. To control system cost and power characteristics, Vivante developed a new class of vector graphics and entry level OpenGL ES 2.0 devices that do not require a traditional frame buffer and the associated cost and power consuming DDR memory subsystems.
Automotive Vision and Compute
Automakers are working on harnessing the massively parallel processing power of GPUs to reduce parallel algorithm execution times and speed-up real-time response in ADAS. Since the GPU is inherently efficient at both massively parallel compute algorithms like neural networks in addition to image and pixel processing, incoming pixel data from camera sensors and other sensors that are parallel in nature can be sent through the GPU to be processed for visualization in surround view and augmented reality. In addition, the compute API OpenCL and vision processing API OpenVX help process parallel data streams (sensor fusion) from cameras, GPS/WiFi positioning data, accelerometers, radar, and LIDAR to guide vehicles safely. Current solutions focus on computer vision (CV) as a first step, but moving forward data from other sensors can be sent to the GPU to offload other computational resources in a system. Autonomous cars like Google's driverless car and those in DARPA competitions have already demonstrated what the future of ADAS will evolve into and these same requirements are driving the next generation of Vivante silicon partner solutions. Vivante has licensed to a current silicon partner a highly configurable vision processing capability that can be added to a traditional GPU or configured as a separate compute/vision engine with an independent context or for applications without rendering requirements.
Safety Features and Standards
The term ADAS or Advanced Driver Assistance Systems describes the latest electronic technologies found in vehicles that focus on increasing safety for occupants, pedestrians, and surrounding vehicles. Features included in ADAS that monitor, predict, and try to prevent accidents include active safety monitoring, collision avoidance systems (CAS), object/pedestrian recognition, lane departure warning, adaptive cruise control, and more. Current solutions use a combination of DSPs, CPUs, and in some cases FPGA with built-in computational units to perform safety monitoring. These solutions use hand written code for specific products, making them harder to port to new platforms or when changing components like DSPs or CPUs. Vivante's solutions enable automotive electronics system developers to overcome these limitations by writing algorithms in OpenCL and or OpenVX and using OpenCV libraries for fast prototyping. The resulting code can be re-used across various platforms and maintained by a generation of software developers with expertise in these industry standards. Vivante, together with ecosystem and silicon partners is offering safety certifiable ISO 26262 / ASIL solutions, initially targeting ASIL-B informational certifiable hardware and software solutions with a path to ASIL-D for systems with active control of bakes, steering and accelerator.
About Vivante Corporation
Smaller – Faster – Cooler: Vivante Corporation, a leader in dedicated Vision Processing and multi-core GPU, Compute, CPC Composition Engine and Vector Graphics IP solutions, provides the highest performance and lowest power silicon characteristics across a range of Khronos Group API conformant standards based on the Vega architecture. Vivante GPUs are integrated into customer silicon in devices targeting wearables, IoT, smartphones, tablets, HDTVs, automotive, consumer electronics and other embedded devices and running thousands of graphics/compute applications across multiple operating systems and software platforms. Vivante is a privately held company headquartered in Santa Clara, California, with additional R&D centers in Shanghai and Chengdu.