IMG A-SERIES ARCHITECTURE
The fastest and smartest graphics processors ever created.
Introducing the Next Generation of Graphics Processors
The A-Series represents the latest evolution of the tile-based deferred rendering PowerVR architecture and contains numerous improvements that together make it up to 2.5x faster than currently shipping PowerVR designs.
A-Series features an ultra-wide arithmetic logic unit (ALU). This 128-wide design, simplified compared to previous generation architectures, enables greater parallelism for up to four times more operations per clock. Compiler optimisations ensure maximum utilisation resulting in a massive increase in performance per millimetre and greatly improved power efficiency.
The IMG A-Series’ multi-dimensional approach to performance scalability ranges from 1 pixel per clock (PPC) parts for the entry-level market right up to 2 TFLOP cores for performance devices, and beyond that to multi-core solutions for cloud applications. Thanks to its hierarchical scaling structure additional scalable processing units can be added to increase TFLOPS, Gigapixels and TOPS depending on performance, area and power requirements.
Configurable Cache Sizes
A-Series GPUs now contain cache configurability options. This allows implementers to significantly reduce GPU bandwidth requirements. This provides flexibility to reduce power, thermals and system cost.
HyperLane Technology offers individual hardware control lanes, each isolated in memory, enabling different tasks to be submitted to the GPU simultaneously for secure GPU multitasking. With Dynamic Performance Control, the GPU can spread its performance across these multiple tasks, executing them all, while maximising GPU utilisation. Priority HyperLanes deliver a dynamic split; for example, prioritising graphics and delivering all the required performance for that application while an AI task runs alongside using the remaining performance. HyperLane Technology can also isolate protected content for rights management. All IMG A-Series GPUs, even the smallest in area, support up to eight HyperLanes.
AI Synergy is a new option in that enables SoC designers to take advantage of the incredible levels of compute capability in the IMG A-Series to accelerate their AI workloads. Through AI Synergy the GPU delivers graphics performance, while using its spare resource to enable programmable AI alongside a fixed-function, highly-optimised Imagination neural network accelerator. AI Synergy delivers programmable AI in the lowest silicon area, while a unified software stack enables flexibility and great performance.
GPU Tile Heatmap
New software optimisation tools enable developers to quickly analyse frames to determine which tiles are the most graphically expensive to output so they can best focus their optimisations and ensure the best return on effort.