dom

引用:

原帖由 Puff 於 2012/4/3 22:52 發表

正常呀，你話佢 Fake HT，咁佢得 Dual-core 270 級數唔合理咩。Time will tell la. Frequency 唔會一直都可以升上去。要講既話，Bulldozer 十足個唔夠 budget 的第一代實驗品設計。唔係講緊錢錢錢錢。 ...

After the test , plus reading lots of Bulldozer Review
AMD really "FAIL" , Bulldozer in concept sounds "awesome"
but in reality , AMD they screwed up the front end ........

One module have OK performance
but when "Two module" fight for resource
You can see it from "HyperPI" result  (留意一齊扯 CPU 效能明顯下降)

dom

引用:

原帖由 qcmadness 於 2012/4/4 08:05 發表

咁我問你
1. 唔用bulldozer, K10仲可以點改?
2. K10仲可以升到幾多頻?
3. 點解bulldozer要decouple INT同FP?

1. Star 已經改無可改絕路....
2.  Stock 3.6GHz ~ 3.8GHz 已經極限
3. Cost down

dom

引用:

原帖由 XT 於 2012/4/4 12:39 發表
要發揮推土機既效能必須使用Linux

Sorry , end user (Desktop) 90% use Windows

dom

引用:

原帖由 Puff 於 2012/4/5 01:11 發表

Are you talking about cores? This is an issue of how AMD is telling Microsoft to profile its Bulldozer for desktop applications. And the flaw is not about the front-end at all, as one core is still e ...

You can see HyperPI result clearly affected ...
Even Disable / Enable Module , when excuse CPU intensive task together ,
FX-4100 have a hard time to allocate its Hardware resources .....

Phenom II / Athlon II don;'t have such issue

EDIT : This issue affect all tested CPU

[ 本帖最後由 dom 於 2012-4-5 21:43 編輯 ]

dom

FUN part begins tonight

Phenom II X6 1045T 正式參戰 (Disable 2 Core as Phenom II X4)

[ 本帖最後由 dom 於 2012-4-5 21:33 編輯 ]