Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Jetson AGX Xavier

nvidia.com

Post reply on HN
Print view View original

71–80 of 95 posts

Re: Jetson AGX Xavier

#71

Post by jerryyu »

Just built a gesture controlled robot[1] with the Xavier board.

We were able to run OpenPose[2] at 27FPS, which we found was even faster than running it on K80 on AWS p2.xlarge. It was a pain to install caffe and all the dependencies on an ARM processor, but it worked out eventually.

We were able to train and run Tensorflow 2 models quickly also. Felt like using an actual GPU at a fraction of the cost.

[1] https://www.youtube.com/watch?v=AF8zmTaa17s

[2] https://github.com/CMU-Perceptual-Computing-Lab/openpose

Re: Jetson AGX Xavier

#72

Post by mchusma »

The original posted title was more helpful. The Jetson AGX Xavier has been out for a couple of years, but it dropped in price from $999 to $699 and has double the ram now at 32GB.

Re: Jetson AGX Xavier

#73

Post by structural »

0x8BADF00D wrote: post #40
king_magic wrote: post #38

My biggest complaint with the Jetson line is it's all ARM. Look, I get it. But the developer experience is horrible. Building Docker containers for ARM devices is a pain. Hell, building anything for a Jetson can be a pain unless it's a pre-packaged NVIDIA thing - really not a fan of building things from source. Add on top of that NVIDIA's very low level documentation for pretty much any tooling they ship, coupled wit…

> Building Docker containers for ARM devices is a pain in the ass. It's not so bad, you just need a beefy ARM machine to build the containers in CI. It would be silly to build a Docker container on the Jetson itself. You would never use an embedded device for compiles and builds, why would you build Docker containers on one?

You don't even need to do this: qemu support for executing arm64 binaries is fairly good, so you can just run the builds on your beefy x86 server anyways.

Re: Jetson AGX Xavier

#74

Post by qubex »

BillinghamJ wrote: post #58
p1necone wrote: post #57

Earlier quoted context omitted.

> Comedy answer: iPad Pro I mean, the iPad Pro does have a relatively beefy processor. If only you could run arbitrary code on it.

A lot of instruction sets aren't there yet, but https://ish.app is doing a truly incredible job in this regard. Gives you a working Alpine Linux installation which you can download and install packages for normally, all within the bounds of the normal Apple sandbox, with decent enough performance. It doesn't have SSE or MMX yet, so eg Go and Node aren't usable at this point. But a shocking amount actually does work p…

I suggest you also check out UTM (Universal Turing Machine), an emulator for the iPad that you can build and that allows you to emulate many different architectures and tun OSes written for them (including ARM).

https://getutm.app

Re: Jetson AGX Xavier

#75

Post by fulafel »

structural wrote: post #73
0x8BADF00D wrote: post #40

Earlier quoted context omitted.

> Building Docker containers for ARM devices is a pain in the ass. It's not so bad, you just need a beefy ARM machine to build the containers in CI. It would be silly to build a Docker container on the Jetson itself. You would never use an embedded device for compiles and builds, why would you build Docker containers on one?

You don't even need to do this: qemu support for executing arm64 binaries is fairly good, so you can just run the builds on your beefy x86 server anyways.

What's the single thread performance difference of a fast x86 cpu running emulated ARM code vs a fast ARM server or an AWS ARM instance?

Re: Jetson AGX Xavier

#76

Post by fxtentacle »

I wonder how to train for those. The biggest one has 32GB of RAM and needs a frozen inference graph converted to TensorRT. So one would need a GPU with 32GB of RAM in addition to this to be able to train the network. AFAIK, Nvidia doesn't sell anything with that much RAM.

Re: Jetson AGX Xavier

#77

Post by panny »

linarism wrote: post #44
0x8BADF00D wrote: post #40

Earlier quoted context omitted.

> Building Docker containers for ARM devices is a pain in the ass. It's not so bad, you just need a beefy ARM machine to build the containers in CI. It would be silly to build a Docker container on the Jetson itself. You would never use an embedded device for compiles and builds, why would you build Docker containers on one?

Genuinely curious, what is an example of a beefy ARM machine?

Amazon Graviton2 instances are faster (and cheaper) than x86_64 machines in the same class.

https://blog.treasuredata.com/blog/2020/03/27/high-performan...

Re: Jetson AGX Xavier

#78

Post by BillinghamJ »

BillinghamJ wrote: post #58
p1necone wrote: post #57

Earlier quoted context omitted.

> Comedy answer: iPad Pro I mean, the iPad Pro does have a relatively beefy processor. If only you could run arbitrary code on it.

A lot of instruction sets aren't there yet, but https://ish.app is doing a truly incredible job in this regard. Gives you a working Alpine Linux installation which you can download and install packages for normally, all within the bounds of the normal Apple sandbox, with decent enough performance. It doesn't have SSE or MMX yet, so eg Go and Node aren't usable at this point. But a shocking amount actually does work p…

Actually looks like MMX was just released, so Go is now running. It can't build yet though.

Re: Jetson AGX Xavier

#79

Post by potiuper »

fluffything wrote: post #4
weinzierl wrote: post #2

They seem to offer a cheaper 8 GB model too but unfortunately I see no price for it. I'm curious how much it'll be because, as much as I'd like to toy around with this, the $699 is a little to much for just experimentation. EDIT: The 8GB Module seems to be $679 here[1]. This makes the $699 or the 32 GB Developer Kit seem like a steal. Still, too expensive for play, I guess I'll stick with my Jetson Nanos for a while.…

There is also the Jetson Nanokit which costs ~120 EUR.

Maxwell does not have unified memory -> custom code compared to latest generation along with performance disadvantages.

Re: Jetson AGX Xavier

#80

Post by fluffything »

king_magic wrote: post #38

My biggest complaint with the Jetson line is it's all ARM. Look, I get it. But the developer experience is horrible. Building Docker containers for ARM devices is a pain. Hell, building anything for a Jetson can be a pain unless it's a pre-packaged NVIDIA thing - really not a fan of building things from source. Add on top of that NVIDIA's very low level documentation for pretty much any tooling they ship, coupled wit…

> Building Docker containers for ARM devices is a pain.

I do this every day from a Linux x64 host using qemu-user. What problems are you hitting ?

> Second biggest complaint is deploying Jetsons in production environments. > > Third biggest complaint is having to flash Jetsons manually.

I don't think these two use cases are the goal of the Jetsons. Feel like more the goal of the EGX devices, which can be programmed, updated, etc. fully remotely.

Post reply on HN