r******y
发帖数: 3838 | 1 Pretty big news from NVIDAI today, my best bet is that NVIDIA is tired and
sick of Intel patent issues
preventing them from developing x86 capable hardware. Now that Intel and AMD
integrate graphics into
their processors NVIDIA will do it the other way around and integrate a
processor into its GPUs.
It has long been rumored that NVIDIA flirting with the the processor market
with some sort of x86
compatibility, many wondered how the firm would do this but with NVIDIA's
announcement of Project
Denver and Microsoft's confirmation that the next version of Windows will be
compatible with ARM the plan
is becoming a bit clearer.
Project Denver is the codename of NVIDIA's CPU+GPU combo, which is basically
a custom ARM Cortex-A15
processor that will be fully integrated on the same chip as NVIDIA's future
GeForce and Tesla GPUs.
NVIDIA announced today that it plans to build high-performance ARM®
based CPU cores, designed to
support future products ranging from personal computers and servers to
workstations and supercomputers.
Known under the internal codename "Project Denver," this initiative features
an NVIDIA® CPU running the
ARM instruction set, which will be fully integrated on the same chip as the
NVIDIA GPU.
This new processor stems from a strategic partnership, also announced today,
in which NVIDIA has
obtained rights to develop its own high performance CPU cores based on ARM's
future processor
architecture. In addition, NVIDIA licensed ARM's current Cortex™-A15
processor for its future-generation
Tegra® mobile processors.
"ARM is the fastest-growing CPU architecture in history," said Jen-Hsun
Huang, president and chief
executive officer of NVIDIA. "This marks the beginning of the Internet
Everywhere era, where every device
provides instant access to the Internet, using advanced CPU cores and rich
operating systems.
"ARM's pervasiveness and open business model make it the perfect
architecture for this new era. With
Project Denver, we are designing a high-performing ARM CPU core in
combination with our massively
parallel GPU cores to create a new class of processor," he said.
Warren East, ARM chief executive officer said, "NVIDIA is a key partner for
ARM and this announcement
shows the potential that partnership enables. With this architecture license
, NVIDIA will be at the forefront
of next generation SoC design, enabling the Internet Everywhere era to
become a reality."
NVIDIA Chief Scientist Bill Dally touts an ARM processor coupled with an
NVIDIA GPU as the computing
platform of the future. In a blog post he explains the ARM chip will run the
serial parts of applications and
provide compatibility while the GPU will take care of the parallel portions
of programs.
Oh and guess what ?: Rumors about ARM support in Windows 8 are true as
Microsoft announced at CES that
the next version of Windows will support SoC architectures, including ARM-
based systems from NVIDIA,
Qualcomm and Texas Instruments! This development will enable computer makers
to create very power
efficient Windows-based tablets and other devices, and could mean x86 may
finally be getting some
competition outside the mobile arena. "
http://www.guru3d.com/news/nvidia-project-denver/# | R*y
发帖数: 994 | 2 吹牛很厉害的公司, Tegra 2连ipad2都搞不定. | s****c
发帖数: 11300 | 3 我从一开始就不看好nv
搞个CUDA出来就忙着搞封闭了 连标准都不想跟人分享 现在OPENCL出来了
DirectCompute出来了 你看他纱布傻眼
其实悲哀的就是当时好多搞研究的跟风学了好长时间cuda。。。
还有物理特效，收购了physX以后就开始封闭，给游戏厂家塞钱搞特殊优化，The way完
全就是一个公开贿赂计划啊。本来支持cpu的引擎也给搞得只支持gpu，后面的路就愈走
愈窄。傻子都能想出来，市场又不是你一家的，还有那么大的主机平台，大厂的游戏怎
么可能只支持你一家。在这种小圈子里面搞封闭只能越高越差
【在 R*y 的大作中提到】
: 吹牛很厉害的公司, Tegra 2连ipad2都搞不定.
| b******t
发帖数: 965 | 4 opencl比cuda难写啊
【在 s****c 的大作中提到】
: 我从一开始就不看好nv
: 搞个CUDA出来就忙着搞封闭了 连标准都不想跟人分享 现在OPENCL出来了
: DirectCompute出来了 你看他纱布傻眼
: 其实悲哀的就是当时好多搞研究的跟风学了好长时间cuda。。。
: 还有物理特效，收购了physX以后就开始封闭，给游戏厂家塞钱搞特殊优化，The way完
: 全就是一个公开贿赂计划啊。本来支持cpu的引擎也给搞得只支持gpu，后面的路就愈走
: 愈窄。傻子都能想出来，市场又不是你一家的，还有那么大的主机平台，大厂的游戏怎
: 么可能只支持你一家。在这种小圈子里面搞封闭只能越高越差
| a***e
发帖数: 27968 | 5 关键是open,什么硬件都能跑
【在 b******t 的大作中提到】
: opencl比cuda难写啊
| l***h
发帖数: 392 | 6 其实差不多吧，难得地方是优化，关键是opencl的硬件支持太多太杂了，
优化难。不过现在好像好多了吧。
【在 b******t 的大作中提到】
: opencl比cuda难写啊
| l***h
发帖数: 392 | 7 跑得不快就没有意义了。呵呵
【在 a***e 的大作中提到】
: 关键是open,什么硬件都能跑
|
|
