▲ 238 ▼ Microsoft claims "2026 is the moment" for AI PCs, but its essay-length beginner explanation only creates more confusion — Is it any wonder adoption is slow? (www.windowscentral.com) submitted 8 months ago by throws_lemy@reddthat.com to c/technology@lemmy.world 83 comments fedilink hide all child comments
[–] Hippy@piefed.social 8 points 8 months ago (2 children) I have a NPU for no fucking reason permalink fedilink source hideshow 2 child comments replies: [–] addie@feddit.uk 3 points 8 months ago That space on the CPU die could have been extra cache or maybe even another core, speed up all computing tasks on the machine. But no, it's a fucking waste of space; not flexible enough to be used for general-purpose compute, not parallel enough to be used for a GPU, not enough RAM to run a local model. Got mine switched off in the BIOS just in case it improves battery life any. permalink fedilink source parent [–] Meron35@lemmy.world 1 point 8 months ago Eh, I don't think NPUs are ready to be marketed so heavily, but they've been around for a while and do get used. They're basically a rebranded tensor processing unit, think a more specialised GPU that's even more energy efficient at tensor/linear algebra. It's mostly used in more technical applications, such as image/audio/video processing, machine learning, or really anything maths heavy. Apple's M series had NPUs, and are an understated reason why they perform extraordinarily well in a lot of scientific applications. Uses for consumers are not as compelling (especially on laptop/desktop), mostly faster/more efficient subtitle generation, face recognition, and maybe blurring your zoom background. permalink fedilink source parent
[–] addie@feddit.uk 3 points 8 months ago That space on the CPU die could have been extra cache or maybe even another core, speed up all computing tasks on the machine. But no, it's a fucking waste of space; not flexible enough to be used for general-purpose compute, not parallel enough to be used for a GPU, not enough RAM to run a local model. Got mine switched off in the BIOS just in case it improves battery life any. permalink fedilink source parent
[–] Meron35@lemmy.world 1 point 8 months ago Eh, I don't think NPUs are ready to be marketed so heavily, but they've been around for a while and do get used. They're basically a rebranded tensor processing unit, think a more specialised GPU that's even more energy efficient at tensor/linear algebra. It's mostly used in more technical applications, such as image/audio/video processing, machine learning, or really anything maths heavy. Apple's M series had NPUs, and are an understated reason why they perform extraordinarily well in a lot of scientific applications. Uses for consumers are not as compelling (especially on laptop/desktop), mostly faster/more efficient subtitle generation, face recognition, and maybe blurring your zoom background. permalink fedilink source parent