Lake Shore wrote:
關於故事的前言，請先...(恕刪)
沒看到新的消息，但是你還是要開新的一篇?
我記得這篇在你的回文中就有了
http://www.mobile01.com/topicdetail.php?f=568&t=3344046&p=35
有何意義?
個人積分：130分
文章編號：44000712
個人積分：27分
文章編號：44000872
victory2000 wrote:
沒看到新的消息，但是你還是要開新的一篇?
我把1F中的時間點改得清楚一些......5/25來自AndreiLux的最新狀況更新是：
http://forum.xda-developers.com/showpost.php?p=41806011&postcount=188
25th May 2013, 02:02 AM
----------------------------------------
Managed to properly enable the IKS driver instead of the IKCS one. The system presents itself as if it would actually work and the CPUFreq layer actually shows two different concurrent frequency planes as one would theorize.
...
But it's all shenanigans, if you actually read the core status registers, the A7's never get switched on, even if the frequency they inside the A7's region. Furthermore the A7's L2 cache is always powered on but never actually does anything.
Regarding the CCI: it is powered off (Or at least unusable beyond its default state), when you try to enable or do something with it, you can't boot at all.
I now have info that this is a problem in silicon that won't be solvable, meaning neither core migration nor HMP will be possible.
翻譯：我的資訊指向這是Exynos 4+4處理器本身無法被解決的硬體問題，也就是不可能啟動CPU Migration模式或是HMP模式。
----------------------------------------
個人積分：94分
文章編號：44001046
個人積分：125分
文章編號：44001093
個人積分：229分
文章編號：44002689
個人積分：5分
文章編號：44003170
繼續關注吧
It's still possible to run the chip asymmetrically in a 1x A15 3x A7 fashion
(or even the full 8 cores) but it would have to use the old-fashioned way of doing things, meaning you flush the L2 cache to RAM and then back to another core.
This still has the problem that HMP would have had because the scheduler is too dumb for it
and it would require most logic of the HMP patches. The point of core migration was that the hardware could do the context switch via the CCI in a very fast and efficient manner,
but that's not usable now. Anyway I doubt anybody, even me, would bother with this.
the road is a dead-end. We focus on other things now.
簡單說, 不是完全不可能, 是目前有困難, 還在尋找其他解決途徑
如果真是完全不可能,那也不會有第一句話,關於這個我沒有想要替big.LITTLE辯什麼
只是認為 AndreiLux 還沒有放棄 大家別一昧只想"把話給說死" 或自己下了"結論"這樣
http://forum.xda-developers.com/showpost.php?p=41834744&postcount=195
至於有人拿出三星曾說他們能夠支援三種架構之說,認為三星這是公開在說謊騙人
AndreiLux 也有跳出來解釋如下(開頭第一句很清楚,並沒有人或誰在說謊)
Nobody is lying per se.
That Samsung LSI slide leaked around last Christmas and is something the public shouldn't have seen. That's how it was supposed to work and how it was designed, but the chip is broken.
LSI have been mum about the workings of the chip short of a single diagram on a YouTube
marketing video displaying a migration model, and the mobile division never mentioned
the Octa beyond a single line in the technical spreadsheets.
The ARM slides have nothing to do with it.
Their own TC2 chip works as advertised with no issues.
AndreiLux看到有人不知道該買9505還是9500,他的看法是:
To the people considering 9505 or 9500:
Both phones are still equal in power consumption despite all of this,
and I subjectively think the 9500 is still more power efficient than the 9505
during frugal use. It's ****ty (in my view) for gaming versus what could have been,
but you're still far from the chip being useless. Shìt happens.
基本上兩隻手機的省耗電程度差不多,但我個人主觀上認為9500比9505更有效能
但9500目前尚無法解決chip問題,這是比較糟糕的問題
9500就是台灣引進來的國際版4+4核.9505就是高通cpu那隻
個人積分：470分
文章編號：44007351
個人積分：125分
文章編號：44011706
，
個人積分：53分
文章編號：44016802
個人積分：125分
文章編號：44021327
