x*****u
发帖数: 3419 | 1 http://thefutureofthings.com/pod/10222/nvidia-unveils-fermi-class-quadro-gpus.html
NVIDIA Unveils Fermi-Class Quadro GPUs
Friday, September 03, 2010 - Anuradha Menon
Home >> Personal Column >> Computer Technology
NVIDIA has revealed its new range of Fermi-based Quadro GPUs that the
company says deliver performance
that is up to five times faster for 3D applications and up to eight times
faster for computational simulation.
The Quadro Plex 7000 Array is a complete system solution capable of
d |
|
g**********2
发帖数: 4881 | 2 have a couple of UA GPUs @ 420 each
PM |
|
g**********2
发帖数: 4881 | 3 have a couple of UA GPUs @ 420 each
PM |
|
g**********2
发帖数: 4881 | 4 have more UA GPUs and AA eVIPs |
|
P**s
发帖数: 170 | 5 出售 UA upgrades GPUs
$400 each |
|
g**********2
发帖数: 4881 | 6 need more UA GPUs @ 320 1/2015
I have a few UA GPU 1/2014 sells for $150 |
|
g**********2
发帖数: 4881 | 7 need more UA GPUs @ 320 1/2015
I have a few UA GPU 1/2014 sells for $150 |
|
|
c******3
发帖数: 23 | 9 Need: 4 to 6 UA 升舱券 (GPUs)
Have: $250 for each upgrade |
|
r***0
发帖数: 406 | 10 http://www.wsj.com/articles/new-chips-propel-machine-learning-1
Computer users have long relied on Nvidia Corp.’s technology to paint
virtual worlds on the screen as they gunned down videogame enemies. Now some
researchers are betting it can also help save lives—of real people.
Massachusetts General Hospital recently established a center in Boston that
plans to use Nvidia chips to help an artificial-intelligence system spot
anomalies on CT scans and other medical images, jobs now carried out by
... 阅读全帖 |
|
w********2
发帖数: 16371 | 11 看着超强，是可以支持4个4k的display？
NVIDIA Quadro K5000 Graphics Card for Mac Pro Debuts
IBC 2012 -- Mac professionals will benefit from dramatically improved
graphics performance and productivity with today's announcement of the
NVIDIA® Quadro® K5000 for Mac Pro systems.
Based on NVIDIA KeplerTM architecture -- the world's fastest, most efficient
GPU design -- the Quadro K5000 for Mac is the most powerful professional-
class GPU ever for the Macintosh, delivering unprecedented visualization and
c... 阅读全帖 |
|
r*****d
发帖数: 922 | 12 "Nvidia officially announced and released the retail version of the
previously OEM only GeForce 210(GT218 GPU) and GeForce GT 220 (GT216 GPU) on
October 12, 2009. Nvidia officially announced and released the GeForce GT
240 (GT215 GPU) on November 17, 2009. The new 40nm GPUs feature the new
PureVideo HD VP4 decoder hardware in them, the older GeForce 8 and 9 GPUs
only have PureVideo HD VP2 or VP3(G98). They also support Compute Capability
1.2, whereas older GeForce 8 and 9 GPUs only supported Com... 阅读全帖 |
|
m*****n
发帖数: 3575 | 13 https://www.quora.com/What-hardware-does-AlphaGo-run-on-Is-it-customized-
hardware-for-best-performance
AlphaGo uses a distributed system of 1920 CPUs and 280 GPUs. AlphaGo uses
Nvidia GPUs for the system. This is comparable to the TU Dresden's Taurus
supercomputer that uses 256 GPUs. In their research paper on Nature, they
talk about how AlphaGo can be run on a single computer, but would have only
a 23% win rate against the distributed system with multiple cores and GPUs.
So, you can view the s... 阅读全帖 |
|
l******h
发帖数: 2 | 14 Highly reputational company with very competitive compensation for all
positions.
Please send in your resume and position/positions you like to apply to my
email address below.
h*******[email protected]
All resumes will be deliver to hiring manager directly. Act fast!
Thanks!
Silicon Engineering Group
Sr. Physical Design Timing Engineer
Timing (STA) Manager
Senior Physical Design Engineer
CAD Manager - Front-End Design and Verification
Sr. CAD Engineer - Place & Route / Physical Design Engineer
Sr. CA... 阅读全帖 |
|
l******h
发帖数: 2 | 15 Highly reputational company with very competitive compensation for all
positions.
Please send in your resume and position/positions you like to apply to my
email address below.
h*******[email protected]
All resumes will be deliver to hiring manager directly. Act fast!
Thanks!
Silicon Engineering Group
Sr. Physical Design Timing Engineer
Timing (STA) Manager
Senior Physical Design Engineer
CAD Manager - Front-End Design and Verification
Sr. CAD Engineer - Place & Route / Physical Design Engineer
Sr. CA... 阅读全帖 |
|
m*****n
发帖数: 1631 | 16 搬一段网文过来，说不定你已经看到过了。
Many companies, perhaps most, opt to access GPUs in the cloud instead of
buying and deploying the hardware directly. AI startups alone are a big
market; over 2300 investors have now funded over 1700 startups, according to
data compiled by Angel List, and the vast majority of these cash-conscious
firms use cloud based NVIDIA GPUs to develop their innovative products and
services. The exception is the world’s largest datacenters, aka the “Super
Seven” (Alibaba, Amazon, Baidu, G... 阅读全帖 |
|
b*********f
发帖数: 1585 | 17 Nvidia is announcing two products today, two Kepler based HPC / GPGPU cards
- K10 and K20.
NVIDIA Tesla K10
Tesla K10 dedicated to seismic analysis where most valuable resource is
bandwidth. It has 3x single precision of today’s fermi tesla and 1.8x the
memory bandwidth.
NVIDIA is preparing two Tesla GPUs, one is Tesla K10, based on dual-GK104
chips, which is to be devoted to high efficient computing in oil and gas
exploration and defense industry. Card is based on dual-GK104 GPUs and has a
memo... 阅读全帖 |
|
s*******h
发帖数: 1361 | 18 With the Pascal line of GPUs such as GTX 1080, you have the option to choose
which sync technology to use for each game
V-sync,
Adaptive-sync,
Fast-sync,
G-sync (monitor specific)
Understanding those are highly recommended for any gamers with Nvidia GPUs,
and are even more important for people gaming on lower-refresh-rate displays
(such as TVs).
It sounds like you may be best suited with Fast-sync with no tearing and
minimum input lag, although Fast-sync means full-load GPUs at all time which
me... 阅读全帖 |
|
h**********9
发帖数: 3252 | 19 a little good news today:
http://finance.yahoo.com/news/amd-demonstrates-full-support-dir
DirectX12 works with GCN hardware
SUNNYVALE, CA--(Marketwired - Mar 20, 2014) - Today, AMD (NYSE: AMD)
announced support for Microsoft® and its revamped graphics application
programming interface, DirectX® 12, a new "console-like" version of the
graphics API that has inspired PC gaming for nearly two decades. During the
Microsoft®-sponsored panel, DirectX: Evolving Microsoft's Graphics
Platfo... 阅读全帖 |
|
t*******i
发帖数: 4960 | 20 实在是忍不住。 ：）
https://news.ycombinator.com/item?id=11251463
edit: some actual estimates. Deep Blue had 11.38 GFLOPS[1]. According to the
paper in Nature, distributed AlphaGo used 1202 CPUs and 176 GPUs. A single
modern GPU can do between 100 and 2000 double precision GFLOPS[2]. So from
GPUs alone AlphaGo had access to 4-5 orders of magnitude more computing
power than Deep Blue did. |
|
l*****l
发帖数: 4170 | 21 Summary
No. At least not yet.
Within hours of CNBC’s initial reporting, a GlobalFoundries spokesperson
clarified the rumor.
This article will discuss implications for Tesla, AMD, and Nvidia should the
CNBC report be true.
Background
On September 20, 2017, CNBC reported that Tesla (NASDAQ:TSLA) is working
with Advanced Micro Devices (NASDAQ:AMD) to develop its own artificial
intelligence chip for self-driving cars. As well, the report mentioned that
Tesla intends to build on top of AMD’s intellec... 阅读全帖 |
|
G**Y
发帖数: 33224 | 22 https://www.anandtech.com/show/12017/intel-to-develop-discrete-gpus-hires-
raja-koduri-as-chief-architect
On Monday, Intel announced that it had penned a deal with AMD to have the
latter provide a discrete GPU to be integrated onto a future Intel SoC. On
Tuesday, AMD announced that their chief GPU architect, Raja Koduri, was
leaving the company. Now today the saga continues, as Intel is announcing
that they have hired Raja Koduri to serve as their own GPU chief architect.
And Raja's task will no... 阅读全帖 |
|
t********e
发帖数: 34 | 23 Manuscript ID TCAD-2015-0250 entitled "An Accurate GPU Performance Model for
Effective Control Flow Divergence Optimization" with Prof. Liang as contact
author has been submitted to the Transactions on Computer-Aided Design of
Integrated Circuits and Systems.
The abstract appears at the end of this letter, along with the names of the
authors.
.....
MANUSCRIPT DETAILS
TITLE: An Accurate GPU Performance Model for Effective Control Flow
Divergence Optimization
AUTHORS: Liang, Yun; Satria, Muhammad;... 阅读全帖 |
|
t*******m
发帖数: 36 | 24 Technology Review's annual list of 35 Innovators Under 35
http://www.technologyreview.com/tr35/profile.aspx?trid=1084
High-speed: This image was generated in a fraction of the time required by
traditional graphics software.
Credit: Courtesy of Kun Zhou
Thanks to Kun Zhou, computer games will become more realistic and animated
movies will reach cinemas faster. The Zhejiang University computer science
professor has released software capable of rendering movie-quality scenes
using graphics chips of... 阅读全帖 |
|
w********1
发帖数: 3492 | 25 Wed, 11 Jul 2012 07:33:38 PDT
With Apple having seeded the golden master build of OS X Mountain Lion to
developers earlier this week, the company has locked in which Macs will
support the forthcoming version of the operating system. While the machine
requirements have been known for some time, the seeding of the final public
release is a good time to remind users which machines will support Mountain
Lion.
Your Mac must be one of the following models:
- iMac (Mid 2007 or newer)
- MacBook (Late 2... 阅读全帖 |
|
r******y
发帖数: 3838 | 26 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
Den... 阅读全帖 |
|
t**t
发帖数: 27760 | 27 1.4TB/s
The Titan — not to be confused with Nvidia’s graphics card of the same nam
e — is loaded with 18,688 AMD Opteron 6274 16-core CPUs, and 18,688 Nvidia
Tesla K20X GPUs. If you’re counting, this makes Titan a 299,008-core comput
er. It sports 710TB of memory, with a split of 598TB dedicated to the CPUs a
nd 112TB to the GPUs. Before this new goal of upgrading Titan’s storage, it
had 10 petabytes of storage, running at 240GB/sec. The rig can perform arou
nd 27 petaflops, and the entire unit ... 阅读全帖 |
|
F***Q
发帖数: 6599 | 28
really depends on your budget, and needs for CPUs and GPUs.
google "supermicro motherboard" if you want something to have 8 PCI-E slots
to host GPUs or Xeon phi for some high throughput tasks (of course, you need
to have the software/algorithm to use them). but be prepared, those
workstations can be noisy. |
|
n***t
发帖数: 8357 | 29 “
Modern motherboards don't have "integrated" graphics, per se. The current
paradigm is that some CPUs have graphics processing units (GPUs) built into
the CPU (AMD calls these APUs, rather than CPUs). In order to utilize this
built in GPU, you need a motherboard that has the necessary circuitry and
connectors to enable the GPU to connect to a display.
In this case, this motherboard does have this circuitry, but you must
install an APU in order to use it. The new Ryzen CPUs that just came on the... 阅读全帖 |
|
i****a
发帖数: 36252 | 30 http://www.tomshardware.com/news/ethereum-effect-graphics-card-prices,34928.html
The Ethereum Effect: Graphics Card Price Watch
The recent resurgence of cryptocurrency and the growing popularity of
Ethereum has led to a massive shortage in the GPU market. Prices are
oscillating wildly, and dozens of graphics card models are sold out. In
short, the mining craze is wreaking havoc on the graphics card market. Below
, we’ve begun tracking pricing and availability for the volatile graphics
card marke... 阅读全帖 |
|
m*****n
发帖数: 1631 | 31 Our software does deep learning training fully synchronously with very low
communication overhead. As a result, when we scaled to a large cluster with
100s of NVIDAI GPUs, it yielded record image recognition accuracy of 33.8%
on 7.5M images from the ImageNet-22k dataset vs the previous best published
result of 29.8% by Microsoft. A 4% increase in accuracy is a big leap
forward; typical improvements in the past have been less than 1%. Our
innovative distributed deep learning (DDL) approach enab... 阅读全帖 |
|
|
|
z*******n
发帖数: 1034 | 34 November 14, 2014 7:00 AM
Dean Takahashi
The Department of Energy has awarded $425 million in federal funding to IBM,
Nvidia, and other companies who will build two giant supercomputers many
times more powerful than today’s most powerful machines.
Ernest Moniz, U.S. Secretary of Energy, announced Friday that the government
will fund two high-performance computing supercomputers as part of a drive
toward exascale computing, or a machine capable of one exaflop, or 10 to the
18th power floating poi... 阅读全帖 |
|
h******t
发帖数: 872 | 35 http://edition.cnn.com/2010/TECH/innovation/10/28/china.supercomputer.mashable/
(Mashable) -- Unveiled Wednesday at the Annual Meeting of National High
Performance Computing (HPC China 2010) in Beijing, Tianhe-1A is the world's
fastest supercomputer with a performance record of 2.507 petaflops, as
measured by the LINPACK benchmark.
Tianhe-1A was designed by the National University of Defense Technology (
NUDT) in China, and it is already fully operational.
To achieve the new performance record, ... 阅读全帖 |
|
g**1
发帖数: 10330 | 36 这是6月的排名。新的下周公布。
http://news.cnet.com/8301-13924_3-20020991-64.html
The new system would top another Chinese supercomputer also using Nvidia
chips called Nebulae, rated at 1.271 petaflops (one petaflop is one
thousand trillion operations per second). Both the Nebulae and Tianhe-1A
performance ratings are based on the Linpack benchmark, the most widely
used performance yardstick for supercomputers. Nebulae is currently
rated No. 2 in the world based on the Top500 June list. The Oak Ridge
system is... 阅读全帖 |
|
|
t**********8
发帖数: 1683 | 38 中国研制出世界最快计算机 运算能力比美快一倍 2013-06-04 00:45:23
2013年06月04日09:59 来源：TechWeb.com.cn
【TechWeb报道】6月4日消息，据国外媒体报道，科技网站Computerworld从一位上周在
华访问的美国学者处获悉，中国研制出了一台具有每秒54.9千万亿次浮点运算(
Petaflops)能力的超级计算机，比美国目前任何一台超级计算机的速度都快一倍。
据悉，中国这台最新的超级计算机名为“天河-2”，配置了3.2万个多核英特尔至
强Ivy Bridge处理器芯片，4.8万个英特尔至强Phi芯片。Phi芯片是基于英特尔MIC（多
集成内核）架构的协处理器。中国政府研发投入为大约2.9亿美元。
根据去年11月发布的超级计算机500强排行榜，美国最快的超级计算机名为“Cray
”，运行速度接近每秒18千万亿次浮点计算。这个排行榜将在今年6月中旬更新。
link address: http://www.computerworld.com/s/article/9239710/China_surpassing_U.S.... 阅读全帖 |
|
g**1
发帖数: 10330 | 39 http://www.top500.org/blog/lists/2013/11/press-release/
China’s Tianhe-2 Supercomputer Maintains Top Spot on 42nd TOP500 List
2013-11-18 08:29:48+00:00
MANNHEIM, Germany; BERKELEY, Calif.; and KNOXVILLE, Tenn.—Tianhe-2, a
supercomputer developed by China’s National University of Defense
Technology, retained its position as the world’s No. 1 system with a
performance of 33.86 petaflop/s (quadrillions of calculations per second) on
the Linpack benchmark, according to the 42nd edition of the twice-... 阅读全帖 |
|
f***y
发帖数: 4447 | 40 还发明新程序语言。这点比任何一个北美码公强千万倍。
SPAP (Same Program for All Processors): a new programming language for
heterogeneous many-core systems. It allows the same program to work
efficiently on all processors of a heterogeneous system and fully utilize
the heterogeneous processing power by automatically distributing
computations among different processors. The language currently supports x86
CPUs and CUDA GPUs. |
|
c******a
发帖数: 4400 | 41 machines can just add more GPUs and scale up.
human only has one brain
how is this fair? Human should have at least twice the time, or AlphaGo
should just use a serial machine |
|
x******g
发帖数: 33885 | 42 全自动化资料库
很多人都要失业了
Huawei takes on Oracle, IBM and Microsoft with new cloud-based database
management system powered by AI
Chinese technology giant Huawei, known for its smartphones and
telecommunications equipment, is making further inroads into the enterprise
IT market with a database product powered by machine learning.
The product will compete with popular database systems provided by IT’s old
-guard, including IBM, Oracle and Microsoft.
Huawei claims the system is the first to use machine lea... 阅读全帖 |
|
s*******1
发帖数: 16479 | 43 The Green Party of the United States (GPUS or Greens) is a green and
progressive political party in the United States.[6]
The party, which is the country's fourth-largest by membership, promotes
environmentalism, nonviolence, social justice, participatory grassroots
democracy, gender equality, LGBT rights, anti-war and anti-racism. On the
political spectrum the party is generally seen as left-wing, and in 2016
officially self-described as an "eco-socialist" party.[2]
看到progressive 这个label就厌恶 |
|
t*c
发帖数: 6929 | 44 据说要求recount理由是希拉里在密歇根某个郡
比应得选票数少了7%，非常可笑，怀疑有人
hack改数据，问题是他们如何知道希拉里应该
得多少票？根据poll？
: The Green Party of the United States (GPUS or Greens) is a green and
: progressive political party in the United States.[6]
: The party, which is the country's fourth-largest by membership,
promotes
: environmentalism, nonviolence, social justice, participatory
grassroots
: democracy, gender equality, LGBT rights, anti-war and anti-racism. On
the
: political spectrum the party is generall... 阅读全帖 |
|
发帖数: 1 | 45 The recount has created confusion about the relationship between the Green
and Democratic parties because the states chosen for the recount are only
states in which Hillary Clinton lost. There were close races in other states
such as New Hampshire and Minnesota where Clinton won, but which were not
part of the recount.
As a candidate, Dr. Stein has the right to call for a recount. However, we
urge the GPUS to distance itself from any appearance of support for either
Democrats or Republicans. We ... 阅读全帖 |
|
F***Q
发帖数: 6599 | 46
it's no where near the complexity of micro processors chips, GPUs, ccd
sensors, and look at where they are now.
also, why you need a laser in the first place? if you just measure distance,
ultrasound sensors are cheap and mature, much more robust for all weather
conditions. even you need 3d shape scanning capability, structure light is
not the only way to get it done. |
|
F***Q
发帖数: 6599 | 47
you still did not get my point - car sensor market is a much bigger market,
thus, it can create the scale that makes expensive, sophisticated technology
cheap and accessible - just like the PC market has made microprocessors,
GPUs affordable today, and mobile communication market has made mobile
sensors and devices ubiquitous.
you kept saying it needs higher accuracy, yes, I never disagreed with you, I
am just saying your current measure of cost is going to become invalid when
the market grows.... 阅读全帖 |
|
m***y
发帖数: 1239 | 48 I have 6 UA GPUs which will expire in 1/31/2017
$450 each, pls PM if interested. |
|
