dumb A64 question

[DanielLevesque]

I dont quite understand what gain i will get in gaming from the 64Bit? I dont see the benefit to upgrading for a gamer? can anyone please explain? I dont know much besides it allows for more memory

 

[Bahumut]

Sure 64bit processors allows for more memory on a system, but their main benifit is from 64bit registers. They allow it to calculate 64bit integers in the time it takes a 32bit processor to calculate a 32bit integer.

Think of it like DX9 cards. They can process advanced effects in one pass that require multiple passes from lesser cards.

Like DX9 cards, 64bit processors won't necessarily provide benifits to games not made to use their capabilities. There are a few games out using 64bit, but most (maybe all) are for 64bit Linux.

64bit games and apps are, however, on their way. However, like DX9 games, they'll be a while in coming.

I should also mention that A64s are supposed to be 25% faster than Athlon XP processors in 32bit apps as well.
Maybe AMD will fix their overly enthusiastic rating system when they come out.

Pain is the realization of your own weakness.

 

[DanielLevesque]

Thank you for your reply. So esentially the same game ported to 64Bit will run better because 64Bit processors can do more calculations faster??

 

[pIII_Man]

that does not sound right...as they are basically sharring the same archetecture as the k7...just with more cache, extra registers, possibly a tad higher ipc and sse2

that does not warent a 25% increase IMO


Proud owner of DOS 3.3

 

[endyen]

Not 25%? Did you check out the oc workbench tests? That is for an xp2500 speed chip, and before they corrected the SSE2 problems. Even if the improved SSE2 gives nothing,the Athlon 64 @ 2.2 will be very good.

 

[Schmide]

You seem to have forgotten that the memory subsystem is completely different. No more EV-6. It now has a crossbar memory architecture to support its integrated low latency memory controller. This should lend its self to 3d games and graphics more than any other improvement.

Dichromatic for your viewing plesure...

 

[pIII_Man]

true...i totally forgot about the memory controllor...that should help with low latencies


Proud owner of DOS 3.3

 

[jmecor]

memory controller, i'm quite confused to this.
Is this something that will make the front-side bus clock equal to that of the clock speed of the cpu?

-J<font color=red>//\</font color=red>ECOR™ -
-J<font color=purple>//\</font color=purple>ECOR™ -

 

[Schmide]

The Opteron has a crossbar memory system that manages access between the CPU, hyper-transport links and integrated memory controller. It has a FSB, running at 333mhz or 400mhz, and cache similar to the Athlon, although latency is greatly improved.

Up until now Opteron processors have used DDR 333 cl2.5 memory. This memory in terms of actual latency time is ~37% slower than DDR 400 cl2. Yet in terms of total latency timings the Opteron comes equal or quicker than the 875P. Presumably the Athlon 64 will run DDR 400 cl2 memory as seen in the <A HREF="http://www.ocworkbench.com/2003/aliuli/m1687/m1687gallery4.htm" target="_new">Ocworkbench</A> article. This should give a 10-15ns improvement to the total latency numbers.

Dichromatic for your viewing plesure...

 

[poncho]

"It has a FSB, running at 333mhz or 400mhz,"

Technically this is not true and jmecor is actually correct when he says the fsb will be equal to the clock speed of the cpu. The opteron may use pc2700 ddr memory running at 166mhz and capable of supporting the so called 333mhz speeds as a result of its double data rate, however the fsb of the cpu is eqivalent to the actual cpu clock.
These specs on the amd web site shows this
http://www.amd.com/us-en/Processors/TechnicalResources/0,,30_182_865_8799,00.html
It states:-
Front Side Bus frequency 1.4 - 2.0 GHz†
† The front side bus (interface to memory) of the AMD Opteron™ processor runs at the speed of the processor

In reality this may not have a great effect on the performance after all what good is a fsb of 2.0ghz if the memory is only operating at 333 or 400mhz, It is still interesting to note none the less.

Arguing on the internet is like running in the special olympics. Even if you win your still retarded!

 

[Pirox]

*Let me Fix something here*

The athlon 64 fx like other hammer processors will not have a FSB to system. The traditional FSB we all know is from CPU to memorycontroller and Backsidebus(BSB) is cpu to L2 cache. Since it is integrated the FSB on all hammer processors now depends on the CPU's clock speed. if it is 2Ghz the FSB is 2ghz. That also means that it can support any memory speed type as long as the speed of the ram is not more than the CPU's clock frequency and it's l2 cache throughput(two factors that must not override each other: the bus speed or bus width)... The integrated memory controller is then connected to the "memory Bus". This can be 100,133,166,200 DDR depending on AMD to what ram speed they will like to support these days. On like todays fsb's the cpu is connected to the northbridge 'memory controller' and then to the 'memory bus'. This is also limited because as cpu clock speed grows latency does not reduce. FSB remains the same. Also this only allows one read/write opteration per cycle. That means that you cannot read and write at the same time no matter how much bandwidth you have*(6,4Gb/sec++). But hammer systems don't work like that. The memory bus does not require any distrubance from the system. The cpu and the memory will be happy . If data need to be read from memory it will pass through the cpu and then hypertransport link to the system.(see errata)

Behind the cpu core is a hypertransport Bus. It supports various frequency's. 200/800Mhz DDR upstream/downstream datapads. It can carry various amounts of bits up to 32bits and also more than one read/write operation per clock cycle because it is a serial bus unlike traditional FSB's and is bidirectional. Even 20 PCI-Express devices can be connected without problems! Traditional FSB's today have to share the bandwidth. For example a system with 6.4Gb/sec bandwidth will have to share its bandwidth with the AGP bus e.t.c...but on a hammer system this is done parralel with the hypertranspot bus. its like hyperthreading but on hardware level. Therefore I/O bottlenecks will autotmatically be removed. It can even work with only 3,2gb of bandwidht depending on the memory speed and still support pci-express and the rest. What you can conclude from this is that the 'new' FSB here is the speed of the HTB(hypertransport-bus). todays systems work with 800Mhz DDR clocks and 16bits datapad. That will get you a total of 6,4 gb/sec per sec of total I/O throughput with 3,2Gb/sec upstream and downstream read/write instantly. but with 32-bits datapad it can climb up to 12,8Gb/sec with 6,4 gb.sec up/down.

errata : *Cpu directly to Agp writes do exist *

---
If you go to work and your name is on the door, you're rich. If your name is on your desk, you're middle class. If your name is on your shirt, you're poor!
<P ID="edit"><FONT SIZE=-1><EM>Edited by pirox on 09/03/03 05:48 AM.</EM></FONT></P>