Some of them do, but then they won't be the ones paying for it. Without literal buy-in from consumers and investors, it isn't worth the financial risk and car makers have to be really careful in balancing features and cost.
Dev boards cost thousands or tens of thousands because they come with direct vendor support. the volume modules will be a lot cheaper. Take Drive PX2 for example: ~$15k for a devkit, but the volume units shipping in Tesla's Model S/X/3 are a fraction of that price.
If you think the Drive PX Pegasus is expensive, just consider the cost of the cameras, lidar, etc. But then consider the market for this hardware. How much does a truck driver make per year? An uber driver? Now all that hardware seems downright cheap.
Exactly. With automation the price is about replacing squishy meat-bags, not about what the costs of similar silicon are. When a sentient breeder costs $30-60K/year (not including benefits, time off, hour labor restrictions, etc) and a chip and sensor suite costs a mere $20-50K lifetime, then it becomes a no-brainer decision for fleet vehicles to justify the costs. Everything gets covered int he first year, and then everything after that is just savings. That is big business for chip and sensor makers, and big savings for fleet operators, which is why the push for this tech is so extremely strong. It has nothing to do with the convenience of getting a nice 20-30 minute nap on our way to and from work. In fact, I would be very surprised if we see wide-spread level-5 deployment for a while yet. This is specifically going to be a fleet and luxury vehicle tech for the next 10-15 years, and will trickle down to the rest of us mere mortals over time.
You also have to account for the fact that people can only work finite shifts and require rest. An automated vehicle can operate 24/7 without taking breaks, short of refueling and for maintenance or repairs.
You could potentially get 2-3x the work from a single vehicle operating around the clock.
In the beginning I'm sure there will be an increase in lawsuits, before the precedents are set, as some people try to take advantage of any situation for financial gain. But, the regulators will look at the situation analytically, because they already do that professionally, and the court precedents will eventually fall in line with that analysis. Then assuming the technology is good, in the long run the amount of money spent on lawsuits, both pay outs and general legal costs, will be lower than it is now. That's because these autonomous vehicles will only be successful if they are safer than human drivers.
Its a little bit interesting how quiet they've turned about post Volta stuff - have to imagine that the big post volta compute GPUs will come as soon as they're remotely practical in a technical sense so it won't be so far off.
Presumably its because of the quite large disconnect developing between their consumer & compute lines.
Yeah, NVIDIA seems to have recently stopped pushing their architecture roadmap and has started pushing a roadmap for various platforms, most notably automotive platforms.
Well, since they have such a dominant position in their other markets it makes sense that they don't need to, or even want to, sell the future. On the other hand, self-driving vehicles have little to no market so far, and NVIDIA is trying to attract customers to their platform now for a future market, so it makes sense for them to be selling the future.
I spy with my little eye, an array of discrete memory chips around the notional 'post-Volta' cores on the SXM2 cards rather than integral HBM as on V100.
Good catch. The Drive PX 2 also does not use the GP100, which is the Pascal-generation data center GPU that uses HBM 2. The power budget for the Drive PX Pegasus is twice that of the Drive PX 2, which makes it seem like they'll be using perhaps a Gx104-grade, or maybe even a Gx102-grade, GPU this time around.
One would assume that the discrete GPUs used in Pegasus have Tensor Cores or some evolution or replacement of them. So the GPU not being the big data center iron implies that NVIDIA will be bringing Tensor Core-functionality to at least some GPU other than the Gx100 part in the post-Volta generation.
"One would assume that the discrete GPUs used in Pegasus have Tensor Cores or some evolution or replacement of them. So the GPU not being the big data center iron implies that NVIDIA will be bringing Tensor Core-functionality to at least some GPU other than the Gx100 part in the post-Volta generation."
Unless, of course, NVIDIA puts an NVDLA on the package with the discrete GPU.
Good, but it's not all TOPS/TFLOPS. Firstly It is at 500W TDP, you need a separate battery to power this thing. Level 5 Automation is not all TFLOPS, it's the Algorithms. Nvidia is poor there (you can guess who has mastered the algorithms and the associated HW and why a premium is paid for it). Yeah they are mixing and matching their Pascals/Voltas/Tegras to get TOPS/TFLOPS
forgot to complete, Tesla Cars come with 1kWh battery packs, 1000Watts used for 1 Hour continuously. So if this Drive PX- Pegasus at 500W is used for 1 hour it consumes half the battery pack, for doing the same thing that other chips can do smartly. Hmm... I am surprised at the ignorance of the Wall St. analysts (in particular Vivek Arya) and Jim Cramer, they should just stick to what they are good at fudging the Revenues and Growth estimates and putting the estimated EPS.
Hmm. I think you need to check your numbers. Tesla Cars don't come with 1 kWh battery packs, they come with about 75 kWh batteries. Also, consider that 500 W is the max TDP. We don't know the average power usage. The self-driving computer would be using 500 W while it's driving, probably not while it's idling. A Tesla can only drive about 5(?) hours before using all its juice. In that amount of time the self-driving computer will have used at most 2500 Wh or about 3.3% of the battery, while the rest of the car will have consumed the remaining 96.7% of the battery.
Also consider that, from what I can find, on a hot day a car A/C pulls well over 500 W (I've seen claims of 1.5 kW). If the power can be afford for A/C surely it can be afforded for something as transformative as self-driving.
Perhaps more importantly, you made the tacit assumption that the automobile must be electric. If the power draw of a self-driving system proves to be too much for an electric car, which do you think is likely to be dropped first by a fleet manager, self-driving ability or electric drive train? I think the economics demands the manager choose the self-driving car.
Finally, I'm not sure how you can judge the current status of the algorithms of the various players developing self-driving car systems. Why do you think NVIDIA is poor? Why do you think your mystery company is so good? (Who is it, by the way?) What's the evidence? Besides, NVIDIA isn't primarily trying to develop their own self-driving networks, anyway. They are trying to develop the platform (hardware and software) that other companies will use to develop their own self-driving networks.
60-100KWh. But the computer is running from low voltage, the lead acid battery. So the unit must be shut off when the car is off unless the DC-DC convert is running all the time, which is very inefficient. So, I wonder how many seconds it takes for the self driving system to boot up (or more likely resume from hibernate)?
According to reports I've seen that cite someone who opened his Tesla and took out the Drive PX 2 module, Tesla is using a configuration with one SoC and one discrete GPU, which is half what the 250 W full Drive PX 2 has. So Tesla's version perhaps has a 125 W TDP. So it's another 375 W they must scrounge, but it's still a good point.
It's a huge chip though. I've wondered what they'll do with the SoCs for their Shield line and for future Nintendo products since their SoC announcements have all been geared towards autonomous vehicles. Maybe they are working on something that they haven't announced, yet. Maybe we'll see something at this coming CES.
With 500w TDP I wonder how loud the fans for this will be inside the dashboard! On Tesla the PX2 is above the glovebox. And when it gets dusty... a warning message to service the unit? Failsafe I suppose will be a 2nd unit?
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
31 Comments
Back to Article
jjj - Tuesday, October 10, 2017 - link
Yeah this is nonsense, that hardware is not fit for high volume production vehicles, the costs are way too high. This is still mostly just a dev kit.Qwertilot - Tuesday, October 10, 2017 - link
The costs for a fully automonous vehicle will be very high at this point! Given the potential gains though.....shabby - Tuesday, October 10, 2017 - link
By the time level 5 cars will be out this will be obsolete and dirt cheap.A5 - Tuesday, October 10, 2017 - link
Right, but they have to start development when it is expensive and cutting edge or else we'd be waiting until 2035.shabby - Tuesday, October 10, 2017 - link
Auto manufacturers have money, don't worry.nathanddrews - Tuesday, October 10, 2017 - link
Some of them do, but then they won't be the ones paying for it. Without literal buy-in from consumers and investors, it isn't worth the financial risk and car makers have to be really careful in balancing features and cost.shabby - Tuesday, October 10, 2017 - link
I think being left behind is a bigger financial risk then some dev kits, whoever has level 5 cars out first will reap all the benefits.edzieba - Tuesday, October 10, 2017 - link
Dev boards cost thousands or tens of thousands because they come with direct vendor support. the volume modules will be a lot cheaper. Take Drive PX2 for example: ~$15k for a devkit, but the volume units shipping in Tesla's Model S/X/3 are a fraction of that price.Yojimbo - Tuesday, October 10, 2017 - link
If you think the Drive PX Pegasus is expensive, just consider the cost of the cameras, lidar, etc. But then consider the market for this hardware. How much does a truck driver make per year? An uber driver? Now all that hardware seems downright cheap.CaedenV - Tuesday, October 10, 2017 - link
Exactly. With automation the price is about replacing squishy meat-bags, not about what the costs of similar silicon are. When a sentient breeder costs $30-60K/year (not including benefits, time off, hour labor restrictions, etc) and a chip and sensor suite costs a mere $20-50K lifetime, then it becomes a no-brainer decision for fleet vehicles to justify the costs. Everything gets covered int he first year, and then everything after that is just savings.That is big business for chip and sensor makers, and big savings for fleet operators, which is why the push for this tech is so extremely strong. It has nothing to do with the convenience of getting a nice 20-30 minute nap on our way to and from work. In fact, I would be very surprised if we see wide-spread level-5 deployment for a while yet. This is specifically going to be a fleet and luxury vehicle tech for the next 10-15 years, and will trickle down to the rest of us mere mortals over time.
XabanakFanatik - Tuesday, October 10, 2017 - link
You also have to account for the fact that people can only work finite shifts and require rest. An automated vehicle can operate 24/7 without taking breaks, short of refueling and for maintenance or repairs.You could potentially get 2-3x the work from a single vehicle operating around the clock.
jwcalla - Tuesday, October 10, 2017 - link
It'll be interesting to see how much they'll have to pay out in lawsuits each year.Yojimbo - Wednesday, October 11, 2017 - link
In the beginning I'm sure there will be an increase in lawsuits, before the precedents are set, as some people try to take advantage of any situation for financial gain. But, the regulators will look at the situation analytically, because they already do that professionally, and the court precedents will eventually fall in line with that analysis. Then assuming the technology is good, in the long run the amount of money spent on lawsuits, both pay outs and general legal costs, will be lower than it is now. That's because these autonomous vehicles will only be successful if they are safer than human drivers.Qwertilot - Tuesday, October 10, 2017 - link
Its a little bit interesting how quiet they've turned about post Volta stuff - have to imagine that the big post volta compute GPUs will come as soon as they're remotely practical in a technical sense so it won't be so far off.Presumably its because of the quite large disconnect developing between their consumer & compute lines.
Yojimbo - Tuesday, October 10, 2017 - link
Yeah, NVIDIA seems to have recently stopped pushing their architecture roadmap and has started pushing a roadmap for various platforms, most notably automotive platforms.Well, since they have such a dominant position in their other markets it makes sense that they don't need to, or even want to, sell the future. On the other hand, self-driving vehicles have little to no market so far, and NVIDIA is trying to attract customers to their platform now for a future market, so it makes sense for them to be selling the future.
edzieba - Tuesday, October 10, 2017 - link
I spy with my little eye, an array of discrete memory chips around the notional 'post-Volta' cores on the SXM2 cards rather than integral HBM as on V100.BurntMyBacon - Tuesday, October 10, 2017 - link
Good catch. GDDR6 perhaps?I have to wonder if a silicon interposer is durable enough to survive the shock and vibe stresses in a automotive vehicle.
thesenate - Tuesday, October 10, 2017 - link
There are only six of them, which suggests that the GPUs are likely Gx106 (192-bit wide interface)Yojimbo - Tuesday, October 10, 2017 - link
Good catch. The Drive PX 2 also does not use the GP100, which is the Pascal-generation data center GPU that uses HBM 2. The power budget for the Drive PX Pegasus is twice that of the Drive PX 2, which makes it seem like they'll be using perhaps a Gx104-grade, or maybe even a Gx102-grade, GPU this time around.One would assume that the discrete GPUs used in Pegasus have Tensor Cores or some evolution or replacement of them. So the GPU not being the big data center iron implies that NVIDIA will be bringing Tensor Core-functionality to at least some GPU other than the Gx100 part in the post-Volta generation.
Yojimbo - Tuesday, October 10, 2017 - link
"One would assume that the discrete GPUs used in Pegasus have Tensor Cores or some evolution or replacement of them. So the GPU not being the big data center iron implies that NVIDIA will be bringing Tensor Core-functionality to at least some GPU other than the Gx100 part in the post-Volta generation."Unless, of course, NVIDIA puts an NVDLA on the package with the discrete GPU.
sunloveca - Tuesday, October 10, 2017 - link
Good, but it's not all TOPS/TFLOPS. Firstly It is at 500W TDP, you need a separate battery to power this thing. Level 5 Automation is not all TFLOPS, it's the Algorithms. Nvidia is poor there (you can guess who has mastered the algorithms and the associated HW and why a premium is paid for it). Yeah they are mixing and matching their Pascals/Voltas/Tegras to get TOPS/TFLOPSsunloveca - Tuesday, October 10, 2017 - link
forgot to complete, Tesla Cars come with 1kWh battery packs, 1000Watts used for 1 Hour continuously. So if this Drive PX- Pegasus at 500W is used for 1 hour it consumes half the battery pack, for doing the same thing that other chips can do smartly. Hmm... I am surprised at the ignorance of the Wall St. analysts (in particular Vivek Arya) and Jim Cramer, they should just stick to what they are good at fudging the Revenues and Growth estimates and putting the estimated EPS.BLee - Tuesday, October 10, 2017 - link
Tesla S and X have 75-100 kilowatt/hour battery packs, not 1 kilowatt/hourYojimbo - Tuesday, October 10, 2017 - link
Hmm. I think you need to check your numbers. Tesla Cars don't come with 1 kWh battery packs, they come with about 75 kWh batteries. Also, consider that 500 W is the max TDP. We don't know the average power usage. The self-driving computer would be using 500 W while it's driving, probably not while it's idling. A Tesla can only drive about 5(?) hours before using all its juice. In that amount of time the self-driving computer will have used at most 2500 Wh or about 3.3% of the battery, while the rest of the car will have consumed the remaining 96.7% of the battery.Also consider that, from what I can find, on a hot day a car A/C pulls well over 500 W (I've seen claims of 1.5 kW). If the power can be afford for A/C surely it can be afforded for something as transformative as self-driving.
Perhaps more importantly, you made the tacit assumption that the automobile must be electric. If the power draw of a self-driving system proves to be too much for an electric car, which do you think is likely to be dropped first by a fleet manager, self-driving ability or electric drive train? I think the economics demands the manager choose the self-driving car.
Finally, I'm not sure how you can judge the current status of the algorithms of the various players developing self-driving car systems. Why do you think NVIDIA is poor? Why do you think your mystery company is so good? (Who is it, by the way?) What's the evidence? Besides, NVIDIA isn't primarily trying to develop their own self-driving networks, anyway. They are trying to develop the platform (hardware and software) that other companies will use to develop their own self-driving networks.
danwat1234 - Friday, October 26, 2018 - link
60-100KWh. But the computer is running from low voltage, the lead acid battery. So the unit must be shut off when the car is off unless the DC-DC convert is running all the time, which is very inefficient.So, I wonder how many seconds it takes for the self driving system to boot up (or more likely resume from hibernate)?
edzieba - Wednesday, October 11, 2017 - link
Tesla already ship the Drive PX2 with a 250W TDP in all their vehicles. Scrounging an extra 250W is not too difficult.'The algorithm' is exactly what Nvidia are during off at GTC. They are demonstrating exposed capabilities based on their own NN training.
Yojimbo - Wednesday, October 11, 2017 - link
According to reports I've seen that cite someone who opened his Tesla and took out the Drive PX 2 module, Tesla is using a configuration with one SoC and one discrete GPU, which is half what the 250 W full Drive PX 2 has. So Tesla's version perhaps has a 125 W TDP. So it's another 375 W they must scrounge, but it's still a good point.syxbit - Wednesday, October 11, 2017 - link
I wish they would release a new Nvidia Shield TV with the DRIVE PX Xavier. It sounds like it would hold up against a PS4!Yojimbo - Wednesday, October 11, 2017 - link
It's a huge chip though. I've wondered what they'll do with the SoCs for their Shield line and for future Nintendo products since their SoC announcements have all been geared towards autonomous vehicles. Maybe they are working on something that they haven't announced, yet. Maybe we'll see something at this coming CES.chjingl - Tuesday, February 27, 2018 - link
<a href="http://www.goleroapp.com/adidas-yeezy-boost-750-24... yeezy boost 950 homme pas cher</a>Translate this page
<a href="http://www.goleroapp.com/adidas-yeezy-boost-950-95... nmd r1 homme pas cher</a>
Translate this page
danwat1234 - Friday, October 26, 2018 - link
With 500w TDP I wonder how loud the fans for this will be inside the dashboard! On Tesla the PX2 is above the glovebox. And when it gets dusty... a warning message to service the unit? Failsafe I suppose will be a 2nd unit?