AMD Processors
Decrease font size
Increase font size
Topic Title: ML-37 2GHz vs LP-Mobile A64 2GHz
Topic Summary:
Created On: 06/29/2005 06:24 PM
Status: Read Only
Linear : Threading : Single : Branch
Search Topic Search Topic
Topic Tools Topic Tools
View similar topics View similar topics
View topic in raw text format. Print this topic.
 06/29/2005 06:24 PM
User is offline View Users Profile Print this message

Author Icon
insdol
Junior Member

Posts: 2
Joined: 06/29/2005

Acer:
Ferrari 3400 uses Low-Power Mobile AMD Athlon™ 64 Processor 3000+ @ 2.0 GHz
and with 512 KB L2 cache. (35W)

Ferrari 4000 uses AMD Turion™ 64 ML-37 @ 2 GHz and 1MB L2 cache (35W)

Have anyone seen these benchmarked head to head!?
My gut feeling tells me that they should be very close in performance
and the difference all but neglible.

Please show me som numbers!
/smile.gif' border='0' style='vertical-align:middle' alt='smile.gif' />


 06/29/2005 08:01 PM
User is offline View Users Profile Print this message

Author Icon
NetZeroZeus
Senior Member

Posts: 685
Joined: 06/18/2005

I would say you would probably experience in most benchmarks less than 10% difference.
I don't have any links that post both of them against each other though..

-------------------------
Athlon 64 3500+ Venice@275x10 - Mushkin Redline XP4000+@3.2v on 180 div. - DFI LanParty UT Nforce4 Ultra-D - Leadtek 7800GTX@540/1425 ⌐_⌐- Creative Soundblaster Live! 24-bit - Seagate SATA 160Gig HDD - CD-RW - DVD-RW - Antec Truepower 2.0 550w - 1337 Case..not - XP-90C, VF-700Cu and a whole lot of fans
 07/01/2005 02:43 PM
User is offline View Users Profile Print this message

Author Icon
Megadeth
Senior Member

Posts: 7822
Joined: 08/14/2004

The AMD Athlon 64 3000+ is 2000/512/1600HTT/130nm. The Turion 64 ML-37 is 2000/1024/2000HTT/90nm. The ML-37 performs very closely to the Athlon 64 3700+ Clawhammer/San Deigo. It would definitely outperform the Athlon 64. Since the Turion is 90nm, the transistors are packed together more tightly than the A64 130nm which means there will be an increase in performance (on the Turion), clock for clock it will be faster than the 130nm part. Secondly, the Turion 64 is the only Socket 754 part out there that has a 2000 HTT and allows for full duplex memory meaning dual channel. The A64 754 doesn't benefit from dual channel memory because it doesn't have dual channel capabilities, so that is another reason the Turion 64 is faster. The Turion 64 also has twice the cache which is beneficial in the long run.

The Turion 64 really displalys AMD's performance equation very well. You would think that the A64 3000+ 754 performs very closely to the ML-37 when in reality the Turion really whoops [content edited].

The Turion 64 is better because
1. 90nm architecture meaning transistors are closer together increasing performance, A64 and Turion at the same clock speeds on 754 means the Turion will be better
2. twice the cache which is beneficial in the long run
3. dual channel capabilites which basically double memory bandwith to the processor
 07/02/2005 05:37 AM
User is offline View Users Profile Print this message

Author Icon
insdol
Junior Member

Posts: 2
Joined: 06/29/2005

QUOTE
The Turion 64 is better because
1. 90nm architecture meaning transistors are closer together increasing performance, A64 and Turion at the same clock speeds on 754 means the Turion will be better



I don't understand why packing transistors clores would increase profrmance at the same clock speed unless there are major core updates aswell.

QUOTE2. twice the cache which is beneficial in the long run



Sure

QUOTE3. dual channel capabilites which basically double memory bandwith to the processor



If the computer system allows it.

That is why some actual number would be fun.
 07/02/2005 08:20 AM
User is offline View Users Profile Print this message

Author Icon
Megadeth
Senior Member

Posts: 7822
Joined: 08/14/2004

For one thing, the Venice/San Diego/Lancaster (Turion 64) have an updated memory controller so that helps performance. Since the transistors are grouped together more closely, the operations can be completed faster. Why do you think die shrinks allow for higher clock speed? Same reason.
Statistics
112018 users are registered to the AMD Processors forum.
There are currently 0 users logged in.

FuseTalk Hosting Executive Plan v3.2 - © 1999-2014 FuseTalk Inc. All rights reserved.



Contact AMD Terms and Conditions ©2007 Advanced Micro Devices, Inc. Privacy Trademark information