Sign in with
Sign up | Sign in
Your question

Intel's Core Architecture vs AMD's Next Gen. Architecture

Last response: in CPUs
Share
March 9, 2007 3:07:07 PM

Source:
http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=274...
http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=293...

Here are some of the differences between Intel's Core Architecture and AMD's next generation architecture (NGA) called K8L or K10, with the reference of AMD K8 architecture.

1. Processor manufacturing technology:
Core Arch.: 65nm, 45nm in 2007 H2, 8 metal layers
K8: 130nm SOI, 90nm SOI, 65nm SOI, 9 metal layers
NGA: 65nm SOI, 45nm in mid-2008, 11 metal layers

2. Cache system
Core Arch:
L1 cache: 32KB, 8-way, latency: 3 cycles
L2 cache: 2-4MB shared, 16-way, 256-bit (64GB/s at 2GHz), latency: 11-20 cycles
L3 cache: absent
K8:
L1 cache: 64KB data+64KB instruction, 2-way, latency: 3 cycles
L2 cache: 512KB, 16-way, 128-bit (32GB/s at 2GHz), latency: 11-20 cycles (90nm version)
L3 cache: absent
NGA:
L1 cache: 64KB data+64KB instruction, 2-way, latency: 3 cycles
L2 cache: 512KB, 16-way, 128-bit (32GB/s at 2GHz), latency: unknown
L3 cache: 2MB shared, 32-way, unknown width and latency

3. x86 decoding ability
Core Arch:
x86 decoders: 3 simple + 1 complex (the complex decoder can decode 2 simple codes in a pass)
Out-of-order execution buffer: 96 instructions
K8:
x86 decoders: 3 complex
Out-of-order execution buffer: 72 instructions
NGA:
x86 decoders: 3 complex
Out-of-order execution buffer: 72 instructions with improvements

4. ALU, FPU and SSE units
Core Arch:
ALU units: 3
Maximum dual-precision (64-bit) FP per cycle: 4
SSE units: 3 units, 128-bit
K8:
ALU units: 3
Maximum dual-precision FP per cycle: 3
SSE units: 2 units, 64-bit
NGA:
ALU units: 3
Maximum dual-precision FP per cycle: 3
SSE units: 2 units, 128-bit

5. Pre-fetch and other tune-ups
Core Arch:
Out-of-order loads: Present
Stack manager: Present
Pre-fetchers: 2 data, 1 instruction (to core), 2 pre-fetchers (to L2 cache)
Instruction fetch width: 24 byte per cycle
K8:
Out-of-order loads: Absent
Stack manager: Absent
Pre-fetchers: 1 data, 1 instruction (to L2 cache)
Instruction fetch width: 16 byte per cycle
NGA:
Out-of-order loads: Present
Stack manager: Present
Pre-fetchers: 1 data, 1 instruction (to L1 cache), 1 DRAM pre-fetcher (to dedicated buffer)
Instruction fetch width: 32 byte per cycle

6. Memory controller
Core Arch: absent
K8: 1x128-bit memory controller (1 operation per cycle)
NGA: 2x64-bit memory controller with NGMA (max 2 operations per cycle)

7. Power management
Core Arch: EIST (min. x6 multiplier), switch off transistor when not in use
K8: Cool'n'Quiet (min. x5 multiplier)
NGA: improved C'n'Q, two separate power planes for crossbar and cores, separate clocks for each core
March 9, 2007 3:50:55 PM

Quote:

While I know a lot about PC's I didnt study nerdology so I will let someone translate all of this.


There's something to be said for holding your tongue and patiently waiting, but who wants to do that?

More importantly, nice complilation qcmadness.
March 9, 2007 3:54:35 PM

From everything I have read, it sounds like the new AMD architecture could be good. We will know for sure come release time around September.
Related resources
March 9, 2007 4:03:35 PM

SEPTEMBER!! ahhh crap!
March 9, 2007 4:15:32 PM

Add on-die memory controler to C2D and it looks like we'll have a fairly even competition starting next summer.

It's good to know we finally might have real choices to do when purchasing a new PC. When you think about it, until C2D, unless stupid or really into video encoding, you had to get a A64 cpu for good performances. Following C2D launch, unless you were a die-hard AMD fanboy or only upgrading, you had to get a C2D for top performances.

Now, if Barcelona perform up to expectation, we might finally be facing a dilemna when getting a new PC depending on the apps we use, price, availability, etc...

Good for us.
March 9, 2007 4:26:28 PM

this is why I like anandtech, very thorough, very balanced.

Good post though, a lot of people can see the ACTUAL differences in cores.
March 9, 2007 4:52:50 PM

though i read the compiliation, i'm still at a loss as to what exactly it means...

perhaps one of our more technically advanced members could break it down for the lesser peons :) 
March 9, 2007 9:33:11 PM

Quote:

While I know a lot about PC's I didnt study nerdology so I will let someone translate all of this.


There's something to be said for holding your tongue and patiently waiting, but who wants to do that?

More importantly, nice complilation qcmadness.

Come on, his name is based on the AMD X2 family (possibly...I'm assuming here) and his username was created in Aug 2006. Maybe he's just bitter about Core2 Duo :-D

And yes, good compilation.
March 9, 2007 9:58:37 PM

Quote:

While I know a lot about PC's I didnt study nerdology so I will let someone translate all of this.


There's something to be said for holding your tongue and patiently waiting, but who wants to do that?

More importantly, nice complilation qcmadness.

Come on, his name is based on the AMD X2 family (possibly...I'm assuming here) and his username was created in Aug 2006. Maybe he's just bitter about Core2 Duo :-D

And yes, good compilation.Actually, he has a Core 2 Duo E6400 overclocked to 3.4GHz with dual Geforce 8800GTXs. :?
March 9, 2007 10:04:44 PM

sounds like amd dual core will be the same not as good - but the quad core will benefit from being unified 4 core

Quote:
[

While I know a lot about PC's I didnt study nerdology so I will let someone translate all of this.


dude you should skip this post - try "will my dual core chip show 2 charts in the task manager" or "will this 350w psu power my p4 systems with 8800gtx's in sli"

i could not help it! :twisted:
March 9, 2007 10:17:20 PM

Wouldn't it make more sense to compare Barcelona to Nehalem, which by all accounts will be its competitor?
March 9, 2007 10:58:37 PM

I just know that anything related to the Core arquitecture is good :D 
March 10, 2007 12:05:03 AM

hey, Im in (almost) the same case as your friend. I wont upgrade my CPU in a looooooong time. I can OC to 333mhz and get the perfomance of a E6650 or whatever is the equivalent to the E6600.

When I said anything with Core arquitecture was good, I never said in any way Dont consider other options, but it would be better to buy something cheap like the E4300 which performs nice for its price dont you think?
Now, if you use the pc for like 10 mins a day, then find something cheaper which will do what u need.
March 10, 2007 12:32:05 AM

Quote:
I am a nerdologist understudy :wink:

Basically what he is saying here is the chunky peanut butter is relative to non chunky rounded up and multiplied by2; Then increased by a magnitude of strawberry jam and divided by sliced bananas.

So in the end you can make a peanutbutter jelly and banana sandwich in half the time with either chunky or smooth peanut butter.



:lol:  :lol:  :lol: 


uhheemmm


:lol:  :lol:  :lol: 

So what your saying is this is the new AMD

March 10, 2007 1:54:57 AM

Quote:
Wouldn't it make more sense to compare Barcelona to Nehalem, which by all accounts will be its competitor?


We should know that the NGA by AMD will be present in server / desktop areas. :wink:

Why I did not include Nehalem:
1. I know little from Nehalem / CSI.
2. Whether Nehalem is a "major" update of Core Architecture is a problem.
March 10, 2007 2:11:34 AM

Quote:
I think once csi is out, if intel can get a top notch mem controller like barcelona's, amd won't have much else to turn to, though th etotal 12mb+ of cache on the penryn cpus is all waste of transitors, amd went for the mem controller since it couldn't afford the keep up in the cache race

May be or not may be :D 
By the time, the second generation of direct connect architecture and the third generation of memory controller is present in AMD's processors :wink:
March 10, 2007 5:47:19 AM

Quote:
maybe is one word :wink: But I think intel has the money to make it happen


Yes, but it takes time :wink:
March 10, 2007 6:19:43 AM

Quote:
the problem, it has turned into a flame war of fanboys, otherwise this could have been a very nice sticky, and I believe it should be one, just with all the clutter taken


You may try to help me by sending PM to mods. :wink:
March 10, 2007 7:01:42 AM

Quote:
I think once csi is out, if intel can get a top notch mem controller like barcelona's, amd won't have much else to turn to, though th etotal 12mb+ of cache on the penryn cpus is all waste of transitors, amd went for the mem controller since it couldn't afford the keep up in the cache race

May be or not may be :D 
By the time, the second generation of direct connect architecture and the third generation of memory controller is present in AMD's processors :wink:


Yes, you have to believe that AMD are masters of the memory subsystem and interconnects.
March 10, 2007 11:46:40 AM

Quote:
just wondering, why cna't you do it, they'll want you to anyways since it's your thread, just pm jake barnes, you can find him easily by searching his name


I tried in my last post, but failed. :?
March 10, 2007 12:53:21 PM

Quote:
(btw, hows the speed difference from the maxtor to the raptor, I have always wondered really how much bias is there when people claim the speed differences)


Dont have the raptor yet :(  sorry

You know the reasons, I explained them to you already.

I thought I was gonna get my Corsair RMA yesterday, when I asked if any UPS package got here, and I heard a NO, I was like F********CK! now gotta wait til monday! :( :( :( 
March 10, 2007 4:39:14 PM

Well yes, I now know that I should not buy the cheap line of Corsair or I will end up RMA'ing 5 or 10 times.
March 10, 2007 5:29:59 PM

either Dominate the world

or suffer with the annoying RMAs with the cheap series
March 10, 2007 5:57:44 PM

Quote:
this is why I like anandtech, very thorough, very balanced.

Good post though, a lot of people can see the ACTUAL differences in cores.

sorry but I laughed at this statement of anandtech XD

in other hand, interesting that the core as more SSE 128bit units (3)



Quote:
Wouldn't it make more sense to compare Barcelona to Nehalem, which by all accounts will be its competitor?


wasnt it the inversed?
P3 vs K7, P4 vs K8, Core vs Barcelona, Nehalem vs Shangai
March 10, 2007 7:09:35 PM

Quote:
Man, I don't even know about Nahalem that much, let alone shanghai


tacos, we know its yourt thread, but... you're seriusly in need to reply EVERY SINGLE POST ?
March 10, 2007 7:20:14 PM

Isnt P3 vs K6 III & K6 III 2 ?
March 10, 2007 7:34:00 PM

Taco is everywhere, he is a frekin lazy guy who doesnt have anything else to do but stay 30 hours a day in the forums. 8O
March 10, 2007 8:01:37 PM

Quote:
comeone slim, you know I don't spend my entire life on forumz, I just happen to post a lot, I do have a life


life?.....
LIER!!!!

March 10, 2007 9:12:09 PM

hehe, Im just kidding taco :) 

but sometimes I ask myself, how do you do to get 300 posts in a day...
March 10, 2007 10:01:41 PM

do what u feel like man, is your money.
March 11, 2007 4:31:00 AM

Quote:

sorry but I laughed at this statement of anandtech XD

in other hand, interesting that the core as more SSE 128bit units (3)

wasnt it the inversed?
P3 vs K7, P4 vs K8, Core vs Barcelona, Nehalem vs Shangai


But for Core arch, it can only do 2 128-bit SSE instructions in a cycle. :wink:
a b à CPUs
March 11, 2007 4:59:01 AM

Quote:
Source:
http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=274...
http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=293...

Here are some of the differences between Intel's Core Architecture and AMD's next generation architecture (NGA) called K8L or K10, with the reference of AMD K8 architecture.

1. Processor manufacturing technology:
Core Arch.: 65nm, 45nm in 2007 H2, 8 metal layers
K8: 130nm SOI, 90nm SOI, 65nm SOI, 9 metal layers
NGA: 65nm SOI, 45nm in mid-2008, 11 metal layers

2. Cache system
Core Arch:
L1 cache: 32KB, 8-way, latency: 3 cycles
L2 cache: 2-4MB shared, 16-way, 256-bit (64GB/s at 2GHz), latency: 11-20 cycles
L3 cache: absent
K8:
L1 cache: 64KB data+64KB instruction, 2-way, latency: 3 cycles
L2 cache: 512KB, 16-way, 128-bit (32GB/s at 2GHz), latency: 11-20 cycles (90nm version)
L3 cache: absent
NGA:
L1 cache: 64KB data+64KB instruction, 2-way, latency: 3 cycles
L2 cache: 512KB, 16-way, 128-bit (32GB/s at 2GHz), latency: unknown
L3 cache: 2MB shared, 32-way, unknown width and latency

3. x86 decoding ability
Core Arch:
x86 decoders: 3 simple + 1 complex (the complex decoder can decode 2 simple codes in a pass)
Out-of-order execution buffer: 96 instructions
K8:
x86 decoders: 3 complex
Out-of-order execution buffer: 72 instructions
NGA:
x86 decoders: 3 complex
Out-of-order execution buffer: 72 instructions with improvements

4. ALU, FPU and SSE units
Core Arch:
ALU units: 3
Maximum dual-precision (64-bit) FP per cycle: 4
SSE units: 3 units, 128-bit
K8:
ALU units: 3
Maximum dual-precision FP per cycle: 3
SSE units: 2 units, 64-bit
NGA:
ALU units: 3
Maximum dual-precision FP per cycle: 3
SSE units: 2 units, 128-bit

5. Pre-fetch and other tune-ups
Core Arch:
Out-of-order loads: Present
Stack manager: Present
Pre-fetchers: 2 data, 1 instruction (to core), 2 pre-fetchers (to L2 cache)
Instruction fetch width: 24 byte per cycle
K8:
Out-of-order loads: Absent
Stack manager: Absent
Pre-fetchers: 1 data, 1 instruction (to L2 cache)
Instruction fetch width: 16 byte per cycle
NGA:
Out-of-order loads: Present
Stack manager: Present
Pre-fetchers: 1 data, 1 instruction (to L1 cache), 1 DRAM pre-fetcher (to dedicated buffer)
Instruction fetch width: 32 byte per cycle

6. Memory controller
Core Arch: absent
K8: 1x128-bit memory controller (1 operation per cycle)
NGA: 2x64-bit memory controller with NGMA (max 2 operations per cycle)

7. Power management
Core Arch: EIST (min. x6 multiplier), switch off transistor when not in use
K8: Cool'n'Quiet (min. x5 multiplier)
NGA: improved C'n'Q, two separate power planes for crossbar and cores, separate clocks for each core



While I know a lot about PC's I didnt study nerdology so I will let someone translate all of this.

TRANSLATION:
AMD K8/Athlon64/Opteron (aka Hammer) = FAST
INTEL Core 2 Duo = FASTER
AMD K10 = BUM FLUF (lol sorry guys, without real samples and real credible benchmarks, it really is bum fluf, but in saying that i hope it grows into something great - either we will get faster AMD's and cheaper Intels, or we might see AMD and ATI go down :( )
March 11, 2007 5:03:44 AM

I had a life once. Then I got married and found this place. Between the two...
March 11, 2007 3:42:24 PM

Well, I dont know about you, but when I buy pheripherals, I always like to get the best out there so that way I wont have to worry later on on getting a new kb or new mouse.
Of course, I first check if there is money available and if that item is in sale or has some kind of instant savings or rebates. If it is not, then I wait til some discounts come out for it and then go and get it at Compusa.

since your case is kinda similar. I suggest you think very well about it. I think the G7 is the cheap version of the G15 right? Will that sattisfy your need for a new KB? is it comfortable enough as the G15? Do you really need those features in the G15 that the G7 doesnt have?

Most important... Will the wire on the KB's annoy you?

I hate that, freaking $80 keyboards with screen and sh*t but they still using the freakin cable
March 11, 2007 4:00:17 PM

What are you gonna do now that CompUSA is basically closing up shop (they are closing over half their stores if you didn't see)?

Myself, I can't stand wired KBs/Mice anymore. I'm spoiled now. :D 
March 11, 2007 4:29:54 PM

Quote:
What are you gonna do now that CompUSA is basically closing up shop (they are closing over half their stores if you didn't see)?

Myself, I can't stand wired KBs/Mice anymore. I'm spoiled now. :D 


YES! I did read that, and Im happy of that because they freakin rop you off if you dont know about computers and buy something in there. But they were good when you needed that ATA cable or that heatsink for your old PC. Well the one here in Miami wont close so Im safe here.

And yes, Im really tire of the cable of my keyboard, my mouse is the only wireless thing hehe apart from my router.

Taco, sorry, I got confused with the Logitech® G11 Gaming Keyboard. Anyways, if you really like the mouse, get it. As you said, the freakin keyboard with the wire is VERY VERY VERY Annoying. Thats why I dont have one g15 hehehe. But for the mouse, I have a question. Which one is better? the G7 or the MX Revolution? I really like more how the MX Revolutions looks but the G7 is a gamers mouse, and thats what I am hehe. I couldnt find what is the maximum dpi of the MX Revolution. But for now I think the G7 is the winner since it has 2000dpi 8O
March 11, 2007 4:59:55 PM

Yeah, CompUsa is over priced, but you can't beat them when you need a part NOW and can't wait for the egg or someone to ship it. Plus their return plociy is/was great.

Though I get automatic SAME DAY shipping from the egg on almost everything. I live like 8 miles from one of their warehouses. Its actually pretty funny. I order, and often the item gets to my house hours before the email with the tracking number.

Ordered my Scythe Ninja at almost midnight, had it installed less than 48 hours later.

I've never got into gaming or specialty keyboard or mice. Though I do need to get new rechargeable batteries for my mouse. The current ones are pretty much toast.
March 11, 2007 6:45:57 PM

Yes, the G7 looks pretty nice since Ill be gaming A LOT!

And hey, because of your tip, I have no keyboard now. You gonna have to send me your current one.
March 11, 2007 6:51:58 PM

Quote:
What do you get when you cross a taco with a burrito? Him!! Shocked Laughing
Or a rough evening spent with (hopefully) extra soft TP. :twisted:
!