AOA Forums AOA Forums AOA Forums Folding For Team 45 AOA Files Home Front Page Become an AOA Subscriber! UserCP Calendar Memberlist FAQ Search Forum Home


Go Back   AOA Forums > Hardware > AMD Motherboards & CPUs

AMD Motherboards & CPUs Questions or comments on AMD products?


Reply
 
LinkBack Thread Tools Rate Thread
  #21 (permalink)  
Old 23rd June, 2006, 03:22 PM
Gizmo's Avatar
Chief BBS Administrator
BassTeroids Champion, Global Player Champion, Aim & Fire Champion, Puzzle Maniax Champion, Othello Champion, Canyon Glider Champion, Unicycle Challenge Champion, YetiSports 9: Final Spit Champion, Zed Champion
 
Join Date: May 2003
Location: Webb City, Mo
Posts: 16,178
Send a message via ICQ to Gizmo Send a message via AIM to Gizmo Send a message via MSN to Gizmo Send a message via Yahoo to Gizmo Send a message via Skype™ to Gizmo

Quote:
Originally Posted by cadaveca
no, they are not. Memorycontrollers have been revised many times over the duration of each core...as really, the memory controller is not part of the core, but part of the die.
So, there's nothing to say that what we are seeing isn't a consequence of the difference in the memory controllers?

Quote:
Originally Posted by cadaveca
And yes, of course, depending on where the data was called from would skew numbers either way, but i figured it was because of the 2-way associative cache interfacing the crossbar before the memory controller that made these differences more apparant @ the ram level. As the number of calls increases, the effect should be more apparant as calls get queued up.
Ok, I have to admit I am getting into territory here that I am not terribly well versed in. My gut tells me that the issue here is the memory controller, not the cache size. However, I really have very little to base that on, other than a somewhat limited understanding of how caches are being implemented these days.

That being said, an 8-way set associative cache is going to inherently have more latency than a 2-way set associative cache; building the cache tag array is MUCH more complex.

Quote:
Originally Posted by cadaveca
I also think this is part of the reason that Conroe is so efficient...with the crossbar between the L1 and L2 for each core, and an 8-way associative cache, it can handle far more calls before showing a negative impact, as it can properly order those calls in the most efficient way. However, this also means that there are situations where the K8 can outshine Conroe...and we are starting to see this reflected a bit more on reviews.
I'm not following you here? The associativity of the cache doesn't have anything to do with the ability to order data access to the bus?


Quote:
Originally Posted by cadaveca
Oh, and one more thing...cpu errata is becoming increasingly more important...in a highly-threaded world, the chance of this, that, the other thing, and that thing, all happening at once is far more likely, IMHO. Less chances means more reliability, and why i mentioned errata even.
I know that is the conventional wisdom, but sometimes the conventionaly wise are idiots. The logic seems reasonable, but I'm not buying it. The reality is that the world has been highly threaded for a very long time; only individual applications have not, and even THAT statement is only relevant to the PC world. In the world of heavy iron, applications have been threaded for a VERY long time. If errata were that important, it would have been evidenced before now, IMHO. To be sure, it is worth paying attention to, but I wouldn't base a buying decision based on the perception that fewer errata mean more reliability.
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #22 (permalink)  
Old 23rd June, 2006, 06:22 PM
cloasters's Avatar
Asst. BBS Administrator
 
Join Date: September 2001
Location: Location, Location
Posts: 21,956

I don't like a gun to my head, it can look like AMD is saying "buy soon, or else!" Screw 'em, I'm going with Via's extra wuss processors.
__________________
When the world will be better.
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #23 (permalink)  
Old 23rd June, 2006, 10:14 PM
Member/Contributor/Resident Crystal Ball
 
Join Date: March 2004
Posts: 7,451

Quote:
Originally Posted by gizmo
So, there's nothing to say that what we are seeing isn't a consequence of the difference in the memory controllers?
possibly, but because the difference is apparant between the 512 single/dual and 1mb single/dual, it leads me to believe there is more to it than different memory controllers.


Quote:
Originally Posted by gizmo
I'm not following you here? The associativity of the cache doesn't have anything to do with the ability to order data access to the bus?
No, but it does allow for a greater magnitude of order of tasks. And sure, this comes @ a penalty overall, but that dpends really on how the pipeline is designed too.


Quote:
Originally Posted by gizmo
I know that is the conventional wisdom, but sometimes the conventionaly wise are idiots. The logic seems reasonable, but I'm not buying it. The reality is that the world has been highly threaded for a very long time; only individual applications have not, and even THAT statement is only relevant to the PC world. In the world of heavy iron, applications have been threaded for a VERY long time. If errata were that important, it would have been evidenced before now, IMHO. To be sure, it is worth paying attention to, but I wouldn't base a buying decision based on the perception that fewer errata mean more reliability.
Oh, I agree, but it's just something to top the cake with.
__________________
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #24 (permalink)  
Old 23rd June, 2006, 11:07 PM
Gizmo's Avatar
Chief BBS Administrator
BassTeroids Champion, Global Player Champion, Aim & Fire Champion, Puzzle Maniax Champion, Othello Champion, Canyon Glider Champion, Unicycle Challenge Champion, YetiSports 9: Final Spit Champion, Zed Champion
 
Join Date: May 2003
Location: Webb City, Mo
Posts: 16,178
Send a message via ICQ to Gizmo Send a message via AIM to Gizmo Send a message via MSN to Gizmo Send a message via Yahoo to Gizmo Send a message via Skype™ to Gizmo

Quote:
Originally Posted by cadaveca
possibly, but because the difference is apparant between the 512 single/dual and 1mb single/dual, it leads me to believe there is more to it than different memory controllers.
I would be inclined to agree that there is more to it than different memory controllers, but I'm hesitant to put it all down to the difference in L2 cache sizes. If that were the case, then I would expect the difference in bandwidth between the 512k chips and the 1m chips would be comparable. It isn't. In fact, the difference between the 1m chips is almost twice the difference between the 512k chips. The fact that it IS almost exactly twice is mildly interesting.

It very well might be that there is something to your theory, but we really don't have enough data from just these four chips to be able to reach any rational conclusions.

Anybody out there with A64 chips care to give us some additional data?

We would need to know:
Which core you are running
What your memory bandwidth scores are

You would need to run MemTest86. To be certain that everyone has the same version, you should use MemTest86 version 3.2.

The boot floppy image can be found here.
The boot CD image can be found here.
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #25 (permalink)  
Old 24th June, 2006, 12:53 AM
keithwalton's Avatar
Member/Contributor
 
Join Date: May 2003
Location: Southampton, UK
Posts: 2,257
Send a message via ICQ to keithwalton Send a message via MSN to keithwalton Send a message via Yahoo to keithwalton

well it seems ocuk are early on biteing this bait, they have heavily reduced most of the afformentioned cpus and put a note on there site that once they're gone thats it there will be no more of them
__________________
ASUS P5W DH (i975X) - Core 2 Quad Q6600 (2.40GHz) Currently 3GHz under water hit 3.3GHz so far - 2x 1GB OCZ PC6400's - 2x Seagate 7200.10 320GB's - Sapphire Radeon x1900xt now water cooled
AOA Team fah
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #26 (permalink)  
Old 24th June, 2006, 05:06 PM
madcatmk3's Avatar
Member
 
Join Date: August 2005
Location: New York, United States of America
Posts: 2,213

personally I've bean saying for a long time intel is just a bigger company then AMD look at the staff nubers. Intel also has much more money therefore the ability to do things quicker. Even if intel has to spend millions to lower the nm level and even lose money they'll do it if it will stop AMD. As long as they are swiching fabs intel will win for the time, they have also bean making really bad cpus for the last year compared to AMD. However thier new stuff is changing that.
Also anyone know when conroe relases?
EDIT: also what about quadcore kentsfield?
__________________
Alienware
3.2 Ghz
1 GB ram
4-4-4-12
160GB
256 MB 6800GT 413/1102
Main Rig
AMD 4000+ 2772 MHz w/ DFI SLI DR
2GB Corsair XMS (with LED's of course)@ 2.5-3-2-11 @ 240MHz
250GB HDD SATA2
Xfi-64MB X-Ram
WMCE
7800GTX OC-516(+40Mhz Delta clock)/1300
AOA Team fah
"The motherboard installation section essentially said "refer to motherboard manual for installation instructions". My motherboard manual of course said "refer to case manual for further installation instructions"."
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #27 (permalink)  
Old 24th June, 2006, 05:10 PM
Pitch's Avatar
AOA Staff
Asteroids Champion, Maeda Path Champion, Disco Racer Champion, Alpha Bravo Charlie Champion, Van Champion
 
Join Date: February 2004
Location: The cake is a lie.
Posts: 5,025
Send a message via MSN to Pitch

23rd July IIRC.
__________________


XBL/PNS = neolad
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #28 (permalink)  
Old 24th June, 2006, 05:12 PM
madcatmk3's Avatar
Member
 
Join Date: August 2005
Location: New York, United States of America
Posts: 2,213

good I'll be able to build a system with them . What pricepoint are then entering at?
__________________
Alienware
3.2 Ghz
1 GB ram
4-4-4-12
160GB
256 MB 6800GT 413/1102
Main Rig
AMD 4000+ 2772 MHz w/ DFI SLI DR
2GB Corsair XMS (with LED's of course)@ 2.5-3-2-11 @ 240MHz
250GB HDD SATA2
Xfi-64MB X-Ram
WMCE
7800GTX OC-516(+40Mhz Delta clock)/1300
AOA Team fah
"The motherboard installation section essentially said "refer to motherboard manual for installation instructions". My motherboard manual of course said "refer to case manual for further installation instructions"."
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #29 (permalink)  
Old 24th June, 2006, 05:25 PM
Favu's Avatar
AOA's resident barman
 
Join Date: October 2005
Location: /Wales/Abergavenny
Posts: 4,004
Send a message via ICQ to Favu Send a message via AIM to Favu Send a message via MSN to Favu

I'd expect them to start at too much, then drop down to expensive after a few weeks :/
__________________
AOA Team fah
 

Custom 8-bit Sharp Z80 @ 4.194304 MHz
Reflective LCD @ 160 × 144
8 kByte S-RAM






Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #30 (permalink)  
Old 24th June, 2006, 05:27 PM
madcatmk3's Avatar
Member
 
Join Date: August 2005
Location: New York, United States of America
Posts: 2,213

Quote:
Originally Posted by Favu
I'd expect them to start at too much, then drop down to expensive after a few weeks :/
mabey $400 or so? Since I will OC it anyway
__________________
Alienware
3.2 Ghz
1 GB ram
4-4-4-12
160GB
256 MB 6800GT 413/1102
Main Rig
AMD 4000+ 2772 MHz w/ DFI SLI DR
2GB Corsair XMS (with LED's of course)@ 2.5-3-2-11 @ 240MHz
250GB HDD SATA2
Xfi-64MB X-Ram
WMCE
7800GTX OC-516(+40Mhz Delta clock)/1300
AOA Team fah
"The motherboard installation section essentially said "refer to motherboard manual for installation instructions". My motherboard manual of course said "refer to case manual for further installation instructions"."
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #31 (permalink)  
Old 24th June, 2006, 07:33 PM
keithwalton's Avatar
Member/Contributor
 
Join Date: May 2003
Location: Southampton, UK
Posts: 2,257
Send a message via ICQ to keithwalton Send a message via MSN to keithwalton Send a message via Yahoo to keithwalton

if you have seen the pre-order prices on ocuk, the conroe's are coming in at moderatly cheap (more performance per £ than x2's) and are to get cheaper. dual 1.86Ghz ~ £150, 2.13GHz ~£180, 2.4GHz ~ £250, 2.66GHz ~ £411, 2.93GHz XE ~ £775.

All but the last two are cheap!

The X2 4600 which is also 2.4GHz but has alot less cache (1mb total vs 4mb total) and costs £380

The 4800 which has 2megs of cache and is also 2.4GHz is £438.

Considering clock for clock the conroe is quicker what chip would you have an x2 4800 or the 2.4 conroe ? (E6600) or even the 2.66 (E6700) for still less money!

Prices shown ages ago i believe put the E6600 at $316 i think.

Even the now the heavily discounted 4400 oem is £246 for 2.2GHz, £326 retail
__________________
ASUS P5W DH (i975X) - Core 2 Quad Q6600 (2.40GHz) Currently 3GHz under water hit 3.3GHz so far - 2x 1GB OCZ PC6400's - 2x Seagate 7200.10 320GB's - Sapphire Radeon x1900xt now water cooled
AOA Team fah
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #32 (permalink)  
Old 24th June, 2006, 07:51 PM
Member/Contributor/Resident Crystal Ball
 
Join Date: March 2004
Posts: 7,451

once Conroe is on the shelves, AMD prices will drop. I think i might get a conroe, as kentsfield is bandwidth limited with all four cores running(single instance SP1m=17.xxseconds, 4x=19.xx). It all depends on motherboard now, as i want 16x16 pci-e and crossfire...no board out like that yet.

First nvidia boards out that support conroe are using "netburst" chipset(C51), as nVidia's Conroe/Kentsfieldchip ain't quite ready yet. I don't think they will get thiers out before ATI does.
__________________
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #33 (permalink)  
Old 26th June, 2006, 07:24 PM
wild_andy_c's Avatar
Pixel Slave to Satan
 
Join Date: September 2001
Location: Back in the UUUK
Posts: 985

I'm still gunning for 754 to outlive 939 giving four market segments

- Value 754
- Value AM2 (Sempron)
- Mainstream AM2 (A64)
- Performance AM2 (FX)
__________________
Macbook 5,2 | GeForce 9400M | 4GB DDR2 667 | Core 2 Duo P7300 | 2.3TB storage | Vestax Spin
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #34 (permalink)  
Old 26th June, 2006, 08:00 PM
Member/Contributor/Resident Crystal Ball
 
Join Date: March 2004
Posts: 7,451

I think 754 will only last because nobody will buy the remaining stock.
__________________
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #35 (permalink)  
Old 26th June, 2006, 08:14 PM
wild_andy_c's Avatar
Pixel Slave to Satan
 
Join Date: September 2001
Location: Back in the UUUK
Posts: 985

Thats a fair assumption - I know for a fact that a certain AMD HQ has a stock issue and is selling chips that are quite old for 754 platform which means that newer stock isn't even made or they are literally selling FIFO.
__________________
Macbook 5,2 | GeForce 9400M | 4GB DDR2 667 | Core 2 Duo P7300 | 2.3TB storage | Vestax Spin
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #36 (permalink)  
Old 26th June, 2006, 08:20 PM
Member/Contributor/Resident Crystal Ball
 
Join Date: March 2004
Posts: 7,451

754...people need more than it offers...mostly in motherboard connectivity. But even finding 754 boards nowadays, without going mailorder, is a bit difficult. It's a bit sad that they overshot sales with production so much, but at the same time, 939 does not have a ton of stock left over ATM...754 is a "skeleton in the closet"...


emachines and the like should be buying the old stock IMHO, but OEM's need to lower board prices at the same time.
__________________
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #37 (permalink)  
Old 26th June, 2006, 08:29 PM
Member
 
Join Date: June 2005
Location: Los Angeles
Posts: 221

I got the July issue of CPU magazine the other day. They have a monthly segment called watching the chips fall. And I noticed that they report 3800 X2s are up three dollars from last month to 291 and Newegg has a 1 day sale today for 297. What is going on with that? Aren’t we expecting them to drop off? It looks like they are going up not down…?
__________________


E8400 @ 3.92 / ASUS P5Q SE/R / MSI 8800GT / OCZ DDR2 1066 / VelociRaptor 150G

P4 3.2 Prescott running at 3.45 / 2G ram / 8800GT / 3dmark03 31345

Alienware 7700 Laptop P4 HT 2.4ghz 1G ram 17"screen

HTPC Silverstone Case / A64 3200 / 2G ram / 7900GTX / Hauppauge PVR250 / Thermaltake Big TyphoonHSF


AOA Team fah
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #38 (permalink)  
Old 26th June, 2006, 08:46 PM
Member/Contributor/Resident Crystal Ball
 
Join Date: March 2004
Posts: 7,451

retailer pricing does not reflect channel pricing, which is what this thread refers to(channel orders...cpu's will be on shelves longafter the dates posted in the first post). It's up to the retailer to pass the savings on down to the consumer, but this does not always happen right away. Nevermind that these price cuts are expected to happen until the end of July(to compete wit hthe Conroe release...dropping until then is kinda silly), which means we(as consumers) might not see them until mid-August, as retaielrs try to push conroe out the door upon release, so they can get newer conroes in.

You'll find alot of stores will raise prices before a big drop...makes teh drop hurt them a bit less
__________________
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #39 (permalink)  
Old 26th June, 2006, 10:37 PM
skool h8r's Avatar
Member
 
Join Date: January 2005
Location: Rotherham, UK
Posts: 3,157
Send a message via MSN to skool h8r

so, does this mean no more Athlon64 939's?

Seems i upgraded at the wrong time...
__________________
i7 2600K (4.3Ghz 1.34v) | GTX580 | 16GB (4x4GB) Patriot Viper Sec. 5 Ser. 2 (1866 - 9-11-9-27) | P67A-UD4-B3
Corsair AX1200 | Vertex II 240GB SSD | 4TB RAID0 (Samsung HD204UI) | Logitech G930 Wireless Headset

YouTube - Benchmark Results (Coming Soon!)
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
  #40 (permalink)  
Old 26th June, 2006, 10:48 PM
Member/Contributor/Resident Crystal Ball
 
Join Date: March 2004
Posts: 7,451

yes, they should be all gone by april 2007. Any remaining cpu's will be whatever retailers already have on the shelf.
__________________
Digg this Post!Add Post to del.icio.usBookmark Post in TechnoratiFurl this Post!
Reply With Quote
Reply



Currently Active Users Viewing This Thread: 1 (0 members and 1 guests)
 
Thread Tools
Rate This Thread
Rate This Thread:

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

BB code is On
Smilies are On
[IMG] code is Off
HTML code is Off
Trackbacks are On
Pingbacks are On
Refbacks are On


Similar Threads
Thread Thread Starter Forum Replies Last Post
Mobile CPU's & Non Mobile CPU's Mad Professor AMD Motherboards & CPUs 2 1st November, 2003 05:16 AM
XP cpu's nightwolf AMD Motherboards & CPUs 3 19th November, 2002 12:55 AM
AMD CPU's loop Online Deals, and Steals 3 5th March, 2002 11:41 PM


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


Copyright ©2001 - 2010, AOA Forums
Don't Click Here Don't Click Here Either

Search Engine Friendly URLs by vBSEO 3.3.0