Imagination delivers industry's first visually lossless image compression for GPUs with a guaranteed reduction in memory footprint
PowerVR PVRIC4™ technology provides significant cost savings for memory and bandwidth-constrained devices such as DTVs, smartphones and tablets
London, UK and Santa Clara, California; 31st October 2018 – Imagination Technologies announces the groundbreaking PowerVR PVRIC4, the new generation of its powerful image compression technology which will enable SoC customers targeting devices such as DTVs, smartphones and tablets to reduce costs without a discernible loss of image quality. PVRIC4 enables random-access visually lossless image compression, ensuring bandwidth and memory footprint savings of at least 50%, and enabling systems to overcome performance bandwidth constraints.
Imagination provides PVRIC4 as a standalone IP block for SoC manufacturers to integrate into their multimedia pipelines. The block is already used by Imagination partners including Chips&Media who have access to PVRIC4 as part of a recent collaboration to deliver an optimum solution for a system leveraging a PowerVR GPU and WAVE5 video codec.
Linley Gwennap, principal analyst of The Linley Group, says: “Imagination’s PVRIC4 is a significant advancement for GPU compression technology. The increasing demands on memory bandwidth and footprint are a real concern for SoC manufacturers, so the ability to combine lossless and visually lossless compression delivers both cost and bandwidth savings.”
PVRIC4 features a dual-pipeline framebuffer compression engine. A new lossy pipeline, used only if the lossless pipeline does not achieve 50% compression, ensures that even difficult to compress ‘noisy’ images are compressed with the highest fidelity. A decision logic block determines which output should be used to guarantee the compression ratio, and due to highly tuned algorithms, the image quality change is imperceptible. Thanks to this hybrid solution, PVRIC4 offers SoC manufacturers the best of both approaches, with the highest fidelity ensuring bandwidth and frame buffer allocation savings on graphics and video content. This is all performed in hardware and achieved without any performance overhead.
PVRIC4’s bandwidth savings translate into better battery life for consumers and cost savings for system manufacturers, enabling more RAM and bandwidth to be freed for other uses, such as enabling simultaneous fast 5G downloads while the GPU is in use, or a reduction in the number of DRAM devices used in the system.
Nigel Leeder, executive vice president, PowerVR, Imagination, says: “With the increasing demands introduced by higher resolution 4K and 8K displays as well as the desire to reduce system costs, the need to minimize memory bandwidth is an ongoing priority for our customers. They require a solution that keeps costs and power down. By introducing visually lossless compression into our GPUs, we can now guarantee a reduction in memory bandwidth and usage.”
PVRIC4 will be available as a feature in next-generation PowerVR GPUs and is available for licensing now as a standalone IP block. For further information, please contact info@imgtec.com.
Related Semiconductor IP
- MIL-STD-1553 Controller IP
- UFS 5.x Device IP
- UCIe 3.x Controller IP
- Ethernet 800G PCS IP
- CHI to UCIe Bridge IP
Related News
- Imagination announces major updates to PowerVR SDK and Toolkit, including ray tracing code examples.
- Imagination's PowerVR architecture marks its 30th anniversary
- Imagination PowerVR SDK wins Design Tool and Development Software Product of the Year
- Is Imagination Technologies China’s backdoor to AI tech?
Latest News
- StarFive and LECARC Forge Partnership to Co-Develop RISC-V Server CPUs and Seize New Opportunities in the Agentic AI Era
- ASICLAND Selected as SK hynix’s Partner for Next-Gen eSSD Development, Establishing a ‘K-Semiconductor Win-Win’ Model
- onsemi to Acquire Synaptics to Enable the Next Generation of Intelligent Systems for Physical AI
- EdgeAI Licensed Andes Technology CPU IP to Power Next-Generation Edge AI Neuromorphic Solution
- Jim Keller: ‘AI Still Obeys the Old Laws of Compute’