A computer components & hardware forum. HardwareBanter

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.

Go Back   Home » HardwareBanter forum » Processors » Overclocking
Site Map Home Register Authors List Search Today's Posts Mark Forums Read Web Partners

fsb speed - why does it matter?



 
 
Thread Tools Display Modes
  #21  
Old October 31st 04, 08:50 PM
Michael Brown
external usenet poster
 
Posts: n/a
Default

Adam Webb wrote:
[...]
Oh and about the locks:

Intel P3 and P4s can not be unlocked (ES dont count)
A64s cant go up on multiplyers, just down.
FX's are totaly unlocked.
2003 week 39 XP's are unlockable, but alittle harder than before


2003 week 39 XP's are not unlockable. Show me a post week 39 desktop CPU
running at anything but the default multiplier on a NF2. Or the cache being
enabled on a post week 39 Duron. You can get around the L3 lock on some
chipsets by enabling PowerNow, but you certainly can't unlock the chip.

2003 week 39 XP's are unlockable with ease.


2003 week 39 XP's aren't locked Well, I suppose the Palomino is if you
want to go back that far (and is easily unlockable as you noted).

--
Michael Brown
www.emboss.co.nz : OOS/RSI software and more
Add michael@ to emboss.co.nz - My inbox is always open


  #22  
Old October 31st 04, 09:58 PM
James Hanley
external usenet poster
 
Posts: n/a
Default

David Maynard wrote in message ...
James Hanley wrote:

David Maynard wrote in message ...

James Hanley wrote:


it seems to me that nobody needs a high fsb. since they could just
push the multiplier really high.

I can see the greatness of ddr since the same speed processor can
read/write twice as much per cycle. (i assume that the cpu has to be
ddr to receive or write double)

How is it you can see the benefit to 'read/write twice as much per cycle'
yet not see any benefit to more of the cycles?



Obviously I see the benefit of more cycles. What do you think I meant
when I said "push the multiplier really high". That increases the
cycles per second.


No, increasing the multiplier does NOT increase the FSB cycles.


I knew that, it increases cycles per second, but just CPU cycles.
So yeah. I just realised that:
Increasing the multiplier increases CPU cycles (not FSB cycles of
course).
Increasing the FSB increases both - that is what hadn't occurred to me
:P

So if the system supported it(processor was unlocked and very
underclocked) doubling the FSB is better than doubling the current
value of the multiplier. It's better to have a faster FSB(thus
increasing CPU cycles and FSB cycles) than to have a slower FSB and a
larger multiplier, which would only increase CPU cycles.

More CPU cycles -- more CPU bandwidth
More FSB cycles -- more FSB bandwidth

I suppose bandwidth and throughput are the same thing



thanks for your response
  #23  
Old November 1st 04, 12:00 AM
James Hanley
external usenet poster
 
Posts: n/a
Default

David Maynard wrote in message ...
James Hanley wrote:
David Maynard wrote in message ...

James Hanley wrote:


snip

Just how fast do you think it can get instructions to execute if you turned
the FSB down to 1 Hz, eh?
It doesn't make any difference how fast the CPU can execute instructions if
you can't feed it the instructions to execute.


I was wrong on that one. thanks for your response

and the RAM multiplies the FSB.


No. It doesn't 'multiply' the FSB. It operates at the memory bus clock rate.


Ok. The thing that made me think it multiplied the FSB was
a)If my memory serves me correctly, Si Sandra lists alongside the
actual and effective memory clock speeds, a multiple, which seems to
work out the actual memory speed correctly if taken as a multiple of
the actual fsb speed.
b)the FSB is often called the base clock, since - i've been told - all
clocks in the system are derived from it - thus, I thought maybe the
memory clock speed was derived from it too (with a multiplier).

I can accept that si sandra is being misleading and that the clock is
independent, since the BIOS does not have a setting to change any
'memory multiplier'.

Maybe the thing I had been told that "all clocks in the system are
derived from the base clock - fsb clock" is wrong, and should read
"all clocks in the system are synchronized with the base/fsb clock"


So the FSB has its own clock, the Synchronous Memory has its own
clock.
But the PCI, AGP and CPU have a derived clock? (I make this
statement by looking at where in the bios i can set the multiplier)

thanks
  #24  
Old November 1st 04, 01:23 AM
David Maynard
external usenet poster
 
Posts: n/a
Default

James Hanley wrote:
David Maynard wrote in message ...

James Hanley wrote:


David Maynard wrote in message ...


James Hanley wrote:



it seems to me that nobody needs a high fsb. since they could just
push the multiplier really high.

I can see the greatness of ddr since the same speed processor can
read/write twice as much per cycle. (i assume that the cpu has to be
ddr to receive or write double)

How is it you can see the benefit to 'read/write twice as much per cycle'
yet not see any benefit to more of the cycles?


Obviously I see the benefit of more cycles. What do you think I meant
when I said "push the multiplier really high". That increases the
cycles per second.


No, increasing the multiplier does NOT increase the FSB cycles.



I knew that, it increases cycles per second, but just CPU cycles.
So yeah. I just realised that:
Increasing the multiplier increases CPU cycles (not FSB cycles of
course).
Increasing the FSB increases both - that is what hadn't occurred to me
:P


It isn't because of increasing 'both': that's a matter of the CPU
multiplier being locked, or not.

A 1.83 Ghz processor on a 333 Mhz FSB will perform better than a 1.83 Ghz
processor running on a 266 Mhz FSB, whether you accomplish the test by
buying two different processors or using one with an adjustable multiplier.

It isn't as dramatic an improvement as changing the CPU speed (multiplier)
partly because it's offset by the L2 cache.


So if the system supported it(processor was unlocked and very
underclocked) doubling the FSB is better than doubling the current
value of the multiplier.


It depends on what you mean by that.

If you mean taking a processor of speed X on FSB Y and *either* doubling
the FSB *or* doubling the CPU speed then no, doubling the FSB, alone, is
not as good as doubling the CPU speed, alone.

If you mean, as I suspect you do, doing one or the other to end up with the
same CPU speed after it's all said and done, then yes, because a processor
at speed X will perform better if it also has a faster FSB (within reason).

Let's put it to a practical example. I have an unlocked mobile Barton 2400
on a DFI motherboard that let's me adjust everything, so I can run it
overclocked to 2.2 Ghz at 266 Mhz FSB, 333 Mhz FSB, or 400 Mhz FSB (if I
stay at 'standard' FSBs) by adjusting the multiplier accordingly. Which do
you think will give me the best performance?

It's better to have a faster FSB(thus
increasing CPU cycles and FSB cycles) than to have a slower FSB and a
larger multiplier, which would only increase CPU cycles.


You're mixing apples and oranges. In one case you alter the CPU speed but
not in the other. That might be a constraint imposed when using a locked
multiplier CPU but it confuses the matter that increasing the FSB, alone,
improves processor performance because more instructions can get to it per
second.


More CPU cycles -- more CPU bandwidth


No. More 'CPU cycles' (all else being equal) --- more instructions
executed per second, assuming it can GET the instructions at that rate.

More FSB cycles -- more FSB bandwidth

I suppose bandwidth and throughput are the same thing


Bandwidth is capability and throughput is what is actually going through.


thanks for your response


  #25  
Old November 1st 04, 02:12 AM
David Maynard
external usenet poster
 
Posts: n/a
Default

James Hanley wrote:

David Maynard wrote in message ...

James Hanley wrote:

David Maynard wrote in message ...


James Hanley wrote:



snip

Just how fast do you think it can get instructions to execute if you turned
the FSB down to 1 Hz, eh?
It doesn't make any difference how fast the CPU can execute instructions if
you can't feed it the instructions to execute.



I was wrong on that one. thanks for your response


and the RAM multiplies the FSB.


No. It doesn't 'multiply' the FSB. It operates at the memory bus clock rate.



Ok. The thing that made me think it multiplied the FSB was
a)If my memory serves me correctly, Si Sandra lists alongside the
actual and effective memory clock speeds, a multiple, which seems to
work out the actual memory speed correctly if taken as a multiple of
the actual fsb speed.
b)the FSB is often called the base clock, since - i've been told - all
clocks in the system are derived from it - thus, I thought maybe the
memory clock speed was derived from it too (with a multiplier).


Well, more like 'system clock' but it, itself, is 'multiplied' from a lower
clock.

The point I was making is that there is no 'multiplier' *in* memory sticks,
as there is with the processor. Memory simply runs at the speed of the bus
it's on.

Typically the memory bus operated at the same speed as the FSB but modern
northbridge implementations often allow for running it at some 'ratio' to
the FSB. That 'not the same as FSB' memory bus clock is generated by the
northbridge and it's not a 'memory' clock, as in the sense of the CPU, it's
a memory *bus* clock.

"Multiplier" has multiple (pun) meanings. One refers to a mathematical
relationship. I.E. 266 is 2 times 133. The other refers to how that number
is physically implemented in the hardware.

While DDR is 'x2' SDR, in terms of theoretical bandwidth, it is not done by
'multiplying' a 133 Mhz clock to get a 266 Mhz clock. It is accomplished by
sending data on both the leading and trailing edges of the same, as SDR, clock.

I.E. | 1 cycle |
____ ____
| | | |
clock --- ---- ---

| | | |
SDR Data | Data |
| | | |
DDR Data Data Data Data

The clock speed is the same and there is no 'multiplier' creating a new,
'double speed' clock. Yet the effective speed is '2x' because it sends the
data twice per clock.

The CPU *does* have a 'multiplier'.

I.E. __________________Processor Package_______________
| |
System | |
clock -- CPU pin -- phase lock loop -- internal CPU clock |
| ^ |
| | |
| multiplier |
|_________________________________________________ _|

The internal CPU clock operates at xMultiplier the external clock.


I can accept that si sandra is being misleading and that the clock is
independent, since the BIOS does not have a setting to change any
'memory multiplier'.


I'm not sure what 'significance' you're trying to ascribe to 'derived' vs
'independent'.


Maybe the thing I had been told that "all clocks in the system are
derived from the base clock - fsb clock" is wrong, and should read
"all clocks in the system are synchronized with the base/fsb clock"


It's an oversimplification that ignores what part of the system is doing
what and why.

So the FSB has its own clock, the Synchronous Memory has its own
clock.


It's both 'their own clock' and derived.

But the PCI, AGP and CPU have a derived clock? (I make this
statement by looking at where in the bios i can set the multiplier)




thanks


  #26  
Old November 1st 04, 02:19 AM
David Maynard
external usenet poster
 
Posts: n/a
Default

James Hanley wrote:

"Michael Brown" wrote in message ...

James Hanley wrote:

"Adam Webb" wrote in message
. ..

it seems to me that nobody needs a high fsb. since they could just
push the multiplier really high.

you cant push the multiplier high because its locked on most modern
CPU's

nobody on an overclocking forum should be saying
"oh no, the multiplier is locked, what am I going to do"
Just like no technician is going to say, oh no, the file is 'hidden'
what am I going to do.


Better analogy: the technician saying "oh no, someone has wiped the disk
then turned it into slag in a blast furnace, what am I going to do?". Given
that people have spent close to 6 years trying to unlock Intel CPUs (no
success) and about 1 year trying to unlock locked AMD chips (no success),



6 years? - but there are loads of articles on unlocking AMD chips, i'm
sure I think I saw one for the AMD XP 1500+, that's less than 6 years
old isn't it?


You didn't pay attention to what he wrote. The 6 years was with regard to
Intel processors and he said "about 1 year" with respect to AMD processors.



The general view is
that both companies are using fuses inside the die, which can't be altered
once set.



*******s.


It all started when unscrupulous resellers simply remarked lower speed
chips to higher speed ones so they could profit by selling cheap processors
at the higher price.

So how can anybody overclock? Just by upping the FSB to whatever the
mobo supports?


Correct. Except that Intel has now tried to lock the FSB.

I suppose that a CPU will have a built in multiplier at a fixed value,
and will assume a certain FSB speed. So if the FSB is lower then it's
underclocked. If it's higher then it's overclocked.


Correct

Or does it not
even derive its clock by multiplying the FSB clock?


It has no other choice.

Would most people have the FSB at the highest setting suported anyway,
and they'd have a CPU that supports it, so how would they overclock?
(they cna't up the FSB clock because it's already on the highest, and
they can't up the multiplier because it's properly locked)


That's why overclockerr's PICK the best processor to overclock, and a
motherboard that provides the ability to do so.


snip

  #27  
Old November 1st 04, 03:42 AM
Adam Webb
external usenet poster
 
Posts: n/a
Default

2003 week 39 XP's are unlockable, but alittle harder than before

2003 week 39 XP's are not unlockable. Show me a post week 39 desktop CPU
running at anything but the default multiplier on a NF2. Or the cache

being
enabled on a post week 39 Duron. You can get around the L3 lock on some
chipsets by enabling PowerNow, but you certainly can't unlock the chip.


oooooh they not unlockable at all? i thought there was a hardway to do it? i
dunno my last XP was a week 20 something ;-)

--
From Adam Webb, Overlag
www.tacticalgamer.com
CS:SOURCE server now active


---
Outgoing mail is certified Virus Free.
Checked by AVG anti-virus system (http://www.grisoft.com).
Version: 6.0.786 / Virus Database: 532 - Release Date: 30/10/2004


  #28  
Old November 1st 04, 06:47 AM
Michael Brown
external usenet poster
 
Posts: n/a
Default

David Maynard wrote:
[...]
The CPU *does* have a 'multiplier'.


Oooo, you're lucky you put that in quotes :P

__________________Processor Package_______________
| |
System | |
clock -- CPU pin -- phase lock loop -- internal CPU clock |
| ^ | |
| | | |
| divider ------------/ |
|_________________________________________________ _|

Yes, I know I'm being picky

--
Michael Brown
www.emboss.co.nz : OOS/RSI software and more
Add michael@ to emboss.co.nz - My inbox is always open


  #29  
Old November 1st 04, 07:14 AM
Michael Brown
external usenet poster
 
Posts: n/a
Default

Adam Webb wrote:
2003 week 39 XP's are unlockable, but alittle harder than before


2003 week 39 XP's are not unlockable. Show me a post week 39
desktop CPU running at anything but the default multiplier on a NF2.
Or the cache being enabled on a post week 39 Duron. You can get
around the L3 lock on some chipsets by enabling PowerNow, but you
certainly can't unlock the chip.


oooooh they not unlockable at all? i thought there was a hardway to
do it? i dunno my last XP was a week 20 something ;-)


The "hard way" is enabling PowerNow on the CPU, and is what people are
calling psuedo-unlocking of the CPU. It doesn't work on NF1/NF2 chipsets,
and is only really of use when you've maxed your FSB without maxing out the
CPU (for example running a Barton 2500 at a good speed on a board that only
works up to a FSB of 150MHz or so).

There actually isn't one multiplier setting on the Athlon XP, but two.
There's the startup multiplier, and the maximum multiplier. When it's
powered on, the CPU reads the startup multiplier and uses this setting. In a
desktop CPU (which doesn't have PowerNow), this is where it ends. You're
stuck with the startup multiplier until you reset the chip. On a mobile CPU
(or rather, any CPU with PowerNow) things are a bit better. Once the CPU has
been started, you can transition to any multiplier less than the maximum
one, as long as the chipset supports PowerNow transitions (pretty much all
do except the NF1/NF2).

What AMD did was not "locking the multiplier" per se, but rather storing the
L3 (and L2, but that's a different thread) bridge configuration inside the
die. So instead of reading it off the bridges/BP_FID pins on boot, it reads
it from its internal storage. Noone has figured out how to talk to this
internal storage, and there's a ery high chance that it's been closed off to
the outside world. For example, there's quite possibly a bit in the storage
that says "ignore any attempt to write into the storage". You can't change
the multiplier (because the "write protect" bit has been set), and you can't
reset the bit (since this would require writing to the storage, which is
denied). Or alternatively, if a bit can only be "set", then there could be
pairs of bits. If both bits are set, then something has been tampered with
and the CPU would refuse to start. Again, this completely prevents any
changing of the settings.

Sooooo, in a locked AMD chip, there's no way to set the startup multiplier,
and if the CPU doesn't have PowerNow support, then there's no way to change
the multiplier at all. All K7 BIOSes that I've seen do multiplier
adjustments through the startup multiplier (messing with the BP_FID pins),
so once you lock the L3 bridge configuration, you disable the ability of all
BIOSes to use anything but the stock startup multiplier.

The "psuedo-unlock" involves activating PowerNow, and setting the maximum
multiplier to something good. Then, you can make the chip operate at any
multiplier that you like, though the chip still boots up at the original
multiplier.

Currently, the die-storage is only used in desktop CPUs. However, it's clear
that there's nothing stopping AMD from using it on mobile CPUs as well.
Mobile systems acheive power saving through PowerNow transitions, not
manipulation of the startup multiplier, so whether the L3 configuration is
locked or not makes no difference to them. It's also obvious that there's
nothing (except possibly technological reasons, such as a limited amount of
data that can be stored in the die) stopping AMD from putting all the
bridges inside the die. It's exactly what they do for the K8 chips. It just
means that
a) You can't adjust the startup multiplier
b) You can't adjust the maximim multiplier
c) You can't enable or disable PowerNow

None of these restrictions will stop a mobile CPU from working correctly in
a mobile system. Restrictions "a" and "b" combine to stop the chip running
at anything over the stock multiplier. Restriction "c" means that a desktop
CPU will ONLY operate at the startup multiplier and nothing else.

What do we have today? Well, mobile CPUs have no restrictions. This is good,
and lets hope it stays this way. Desktop CPUs have restriction "a", which
means that as long as your board supports PowerNow, you have a bit more
freedom as to how you run your CPU. However, if you have a NForce chipset
(which don't support PowerNow transitions), you effectively have restriction
"c" imposed. Which means that on an NF board, a desktop CPU will only
operate at it's stock startup multiplier.

--
Michael Brown
www.emboss.co.nz : OOS/RSI software and more
Add michael@ to emboss.co.nz - My inbox is always open


  #30  
Old November 1st 04, 10:22 AM
David Maynard
external usenet poster
 
Posts: n/a
Default

Michael Brown wrote:

David Maynard wrote:
[...]

The CPU *does* have a 'multiplier'.



Oooo, you're lucky you put that in quotes :P


It wasn't 'luck'. I use single quotes to denote irony, the 'colloquial
gist' (sometimes akin to irony), or non literal use of a word/phrase.

In that case I was indicating the colloquial gist of the function and not
necessarily a literal.


__________________Processor Package_______________
| |
System | |
clock -- CPU pin -- phase lock loop -- internal CPU clock |
| ^ | |
| | | |
| divider ------------/ |
|_________________________________________________ _|

Yes, I know I'm being picky


Technically what you did was break the block diagram down further and show
how the phase lock loop accomplishes the multiply. Both are appropriate,
depending on what one is trying to convey: how the multiplier works or
simply that there's a multiplier.


--
Michael Brown
www.emboss.co.nz : OOS/RSI software and more
Add michael@ to emboss.co.nz - My inbox is always open



 




Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

vB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Forum Jump

Similar Threads
Thread Thread Starter Forum Replies Last Post
How to speed up my CPU? MC General 11 December 12th 04 09:11 PM
AthlonXP 2000 on MSI KT4AV with (VIA KT400A) chipset Mainboard has Speed ÎÔ»¢²ØÁúCrouching Tiger Hidden Dragon Overclocking AMD Processors 18 May 6th 04 12:14 AM
AthlonXP 2000 on MSI KT4AV with (VIA KT400A) chipset Mainboard has Speed Complexity LongBow Overclocking AMD Processors 7 May 2nd 04 12:23 AM
D865GLC + CPU Fan Speed HELP Ron Reaugh General 1 December 16th 03 03:28 PM
CD burning speed determines read speed? David K General 4 July 22nd 03 09:31 AM


All times are GMT +1. The time now is 08:33 PM.


Powered by vBulletin® Version 3.6.4
Copyright ©2000 - 2024, Jelsoft Enterprises Ltd.
Copyright ©2004-2024 HardwareBanter.
The comments are property of their posters.