I don't normally care too much about mobile processors but I think Lunar Lake seems to be very impressive given how much is packed into it. On the other hand, though Intel has to stay competitive with Qualcomm encroaching with its Snapdragon Elite processors.
I'm looking forward to reviews, and they're going to be a doozy given the CPU/AI/GPU aspects to cover.
Brian_B
The thing that boggles me right now:
Everyone is talking about NPUs as separate silicon built onto the CPU die. No one is talking about GPU acceleration of NPU tasks, or at least in reference to all these new consumer-level AI tasks that Microsoft (and Apple and others) are pushing.
I'd imagine a GPU can vastly out-calculate an NPU on a CPU die. I can't believe nVidia hasn't come out with a GPU driver (or at the very least hinted at the possibility of one) that allows it to serve as the NPU for all these new CoPilot things. Or AMD leveraging their APU expertise to push it in that direction (or maybe they are and they are just spinning it as "NPU" even though it's GCN cores or something)
Maybe there is and I just have my head in the sand (I admittedly care very little about CoPilot stuffs)
Peter_Brosdahl
👍 1
Honestly, I can barely keep my head wrapped around it. In reading this article it quickly made me aware, and I know this isn't a new concept with Intel's and NVIDIA's more recent consumer silicon since I tend to track them a bit more than AMD, how for "packages" or dies, one has to keep track of multiple generations per each release now which can be a bit mindboggling. Factor in how they all interact with each other, including AI, and my brain starts to hurt a little.
Former managing editor of GPUs at HardOCP for 18 years, Brent Justice has been reviewing computer components since the late 90s, educated in the art and method of the computer hardware review, he brings experience, knowledge, and hands-on testing with a gamer-oriented and hardware enthusiast perspective.
You can follow him on Twitter - @Brent_Justice
You can sub to his YouTube channel - Justice Gaming
https://www.youtube.com/c/JusticeGamingChannel
You can check out his computer builds on KIT - @BrentJustice
https://kit.co/BrentJustice
Discussion (3 replies)
Join Discussion →I don't normally care too much about mobile processors but I think Lunar Lake seems to be very impressive given how much is packed into it. On the other hand, though Intel has to stay competitive with Qualcomm encroaching with its Snapdragon Elite processors.
I'm looking forward to reviews, and they're going to be a doozy given the CPU/AI/GPU aspects to cover.
The thing that boggles me right now:
Everyone is talking about NPUs as separate silicon built onto the CPU die. No one is talking about GPU acceleration of NPU tasks, or at least in reference to all these new consumer-level AI tasks that Microsoft (and Apple and others) are pushing.
I'd imagine a GPU can vastly out-calculate an NPU on a CPU die. I can't believe nVidia hasn't come out with a GPU driver (or at the very least hinted at the possibility of one) that allows it to serve as the NPU for all these new CoPilot things. Or AMD leveraging their APU expertise to push it in that direction (or maybe they are and they are just spinning it as "NPU" even though it's GCN cores or something)
Maybe there is and I just have my head in the sand (I admittedly care very little about CoPilot stuffs)
Honestly, I can barely keep my head wrapped around it. In reading this article it quickly made me aware, and I know this isn't a new concept with Intel's and NVIDIA's more recent consumer silicon since I tend to track them a bit more than AMD, how for "packages" or dies, one has to keep track of multiple generations per each release now which can be a bit mindboggling. Factor in how they all interact with each other, including AI, and my brain starts to hurt a little.