NVIDIA Kal-El Cortex A9 四核架构 SOC 及开发平台

楼上的老狼

什么时候上市？
上市价格多少？
WIN8什么时候发布？

这些才是我最关心的。其他的我只当看黑盒子。

梦游的猪

80mm^2的手机芯片，NV你别玩爹。

diamondM2

看上去很强

eiceman

Qualcomm的quad core居然是23*23封装的我没记错的话。dual cor尺寸从11*11到14*14的。很奇怪Tegra的PMIC是谁家的？

rickerlian

如果对比图少了t7200会好很多，我不是说数据不真实，不过这就是市场运作，nv牛必的地方

kyrome

意法－爱立信也公布了它们下一代SOCs Nova A9600，双核A15+POWERVR 6系，市场竞争激烈啊。
Semiconductor giant ST-Ericsson spilt the beans on the next generation of PowerVR graphics processing unit, the Series6, codenamed Rogue which is going to be used in the Nova A9600, its top end system on chip, which will sample at the end of 2011.

In a press release issued yesterday, ST-Ericsson says that the A9600 will bring a more than 20-fold improvement in graphics performance compared to the U8500, which uses a single core ARM-based Mali 400 GPU clocked at 400MHz.

This corresponds to the comments made the day before by David Harold, the director of PR at Imagination Technologies, who told us that the Series6 architecture would bring a 20x improvement compared to the Series5 SGX.

The Rogue GPU will deliver more than 210GFlops (no details as if single or double precision), deliver 350 million real polygons per second and more than five gigapixels per second visible fill rate, which translates into 13 gigapixels of effective fill rate.

This is because, unlike other rival technologies, PowerVR only processes pixels that will be displayed, leaving out hidden ones.

Rogue will be compatible with existing APIs and soon-to-come ones like the OpenGL ES codenamed Haiti. The Nova A9600, which is the first official SoC to come with Rogue, will be manufactured using a 28nm geometry.

Imagination Technologies did confirm that the performance comparisons are for the same power envelope which makes it more than likely that Rogue's figures are for multicore parts.

66666

回复 kyrome 的帖子

tegra3八月份出货，索爱这个明年这时候能看到实物就不错了

closeyou

66666 发表于 2011-2-18 16:52
回复 kyrome 的帖子

tegra3八月份出货，索爱这个明年这时候能看到实物就不错了

明年这个时候T40就出来了，搞不好4核A15 + kepler 核心

gk104

回复 closeyou 的帖子

You get it

Edison

T40 也只是 DX9.0C 而已。

Edison

使用新编译器后 C2D T7200 的测试结果出来了：
http://www.ilsistemista.net/inde ... core2-.html?start=3

Edison

http://blogs.nvidia.com/2011/02/ ... e-mobile-processor/

NVIDIA 的 Michael Rayfield 对外界认为的测试结果不公平做出回应：

@Bob We did not mean to be unfair. I ran the Kal-El on the latest compiler I had and pulled the Intel data from the Coremark web site. To be fair I also tested my 1.0GHz part and not the 1.5GHz part. Thanks for point out my oversight, mjr

@SNUS & Mark These are architectures on the roadmap. That said, I believe that at any given generation I must have an offering that will be able to do any given task that the previous generation does but at a lower power. Kal-El will accomplish that, mjr

@Atlanta Big difference, I demonstrated a complete system. Chip, OS, applications and industrial design. QCOM demonstrated their ability to type a press release, just like TI did on OMAP5. Customers can’t build systems out of press releases (-: thanks mjr

66666

eoc 发表于 2011-2-22 02:10
硬解码方面，NV相比三星落后了。S5PC110已经可以硬解10REF FRAME以上的HIGH PROFILE H.264视频了。NV的Tegr ...

是落后了点，但main已经足以播放绝大部分网络视频了

PRAM

Edison 发表于 2011-2-16 23:42
高通的是 Cortex A-15，不过时间依然落后同等级的 NVIDIA Tegra 4 一年。

NVIDIA Tegra 2是CES2010发布的，可是上市远远晚于发布，Tegra 4 就算 CES 2012发布，上市也是2013了吧，落后1年好像不准确吧

kyrome

Tegra 2的视频解码果然悲剧了，High profile的H.264不能放，它的A9还不支持NEON,软解也没望了。
http://forum.xda-developers.com/showthread.php?t=963569

66666

回复 kyrome 的帖子

如果软解利用到双核，D1分辨率的HP还是能放。720P的HP等tegra3咯