Samsung Exynos 5250 - production starting in Q2 2012

  • Thread starter Deleted member 13524
  • Start date
Being a new generation of Mali architecture and being clocked modestly higher than the previous generation's 440 MHz implementation should privilege it enough to impress against the competition of late 2012.
 
Nuker said:
Well, it should be a good deal faster than the MP400 in GS3, even if 5x is stretching it. At 500 MHz the t604 is 68 Gflops vs ~16 Gflops for the 440 MHz MP400. I would hope that it is more than 2x as fast on average.
Click to expand...

It should be and not only because of increase fragment shader performance but also a quite high difference in geometry performance. If you'd count the VS lanes in a Mali400 as SPs you'll probably end up at 4, while on anything T6xx (all of them having USC ALUs) it's more like 64 and beyond.
 
Ailuros said:
It should be and not only because of increase fragment shader performance but also a quite high difference in geometry performance. If you'd count the VS lanes in a Mali400 as SPs you'll probably end up at 4, while on anything T6xx (all of them having USC ALUs) it's more like 64 and beyond.
Click to expand...

Pack it in...your getting me excited! :)
 
Laurent06 said:
I guess we can trust ARM official page for that: OpenVG 1.1, OpenGL ES 1.1, 2.0, DirectX 11 and OpenCL 1.1.

Interestingly Samsung Exynos 5 Web pages and PDF don't say anything about DirectX.
Click to expand...

To quote Anand he states:

The Mali-T604 also brings expanded API support including DirectX 11 (feature level 9_3 though, not 11_0).
Click to expand...
I browsed through the different T6xx variants and while for T604 ARM stops at OGL_ES2.0, T624 f.e. is also listing OGL_ES3.0. I couldn't imagine that the 604 isn't OGL_ES3.0 or just DX9L3 (DX11 certified DX9), so it's more a call for ARM's marketing department to set the record straight.

***edit: on another note 5250 for Q4 12 or Q1 13? It seems that 28nm irrelevant of process variant and/or foundry are quite a headache for everyone.
 
I really don't think we will be seeing a mobile gpu with full dx 11 support..including tesselation..this year..very doubtfull.

Anands reasoning (or another site?) that geometry processing would vastly increase die size and power consumption let alone never be used seems quite reasonable..after all windows 8 rt is 9.3 minimum...the dx11 bit must be efficiency improvements.
 
Are there SW incompatibilities between Samsung HW because of the use of different GPU and CPU cores, sometimes within the same product lines?

There are criticisms about fragmentation among Android HW in general but Samsung seems to source different SOCs all the time.
 
seeingwhite said:
Regarding the whole LTE on chip topic, can you guys explain this diagram to me? On the bottom of the second page of this product information sheet, (http://www.samsung.com/global/business/semiconductor/minisite/Exynos/data/Exynos 5 DUAL.pdf) on Samsung's Exynos 5 website there is a diagram with an arrow going to an "LTE Modem". I am unclear how that works. Does it simply mean that the Exynos 5 works well with a separate LTE modem, or that it can be integrated on the SOC? There seems to be some confusion over this from commenters on the popular blogs, too. Thanks guys.
Click to expand...

Just in case anyone missed my question, any help on this? Thanks in advance.
 
That particular chip supports external cellular connectivity, so LTE isn't integrated in to the SoC.
 
Rys said:
That particular chip supports external cellular connectivity, so LTE isn't integrated in to the SoC.
Click to expand...

Thanks. So I guess my question is why wouldn't Samsung have integrated LTE for the power saving benefits like on Krait? Please bear with me, I'm not nearly as knowledgeable as you guys on this stuff.
 
Laurent06 said:
Perhaps because they don't have their own LTE IP?
Click to expand...

Samsung does make discrete LTE modems. Albeit not true multi-mode like the qcom ones.

Modem integration can cause quite a few hassles. Not the least of which is qualification and validation on top of heavier IP protection that requires encryption ROMs and thus, difficulty with chip bringup.

It adds significantly to the time-to-market of an SoC.
 
It seems from what can be seen as Exynos5 activity on the ChromiumOS gerrit that we'll be seeing a ChromeOS laptop using the chip; https://gerrit.chromium.org/gerrit/#/q/status:open+project:chromiumos/third_party/kernel,n,z
So my previous declaration of it being one of the next Nexus devices seems to be wrong, replaced by something weirder.

Samsung's own sources still point out to a device using the chip, but without any device configuration file it's just a guess what it actually is from all the devices defined in the machine file. My guess is that is still a tablet.
 
My guess is we are unlikely to see this chip before MWC. It will likely premiere in the next Galaxy smartphone and tablet for 2013.
 
The price certainly looks great. I hope one can remove Chrome OS and put some Linux on it :) Anway battery life looks too low to me.
 
You must log in or register to reply here.

Similar threads

F
Exynos 5450
2 3
Replies
43
Views
14K
Lazy8s
L
D
Creative ZMS-20 and ZMS-40
2 3 4
Replies
75
Views
24K
darkblu
D
M
Samsung Orion SoC - dual-core A9 + "5 times the 3D graphics performance"
16 17 18
Replies
358
Views
113K
Nebuchadnezzar
N
A
Holy Wall of Text: My impressions post Playstation 4 (PS4) unveil
2 3 4
Replies
70
Views
20K
(((interference)))
I
Back
Top