NVIDIA is creating a new ecosystem of “Premium” AI PCs powered by its RTX hardware that are much faster than the AI-capable NPUs that are taking the industry by storm.

NVIDIA's RTX platform is the “premium” choice of AI PCs and all RTX owners can run GenAI and AI-powered workloads faster than NPUs.

NVIDIA is developing a suite of new ecosystems for the consumer market. We've already talked about the new “SFF Enthusiast GeForce GPU” platform that will empower manufacturers to create new compact and small form factor PCs powered by RTX GPUs but that's not all. In a meeting with manufacturers and the media, NVIDIA highlighted its contributions to the AI ​​PC segment and how it plans to take the next leap with exciting new ideas.

Starting with the most basic premise, we have the NVIDIA GeForce RTX GPU. The current GeForce RTX lineup and its predecessors have featured AI support since 2018, almost 6 years ago when the company first introduced its deep learning model to gamers, known today as DLSS. known as. DLSS is widely used and the driving force behind DLSS is the Tensor architecture, which was first adopted for data center “Volta” GPUs and in the mainstream graphics segment with the arrival of the GeForce RTX 20 “Turing” family. was launched.

So far, the most basic RTX GPUs, the RTX 2050 and RTX 3050, offer around 15-20 TOPS of AI performance which matches or exceeds the 16 TOPS offered in the fastest NPU, the XDNA 1 from AMD. “Hawkpoint” APU for its Ryzen 8040. These NPUs provide users with the basic compute capabilities to handle AI tasks locally instead of running them in the cloud, which is now considered the “old way” and only useful for large-scale enterprises. NVIDIA has some really fast GPUs such as its recently introduced Blackwell lineup.

This year, several PC vendors will upgrade their AI PC portfolio with faster NPU capabilities, up to 45-50 TOPS (Lunar Lake, Arrow Lake, Strix Point, Snapdragon X). These NPUs are designed to handle Microsoft CoPilot AI and similar AI-based workloads, but while these chipmakers are trying to target 50 TOPS, NVIDIA's GPUs already offer more than 100 TOPS. have been, in some cases, even exceeding 1000 tops with the fastest GPUs. On the planet

Thus, NVIDIA wants to create a new segment of AI PCs and refer to it as “Premium AI PC”. These AI PCs will scale from 100-1300+ TOPS (INT8/FP8), and offer significantly improved performance in multiple workloads such as content creation, video capabilities, productivity, gaming, and developer tasks. An NPU can only do so much, and yet, chipmakers rely on total TOPS data by combining onboard CPU, GPU, and NPU capabilities while NVIDIA's RTX GPUs provide users with dedicated Tensor Core performance. Can as they will. Furthermore, We recently discussed how NPUs are taking priority in these chips while draining CPU and GPU resources..

Another factor where NVIDIA's bets may pay off with the “Premium AI PC” segment is the AI ​​ecosystem. NVIDIA has a huge suite of AI-ready tools that complement their RTX GPUs. The company recently revealed its Chat with RTX (AI Chatbox) and includes optimizations for a wide range of GenAI and LLM (large language models). TensorRT that helps boost AI performance by leaps and bounds.. We have to mention DLSS again because it's the premier AI tech for gamers and unlike anything that's been done before.

DLSS 3.5 And DLSS 3.7 The latest versions of the tech are not only helping gamers run faster with higher visual quality that can often provide better image quality than native resolution. But RTX also allows modders to breathe new life into old games using Remix.a platform that has become massively popular and has seen many classics given a modern graphical touch.

There is no doubt that NVIDIA has been at the forefront of the AI ​​department, be it the enterprise segment or the consumer segment. While others have only just begun to realize the potential of AI and rapidly advance their NPU roadmaps, NVIDIA has quietly released a large range of RTX-capable GPUs, AI-enabled apps (500 +) has amassed a large list, and currently has an installed user base of over 100 million RTX owners who fall into this “premium AI PC” segment (as of CY2023). This new “premium AI PC” ecosystem will further differentiate between NPUs and RTX GPUs as already exists between the iGPU and dGPU segments.

So to put everything in perspective, users who engage in a lot of AI tasks on a daily basis will mostly use their GPU and NVIDIA's RTX hardware is equipped with the horsepower to do so and NPUs. Competitions much faster and better.

It will be interesting to see how things evolve in the future and we can't wait for more interesting and useful developments in the AI ​​PC segment that focus not only on adding more AI tops but also to consumers and gamers alike. I also give reasons to invest. Hardware NVIDIA's ACE There is another technology that I am personally looking forward to and should be a game changer if implemented correctly.

News Source: Bench life