nobody i know, knows this help pls

dumbfish · Mar 12, 2004

lets pretend i had two systems that i wasn't going to overclock.so i can learn this.

system 1-------------------------!----------- system 2
-----------------------------------!----------------------------------------------------
cpu 1.1 ghz 512 cache 400 fsb --- !-- cpu 3.1 ghz 512 cache 400 fsb
same mobos
same gfx card
same ram
same the rest

question 1. are they the same speed? since the extra 2ghz travels gets blocked by the 400 mhz bus.
both systems run at 400mhz same speed.
true or false? explain pls.

question 2. if both systems had all same stuff but this
again no overclocking for system or gfx cards
system 1---------------------------!------------ system 2
----------------------------------!---------------------------------------
gfx card vpu 200mhz/250-----------!-----gfx card vpu 600mhz/800mhz
cpu barrton 333mhz ---------------!--------cpu barrton 333 mhz

would they run same speed ? or would system one have its bus
blocked at the gfx card because 333>200 or is it the 250?

help me understand pls?
or is this like a relay race where all the componets play a part and
if your total time for all runners was 18 secs and your fastest runner improved by .5 sec then at least we are at 17.5.so you dont have to always go after the slowest componet even though its the most effective.
the way i see it without overclocking you can never beat the bus of your board .so if i have a 400mhz board there is no point in dual channel ram at all.or paying for parts that go any faster than 401 mhz.

dumbfish · Mar 12, 2004

and if my thoughts are right i feel sorry for all the suckers. my theory has been for the last 10 yrs buy the lowest mhz (cheapest mhz)at the highest bus.

GT2000 · Mar 12, 2004

No, the FSB is basically the speed at which your memory is running, divided by 2 in this case, so the memory is running at 200MHz...your theoretical CPUs would have different multipliers, which are multiplied to the 200MHZ, to derive the true running frequency).

A multiplier of 10 would give you a CPU running at ~2000MHz.

As for the video cards, system 2 would be NOTICEABLY faster in games, 3d rendering in general, due to the higher GPU speeds.

I hope that helped you with your questions, I had a hard time understanding them personally..

Sentential · Mar 13, 2004

question 1. are they the same speed? since the extra 2ghz travels gets blocked by the 400 mhz bus.

It depends upon how long the pipeline for the 1.1ghz chip is. If its very short, they could be equal.

The bus and CPU speed have nothing in common. The bus can either work in synch with the memory. Or out of synch, period!

would they run same speed ? or would system one have its bus
blocked at the gfx card because 333>200 or is it the 250?

Same thing. It depends upon the pipeline and how efficeint they are. Nvidia makes fast but inefficiant cards. ATi make slow but efficient cards.

so if i have a 400mhz board there is no point in dual channel ram at all.or paying for parts that go any faster than 401 mhz.

Dual channel for AMD chips boosts teh memrates by almost 50%. For Intel chips its 2x

dumbfish · Mar 13, 2004

so i am wrong and the relay race idea is right. so how can i compare pipelines?

Sentential · Mar 13, 2004

so i am wrong and the relay race idea is right. so how can i compare pipelines?

Pipelines are the length of the race that is required to complete. Sure, Intel is fast but it has a loooooong way to the finish line. AMD is much slower but have a very short distance to truck along.

BTW manufacturers dont list pipeline lentgh openly.

dumbfish · Mar 13, 2004

ok so from what i can compare list of importance is as follows?
1 fsb board
2 mhz of chip
3 mhz of gfx card
4 mhz of ram
5 amount of ram
6 amout of hd cache
7 speed of hd as in 66/100/133/150 ata or sata
8 cache of opticle drive

hitechjb1 · Mar 13, 2004

FSB is for moving data between CPU and memory + video subsystem.

CPU executes program codes (logic computation), and
has to get data from and store data to memory via the FSB, and
has to comunicate video data via the FSB.

Analogy:
CPU is a factory for cranking data.
FSB is moving data (highway) to / from memory, video subsystem (diaplay).

Overall system performance, both CPU and FSB are important, and have to work in a balanced manner.

For small programs such as kernal code, inner loop code, CPU speed (frequency) is more important.

For programs that requires lots of memory data, such as video compression, large scientific computation, both CPU and FSB speed are important.

In general, in a computer system, CPU, FSB (NB, SB), memory, hard drives, video subsystem are working in parallel, so each should be as fast as possible. Further they all should work in a balanced manner, so there is no bottleneck created in a system.

For example, this is a more balanced system
CPU: 2.5 to 3+ GHz
FSB: 200 - 250 DDR (for AMD), 200 - 250 QDR (for intel)
Memory: 1 GB (less paging via hard drive)
Hard drive: ATA 100/133 RAID-0 (for faster disk I/O, paging)

If a slow hard drive such as ATA66, or even ATA100 is used, the hard drive would create a bottleneck. File access and paging would be slow.

If slower memory such as PC2700 or FSB 166 is used, performance of memory intensive programs would be degraded.

hitechjb1 said:
Why frequency and voltage are important for overclocking performance

CPU and motherboard FSB operate and repeat operations at a fixed time interval called cycle time, and so they operate a fixed number of operations per second called frequency.
The unit of time is second, and the unit of frequency is Hz. Hz stands for Hertz, and is the same as cycle per second.

The relationship between frequency and cycle time is
f = 1/T

Today, typical CPU operates around 2.5 - 3.0+ GHz, meaning it repeats 2,500,000,000 - 3,000,000,000+ operations every second.
Typical FSB of mothboard and system memory operates around 200 - 250 MHz, about 1/10 times of CPU. (1 MHz = 1,000,000 Hz).

So it is apparent that the faster the frequency (MHz), the more operations the CPU can repeat every second, the more computer instructions it can do per second.
For the same programs with the same amount of instructions to execute, a higher MHz CPU can finish it sooner, hence faster turn around in time.

Same is true for moving memory data, video data, ..., over the FSB. Higher FSB frequency would enable programs that require lots of memory access, video subsystem access to finish sooner in time.

Overall_performance = A FSB + B CPU

where A and B are some constants, CPU and FSB stand for frequency of CPU and FSB.

For CPU intensive programs where everything can reside in the CPU cache (e.g. small kernel code, inner loop code)
A ~ 0
Overall_performance = B CPU (only CPU frequency is important)

For memory intensive programs such as large matrix computation, video compression in which lots of memory and video access are needed, B is also important, so is FSB.

In general, A and B are non-zero, so both CPU and FSB frequency are important.

How does Vcore improve CPU frequency?

When certain higher Vcore is applied to a CPU or any logic chip, the current, called Idsat, in transistors would increase, hence the transistors can operate the logic gates faster. The delay of a logic gate, transistor current (Idsat), voltage (Vcore), loading (Cload) are related by

delay = Vcore Cload / Idsat
Idsat = k (Vcore - Vt)^n

where Vt is transistor threshold voltage and k is some constant, n is between 1 and 2.
Simply speaking, the higher the Vcore, the higher the current Idsat, the smaller the delay (hence chips run faster).

It can be shown that for a given temperature and without temperature constraint, increase Vcore can speed up frequency about linearly, that is the higher the Vcore, the higher the max frequency.

frequency / Vcore ~ constant

Originally posted by hitechjb1
At a given temperature, the higher the Vcore is, the smaller the delay in a logic gate for a given circuit, hence the smaller the cycle time T can be, or the higher the clock frequency f can be. As seen above, to the first order, without the contraint of heat, the maximum clock frequency varies somewhere, from with the square root of voltage to linearly with voltage. This is the good news - higher voltage can get it to run faster.

The bad news is, the higher the Vcore, the active power (C Vcore^2 f) and leakage power (Vcore^2/R) would also increase, where C and R are the equivalent capacitance and resistance to model the chip power dissipation. Up to a point, the slow down and instability effects due heat and temperature increase outpace the gain in clock speed, and diminishing return occurs. There is a delicate balance between voltage and temperature at optimal overclocking.

To summarize, Vcore improves the maximum CPU clock frequency (fmax) for a given CPU chip with same architecture and circuit under certain operating condition of temperature. So with sufficient voltage, within a (very) short period of time (1/1000 – few seconds), the CPU should be able to operate at such maximum frequency (fmax), before temperature begins to rise, leading to instability unless sufficient cooling is incorporated to limit any adverse effect of temperature on electron mobility, higher leakage current and instability perturbation on electronic components.

Click to expand...

For details:

What is cycle time and frequency

Frequency, clock, period of synchronous operations, latency

Latency

Analogy on Bus Speed, Bandwidth and Latency

Analogy for FSB, CAS2, CAS3 latency and bandwidth for DRAM memory

Memory bandwidth efficiency

Vcore vs processor frequency and cycle time (page 19)

What is CPU stability (page 19)

dumbfish · Mar 13, 2004

now im all screwed up and i feel like starting this question over.

"Overall system performance, both CPU and FSB are important, and have to work in a balanced manner.
If a slow hard drive such as ATA66, or even ATA100 is used, the hard drive would create a bottleneck."

contradicts

It depends upon how long the pipeline for the 1.1ghz chip is. If its very short, they could be equal.

The bus and CPU speed have nothing in common. The bus can either work in synch with the memory. Or out of synch, period!

because the should be equal reguardless if the chain is only is strong as its weakest link the extra pipeline of the cpu shouldn't produce a $200 difference in or even a $50 difference.
or maybe if one benchs 10000 3dmark the other would give 10500
im guessing.
i guess i need to make myself as clear as possible .
can changing just adding a super chip to a poor system help?
can a super system run just as good with a poor chip?
you did say that a poor gfx card will run poor on a super system.
but i guess im asking more or less about mobos vs chips.
thanks for fixing my dual ram question i got that now.
and i still think faster ram is better than more ram.

ChillPhatCat · Mar 13, 2004

Man you guys just compounded the problem! It's really far more simple than they're saying.

Look at it like this... The FSB of a chip is how fast data goes from RAM to the CPU, the clock speed (dictated by the front side bus multiplier) determines how fast the data is processed. So with an equal front side bus, the difference between two computers is which one can calculate data faster and put it back on the "bus".

Now the speed of the hard drive doesn't directly effect gaming performance or any program usage.

The way it goes, the Speed of the hard drive dictates how fast data can be loaded into the RAM. If you have enough RAM you can load an entire program into memory and it will not have to read data off the hard drive while it is loading... so the speed of a hard drive says how fast a program loads.

The Speed of the RAM has nothing to do with loading time, the speed of the RAM simply dictates how fast data can be transported to the CPU... so once data is loaded off the hard drive and into RAM, it sits there until the CPU asks for specific Data which is then transported along the front side bus.

That Data gets to the CPU, it works on it and sends it back, the speed of the CPU is what dictates how long it will take to get that data back on the front side bus back to the memory where it will eventually be used again or saved onto the hard drive.

Now take that in and realize that what I am about to say has nothing to do with what I just said... just a quick word on pipeline length

Now, if we have a pentium 4 and an Athlon XP side by side running at the same speed and same front side bus, there is a difference in how much work can be done within a specific amount of time.

There are 12 steps in the pipeline of the XP and 20 steps in the pipeline of the P4, so lets say there is a little guy in the CPU and he has to get through one iteration of the pipeline on each CPU (one clock cycle) it takes him only 12 steps to get to the end of the line in the Athlon, where as it takes him 20 steps to get to the end of the P4's pipeline.

Now remember this guy has to complete each cycle in the same amount of time so he has to walk a lot faster to cover the same ground in the Pentum. The data in the pentium has to travel faster to get to the same destination (the bus) in the same amount of time as the Athlon.

dumbfish · Mar 13, 2004

so like i said its the speed of the bus and ram that sets a computer.
all other things just help.but the bottom line is fsb and ram mhz

but dont worry im not thinking intel vs amd. i dont compare them.
im thinking 266 vs 333 vs 400.

an example my wifes system is .athlon tbred with ecs board 266mhz max .while mine is duron morgan 200mhz with biostar 400mhz.

so which one is faster? one more difference we both have nvidia cards but mine is 128bit/128 mb nvidia 5200.hers is a 64.but the vpu speeds and mem speeds on the cards are the same. 3d mark scores are both in the 4,000's.

dumbfish · Mar 13, 2004

an example my wifes system is .athlon tbred with ecs board 266mhz max .while mine is duron morgan 200mhz with biostar 400mhz.

WHICH ONE IS FASTER?

ogboot · Mar 13, 2004

ok, think of it this way, this is just an example. k, 2 systems with the same bus speed. we'll use your 1.1g chip on one, and the 3.1g chip on the other, everything else is identical. send both chips the same data to be processed. bus on both systems is the same, data hits chips to be processed at the same time. 1.1g chip actually processes the data infinitely slower than the 3.1g, even though the data got to both chips at the same time. therefore, even though both chips have the same bus and received the same data at the same time, the 3.1g chip produces its results and sends them to the memory before the 1.1g can. once the data travels along the system bus it travels at the same speed on both systems, but the system with the 3.1ghz chip starts to send it before the 1.1g can, so it gets to the memory first; 3.1system is faster with same bus speed.

t1mex · Mar 14, 2004

dumbfish said:
an example my wifes system is .athlon tbred with ecs board 266mhz max .while mine is duron morgan 200mhz with biostar 400mhz.

WHICH ONE IS FASTER?

this partially depends on what your ram is at. if you have the ram on the tbred in sync at 266mHz (pc2100 - correct me guys if im wrong) then the tbred system would run very nicely. now if you have the duron system with pc3200(400mHz) ram like the motherboard can run, you would create a bottleneck because the chip is sending things at half of the speed (200mHz)

therefore

your wife's system would be running faster IN THIS HYPOTHETICAL (with the ram)

however, if you overclock that duron at say...333mHz FSB (is this is possible) and choose the ram in sync (pc2700) then you would be FASTER than your wife's system.

hopefully this makes some sense.

dumbfish · Mar 14, 2004

its not possible without some volt modding and stuff on my board.
anyway mine seems faster because of my better gfx card.
i just want to understand by theory.i believe the bus means way more than the chip.lets try a new example.good one ogboot

if this were possible.

say we had the same gfx cards.but say mine has a 1.8 ghz 333 barton.and if they made one she had a 2.7ghz 266 athlon.neither was overclocked .both ram settings were 2.5/2/2/2.we both have pc3200 ddr even thought her board is only 266max so it shows 266 when she boots up.
WHO IS FASTER?

The Coolest · Mar 14, 2004

2.7GHz.
The FSB matters but not as much as CPU speed. As simple as that.
FSB is just the speed that the northbridge can talk to the CPU, the CPU speed is HOW FAST data is actually being processed. Although higher FSB will make a machine run faster at a given CPU MHz, it won't make that much of a difference if you have a 1.5GHz and a 2GHz CPUs. In most if not all cases the 2Ghz will be faster.

dumbfish · Mar 14, 2004

thanks that was the bottom line question

but im gonna try to do the math on it.im gonna start a new thread to get alot of people to check my math on this.

redface · Mar 14, 2004

what i've heard:
if the cpu itself have big cache and rarely access the ram then cpu speed is the single factor. with the same 512k cache, the 3.1ghz's cache is about three times as fast as the 1.1ghz's cache so this will be the difference maker.

however in most cases we will have intense access to the rams, so fsb becomes important too because it is the bridge where cpu communicates with the ram. but 3.1ghz is still faster than 1.1ghz because of the speed difference in the cache.

dumbfish · Mar 14, 2004

now that even puts a new twist in the mix

nobody i know, knows this help pls

dumbfish

Member

dumbfish

Member

GT2000

Member

Sentential

Contributing Member

dumbfish

Member

Sentential

Contributing Member

dumbfish

Member

hitechjb1

Senior Member

dumbfish

Member

ChillPhatCat

Member

dumbfish

Member

dumbfish

Member

ogboot

Member

t1mex

Member

dumbfish

Member

The Coolest

Senior Member

dumbfish

Member

redface

Member

dumbfish

Member

Similar threads