Connect with us

Tech

Smartphones to Genius-Phones with Snapdragon 8 Gen 3

Published

on

Snapdragon 8 Gen 3

Smartphones to Genius-Phones with Snapdragon 8 Gen 3

 

I believed that the smartphone industry was beginning to shift from smartphones to “genius-phones” around ten years ago, when the first smartphones began utilizing on-board sensors like the camera and microphone to interact with the outside world.

Advertisements

With hindsight, it’s evident that those were only the beginning of that evolutionary journey. During the first day of the 2023 Snapdragon Summit last week, Qualcomm unveiled the next steps with the release of their mobile SoC, the Snapdragon 8 Gen 3.

The goal of this most recent mobile SoC is to enable generative AI on the device. Previously, Qualcomm used its earlier generation mobile SoC to demonstrate a Stable Diffusion text-to-image generative artificial intelligence (genAI) model with about 1 billion parameters. With over 10 billion parameters on phones and over 13 billion parameters on PCs, this most recent version supports genAI models.

Advertisements

READ OnePlus has released OxygenOS 14 Open Beta 1 for the Nord 3

The speed at which the device can return outputs from those models is another important metric to consider, in addition to model size. Depending on the model, the Snapdragon 8 Gen 3 delivers 15–30 tokens per second and produces images in less than a second.

Advertisements

Qualcomm’s most recent AI Engine and AI Stack leverage generational improvements to enable the aforementioned capabilities.

The newest Adreno GPU, Kryo CPU, Hexagon neural processing unit (NPU), Sensing Hub, and supporting memory architecture make up the Snapdragon 8 Gen 3’s AI Engine, which Qualcomm claims offers up to 98% faster performance and 40% more power efficiency than the previous generation.

Advertisements

 

The GPU has been upgraded to not only enable real-time hardware-accelerated ray tracing but now provides global illumination support, as well as various gaming and hardware-accelerated image and video encoding/decoding enhancements.

Based on a 64-bit Arm Cortex-X4 architecture, Qualcomm upgraded the CPU to have five performance cores and two efficiency cores instead of the previous 4+3 configuration. In conjunction with one primary core, which can be clocked up to 3.3 GHz, the performance cores are capable of running at up to 3.2 GHz, while the efficiency cores support a clock rate of up to 2.3 GHz.

Advertisements

The NPU consists of scalar, vector, and tensor accelerators and has been upgraded with an enhanced power delivery system and micro tile inferencing to help with performance versus power optimization. Micro tile inferencing is the technique Qualcomm uses in its Hexagon NPU’s scalar accelerator. Ignacio Contreras, Qualcomm’s senior director of product marketing, explained that with micro tile inferencing, they can “slice neural network layers up in even smaller micro tiles to speed up the inferencing process of deep and complex neural networks and achieve even better power savings.”

Additionally, to enable multiple model modalities, as well as optimizing model size versus accuracy and latency, the NPU supports INT4, INT8, INT16 and FP16 data types.

Advertisements

Last but certainly not least, given the critical role the on-board sensors like the cameras and microphones play in personalizing the on-device generative AI experience, the Sensing Hub has also been updated to yield up to 3.5× the AI performance compared to the previous generation with two micro NPUs, 30% more memory and two always-sensing image sensor processors (ISPs). The Snapdragon 8 Gen 3 is also equipped with a 12-layer cognitive ISP.

Upgraded intelligence

Ultimately, it’s not just about performance or increased intelligence. It’s about what you can really do with it. Support for increased model parameter sizes, the Sensing Hub and ISP improvements, and upgraded memory architecture allow the SoC to support one of the most critical features for ensuring maximum AI capability and the most natural way of interacting with those capabilities: multi-modal model support.

Advertisements

Just as humans interact with each other and the world around them through a combination of speech, sight, feel and hearing, interactions with on-device AI should also support voice/audio, text, image, and physical sensor sampling, such as with infrared sensors and video. Multi-modal model capability allows a device to ingest all these types of input prompts, as well as output different types of content from the written or spoken word to pictures and video clips.

Advertisements

For example, increased performance and multi-modal model support enables on-device photo expansion. This feature comes in handy when the user wants to resize an image without distorting it or reducing the image resolution. Take, for instance, a user who shot a picture in portrait mode for use in a social media post.

Using the same image as a banner advertisement now requires nothing more than a  finger tap or even a speech prompt to direct the device to expand the image with a new aspect ratio and fill the empty expanded space with new content that seamlessly matches the existing background through the use of generative AI.

Advertisements

ALSO Xiaomi To Equip Its Cars With An Internal Combustion Engine

The digital versions of speech, sight and hearing are relatively straightforward. However, how can a device use ‘feel’ as an input? The answer is through the use of different sensors, such as time-of-flight and infrared sensors.

Advertisements

One example Qualcomm demonstrated at the recent Snapdragon Summit was the use of a time-of-flight sensor to sample the number of particles present in the air and, using AI, determine the air quality to see if it’s safe to exercise outside. Another demonstration used infrared sensors with an AI model running on a phone that determined an individual’s hydration level with a touch of their skin or determined a cookie’s freshness after it had been left out.

Next steps

The first wave of devices based on the new Snapdragon 8 gen 3 SoC  will appear this quarter from smartphone OEMs. However, this is just the beginning of the transition from smartphones to genius-phones. Ongoing research and development, as well as the competitive landscape, will deliver even more performance, efficiency and ultimately, AI capability over the next few years.

Advertisements

As the industry and use cases mature and become more sophisticated, the AI experience will also be refined. We will carry personalized AI models, that we have fine-tuned by using them, from device to device. It’s not that difficult to imagine a situation where the AI models on our devices will learn about our preferences and interests and we won’t want to start from scratch when we move between phone, laptop and car.

As we continue down this path, it’s clear that the next generation of genius, AI-powered phones is an evolutionary step towards a whole new world of use cases and experiences. It will be exciting to see by this time next year how big the next step will be.

Advertisements
Continue Reading
Advertisement
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Tech

My Everyday Tech Essentials 2024 (EDC)

Published

on

My Everyday Tech Essentials

My Everyday Tech Essentials 2024 (EDC)

 

As a young and beginner tech content creator, i always want to keep my followers and friends updated on how i shoot and do my stuff online.

ALSO oraimo Discount Code

Advertisements

In this video, i made reviews on the various tech gadgets i carry along anytime i go out to create content.

From my iPhone to my favorite oraimo BoomPop2 and many others,

Advertisements

 

Watch Video below:

Advertisements
Continue Reading

Tech

Gemini To Get Assistant Routines

Published

on

Gemini

Gemini To Get Assistant Routines

 

Assistant Routines may soon be supported on Gemini, according to an APK dissection of the Google app.
One of the main reasons so many are using Google Assistant rather than signing up for Gemini is that it lacks routines.
Regretfully, neither the precise integration of Routines into Gemini nor the possible release date are known

Advertisements

ALSO Unlock Google’s Reverse Image Search Potential

 

Google first launched Google Assistant Routines back in 2017. You can use this functionality to perform several actions with a single voice command. Saying “Hey Google, let’s watch a movie,” for instance, would cause Assistant to simultaneously turn out the lights, switch on the TV, and put your phone in do not disturb mode.

Advertisements

Even while Google is pitching Gemini, its generative AI-powered assistant, as a replacement for Google Assistant, Gemini still lacks Routines-like functionality. Fortunately, that might not last long.

Based on work-in-progress code, an APK breakdown assists in forecasting features that might be added to a service in the future. It’s possible, though, that these anticipated features won’t be released to the general public.

Advertisements

READ Google Bard : Create Social Media Content With AI

The Google app for Android is now in beta version 15.24.28.29.arm64 beta. We discovered a work-in-progress page that makes explicit reference to Assistant Routines and how Gemini would support them. This page is viewable in the screenshot below, which we must stress is a work in progress:

Advertisements

Assistant Routines

Based on the information available on this website, it seems that Gemini will not be getting its own Routines system—at least not quite yet. Rather, it seems that Gemini will allow you to manage Assistant Routines. It will be awkward because you will have to use Assistant to create new routines and Gemini to activate them, but at least it’s an improvement over nothing.

Advertisements

While there are many additional features that Assistant can perform that Gemini cannot, one of the main drawbacks that keep Android users from fully committing to Gemini is likely the inability to control routines. If nothing else, this APK disassembly demonstrates Google’s ongoing efforts to bring Gemini’s features up to line with Assistant.

Advertisements

Regretfully, we are unsure of the timeline for when this functionality will be activated. However, given that it’s showing up in beta code, we anticipate it to be available in a few weeks or months.

Continue Reading

Reviews

oraimo Discount Code

Published

on

oraimo Discount Code

oraimo Discount Code

 

oraimo is currently one of the most leading online shop for your fashion, tech, home and office needs. In times of bulk purchasing, you might be wondering if you can save some money on items you shop from oraimo.

READ oraimo BoomPop2 Unboxing and Review

Advertisements

In this post i will give you a permanent oraimo discount code which offers 5% discount on all orders. It works for Ghana, Nigeria, Kenya and Cameroon so that’s a good news if you reside in any of these countries.

Advertisements

The discount code is kwami20 and it can be used on all orders via their official website only.

You can access their official website here

Advertisements

 

 

Continue Reading

Trending