Would make a decent open source alternative to a M1 Mac mini or just a nice workstation, even gaming console. Too bad the prices won't be anywhere near the Jetson Nano, so unlike the Nano or a PI it won't fit into my 'toy allowance' and I'd have argue an actual use case to buy one...
I'm not sure why the Jetson Nano is being compared to AGX Xavier. But the Jetson Xavier NX launched at $400, which is not ideal to those who want Jetson Nano prices, but a lot more affordable than the AGX Xavier.
The problem with Nano is that it's getting pretty ancient, by this point. It'd be great to have something in that price range, size, and power budget, but with newer ARM cores and modern tensor cores. Even Xavier NX still isn't a good fit for many projects and budgets.
Newer cores cost more to license and tend to be run on newer manufacturing process nodes, which are more expensive. Thus, they tend to mostly be used for parts which can be sold for more money. That's why Nvidia is just releasing a high-end SBC with new cores right now.
The exception to this is smartphones, but that comes from the exceptional scale there.
That's because it's intended at people doing commercial hardware development, not hobbyists, students, or the homebrew crowd.
Frequently, hardware development kits can cost in the tens of thousands of dollars. They're simply not meant for the casual tinkerer that Nvidia is targeting with these kits.
Huh? Carmel is Nvidia's own design, as with probably all the rest of the IP in those chips!
> newer manufacturing process nodes
Yeah, so cut down the size and make it cheaper. That would also help with power, size, and cooling. You wouldn't need such a wide memory interface, either.
Again, there are lots of robotics projects that would like to go beyond Nano but there's no viable option.
All ARM cores are licensed IP from ARM. Nvidia just designed "on top" of the existing ARM IP, which they pay for. As a company, you will pay more to license newer ARM IP (e.g. that from the ARMv8.2-A ISA Carmel is based on).
Yes, even building your own ARM core requires requires an ISA license, but it's unlikely the ARMv8 ISA licenses cost more than licensing the actual design of the A57 cores they have in Jetson Nano.
Plus, I think it doesn't matter if it's trivially more expensive. It's not a deal-breaker if the successor is *a little* more expensive. It just can't be > 3x.
Also, the fact that Nvidia is doing custom ARM chips in-house is also a HUGE cost factor, and the division working on this can probably only focus on one chip release at a time. Take for contrast RasPi, where many have wished for custom designs. RasPi just did a custom microcontroller, but the engineering effort/cost to produce a full scale general purpose SoC is an order of magnitude higher. Nvidia can only afford the luxury of full custom SoC designs on the back of their other divisions and the expectation that the edge AI vertical will expand greatly in the future (and wanting to establish their dominance for the sector early), but the team is surely focused on one design at a time still.
They obviously have a design cycle where they're going to keep updating Jetson. Since this Orin represents a new high end offering, it wouldn't be a surprise if their next release next year is a refresh on the low end.
> the fact that Nvidia is doing custom ARM chips in-house is also a HUGE cost factor, > and the division working on this can probably only focus on one chip release at a time.
Taking a chip design and chopping it into multiple sizes is what they do with their GPUs like almost every year.
Looking at the specs, it seems that Xavier NX already is a cut down version of full Xavier. I don't know what else they have to do to cut the cost and power, but both are still too much to be a proper Nano successor.
It is also notable that it looks like Nvidia is moving towards a less-custom design with the Orin, choosing to adopt Cortex-A78 cores from ARM instead of developing a custom core (and focusing their customization more on the GPU and NPU aspects).
I was a bit rusty on the history of this whole setup. Now that I look back on it I'm remembering that Nvidia's custom cores were originally motivated by wanting to use Project Denver as a means of creating cores which abstract over both ARM and x86, but they were unable to obtain the licensing from Intel. That's probably why they are now winding back to using Cortex IP.
most of nvidia's software is open source. And as far as open source, most of the world's open source software is designed and maintained by cloud companies like aws and google. their platforms still result in steep customer lock-in because each cloud builder has their own custom way of doing things. it's expensive for a customer to switch from one cloud to another or from cloud to on-site because of all the IT changes that are necessary (plus there are data egress fees).
The point is that Nvidia is quite open source. but just like the cloud builders that doesn't prevent them from building a platform that allows them to profit from r&d investment. At this point nvidia surely invests more money in software r&d than hardware r&d. it's greedy to expect a company to spend billions of dollars developing functionality for its products only to turn around and make its products commodities. it might as well give away the verilog code for its chips too.
Quick note is that Microsoft is by far the largest open source contributor.
They do have a large cloud service, but most of their open source is unrelated (e.g. the entire .NET ecosystem, Visual Studio Code, PowerShell, and contributions to MySQL and Linux).
Not their drivers or CUDA. Sure, the stuff around it, but they keep their crown jewels locked up tight.
> their platforms still result in steep customer lock-in
If Nvidia open sourced their drivers & API stack like AMD and Intel do, then we could have a community OpenCL implementation atop the bare hardware/drivers, rather than having to layer it atop CUDA.
> it's greedy to expect a company to spend billions of dollars developing functionality for > its products only to turn around and make its products commodities.
All of Nvidia's peers oupensource their drivers and API stacks, and they're hardly going out of business. We just want Nvidia to be a good Linux citizen, not a... um... what do you call it when an organism only takes from a host without giving back? Oh, that's right: a parasite.
And this is the price they pay for their sociopathic tendencies:
I don't like that Nvidia are the worst corporate citizen that is a major player in the open source world. Still, one could argue that their competitors are only better precisely because that offers them a competitive differentiation from Nvidia.
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.
19 Comments
Back to Article
abufrejoval - Tuesday, November 9, 2021 - link
Would make a decent open source alternative to a M1 Mac mini or just a nice workstation, even gaming console. Too bad the prices won't be anywhere near the Jetson Nano, so unlike the Nano or a PI it won't fit into my 'toy allowance' and I'd have argue an actual use case to buy one...Alas, it is really tempting!
nandnandnand - Tuesday, November 9, 2021 - link
I'm not sure why the Jetson Nano is being compared to AGX Xavier. But the Jetson Xavier NX launched at $400, which is not ideal to those who want Jetson Nano prices, but a lot more affordable than the AGX Xavier.mode_13h - Tuesday, November 9, 2021 - link
The problem with Nano is that it's getting pretty ancient, by this point. It'd be great to have something in that price range, size, and power budget, but with newer ARM cores and modern tensor cores. Even Xavier NX still isn't a good fit for many projects and budgets.bondr - Tuesday, November 9, 2021 - link
Newer cores cost more to license and tend to be run on newer manufacturing process nodes, which are more expensive. Thus, they tend to mostly be used for parts which can be sold for more money. That's why Nvidia is just releasing a high-end SBC with new cores right now.The exception to this is smartphones, but that comes from the exceptional scale there.
bondr - Tuesday, November 9, 2021 - link
A good example of this: the Snapdragon 888 developer board costs nearly double what some Snapdragon 888 phones cost.mode_13h - Wednesday, November 10, 2021 - link
That's because it's intended at people doing commercial hardware development, not hobbyists, students, or the homebrew crowd.Frequently, hardware development kits can cost in the tens of thousands of dollars. They're simply not meant for the casual tinkerer that Nvidia is targeting with these kits.
mode_13h - Wednesday, November 10, 2021 - link
> Newer cores cost more to licenseHuh? Carmel is Nvidia's own design, as with probably all the rest of the IP in those chips!
> newer manufacturing process nodes
Yeah, so cut down the size and make it cheaper. That would also help with power, size, and cooling. You wouldn't need such a wide memory interface, either.
Again, there are lots of robotics projects that would like to go beyond Nano but there's no viable option.
bondr - Thursday, November 11, 2021 - link
All ARM cores are licensed IP from ARM. Nvidia just designed "on top" of the existing ARM IP, which they pay for. As a company, you will pay more to license newer ARM IP (e.g. that from the ARMv8.2-A ISA Carmel is based on).mode_13h - Friday, November 12, 2021 - link
> All ARM cores are licensed IP from ARM.Huh? Do you even know that Carmel is Nvidia's own clean-sheet design?
https://en.wikipedia.org/wiki/Project_Denver
Yes, even building your own ARM core requires requires an ISA license, but it's unlikely the ARMv8 ISA licenses cost more than licensing the actual design of the A57 cores they have in Jetson Nano.
Plus, I think it doesn't matter if it's trivially more expensive. It's not a deal-breaker if the successor is *a little* more expensive. It just can't be > 3x.
bondr - Thursday, November 11, 2021 - link
Also, the fact that Nvidia is doing custom ARM chips in-house is also a HUGE cost factor, and the division working on this can probably only focus on one chip release at a time. Take for contrast RasPi, where many have wished for custom designs. RasPi just did a custom microcontroller, but the engineering effort/cost to produce a full scale general purpose SoC is an order of magnitude higher. Nvidia can only afford the luxury of full custom SoC designs on the back of their other divisions and the expectation that the edge AI vertical will expand greatly in the future (and wanting to establish their dominance for the sector early), but the team is surely focused on one design at a time still.They obviously have a design cycle where they're going to keep updating Jetson. Since this Orin represents a new high end offering, it wouldn't be a surprise if their next release next year is a refresh on the low end.
mode_13h - Friday, November 12, 2021 - link
> the fact that Nvidia is doing custom ARM chips in-house is also a HUGE cost factor,> and the division working on this can probably only focus on one chip release at a time.
Taking a chip design and chopping it into multiple sizes is what they do with their GPUs like almost every year.
Looking at the specs, it seems that Xavier NX already is a cut down version of full Xavier. I don't know what else they have to do to cut the cost and power, but both are still too much to be a proper Nano successor.
bondr - Thursday, November 11, 2021 - link
It is also notable that it looks like Nvidia is moving towards a less-custom design with the Orin, choosing to adopt Cortex-A78 cores from ARM instead of developing a custom core (and focusing their customization more on the GPU and NPU aspects).bondr - Thursday, November 11, 2021 - link
I was a bit rusty on the history of this whole setup. Now that I look back on it I'm remembering that Nvidia's custom cores were originally motivated by wanting to use Project Denver as a means of creating cores which abstract over both ARM and x86, but they were unable to obtain the licensing from Intel. That's probably why they are now winding back to using Cortex IP.kgardas - Tuesday, November 9, 2021 - link
This is NVidia, please do not confuse that with "open-source", it's quite the contrary unfortunately.Yojimbo - Tuesday, November 9, 2021 - link
most of nvidia's software is open source. And as far as open source, most of the world's open source software is designed and maintained by cloud companies like aws and google. their platforms still result in steep customer lock-in because each cloud builder has their own custom way of doing things. it's expensive for a customer to switch from one cloud to another or from cloud to on-site because of all the IT changes that are necessary (plus there are data egress fees).The point is that Nvidia is quite open source. but just like the cloud builders that doesn't prevent them from building a platform that allows them to profit from r&d investment. At this point nvidia surely invests more money in software r&d than hardware r&d. it's greedy to expect a company to spend billions of dollars developing functionality for its products only to turn around and make its products commodities. it might as well give away the verilog code for its chips too.
Sivar - Tuesday, November 9, 2021 - link
Quick note is that Microsoft is by far the largest open source contributor.They do have a large cloud service, but most of their open source is unrelated (e.g. the entire .NET ecosystem, Visual Studio Code, PowerShell, and contributions to MySQL and Linux).
mode_13h - Tuesday, November 9, 2021 - link
> most of nvidia's software is open source.Not their drivers or CUDA. Sure, the stuff around it, but they keep their crown jewels locked up tight.
> their platforms still result in steep customer lock-in
If Nvidia open sourced their drivers & API stack like AMD and Intel do, then we could have a community OpenCL implementation atop the bare hardware/drivers, rather than having to layer it atop CUDA.
> it's greedy to expect a company to spend billions of dollars developing functionality for
> its products only to turn around and make its products commodities.
All of Nvidia's peers oupensource their drivers and API stacks, and they're hardly going out of business. We just want Nvidia to be a good Linux citizen, not a... um... what do you call it when an organism only takes from a host without giving back? Oh, that's right: a parasite.
And this is the price they pay for their sociopathic tendencies:
https://www.phoronix.com/scan.php?page=news_item&a...
bondr - Tuesday, November 9, 2021 - link
I don't like that Nvidia are the worst corporate citizen that is a major player in the open source world. Still, one could argue that their competitors are only better precisely because that offers them a competitive differentiation from Nvidia.mode_13h - Wednesday, November 10, 2021 - link
> one could argue that their competitors are only better> precisely because that offers them a competitive differentiation
By itself, that's not reason enough to do it. It's an added bonus, though.