Nvidia: Tesla 提高了自駕車製造商的門檻 - 汽車
By John
at 2019-04-26T08:47
at 2019-04-26T08:47
Table of Contents
來源:http://bit.ly/2DyEddv
Tesla Raises the Bar for Self-Driving Carmakers
In unveiling the specs of his new self-driving car computer at this week’s
Tesla Autonomy Day investor event, Elon Musk made several things very clear
to the world.
Tesla 在本周面向投資人的"Tesla Autonomy Day" 上發布了其新自駕車電腦的
規格。同時,Elon Musk 也在活動上向世界傳遞出了幾條非常清楚的訊息。
First, Tesla is raising the bar for all other carmakers.
首先,Tesla 正在提高所有其他汽車製造商的門檻。
Second, Tesla’s self-driving cars will be powered by a computer based on two
of its new AI chips, each equipped with a CPU, GPU, and deep-learning
accelerators. The computer delivers 144 trillion operations per second
(TOPS), enabling it to collect data from a range of surround cameras, radars
and ultrasonics and power deep neural network algorithms.
其次,Tesla 的自動駕駛車將由一台基於兩顆全新AI 晶片的電腦所驅動,每顆
晶片都配備了CPU、GPU 以及深度學習加速器。該電腦運算能力每秒可達到144
TOPS,這使其能夠從一系列的環繞鏡頭、雷達和超音波雷達中收集數據,同時驅
動深度神經網路算法。
Third, Tesla is working on a next-generation chip, which says 144 TOPS isn’t
enough.
第三,Tesla 正在研發下一代晶片,這表示144 TOPS 的運算能力是不夠的。
At NVIDIA, we have long believed in the vision Tesla reiterated: self-driving
cars require computers with extraordinary capabilities.
NVIDIA 長期以來一直相信Tesla 不斷重申的願景:自動駕駛車輛需要性能卓越
的電腦。
Which is exactly why we designed and built the NVIDIA Xavier SoC several
years ago. The Xavier processor features a programmable CPU, GPU and deep
learning accelerators, delivering 30 TOPs. We built a computer called DRIVE
AGX Pegasus based on a two chip solution, pairing Xavier with a powerful GPU
to deliver 160 TOPS, and then put two sets of them on the computer, to
deliver a total of 320 TOPS.
這也正是幾年前我們設計並製造NVIDIA Xavier SoC 晶片的初衷。NVIDIA Xavier
處理器具有可編程的CPU、GPU 以及深度學習加速器,可提供30 TOPS 的運算能
力。我們還打造了一個名為DRIVE AGX Pegasus 的電腦。DRIVE AGX Pegasus基
於雙晶片解決方案,一個Xavier 搭配一個強大的獨立GPU,可以提供160 TOPS的
運算能力,將兩組這樣的晶片裝載到一台電腦中,可實現總共320 TOPS 的運算
能力。
And as we announced a year ago, we’re not sitting still. Our next-generation
processor Orin is coming.
如同一年前所宣布的那樣,我們未曾止步。新一代處理器–Orin 即將到來。
That’s why NVIDIA is the standard Musk compares Tesla to—we’re the only
other company framing this problem in terms of trillions of operations per
second, or TOPS.
這也是為什麼Musk 將NVIDIA作為與Tesla 比較的參考基準 — 我們是唯一一間
除Tesla 之外提供每秒數兆次級運算(或稱TOPS)作為解決方案的公司。
But while we agree with him on the big picture—that this is a challenge that
can only be tackled with supercomputer-class systems—there are a few
inaccuracies in Tesla’s Autonomy Day presentation that we need to correct.
儘管我們同意他所描述的自動駕駛發展藍圖,即我們面臨著一個只能用超級電腦
級的系統來應對挑戰的未來,但我們依然需要對一些Tesla Autonomy Day 中不
準確的介紹進行更正。
It’s not useful to compare the performance of Tesla’s two-chip Full Self
Driving computer against NVIDIA’s single-chip driver assistance system. Tesla
’s two-chip FSD computer at 144 TOPs would compare against the NVIDIA DRIVE
AGX Pegasus computer which runs at 320 TOPS for AI perception, localization
and path planning.
拿Tesla 的雙晶片全自動駕駛電腦與NVIDIA 的單晶片駕駛輔助系統進行性能對
比是沒有意義的。運算能力達到144 TOPS 的Tesla 的雙晶片FSD 電腦應與能在
AI 感知、定位以及路徑規劃方面提供320 TOPS 的NVIDIA DRIVE AGX Pegasus
進行比較。
Additionally, while Xavier delivers 30 TOPS of processing, Tesla erroneously
stated that it delivers 21 TOPS. Moreover, a system with a single Xavier
processor is designed for assisted driving AutoPilot features, not full
self-driving. Self-driving, as Tesla asserts, requires a good deal more
compute.
此外,Xavier 擁有30 TOPS 的運算能力,但Tesla 錯誤地宣稱它只擁有21 TOPS
的處理性能。而且,使用單個Xavier 處理器的系統是針對輔助駕駛AutoPilot
的特點設計的,而不是為了全自動駕駛而設計。正如Tesla 所說,自動駕駛需要
更大量的計算。
Tesla, however, has the most important issue fully right: Self-driving cars—
which are key to new levels of safety, efficiency, and convenience—are the
future of the industry. And they require massive amounts of computing
performance.
然而,Tesla 在最重要問題上的看法是完全正確的:自動駕駛車輛是提高安全、
效率和便利性的關鍵所在,也是整個行業的未來。而做到這些需要大量的運算能
力。
Indeed Tesla sees this approach as so important to the industry’s future
that it’s building its future around it. This is the way forward. Every
other automaker will need to deliver this level of performance.
事實上,Tesla 認為強大的運算能力對自動駕駛行業的發展未來十分重要,這也
成為了Tesla 未來發展的核心。這是發展向前的方向。每個汽車製造商都應該提
供這種水平的性能。
There are only two places where you can get that AI computing horsepower:
NVIDIA and Tesla.
如果你想獲得強大的AI 計算性能,只有兩種選擇:NVIDIA和Tesla。
And only one of these is an open platform that’s available for the industry
to build on.
但兩者之中只有一個能夠提供可供整個行業使用的開放平台。
=============================================================================
這篇文章是Tesla 在發佈其FSD 電腦後沒幾個小時Nvidia 就公佈的文章,在捧
Tesla 的同時也不忘糾錯,最後順便還強調一下只有他們有在賣跟Tesla 同級的
自動駕駛電腦(不跟我們買你就自己開發吧 XD)。
從這篇文章大概就能看出大約需要怎麼樣的能力才足夠供給全自動駕駛車輛來做
運算。不過Nvidia 也還是省去了自己的缺點不說。首先是他們有320 TOPS 運算
能力的Pegasus 還在開發當中,可能至少還要1~2 年才能提供成品。其次就是功
耗太高,TDP 500W。而Tesla 在設計之初就將功耗考慮進去,目標是要做到小於
100W,最後的成果是72W。這就跟當初Google 在發展深度學習時放棄以GPU 為主,
自行研發TPU 一樣,能耗是一個很重要的關鍵,有興趣可以參考以下的文章:
僅需1/5成本:TPU是如何超越GPU,成為深度學習首選處理器的
http://bit.ly/2UWKF8L
Google 研發了一塊晶片,省下建資料中心的錢還推動機器學習的發展
http://bit.ly/2DAAXyd
同時Elon 也提到,全自動駕駛每英里的電耗是250W,若以平均時速30 km/h 來
計算,那大約是每小時要耗費約4.69度電,而若不用72W 的Tesla FSD 電腦改用
500W 的Pegasus,等於每小時要再額外花費約0.43度電,這相當於整體功耗多了
8.67%,關於功耗這問題就是Nvidia 沒有提的,他們還沒解決。
另外成本也是一個重點,Tesla 在設計之初就決定了要兼顧性能、功耗、與成本,
最後做出的成果也是性能比起以前Nvidia 提供的Drive PX 2 要好上一個數量級,
同時成本只有Drive PX 2 的80%。
╭────────────┬────┬────┬───╮
│ │晶片數量│運算性能│功耗 │
├────────────┼────┼────┼───┤
│Tesla FSD Computer │ 2 │144 TOPS│ 72 W│
│Drive PX 2(Tesla HW 2.5)│ 3 │ 12 TOPS│ 60 W│
│Drive PX Xavier │ 1 │ 30 TOPS│ 30 W│
│Drive PX Pegasus │ 4 │320 TOPS│ 500 W│
╰────────────┴────┴────┴───╯
Tesla FSD Computer,兩顆自研的SoC 晶片,功耗72W:
https://i.imgur.com/60khZxi.jpg
Drive PX 2,兩顆Parker SoC 晶片 + 兩顆輔助Pascal GPU,功耗250W:
https://i.imgur.com/aaZj5db.jpg
基於Drive PX 2 所訂製的Tesla HW 2.5,兩顆SoC 晶片 + 一顆輔助GPU,功耗60W:
https://i.imgur.com/4L5wnkN.png
Drive PX Xavier,單顆SoC 晶片,功耗30W:
https://i.imgur.com/oOhaAw0.jpg
Drive PX Pegasus,兩顆Xavier SoC 晶片 + 兩顆GPU,功耗500W:
https://i.imgur.com/sinVMOh.jpg
https://i.imgur.com/OXuzhcU.jpg
--
Elon Musk vs Mark Zuckerberg
https://youtu.be/a2GVxYfKSxA
中文字幕:
https://www.bilibili.com/video/av37804239/
--
Tesla Raises the Bar for Self-Driving Carmakers
In unveiling the specs of his new self-driving car computer at this week’s
Tesla Autonomy Day investor event, Elon Musk made several things very clear
to the world.
Tesla 在本周面向投資人的"Tesla Autonomy Day" 上發布了其新自駕車電腦的
規格。同時,Elon Musk 也在活動上向世界傳遞出了幾條非常清楚的訊息。
First, Tesla is raising the bar for all other carmakers.
首先,Tesla 正在提高所有其他汽車製造商的門檻。
Second, Tesla’s self-driving cars will be powered by a computer based on two
of its new AI chips, each equipped with a CPU, GPU, and deep-learning
accelerators. The computer delivers 144 trillion operations per second
(TOPS), enabling it to collect data from a range of surround cameras, radars
and ultrasonics and power deep neural network algorithms.
其次,Tesla 的自動駕駛車將由一台基於兩顆全新AI 晶片的電腦所驅動,每顆
晶片都配備了CPU、GPU 以及深度學習加速器。該電腦運算能力每秒可達到144
TOPS,這使其能夠從一系列的環繞鏡頭、雷達和超音波雷達中收集數據,同時驅
動深度神經網路算法。
Third, Tesla is working on a next-generation chip, which says 144 TOPS isn’t
enough.
第三,Tesla 正在研發下一代晶片,這表示144 TOPS 的運算能力是不夠的。
At NVIDIA, we have long believed in the vision Tesla reiterated: self-driving
cars require computers with extraordinary capabilities.
NVIDIA 長期以來一直相信Tesla 不斷重申的願景:自動駕駛車輛需要性能卓越
的電腦。
Which is exactly why we designed and built the NVIDIA Xavier SoC several
years ago. The Xavier processor features a programmable CPU, GPU and deep
learning accelerators, delivering 30 TOPs. We built a computer called DRIVE
AGX Pegasus based on a two chip solution, pairing Xavier with a powerful GPU
to deliver 160 TOPS, and then put two sets of them on the computer, to
deliver a total of 320 TOPS.
這也正是幾年前我們設計並製造NVIDIA Xavier SoC 晶片的初衷。NVIDIA Xavier
處理器具有可編程的CPU、GPU 以及深度學習加速器,可提供30 TOPS 的運算能
力。我們還打造了一個名為DRIVE AGX Pegasus 的電腦。DRIVE AGX Pegasus基
於雙晶片解決方案,一個Xavier 搭配一個強大的獨立GPU,可以提供160 TOPS的
運算能力,將兩組這樣的晶片裝載到一台電腦中,可實現總共320 TOPS 的運算
能力。
And as we announced a year ago, we’re not sitting still. Our next-generation
processor Orin is coming.
如同一年前所宣布的那樣,我們未曾止步。新一代處理器–Orin 即將到來。
That’s why NVIDIA is the standard Musk compares Tesla to—we’re the only
other company framing this problem in terms of trillions of operations per
second, or TOPS.
這也是為什麼Musk 將NVIDIA作為與Tesla 比較的參考基準 — 我們是唯一一間
除Tesla 之外提供每秒數兆次級運算(或稱TOPS)作為解決方案的公司。
But while we agree with him on the big picture—that this is a challenge that
can only be tackled with supercomputer-class systems—there are a few
inaccuracies in Tesla’s Autonomy Day presentation that we need to correct.
儘管我們同意他所描述的自動駕駛發展藍圖,即我們面臨著一個只能用超級電腦
級的系統來應對挑戰的未來,但我們依然需要對一些Tesla Autonomy Day 中不
準確的介紹進行更正。
It’s not useful to compare the performance of Tesla’s two-chip Full Self
Driving computer against NVIDIA’s single-chip driver assistance system. Tesla
’s two-chip FSD computer at 144 TOPs would compare against the NVIDIA DRIVE
AGX Pegasus computer which runs at 320 TOPS for AI perception, localization
and path planning.
拿Tesla 的雙晶片全自動駕駛電腦與NVIDIA 的單晶片駕駛輔助系統進行性能對
比是沒有意義的。運算能力達到144 TOPS 的Tesla 的雙晶片FSD 電腦應與能在
AI 感知、定位以及路徑規劃方面提供320 TOPS 的NVIDIA DRIVE AGX Pegasus
進行比較。
Additionally, while Xavier delivers 30 TOPS of processing, Tesla erroneously
stated that it delivers 21 TOPS. Moreover, a system with a single Xavier
processor is designed for assisted driving AutoPilot features, not full
self-driving. Self-driving, as Tesla asserts, requires a good deal more
compute.
此外,Xavier 擁有30 TOPS 的運算能力,但Tesla 錯誤地宣稱它只擁有21 TOPS
的處理性能。而且,使用單個Xavier 處理器的系統是針對輔助駕駛AutoPilot
的特點設計的,而不是為了全自動駕駛而設計。正如Tesla 所說,自動駕駛需要
更大量的計算。
Tesla, however, has the most important issue fully right: Self-driving cars—
which are key to new levels of safety, efficiency, and convenience—are the
future of the industry. And they require massive amounts of computing
performance.
然而,Tesla 在最重要問題上的看法是完全正確的:自動駕駛車輛是提高安全、
效率和便利性的關鍵所在,也是整個行業的未來。而做到這些需要大量的運算能
力。
Indeed Tesla sees this approach as so important to the industry’s future
that it’s building its future around it. This is the way forward. Every
other automaker will need to deliver this level of performance.
事實上,Tesla 認為強大的運算能力對自動駕駛行業的發展未來十分重要,這也
成為了Tesla 未來發展的核心。這是發展向前的方向。每個汽車製造商都應該提
供這種水平的性能。
There are only two places where you can get that AI computing horsepower:
NVIDIA and Tesla.
如果你想獲得強大的AI 計算性能,只有兩種選擇:NVIDIA和Tesla。
And only one of these is an open platform that’s available for the industry
to build on.
但兩者之中只有一個能夠提供可供整個行業使用的開放平台。
=============================================================================
這篇文章是Tesla 在發佈其FSD 電腦後沒幾個小時Nvidia 就公佈的文章,在捧
Tesla 的同時也不忘糾錯,最後順便還強調一下只有他們有在賣跟Tesla 同級的
自動駕駛電腦(不跟我們買你就自己開發吧 XD)。
從這篇文章大概就能看出大約需要怎麼樣的能力才足夠供給全自動駕駛車輛來做
運算。不過Nvidia 也還是省去了自己的缺點不說。首先是他們有320 TOPS 運算
能力的Pegasus 還在開發當中,可能至少還要1~2 年才能提供成品。其次就是功
耗太高,TDP 500W。而Tesla 在設計之初就將功耗考慮進去,目標是要做到小於
100W,最後的成果是72W。這就跟當初Google 在發展深度學習時放棄以GPU 為主,
自行研發TPU 一樣,能耗是一個很重要的關鍵,有興趣可以參考以下的文章:
僅需1/5成本:TPU是如何超越GPU,成為深度學習首選處理器的
http://bit.ly/2UWKF8L
Google 研發了一塊晶片,省下建資料中心的錢還推動機器學習的發展
http://bit.ly/2DAAXyd
同時Elon 也提到,全自動駕駛每英里的電耗是250W,若以平均時速30 km/h 來
計算,那大約是每小時要耗費約4.69度電,而若不用72W 的Tesla FSD 電腦改用
500W 的Pegasus,等於每小時要再額外花費約0.43度電,這相當於整體功耗多了
8.67%,關於功耗這問題就是Nvidia 沒有提的,他們還沒解決。
另外成本也是一個重點,Tesla 在設計之初就決定了要兼顧性能、功耗、與成本,
最後做出的成果也是性能比起以前Nvidia 提供的Drive PX 2 要好上一個數量級,
同時成本只有Drive PX 2 的80%。
╭────────────┬────┬────┬───╮
│ │晶片數量│運算性能│功耗 │
├────────────┼────┼────┼───┤
│Tesla FSD Computer │ 2 │144 TOPS│ 72 W│
│Drive PX 2(Tesla HW 2.5)│ 3 │ 12 TOPS│ 60 W│
│Drive PX Xavier │ 1 │ 30 TOPS│ 30 W│
│Drive PX Pegasus │ 4 │320 TOPS│ 500 W│
╰────────────┴────┴────┴───╯
Tesla FSD Computer,兩顆自研的SoC 晶片,功耗72W:
https://i.imgur.com/60khZxi.jpg
Drive PX 2,兩顆Parker SoC 晶片 + 兩顆輔助Pascal GPU,功耗250W:
https://i.imgur.com/aaZj5db.jpg
基於Drive PX 2 所訂製的Tesla HW 2.5,兩顆SoC 晶片 + 一顆輔助GPU,功耗60W:
https://i.imgur.com/4L5wnkN.png
Drive PX Xavier,單顆SoC 晶片,功耗30W:
https://i.imgur.com/oOhaAw0.jpg
Drive PX Pegasus,兩顆Xavier SoC 晶片 + 兩顆GPU,功耗500W:
https://i.imgur.com/sinVMOh.jpg
https://i.imgur.com/OXuzhcU.jpg
--
Elon Musk vs Mark Zuckerberg
https://youtu.be/a2GVxYfKSxA
中文字幕:
https://www.bilibili.com/video/av37804239/
--
Tags:
汽車
All Comments
By Elma
at 2019-04-27T08:07
at 2019-04-27T08:07
By Kelly
at 2019-04-29T10:34
at 2019-04-29T10:34
By Yedda
at 2019-04-29T18:49
at 2019-04-29T18:49
By Freda
at 2019-05-02T02:06
at 2019-05-02T02:06
By Hazel
at 2019-05-05T17:27
at 2019-05-05T17:27
By Franklin
at 2019-05-09T07:15
at 2019-05-09T07:15
By Damian
at 2019-05-12T00:56
at 2019-05-12T00:56
By Damian
at 2019-05-16T16:22
at 2019-05-16T16:22
By Barb Cronin
at 2019-05-21T03:58
at 2019-05-21T03:58
By Thomas
at 2019-05-22T11:38
at 2019-05-22T11:38
By Yuri
at 2019-05-24T02:37
at 2019-05-24T02:37
By Hedy
at 2019-05-28T22:54
at 2019-05-28T22:54
By Charlotte
at 2019-06-02T17:28
at 2019-06-02T17:28
By Hedwig
at 2019-06-04T01:37
at 2019-06-04T01:37
By Andrew
at 2019-06-05T09:33
at 2019-06-05T09:33
By Kama
at 2019-06-07T06:13
at 2019-06-07T06:13
By Ivy
at 2019-06-10T23:35
at 2019-06-10T23:35
By Madame
at 2019-06-14T14:56
at 2019-06-14T14:56
By Andrew
at 2019-06-17T13:11
at 2019-06-17T13:11
By George
at 2019-06-18T18:34
at 2019-06-18T18:34
By Genevieve
at 2019-06-19T16:02
at 2019-06-19T16:02
By Blanche
at 2019-06-20T09:34
at 2019-06-20T09:34
By Mary
at 2019-06-25T07:28
at 2019-06-25T07:28
By Victoria
at 2019-06-28T01:22
at 2019-06-28T01:22
By Blanche
at 2019-07-01T00:13
at 2019-07-01T00:13
By Victoria
at 2019-07-04T11:32
at 2019-07-04T11:32
By Jessica
at 2019-07-07T07:23
at 2019-07-07T07:23
By Daph Bay
at 2019-07-08T03:18
at 2019-07-08T03:18
By Odelette
at 2019-07-10T18:07
at 2019-07-10T18:07
By Tracy
at 2019-07-12T06:48
at 2019-07-12T06:48
By Ula
at 2019-07-14T06:45
at 2019-07-14T06:45
By Kyle
at 2019-07-18T04:26
at 2019-07-18T04:26
By Kumar
at 2019-07-22T23:06
at 2019-07-22T23:06
Related Posts
國道瞌睡
By Agatha
at 2019-04-26T08:27
at 2019-04-26T08:27
為什麼台灣自己類uber系統不普及
By Delia
at 2019-04-26T07:33
at 2019-04-26T07:33
【獨家】AIT致函關切Uber條款爭議 質疑
By Agnes
at 2019-04-26T07:08
at 2019-04-26T07:08
左手扮勞工右手搞中資!計程車大戰UBER
By Candice
at 2019-04-26T00:39
at 2019-04-26T00:39
林口坡為何不用爬坡檔?
By Odelette
at 2019-04-26T00:13
at 2019-04-26T00:13