
UK IP developer Imagination Technologies has shown its next generation of mobile gaming graphic technology using hardware ray tracing.
Imagination’s CXT graphics processing unit for mobile chips is now running the Open 3D Engine (O3DE) for hardware-accelerated global illumination ray tracing. Imagination’s PowerVR Open Source GPU driver has been accepted into the Mesa 3D Graphics Library, starting the process for upstream Kernel contributions.
“Our two-decade journey set us on a path to revolutionise mobile gaming graphics. Today we’ve reached a true milestone in gaming performance, with a first of its kind hardware-accelerated mobile ray tracing solution. The recently announced IMG CXT GPU offers OEMs the possibility of unlocking RTLS Level 4 ray tracing capabilities, enabling more processes to be performed on hardware for greater efficiency,” said Chris Porthouse, Chief Product Officer at Imagination.
Related ray tracing articles
“As a part of our goal to bring efficient and innovative mobile ray-tracing capabilities to our developers, we have partnered with AWS to showcase our global illumination ray-tracing demonstration via the Open 3D Engine (O3DE),” he said.
“Working with companies such as Imagination helps drive the delivery of next-generation graphics capabilities to developers to shape the future of mobile gaming,” said Royal O’Brien, General Manager of Digital Media and Games at the Open 3D Foundation. “Mobile GPU solutions often compromise performance in favour of maintaining power efficiency. However, our collaboration with Imagination has enabled us to navigate these constraints efficiently while also unlocking innovative hardware-accelerated ray tracing on the open-source Open 3D Engine. We look forward to continuing our great work together.”
Ray tracing can be performed with varying levels of performance and efficiency and to highlight this Imagination established the Ray Tracing Levels System (RTLS), identifying six levels of ray tracing, from Level 0 to Level 5. The Photon architecture inside IMG CXT sits at Level 4 of the RTLS and supports up to 1.3GRay/s for desktop-quality ray traced images in a mobile chip with ray traced shadows, reflections, global illumination and ambient occlusion.
PowerVR Photon architecture features the RAC, a new low-power, dedicated hardware GPU block which accelerates and offloads more of the ray tracing computations from the shader cores. This consists of the Ray Store, Ray Task Scheduler and Coherency Gatherer and is closely coupled to two 128-wide Unified Shading Clusters (USCs) featuring high-speed dedicated data paths for the most efficient and lowest-power ray traced deployment.
The Ray Store keeps ray data structures on-chip during processing, providing high-bandwidth read and write access to all units in the RAC, avoiding slowdowns or power increases from storing or reading ray data to DRAM. The Ray Task Scheduler offloads the shader clusters, deploying and tracking ray workloads with dedicated hardware, keeping ray throughput high and power consumption low. The unique Coherency Gatherer unit analyses all rays in flight and bundles rays from across the scene into coherent groups enabling them to be processed with much greater efficiency.
Related articles
- Imagination launches four RISC-V processor IP families
- Unisoc and Imagination strategic partners on AI acceleration
- Neural network accelerator scales up multi-core AI
- Imagination in China lab RISC-V deal
- Multicore GPU aims at 3nm for data centre designs
Other articles on eeNews Europe
- Nexperia enters analog chip market with first US design centre
- Europe sees record year as global fab equipment spending hits new high
- Nvidia opens up NVLink for chiplets to take on PCI Express
- €3m for hybrid AI chip inspired by insects
- Pasqal puts quantum computer on Azure
- SiFive raises $175m for RISC-V design as a double unicorn