Linux - HardwareThis forum is for Hardware issues.
Having trouble installing a piece of hardware? Want to know if that peripheral is compatible with Linux?
Notices
Welcome to LinuxQuestions.org, a friendly and active Linux Community.
You are currently viewing LQ as a guest. By joining our community you will have the ability to post topics, receive our newsletter, use the advanced search, subscribe to threads and access many other special features. Registration is quick, simple and absolutely free. Join our community today!
Note that registered members see fewer ads, and ContentLink is completely disabled once you log in.
If you have any problems with the registration process or your account login, please contact us. If you need to reset your password, click here.
Having a problem logging in? Please visit this page to clear all LQ-related cookies.
Get a virtual cloud desktop with the Linux distro that you want in less than five minutes with Shells! With over 10 pre-installed distros to choose from, the worry-free installation life is here! Whether you are a digital nomad or just looking for flexibility, Shells can put your Linux machine on the device that you want to use.
Exclusive for LQ members, get up to 45% off per month. Click here for more info.
Currently Intel chips generate less heat at same performance level. Less heat = longer life of all components. And here in deep south I do not want anything generating heat anyhow.
@zhjim, what TobiSGD was trying to point out is that "fast" as used with CPUs is generally a term used to describe the overall effective performance, not the clock speed. So it is best not to use "fast" to describe clock speed, because it confuses people. In most cases, Intel is quite a bit "faster", even though it is "slower" in clock speed.
There are a number of other variables, though, such as cache, HT, cores, turbo, etc., so it can be hard to reliably compare.
Nothings definitely. Just a quick CPU compare list shows highest speed of an AMD as 4.7GHz and Intel 4.4 GHz. Thats what i mean with as fast as.
You can easily overclock one of the later Pentium 4 CPUs to 4.4 GHz, that doesn't make them as fast as modern CPUs. Unless you compare CPUs of the same internal architecture the clockspeed is next to meaningless in determining which CPU is faster.
Intel - you pay a lot more for bleeding edge performance. Intel chips will vary according to heat, so saying they run cooler is a stretch. Some AMD chips run cool, some run hot. Mostly it's the wattage that tells the tale of heat.
AMD - you pay less for performance near Intel. AMD chips vary by wattage, so if heat is a concern, do your homework wholeheartedly. Those under 95w run fairly average temperatures. Those over 95w run hot so you will want ample cooling.
Consider an AMD CPU with 4GhZ and a Intel CPU with 4GhZ. Then just do a
I bet you both commands take the same clock cycle on Intel and on AMD. Now tell me which ones faster?
Now, I think you know that is unhelpful, and you are doing this deliberately. Apart from anything else, efficiency of caching comes in to this, as do various other architectural details, so any attempt to make this a simple clock speed race is probably going to unsuccessful.
Now, also, you are dismissing any possibility of multiple threads helping to give you performance, and that is also a somewhat pointless approach for any modern architecture.
And, your performance test is a test of doing nothing and that is a hopeless way of doing a performance test, given that optimising compilers can eliminate useless code entirely. Performance tests need to do something in order to test performance, and you've lost that in an attempt to make it seem that the two processors are the same when they are not.
Im just bringing my "fast" thing into the right light. And this loop does something. Could be used as a cpu burn test. And yes I'm doing this deliberately. What type of cache you wanna use on a single register and a jump that is within range?
Only thing I'm trying to get accross is that speed is speed. GhZ is GhZ. The rest is absolute architecturel for sure. I never said anything about performance test. Only asked which ones is faster and not more performance. If we decide to go into deep water and have every word taken for granted and set into stone. Read them as they are and not what you want to interpret into my writing. Also don't blame me if I refuse to accept that I said something definietly wrong.
Even this test is nearly guaranteed to have a wide margin of difference, because one processor (I won't say which) is certain to be able to fit more jumps and increments into those same 4GHz. The only reason anyone's talking about this is because "speed" is taken as overall performance. Something like "clock speed" would generally be used to refer to the fact that two CPUs have equal clocks.
And now, I don't want to get the thread off-topic, so I'll bow out of this.
Last edited by oldtechaa; 02-22-2016 at 06:36 AM.
Reason: Mistype.
And now, I don't want to get the thread off-topic, so I'll bow out of this.
You stay till the end.
Quote:
Originally Posted by oldtechaa
Even this test is nearly guaranteed to have a wide margin of difference, because one processor (I won't say which) is certain to be able to fit more jumps and increments into those same 4GHz. The only reason anyone's talking about this is because "speed" is taken as overall performance. Something like "clock speed" would generally be used to refer to the fact that two CPUs have equal clocks.
Not telling which one is a clear example that you don't want to share knowledge but show off with it. Poor boy. Reading it up on the net I get the same numbers for the latest AMD as well as Intel CPU's. One uops and 2 for throughput. I assume you know those words mister smarty pants.
The 1.6GHz Atom 330 CPU (dual-core, Hyperthreading) from Intel with its rather simple in-order architecture (or let's say an Athlon XP core, which can be found in AMD's Geode LX CPUs) is not even close to a 1.6GHz Intel or AMD CPU with out-of-order design (and with that highly sophisticated caching, jump prediction, and register swapping algorithms), at least in the real world. zhjim, what you have done here is nothing more than to show us that benchmark results, especially of synthetic benchmarks like yours, are always to be taken with a grain of salt. The OP, by the way, has asked for real world performance, not for hypothetical results of a benchmark that doesn't make much sense, and in the real world Intel desktop CPUs have a much higher IPC than AMD CPUs. Even AMD will tell you that, which is why they aim to get a 40 percent better IPC rating with their upcoming Zen CPUs.
I showed some even more intresting stuff then that benchmarks should be taken with a grain of salt. I showed that you don't read what people write or at least interpret it to an extend which I can't describe. What the OP actually asked is if Intel CPU's are better then AMD ones. That AMD just can't keep up. Also if the CPU initial bought would work with Ubuntu. And I also stated that I want a forum where people not getting punched at when they just answer simple questions with simple words. Certain CPU's for certain tasks. Just like software. Just humans lacking like always.
the A-6 is not bad cpu for a low budget set up. That cpu handles the newer media extensions mvx2 etc . this makes use few less cycles compared to the phenom II the A-10 is a nice little work horse also. if ran with a nice video card that would free up even more
resources instead of using the graphics on chip.
I showed some even more intresting stuff then that benchmarks should be taken with a grain of salt. I showed that you don't read what people write or at least interpret it to an extend which I can't describe. What the OP actually asked is if Intel CPU's are better then AMD ones. That AMD just can't keep up. Also if the CPU initial bought would work with Ubuntu. And I also stated that I want a forum where people not getting punched at when they just answer simple questions with simple words. Certain CPU's for certain tasks. Just like software. Just humans lacking like always.
Well trust me I am very happy with make j9 ok. Just like many of us that need the cores not virtual cores. That's my two cents.
My mother bought an HP Notebook off of QVC that has the AMD A6-6310 quad-core processor with 8GB RAM
Will this processor run fine with Ubuntu 14.04 lts?
He later added:
Quote:
The most intensive thing we do on our computers is PCSX and Higan game emulators.
My take on this question was that the OP merely wished for reassurance that the purchased HP notebook with an AMD A6-6310 CPU would perform adequately with Ubuntu 14.04 whilst carrying out the specified tasks.
Subsequent posts, whilst informative, discussing the technical merits of AMD and Intel CPUs seem to have steered well off the OP's main question, in my opinion.
Im just bringing my "fast" thing into the right light. And this loop does something. Could be used as a cpu burn test. And yes I'm doing this deliberately. What type of cache you wanna use on a single register and a jump that is within range?
Only thing I'm trying to get accross is that speed is speed. GhZ is GhZ. The rest is absolute architecturel for sure. I never said anything about performance test. Only asked which ones is faster and not more performance. If we decide to go into deep water and have every word taken for granted and set into stone. Read them as they are and not what you want to interpret into my writing. Also don't blame me if I refuse to accept that I said something definietly wrong.
and we will never know if inc R16 runs faster on amd or rjmp loop occasionally....
LinuxQuestions.org is looking for people interested in writing
Editorials, Articles, Reviews, and more. If you'd like to contribute
content, let us know.