Skip to content
POWERVR GRAPHICS ARCHITECTURES
Graphics processor technologies are the de-facto standard for mobile and embedded GPUs.
Advanced scalable graphics architectures
IMG A-Series
The new IMG A-Series is the next generation of graphics architecture delivering the latest evolution of the PowerVR TBDR architecture. Fetauring a number of new features and improvements to previous ones including a redesigned ALU, performance scalability, configurable cache sizes, HyperLane Technology, AI Synergy and GPU tile heatmap.
PowerVR Furian
PowerVR Furian architecture is a new architecture for embedded GPUs, the successor to the industry-leading PowerVR Rogue architecture. The new architecture brings about a large number of completely changed blocks for improved performance, power and density. It encompasses significant improvements made to Rogue.
PowerVR Rogue
PowerVR Rogue designs enable our partners to deliver amazing user experiences in devices that range from innovative, ‘natural’ user interfaces to ultra-realistic gaming, as well as enabling new applications never before thought of, from advanced content creation and image processing to sophisticated augmented reality.
PowerVR Ray Tracing
PowerVR ray tracing graphics IP is highly scalable, making it potentially disruptive to many markets from mobile to high-end gaming and the creative arts enabling more immersive games and apps with real-life dynamic lighting models that produce advanced lighting effects, dynamic soft shadows, and life-like reflections and transparencies.
Tile Based Deferred Rendering (TBDR) architecture
All PowerVR GPUs are based on our unique Tile Based Deferred Rendering (TBDR) architecture; the only true deferred rendering GPU architecture in the world. TBDR combines two complementary architectural features to provide the very highest levels of efficiency and performance.
Tile-Based Rendering
The PowerVR architecture splits the screen into a number of ‘tiles’, which are then processed individually (in parallel to other tiles). Since the GPU only needs to work on a subset of the complete scene data at any given time, this data (such as colour and depth buffers) is small enough to be stored in internal GPU memory, significantly reducing the required number of accesses to system level memory. This results in lower energy and bandwidth consumption and also higher performance.
Deferred Rendering
PowerVR deferred rendering uses a unique, patented method of Hidden Surface Removal which defers all texturing and shading operations until the visibility of each pixel in the tile is known – only the pixels that will actually be seen by the end user consume processing resources. This means that unnecessary processing of hidden pixels is eliminated, which further ensures the lowest possible bandwidth usage and number of processing cycles per frame, resulting in the highest performance levels and the lowest power consumption.
Virtualization and Security
GPU virtualization is now a must-have for a range of next-generation applications, from automotive, to consumer electronics, to the IoT. GPUs that implement hardware virtualization can provide isolation between the various applications/OSs for increased security, as well as maximum utilisation of the underlying GPU hardware. PowerVR GPUs, from Series6XT onwards, support hardware virtualization and in Series8XT its capabilities have been further enhanced.
PVR3C Compression
PowerVR GPUs feature PVR3C Triple Compression, a suite of three compression technologies to ensure the most efficient use of memory bandwidth. Image compression (PVRIC), texture compression (PVRTC, ASTC) and geometry compression (PVRGC) can significantly reduce system-level memory accesses required by the GPU. Benefits of reduced memory bandwidth consumption include lower power consumption, better overall system efficiency and reduced system-level memory costs.
PVRIC4
Available in future PowerVR GPUs, PVRIC4 implements a dual-pipeline architecture that simultaneously passes data through lossless and visually lossless compression pipelines and automatically chooses between them to deliver a guaranteed minimum 50% reduction in memory footprint and at least a 50% reduction in system bandwidth. This enables SoC manufactures to reduce costs and optimise power consumption.
Texture
Enabling the compression of textures can significantly reduce application file size and download times; it also dramatically improves runtime performance and power consumption by keeping bandwidth usage to an absolute minimum. PowerVR GPUs provide support for a number of industry-standard texture compression formats.
Geometry
To manage the increasing geometry complexity of 3D scenes, PowerVR GPUs can include PVRGC (PowerVR Geometry Compression) . PVRGC minimises memory usage by automatically compressing the intermediate geometry parameter data that is written to memory as part of the tiling process. The data is then automatically decompressed as it is read back into the GPU later in the pipeline.
Related blog articles
The Android Invasion: Imagination GPU IP buddies up with Google-powered devices
December 14, 2020
Google Android continues to have the lion share of the mobile market, powering around 75% of all smartphones and tablets, making it the most used operating system in the world. Imagination’s PowerVR architecture-based IP and the Android OS are bedfellows, with a host of devices based on Android coming to market all the time. Here we list a few that have appeared in Q4 2020.
Back in the high-performance game
October 13, 2020
My first encounter with the PowerVR GPU was helping the then VideoLogic launch boards for Matrox in Europe. Not long after I joined the company, working on the rebrand to Imagination Technologies and promoting both our own VideoLogic-branded boards and those of our partners using ST’s Kyro processors. There were tens of board partners but only for one brief moment did we have two partners in the desktop space: NEC and ST.
What is PVRTune Complete?
August 10, 2020
PVR Tune Complete highlights exactly what the application is doing at the GPU level, helping to identify any bottlenecks in the compute stage, the renderer, and the tiler.
