1 |
Nikos Chantziaras wrote: |
2 |
> On 06/12/2018 23:45, Dale wrote: |
3 |
>>> |
4 |
>>> You won't get anything close to double the speed. The extra cores will |
5 |
>>> mostly go unused, unless you use applications that make use of them. |
6 |
>>> |
7 |
>>> You will still get a speed up due to the newer CPU architecture and |
8 |
>>> the higher frequency. |
9 |
>> |
10 |
>> What I was thinking about is something like when compiling and all the |
11 |
>> cores are used. In other words, CPU is at max load. Right now, I have |
12 |
>> only 4 cores. New CPU doubles that and each core is faster as well. As |
13 |
>> a example, Firefox takes about a hour to compile. I was hopeful that |
14 |
>> would drop to 30 or 35 minutes or so. |
15 |
> |
16 |
> Oh that. Yeah, there will be a 2x speedup when emerging packages |
17 |
> (MAKEOPTS="-j8"). I was referring to application performance when |
18 |
> using the machine. I don't consider package installation as "using the |
19 |
> machine" :-) |
20 |
> |
21 |
> |
22 |
|
23 |
Well, one thing I been doing that uses a LOT of memory and CPU, scanning |
24 |
images and editing them in Gimp. The biggest problem was Dolphin and |
25 |
its memory leak, which at the time I didn't realize was abnormal. At |
26 |
one point, just opening the directory with a lot of large images made |
27 |
Dolphin go crazy with memory usage. I've since realized that Dolphin |
28 |
has a bug. Still, having 32GBs of ram is better since I can now compile |
29 |
Firefox and others in tmpfs instead of on the hard drive. That said, |
30 |
Gimp uses quite a bit CPU power at times too. I also sometimes convert |
31 |
videos which can get CPU and/or memory hungry. |
32 |
|
33 |
|
34 |
>>> The two speeds specify the lower and upper speeds, depending on how |
35 |
>>> many CPU cores are currently being under load, and also how much load |
36 |
>>> there is. You don't have to worry about it though. It's all automatic. |
37 |
>>> [...] |
38 |
>> |
39 |
>> That's good to know. That I was wondering about and couldn't find a |
40 |
>> clear answer on. I didn't know if I needed to install something to |
41 |
>> manage that or what. |
42 |
> |
43 |
> The kernel takes care of that. You should be able to observe the CPU's |
44 |
> frequency and temperature in KSysGuard. Here's how it looks here: |
45 |
> |
46 |
> https://i.imgur.com/Xogy3h0.png |
47 |
> |
48 |
> In that screenshot, the CPU has all 4 cores clocked down to 1.6GHz |
49 |
> because they're all mostly idle. Once there's high CPU load, it will |
50 |
> crank up the clocks towards 4GHz. |
51 |
> |
52 |
> You need to add these sensors manually to KSysGuard though. But if you |
53 |
> do, it's a good way to verify things are working as intended. |
54 |
> |
55 |
> |
56 |
> |
57 |
|
58 |
|
59 |
I use the sensors built into the kernel. Last time I tried lm-sensors, |
60 |
I couldn't get it to work right. I enabled and recompiled the kernel |
61 |
with the needed drivers and I haven't had any trouble since. That was |
62 |
on a previous rig too. I guess I can cat /proc/cpuinfo to see if it is |
63 |
working as well. As long as I can see it is working as it should, I'm |
64 |
not going to worry about checking it much. I use gkrellm to monitor my |
65 |
stuff. I do check Ksysguard at times tho. |
66 |
|
67 |
Right now, I'm waiting on a new fan for my CPU. I noticed when I turned |
68 |
the rig back on last time, it was slow to get going. I had to give it a |
69 |
little push with my finger. Since it has a lot of hours on it, I oiled |
70 |
it a bit to help it along temporarily and ordered a new fan. I plan to |
71 |
clean the CPU cooler real good, replace the fan and upgrade the CPU all |
72 |
at one time. Then the video card and hard drive stuff after that. |
73 |
|
74 |
What I'm doing, upgrading to almost a new system. I have a Gigabyte 970 |
75 |
mobo. With the new CPU, video card, memory and such, I should get |
76 |
several more years unless something burns out. Looking at newer stuff, |
77 |
I'm not sure it is worth building a whole new rig at this point. |
78 |
Computers seem to have sort of peeked unless you spend lots of money. I |
79 |
just wonder what will come next that gives a whole new generation of |
80 |
computing. It seems clock speed has pretty much reached its limit or |
81 |
something. |
82 |
|
83 |
Dale |
84 |
|
85 |
:-) :-) |