Wednesday, May 1st 2024

More than 500 AI Models Run Optimized on Intel Core Ultra Processors

Today, Intel announced it surpassed 500 AI models running optimized on new Intel Core Ultra processors - the industry's premier AI PC processor available in the market today, featuring new AI experiences, immersive graphics and optimal battery life. This significant milestone is a result of Intel's investment in client AI, the AI PC transformation, framework optimizations and AI tools including OpenVINO toolkit. The 500 models, which can be deployed across the central processing unit (CPU), graphics processing unit (GPU) and neural processing unit (NPU), are available across popular industry sources, including OpenVINO Model Zoo, Hugging Face, ONNX Model Zoo and PyTorch. The models draw from categories of local AI inferencing, including large language, diffusion, super resolution, object detection, image classification/segmentation, computer vision and others.

"Intel has a rich history of working with the ecosystem to bring AI applications to client devices, and today we celebrate another strong chapter in the heritage of client AI by surpassing 500 pre-trained AI models running optimized on Intel Core Ultra processors. This unmatched selection reflects our commitment to building not only the PC industry's most robust toolchain for AI developers, but a rock-solid foundation AI software users can implicitly trust."
-Robert Hallock, Intel vice president and general manager of AI and technical marketing in the Client Computing Group
Why It Matters: Surpassing 500 AI models is a landmark moment for Intel's efforts to nurture and support the AI PC transformation. Not only is the Intel Core Ultra processor the fastest-growing AI PC processor to date—selling more units in a single quarter than competing processors in all of 2023—it is also the most robust platform for AI PC development, with more AI models, frameworks and runtimes enabled than any other processor vendor.

Models form the backbone of AI-enhanced software features like object removal, image super resolution or text summarization. There is a direct link between the number of enabled/optimized models and the breadth of user-facing AI features that can be brought to market. Without a model, the feature cannot be designed. Without runtime optimization, the feature cannot reach its best performance.

How AI Models Work: AI models are one of many critical layers in the software stack that determine the ultimate performance, stability and capabilities of an AI-driven application. AI models are trained to analyze large quantities of data, draw conclusions and take actions based on such inferences. Developers creating new AI PC features can utilize these models and build on them. The more AI models there are, the more AI PC features are enabled.

AI models can act on text, speech, audio, images and other audiovisual sources common to the PC experience. AI models form the foundation of AI-enhanced features developed for users to enjoy, such as automatic text summarization, reducing energy consumption during teleconferencing or removing unwanted objects from a picture. OpenVINO optimizes for Intel Core Ultra by load-balancing across all the compute units, compressing the models to run efficiently in an AI PC, and optimizing the runtime to take advantage of memory bandwidth and core architecture within Intel Core Ultra.

Continuous efforts to enable an unmatched set of high-performance models on Intel Core Ultra offer a wide field of innovation for software developers and simplifies the delivery of AI PC applications and features to users.

About Additional Features and Benefits: Features and benefits of the more than 500 optimized AI models:
  • Facilitates development and deployment.
  • Spans more than 20 categories of AI, including large language, diffusion, super resolution, object detection and computer vision.
  • Includes Phi-2, Mistral, Llama, Bert, Whisper and Stable Diffusion 1.5.
  • Improves system stability, reliability and performance.
About Intel's AI PC Developer Program: Developers in Intel's AI PC Developer Program can access tools, workflows, AI-deployment frameworks for Intel Core Ultra processors. Developers can also utilize Intel's software tools for optimizing AI, multiarchitecture programming, gaming, media and rendering on the AI PC.
Source: Intel
Add your own comment

6 Comments on More than 500 AI Models Run Optimized on Intel Core Ultra Processors

#1
john_
Intel posts press releases like the above.
Nvidia posts press releases about Premium AI PCs.
AMD's marketing department is having a pajama party.
Posted on Reply
#2
Vayra86
john_Intel posts press releases like the above.
Nvidia posts press releases about Premium AI PCs.
AMD's marketing department is having a pajama party.
Look on the bright side, there isn't much to sell here in reality, at least they're being sensible.

Sense doesn't make money tho
Posted on Reply
#3
HisDivineOrder
"C'mon, guys. AI is real. It's not a fad. Honest. It's going to be the next big thing. It's not wasting space where actual cores could be. Really."
Posted on Reply
#4
dragontamer5788
HisDivineOrder"C'mon, guys. AI is real. It's not a fad. Honest. It's going to be the next big thing. It's not wasting space where actual cores could be. Really."
I think you're overestimating the space cost of the vpdpbusd instruction (and all the other AVX512-VNNI instructions, for that matter).
Posted on Reply
#5
Minus Infinity
Mediocre Lake slower than Hawk Point in AI (11/34) vs (16/39) TOPS but is the "PREMIERE" AI cpu. In most benchmarks not optimised specifically for Intel it gets beaten by Hawk Point
Posted on Reply
#6
ScaLibBDP
>>...The models draw from categories of local AI inferencing, including large language, diffusion, super resolution,
>>object detection, image classification/segmentation, computer vision and others...

Take into account that this is for AI inferencing only. It is still Not possible to do large-scale AI training on CPUs.
Posted on Reply
May 15th, 2024 22:18 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts