Back in March of this year, Imagination announced their next-generation GPU architecture: Furian. Their first new architecture since Rogue in 2010, Furian iterates off of what Imagination has learned in the intervening years to further improve their architecture’s performance, power efficiency, and die area efficiency. At the time the company only announced the architecture and not any GPU designs based off of it, but today they are taking the wraps off of the first Furian design: the PowerVR Series 8XT GT8525.

With their first design, Imagination is taking the pragmatic route – or as they like to put it, the balanced route. Outside of Apple, most of Imagination’s customers have been licensing two cluster designs from the high-performance PowerVR families (6XT, 7XT, 7XT+), so this is where Imagination is starting for Furian and the new Series 8XT.

By and large then, the GT8525 is exactly what you’d expect for a 2 cluster design based on Imagination’s earlier disclosure. 2 clusters are by design intended to fit inside of one of Imagination’s shader processing units, giving the design a single such unit.

The significance of this choice, besides being the smallest possible full implementation of Furian (before you start removing pieces from the design and get fractional) is that one of the areas Imagination focused on was improving the pixel and texel throughput at this level. As a result, a 2 cluster Furian design offers 8 pixels and 8 bilinear filtered texels per clock whereas a 2 cluster Rogue (e.g. GT7200) offered 4 of each. So even though it’s still only 2 clusters, even after you ignore the architectural improvements, there’s actually a lot more hardware working in a 2 cluster design.

PowerVR GPU Comparison
  GT8525 GT7200 Plus
Clusters 2 2
FP32 FLOPS/Clock 192
(128 MAD + 64 MUL)
FP16 Ratio 2:1 (Vec2) 2:1 (Vec2)
Pixels/Clock (ROPs) 8 4
Texels/Clock 8 4
APIs OpenGL ES 3.2 + Vulkan OpenGL ES 3.2 + Vulkan
OpenCL 2.x 2.0
Architecture Furian Rogue

By the numbers, Imagination is touting some rather significant performance improvements for GT8525 over its predecessor, GT7200. 50% faster performance in GFXBench Manhattan, 80% faster in GFXBench T-Rex, 50% more (on paper) FLOPS, etc. All of this would be at equal clockspeeds, though the company isn’t talking about power consumption or die size right now, so it’s hard to get a feel for where energy and area efficiency of the new design stands.

With this 2 cluster design, Imagination is going to be pursuing a mix of markets, though ultimately it’s up to SoC venders to build suitable SoCs. This includes smartphones, of course, but also mobile VR, which is a growing market that has a lot of potential for GPU vendors like Imagination given the performance requirements. The company is also pitching the new GPU design for the automotive market, where along with infotainment duties, a 2 cluster design should be powerful enough for some light ADAS work (presumably just doing computer vision on one or two camera streams).

To that end, the company has also announced that the design has already been delivered to their (unnamed) lead customer. Traditionally this would be Apple, but of course we know that Apple will be rolling out their own GPU architecture starting in the next 1-2 years. Instead this could be the likes of MediaTek or another at-large SoC vendor. In any case it’s possible we’ll see the devices using this design in 2018, though it’s ultimately up to the SoC vendor and device vendor on how quickly they want to move.

More broadly speaking, Furian and the GT8525 will be a critical product for Imagination. As the company announced last week, they are doubling-down on their GPU products and selling off everything else. Without Apple,  they need to capture a larger part of the GPU market share in smartphones and other embedded devices. Consequently, starting with a  2 cluster design is the smart choice here, as 2 cluster designs are going to have the highest volume.

Comments Locked


View All Comments

  • Alexvrb - Wednesday, May 10, 2017 - link

    that's not where*

    I usually try to proofread. Sigh.
  • rahvin - Wednesday, May 10, 2017 - link

    Apple announced they will stop using PowerVR within 2 years. It's expected that either the next iteration of their chips or the one after will be using an internally developed GPU.

    This was all over the financial news because Apple accounts for 75% of the revenue of Imagination. If Apple does switch as they've said and this is 2 years out it likely will never see the light of day when Imagination goes bankrupt before they can develop it.
  • Yojimbo - Wednesday, May 10, 2017 - link

    I wonder what's going to happen to Imagination's ray tracing acceleration efforts. I know OTOY has shown interest in it. Although, OTOY promised to have CUDA cross-compiling support for non-CUDA architectures in OctaneRender by now, which is something they'd need in order to use PowerVR GPUs, and they haven't released it, yet. I suppose there's a chance they might skip OctaneRender 3.1 completely and move straight to 4, releasing the cross-compiling support at that time.
  • StrangerGuy - Wednesday, May 10, 2017 - link

    SoC CPU/GPU performance has reached a point where it is almost purely academic: The underlying economics of the software running on them simply doesn't demand much performance out of even budget SoCs. Doesn't matter whether its Android or iOS either: It's either targeting the lowest common denominator hardware for maximum ad-eyeballs or bust.
  • skavi - Wednesday, May 10, 2017 - link

    Mobile VR
  • osxandwindows - Wednesday, May 10, 2017 - link

    Faster chips are still needed for local machine learning, and AI.

    Local image recognition on the iPhone is still slow with the a10 fusion.
  • darkich - Friday, May 12, 2017 - link

    No you're all simoly just clueless about the state of mobile gaming.
    If anything, the GPU's are still way underpowered for the demands they are facing.
    I'll just go by examples - in order to provide 60fps on native high end smartphone and tablet resolution(1400p+) games such as CSR 2, Dawn of Titans, Legacy of Discord, Marvel Contest of Champions ,Modern Combat versus, Transformers Forget to fight, Battle Bay, NBA 2k 17...need AT LEAST 200-400 GFLOPS of raw GPU power.
    Now consider that mobile SoC's typically throttle to about 60% of their theoretic performance over the sustained gaming, and do the math.

    Fun fact- ALL the games mentioned above play at around 30fps on native resolution even on current highest end hardware (iPad Pro)
  • Mat3 - Wednesday, May 10, 2017 - link

    Was the Wizard GPU ever released?
  • Alexvrb - Thursday, May 11, 2017 - link

    It was released, in the way they release all their designs. Now if you're asking if a SoC manufacturer ever licensed and integrated Wizard into a product, I don't believe so. Without a major API vendor (Khronos, MS, Apple) supporting it, it's a niche feature.
  • Yojimbo - Thursday, May 11, 2017 - link

    Otoy said they are interested in taking advantage of it, but I haven't seen anything about that recently.

Log in

Don't have an account? Sign up now