NVIDIA isn’t going to be left out with the coming AI PC revolution, with AMD and Intel already releasing NPU-powered processors for AI workloads, NVIDIA has just announced the “Premium AI PC” with RTX hardware, compared to the “Basic AI PC” with an NPU on the CPU.
5VIEW GALLERY – 5 IMAGES
NVIDIA compares that a Premium AI PC with an RTX GPU for AI workloads can provide gigantic performance uplifts for AI TOPS of between 100 and a whopping 1300+ TOPS (int8 + FP8 workloads) compared to just 10-45 TOPS on current, and next-gen CPUs with beefed-up NPUs.
Intel and AMD will combine the TOPS performance of the CPU + GPU + NPU, because if they used the NPU alone, the AI power is nowhere near as great. The more the NPU is used, the more resources that are taken away from other key parts of the chip: ya know, like the CPU and GPU.
5NVIDIA has been filling out its AI ecosystem with new tools including Chat With RTX — a new RTX-powered AI chatbot — which includes optimizations for GenAI and LLM (large language models) in the form of TensorRT which greatly increases AI performance.
5Think about it: there are over 100 million RTX owners out there, so the “Premium AI PC” segment already has a gigantic userbase. The new “AI PC” will be for more basic generative AI tasks, but you’re going to need much more power (from your CPU and GPU on your new Intel or AMD processor) but for massive performance leaps, a dedicated GPU is what you need.
At least it’s not like back in teh day with a PhysX card from Ageia, where if you wanted to run PhysX, you’d need a dedicated PhsyX card that was used in conjunction with your graphics card. I’m surprised we’re not seeing NPU-specific AICs yet, but maybe in the future.