前天Tesla所宣布的新车将全部配备新的硬件以供未来自动驾驶使用
而其中的运算单元将会是NVIDIA's new Drive PX 2 AI
http://i.imgur.com/8Q79mxH.png
http://i.imgur.com/JaByPTQ.jpg
Drive PX 2这套系统其实是一个专门为车子所打造的超级电脑
关于这套系统的简单介绍可以看这里：
http://chinese.engadget.com/2016/01/05/nvidia-drive-px2/
http://www.nvidia.com.tw/object/drive-px-tw.html
这套系统里面有12 CPU cores，号称有着150台 MacBook Pro的运算能力
8万亿次浮点运算能力大概等于是6张Titan X显示卡
(题外话，Titan X这张显示卡在台湾预估价格会是4.5万台币上下，目前还没发售)
Volvo XC90是第一辆搭载这套系统的车型
当初是以100辆XC90搭载这套系统去做深度运算与学习
用在一个叫做"Drive me"的试用方案中
而现在Tesla将会把他标配在全车系全车型
Nvidia并没有透露是以多少价格提供给Tesla这套系统
但是在今年稍早的时候，Nvidia是以一套1.5万美元的价格提供给OEM厂商
写到这觉得根本超值
Tesla除了Drive PX 2这套系统外
另外的硬件还包括8个镜头，超音波传感器和雷达天线
只收你5000或8000美元
就连只有3.5万美元的Model 3也会搭载这套系统(不过如果想用的话就要多付5k or 8k)
这是赔钱在卖这套系统吧
Tesla为了打造自动驾驶技术真的是下了重本
=============================底下原文==============================
https://goo.gl/5ss4ke
We reported in exclusivity earlier this month that Tesla was going with
Nvidia hardware to power its imagine processing platform called ‘Tesla Vision
’, but we couldn’t pinpoint which product Tesla was going to use exactly.
While we discussed the possibility of using Nvidia’s new Drive PX2 AI
computing platform for self-driving cars, we also noted that the product is
fairly new and expensive to be included in all new Tesla cars coming off the
line.
We thought the theory was confirmed when Tesla CEO Elon Musk said this week
that the automaker ended up choosing the ‘Nvidia Titan GPU’, an
off-the-shelves but powerful GPU card, to power ‘Tesla Vision’, but as it
turns out, Musk misspoke and Nvidia confirmed that the “in-vehicle
supercomputer is powered by the NVIDIA DRIVE PX 2 AI computing platform.”
When talking about ‘Tesla Vision’ in a press call with journalists on
Wednesday, Musk said:
This is a Teslaeveloped neural net. Although it’s somewhat hardware
independent, it can be we can actually run this on Nvidia, AMD or Intel.
We did pick the Nvidia titan GPU as the main chip for the neural net. But it
was pretty tight call between particularly between AMD and Nvidia. But
ultimately we felt that Nvidia had the better hardware.
In a blog post today, Nvidia corrected the information (see in full below).
The company also announced that the DRIVE PX 2 is now in full production.
Both the Titan and the DRIVE PX 2 are using the Nvidia’s Pascal GPU
architecture, which might explain the confusion.
The Volvo XC90 was previously going to become the first vehicle to use the
platform with 100 units being deployed through the Swedish carmaker’s Drive
Me autonomous-car pilot program next year, but Tesla beat them to market with
the platform now going into each new Tesla.
Nvidia didn’t disclose the price of the Drive PX 2 platform, but it is
believed to be an expensive piece of equipment. While unlikely to be
representative of the price Tesla is paying for its production cars, Nvidia
was selling the system to OEMs for their development programs at $15,000 per
unit earlier this year.
It likely represents an important part of the cost of Tesla’s new hardware
suite, which also includes 8 cameras, ultrasonic sensors, and a radar
antenna. It’s impressive that Tesla is able to include the system in all
vehicles as a standard hardware and enable its features for $5,000 or $8,000
depending on the options.
Tesla says that the new ‘supercomputer’ powered by the Drive PX 2 platform
represents a 40x processing power increase over its previous system:
To make sense of all of this data, a new onboard computer with over 40 times
the computing power of the previous generation runs the new Tesla-developed
neural net for vision, sonar and radar processing software.
Nvidia’s blog post to confirm the computer powering ‘Tesla Vision’:
Tesla Motors has announced that all Tesla vehicles — Model S, Model X, and
the upcoming Model 3 — will now be equipped with an on-board “supercomputer
” that can provide full self-driving capability.
The computer delivers more than 40 times the processing power of the previous
system. It runs a Tesla-developed neural net for vision, sonar, and radar
processing.
This in-vehicle supercomputer is powered by the NVIDIA DRIVE PX 2 AI
computing platform.
NVIDIA DRIVE PX 2 is an end-to-end AI computing system that uses
groundbreaking approaches in deep learning to perceive and understand the car
’s surroundings.
Our deep learning platform is open and lets carmakers first train their own
deep neural networks on GPU supercomputers. Once loaded into the car, it
processes the networks at high speed to provide the real-time, accurate
response required for autonomous driving.