If this is your first visit, be sure to
check out the FAQ by clicking the
link above. You may have to register
before you can post: click the register link above to proceed. To start viewing messages,
select the forum that you want to visit from the selection below.
Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite
So far in the three or four hours that I have had 4.4 installed on my Carrizo notebook, it seems to have lowered the heat coming from my cpu significantly compared to 4.3.3.
That's with one core running at 100% utilization continuously.
So far in the three or four hours that I have had 4.4 installed on my Carrizo notebook, it seems to have lowered the heat coming from my cpu significantly compared to 4.3.3.
That's with one core running at 100% utilization continuously.
One core running at 100% will always eat the same amount of power, regardless of the OS. If there's a real difference in heat output, it's coming from somewhere else.
One core running at 100% will always eat the same amount of power, regardless of the OS. If there's a real difference in heat output, it's coming from somewhere else.
Intuitively, yes you are correct about the power consumed by the CPU core proper. Carrizo has the most sophisticated power handling of all of the AMD chips so far and is supposed to be cable of turning off sections of the chip that aren't necessary for particular tasks. How much of that is under OS control I don't know.
All I know is that the chip isn't producing that much heat with just one core active, which is quite amazing in my experience with notebooks.
Intuitively, yes you are correct about the power consumed by the CPU core proper. Carrizo has the most sophisticated power handling of all of the AMD chips so far and is supposed to be cable of turning off sections of the chip that aren't necessary for particular tasks. How much of that is under OS control I don't know.
All I know is that the chip isn't producing that much heat with just one core active, which is quite amazing in my experience with notebooks.
How do you measure the difference? Because it could be caused by things like a better driver for the iGPU or some optimizations for the memory controller.
I mean, it's great that the new kernel works better for you, but the original statement attributing the gains to the CPU I think my be incorrect. Then again, these days CPU means CPU+iGPU+memory controller+PCIe controller... so you could also be correct.
How do you measure the difference? Because it could be caused by things like a better driver for the iGPU or some optimizations for the memory controller.
I mean, it's great that the new kernel works better for you, but the original statement attributing the gains to the CPU I think my be incorrect. Then again, these days CPU means CPU+iGPU+memory controller+PCIe controller... so you could also be correct.
The fact that the cpu is running 1 core at 100% was purely anecdotal. All I really said was the chip is running cooler between 4.3.3 and 4.4.0. Whatever code was involved whether it be GPU related code or not, it is kernel related, since the only thing I changed between the two was the kernel.
Comment