Massive ISP Upgrades

I’ve been hearing for some time now that 2022 flagships will have massive camera upgrades, and the new features of the next-gen SoCs being described by MediaTek and now also Qualcomm explain why that is.

The new ISP of the Snapdragon 8 Gen 1 falls under a new marketing name – “Snapdragon Sight”, and includes large improvements of the capabilities of the IP blocks within the image processing chain.

The big flagship feature being advertised is the fact that the new ISP is now capable of 18-bits of color depth per channel, up from the previous generation 14-bit ISP. While mobile image sensors nowadays still are barely 12-bit native in terms of their ADCs, the ushering of new HDR techniques such as staggered HDR capture, where exposures are immediately subsequent to each other on the sensor’s readout, means that new phones now are able to capture images a lot faster, recombining them into higher bit-depth results. Particularly here, the new 18-bit ISP pipeline now allows for three exposure HDR stacking off these new sensors.

The increased bit-depth should allow for an increase of 4 stops in dynamic range (or 2^4 = 16x the range), which greatly helps with very contrasting environments and challenging lighting situations. This is quite beyond any other camera solution right now, and being able to have this implemented in such a hardware fashion sort of blurs the line between traditional image capture techniques and the more software-defined computational photography methods of the last few years.

Indeed, the new ISP architecture seems to be very much a way to implement many of the existing computational photography techniques into fixed-function blocks: there’s a new neural-net controlled 3AA (auto-exposure, auto-focus, auto-white-balance) and face detection block, which sounds eerily similar to Google’s HDRnet implementations.

Night mode is also said to be vastly improved through a new multi-frame noise reduction and image stacking block, being able to now stack and align up to 30 images, and achieve also much finer detail this generation. Qualcomm here claims up to 5x better night mode shots.

Further improvements include a new distortion correction block that’s able to now also correct for chromatic aberrations, and a hardware video Bokeh engine, being able to operate at up to 4K video recording. Think of it as the same as the new Cinematic mode on the new A15 iPhones, but not only limited to 1080p.

Qualcomm notes that all the AI/ML/neural network features on the ISP are actually run and accelerated on the ISP itself, meaning that it is not offloaded onto the Hexagon dedicated ML processing blocks or the GPU.

Just as a note- Qualcomm’s 3.2Gigapixel/s throughput metric here seems low compared to the Dimensity 9000’s 9Gpixel/s, it’s possible that the companies are advertising very different metrics, with MediaTek advertising the throughput of lower-bit depth pixels coming from the image sensors per frame, while Qualcomm quoting the full bit depth pixel processing within the ISP itself.

In terms of video encoders and decoders, the new chip allows for 8K HDR recording now, but otherwise is seemingly on par with the Snapdragon 888 media blocks. Unfortunately, this also means no AV1 decoding this year yet again. Qualcomm isn’t part of the Alliance for Open Media consortium and instead is backing VVC/H.266 and EVC, however with AV1 being actively pushed by Google and YouTube, and seeing large adoptions such as by Netflix, it’s becoming questionable for Qualcomm to still not support the format in 2022 devices.

AI Performance - Iterative, but solid

Last year’s Hexagon IP block was a very large change for the Snapdragon 888. At the time, Qualcomm moved on from a more segregated DSP/AI architecture to a single more fused-together block being able to operate on scalar, vector, and tensor operations at the same time. This year’s iteration is an improvement of that larger change. Qualcomm notes that amongst many changes, they’ve doubled up on the shared memory of the block, allowing for greater performance for larger ML models (which are growing at a very fast pace).

Qualcomm didn’t note any TOPS figures this time around, instead stating we’re seeing 2x the tensor throughput performance, and smaller increases for scalar and vector processing. They do quote a day-1 to day-1 performance increase of 4x when compared to the Snapdragon 888, via a combination of both hardware and software improvements, but of course that figure is smaller when comparing both platforms on an equal software footing.

Power efficiency for AI workloads is said to be 70% better this generation, which is actually more significant, and should help with more demanding sustained ML workloads.

X65 Modem Integrated

In terms of connectivity, the Snapdragon 8 Gen 1 is quite straightforward, as it integrates the X65 modem IP that Qualcomm had already announced as a discrete model earlier this year.

The improvements here are the fact that it’s a 3GPP Release 16 compatible modem, including new features such as uplink carrier aggregation. Other improvements are 300MHz of Sub-6 bandwidth on 3 100MHz carriers, and an increase of the mmWave bandwidth from 800 MHz to 1000MHz, allowing a new peak theoretical downlink speeds of 10Gbps.

Introduction & Specifications - CPU & GPU Conclusion & First Impressions
Comments Locked

219 Comments

View All Comments

  • ChrisGX - Wednesday, December 1, 2021 - link

    For the record, MediaTek Dimensity 1200 and Google Tensor have AV1 decode now and we know that the MediaTek Dimensity 9000 and Kompanio 1200 and 1300T will support AV1 decode in 2022. The list of processors supporting AV1 decode will probably grow longer before the end of 2022. The Dimensity 9000, unlike the others, will support 8K playback (in addition to 4K).
  • SydneyBlue120d - Wednesday, December 1, 2021 - link

    Is Dolby Vision encoding supported?
    I think it is only decoding.
    No AV1 support is just unqualifiable.
  • scarp - Wednesday, December 1, 2021 - link

    Lack of AV1 decoder is a deal breaker for me. So unimpressed.
  • Nicon0s - Wednesday, December 1, 2021 - link

    So buy an iphone, oh wait...
  • 69369369 - Wednesday, December 1, 2021 - link

    Yawn. Nuvia cores or bust.
  • tkSteveFOX - Wednesday, December 1, 2021 - link

    Big doubt about the numbers Nuvia showed and Qualcomm actually going full custom cores. Definitely not before 2023, if ever.
  • Kangal - Thursday, December 2, 2021 - link

    Nuvia cores seem impressive.
    Whilst ARM cores are still struggling to catch up to the Apple A13, Nuvia cores are better than the latest Apple A15 cores. The caveat being that we will never buy those Nuvia cores on a phone.

    Qualcomm is going all-in by using Nuvia's cores in an Apple M1 type of configuration. So we will see some Windows 11s/Pro tablets and laptops releasing with it in the next 6-12 months.

    We might even get an Nvidia Shield TV competitor, just a Mini Box similar to the Mac Mini but running the Apple M1 equivalent Nuvia-Snapdragon. Possible but I doubt it.
  • michael2k - Thursday, December 2, 2021 - link

    But there are no Nuvia cores. They aren’t supposed to be out until 2023, which would align with Cortex X3 and X4 designs, as well as M2 or M3 parts.
  • Kangal - Thursday, December 2, 2021 - link

    Yeah, you're right.
    I thought we were getting some Qualcomm-Nuvia chips in like June 2022. I didn't see that they pushed it back to 2023. Right now, they're releasing the Snapdragon 8cx Gen3.

    By the time the Q-Nuvia chip releases, we should have the Cortex-X3 processor which is going to be a major design overhaul. So it's likely it will catch up to the Q-Nuvia projected performance anyways... and on top, it would be ARMv9 based whilst the Nuvia was designed per ARMv8 protocol.

    Even more troubling we will see the Apple A16 and then A17 at that period. Both expected to raise the performance envelope, so they'll be somewhat competing from that end. Also there's the Apple M2, Pro, Max chipsets that are likely to be released around the same time... and they would likely destroy the Q-Nuvia devices in efficiency and performance and software support.
  • mode_13h - Friday, December 3, 2021 - link

    > we should have the Cortex-X3 processor which is going to be a major design overhaul.

    According to whom? Or, are you saying that because there's an overhaul expected in the A710-successor, which is the likely basis for the X3?

    > So it's likely it will catch up to the Q-Nuvia projected performance anyways...

    That's like saying X3 will beat Apple, which I think is a stretch.

    > the Nuvia was designed per ARMv8 protocol.

    How do you know? And ARMv9 isn't so different than later ARMv8. If they weren't very far along when they learned of v9, they could've conceivably re-targeted.

    > the Apple ... released around the same time... ... would likely destroy
    > the Q-Nuvia devices in ... software support.

    Granted, Qualcomm's laptop ambitions are largely dependent on the success of Windows-on-ARM. That aside, I don't see you point about software support. Apple exists in its own world. Of course their software support will be strong. I just don't really see what that has to do with Qualcomm.

Log in

Don't have an account? Sign up now