General AMD vs Intel thread

Feel like posting Off Topic? Do it here.

Moderator: MaxCoderz Staff

Which cpu do you think is better?

AMD
14
48%
intel
3
10%
Don't give a shit
12
41%
 
Total votes: 29

CompWiz
Calc King
Posts: 1950
Joined: Thu 13 Oct, 2005 1:54 pm
Location: UB

Post by CompWiz »

dysfunction wrote:So the FX-57 is a bad example. Honestly I can't see spending over $400 on a processor unless you have an application where you will actually notice a difference.
well, any cpu intensive task will perform better with a better cpu. Video editing, gaming, etc. And you should get at least dual core.
coelurus
Calc Wizard
Posts: 585
Joined: Sun 19 Dec, 2004 9:02 pm
Location: Sweden
Contact:

Post by coelurus »

High-end CPUs for gaming... I do not pity the fools who live their lives to buy expensive CPUs only to play demanding games, which are most often crap nowadays anyway :) Video editing shouldn't need much power either for regular use, but again, I don't care what people do with their money.

Multithreading has had a very slow entry into game programming, it's mostly reported as being used for behind-the-scenes streaming of content. Funny thing is, not a lot of games implement streaming properly either :P Developers also say that the PS3 is a mess to develop on because of the Cell CPU with its 8 sub-CPUs or whatever. Nobody complained when graphics cards got programmable pipelines for vertices and fragments...

I hope the AMD + ATI merge will take place, AMD is very interested in open source so maybe ATI would be told to stop using "stupid" hardware (dvd decoding or similar?) and be able to give full details on their cards => open source drivers!
CompWiz
Calc King
Posts: 1950
Joined: Thu 13 Oct, 2005 1:54 pm
Location: UB

Post by CompWiz »

coelurus wrote:High-end CPUs for gaming... I do not pity the fools who live their lives to buy expensive CPUs only to play demanding games, which are most often crap nowadays anyway :) Video editing shouldn't need much power either for regular use, but again, I don't care what people do with their money.

Multithreading has had a very slow entry into game programming, it's mostly reported as being used for behind-the-scenes streaming of content. Funny thing is, not a lot of games implement streaming properly either :P Developers also say that the PS3 is a mess to develop on because of the Cell CPU with its 8 sub-CPUs or whatever. Nobody complained when graphics cards got programmable pipelines for vertices and fragments...

I hope the AMD + ATI merge will take place, AMD is very interested in open source so maybe ATI would be told to stop using "stupid" hardware (dvd decoding or similar?) and be able to give full details on their cards => open source drivers!
there was an article that I read that said that this was definitely not going to happen. I'd rather that AMD would team up with nVidia anyway. They have better graphics cards, and make more motherboards for AMD.
User avatar
crzyrbl
Calc Wizard
Posts: 518
Joined: Wed 06 Jul, 2005 4:56 pm
Location: 3rd rock....

Post by crzyrbl »

The REAL problem with the cell cpu's is that they have a read speed of a blazing 16 Mb/s, according to http://www.theinquirer.net/?article=32171
(\__/)
(='.'=)This is Bunny. Copy and paste bunny into your
(")_(")signature to help him gain world domination.

Image
coelurus
Calc Wizard
Posts: 585
Joined: Sun 19 Dec, 2004 9:02 pm
Location: Sweden
Contact:

Post by coelurus »

Since NVidia already works closely with AMD, all that's left is ATI. Buying them could work :wink: I generally like NVidia better, but that's only because of their support in alternative OSs.

Woah, 16MB/s read from local memory, must be bad? Right?
What's local memory? :) A little too much of a buzz-feel over that piece of news and trying to find some hard info on that online is pretty tiresome too.
User avatar
Arcane WIzard
Calc Guru
Posts: 856
Joined: Mon 21 Feb, 2005 7:05 pm

Post by Arcane WIzard »

http://www.theinquirer.net/images/artic ... widths.jpg
If you can write at 250x the read speed, it makes Cell local memory just about useless. That means you do all your work out of main memory, and the whole point of local is, well, pointless. This can lead to contention issues for the main memory bus, and all sorts of nightmarish to debug performance problems. Basically, if this Sony presentation to PS3 devs shown to us is correct, it looks like PS3 will be hobbled in a serious way.

The next slide goes on to say "Don't read from local memory, but write to main memory with RSX(tm) and read it from there instead", and repeats the table numbers. This is very very bad. The number of times the presentation goes on to say that it is correct, and the lack of anything like "this will be fixed by production steppings, so take measures X, Y and Z" say to me that it is not a fixable snafu. Remember at E3 when I said that the PS3 demos there were object sparse? Any guesses why?
If I'm not mistaking local memory is the memory on the processor itself, main memory are the RAM modules on the main board.

Local memory being completely useless is very very very very very very bad, especially for consoles.
User avatar
Jim e
Calc King
Posts: 2457
Joined: Sun 26 Dec, 2004 5:27 am
Location: SXIOPO = Infinite lives for both players
Contact:

Post by Jim e »

Arcane WIzard wrote:http://www.theinquirer.net/images/artic ... widths.jpg
If I'm not mistaking local memory is the memory on the processor itself, main memory are the RAM modules on the main board.

Local memory being completely useless is very very very very very very bad, especially for consoles.
Please don't tell me that you are taking this inquire stuff at face vaule, they aren't exactly known for their fact checking ability.

I find it interesting that RSX(ps3 reality gpu) can access the so called CPUs memory faster than the cpu can. Even more so it can access it faster than the cpu can access the main memory.

Its mostly been discredited, atleast by more credible sources.
http://firstpersonshooters.joystiq.com/ ... ps3-claim/
Image
User avatar
crzyrbl
Calc Wizard
Posts: 518
Joined: Wed 06 Jul, 2005 4:56 pm
Location: 3rd rock....

Post by crzyrbl »

:P I dont think either of those sites are very credible.
anyone hear about intel's flash boot?
http://www.tomshardware.com/site/computex_2006/
sounds awsome
(\__/)
(='.'=)This is Bunny. Copy and paste bunny into your
(")_(")signature to help him gain world domination.

Image
coelurus
Calc Wizard
Posts: 585
Joined: Sun 19 Dec, 2004 9:02 pm
Location: Sweden
Contact:

Post by coelurus »

It's possible to boot up Linux on current HW in a couple of seconds with an open source BIOS, dunno which. Low-level stuff is very well kept under wraps, even the most important and basic features of mobos are pure awful hacks (try to fetch the acpi tables and recompile with sane compilers, most acpis won't get through).
I've never liked messing with PC HW, innovation and "elegance" has been put aside only to make customers happy. And that's not always a good thing :) Applies to a lot of things in this world, but considering my lifestyle, I've noticed this particularly with PCs...
CompWiz
Calc King
Posts: 1950
Joined: Thu 13 Oct, 2005 1:54 pm
Location: UB

Post by CompWiz »

crzyrbl wrote::P I dont think either of those sites are very credible.
anyone hear about intel's flash boot?
http://www.tomshardware.com/site/computex_2006/
sounds awsome
At a demonstration here at Computex in Taipei, the test bed Dell Inspiron 630m machine with Robson inside managed an impressive 30 second start up time.
I made a super cheap sub $300 computer a few months ago with an old socket A AMD sempron 3300+ CPU that could boot Windows XP PRO in 30 seconds easy. I timed it. It could go from power off to the windows desktop in about 27 seconds. This Intel demonstration is really not impressive at all. Image
User avatar
Arcane WIzard
Calc Guru
Posts: 856
Joined: Mon 21 Feb, 2005 7:05 pm

Post by Arcane WIzard »

... my P3 500mhz booted XP Pro in about 18-20 seconds just like my 1.4Ghz laptop.

People who think start up times mean anything at all are silly.
CompWiz
Calc King
Posts: 1950
Joined: Thu 13 Oct, 2005 1:54 pm
Location: UB

Post by CompWiz »

Arcane WIzard wrote:... my P3 500mhz booted XP Pro in about 18-20 seconds just like my 1.4Ghz laptop.

People who think start up times mean anything at all are silly.
Well, P3's are better than P4's, so you have an advantage over the Dell. :lol:
coelurus
Calc Wizard
Posts: 585
Joined: Sun 19 Dec, 2004 9:02 pm
Location: Sweden
Contact:

Post by coelurus »

Boot times mean a little, I would love to see my computer boot up in just a few seconds. There are of course other aspects that are much more important, but long boot times is an old little issue I could definitely live without.
User avatar
benryves
Maxcoderz Staff
Posts: 3089
Joined: Thu 16 Dec, 2004 10:06 pm
Location: Croydon, England
Contact:

Post by benryves »

Since when have P3s been better than P4s?
Yours, puzzled owner of both P3 (slow) and P4 (fast) machines.
User avatar
Spellshaper
New Member
Posts: 24
Joined: Sat 24 Dec, 2005 9:20 pm
Location: Freiburg, Germany
Contact:

Post by Spellshaper »

I think he relates to the fact that if you'd take a P3 (probably overclocked) and a P4, both at the same Mhz, the P3 would pwn.
So the P3 has a better work-per-cycle ratio.

The P4 was designed with wow-we-want-more-Mhz-cause-that-leads-to-users-thinking-we-can-pwn-AMD in mind ;)
And it just backfired :P
Image
PSYCALYPSE
Nigecha dame da!
Post Reply