Benchmarks Of Many ARM Boards From The Raspberry Pi To NVIDIA Jetson TX2

[jrch2k8]

Can someone ask to bridgman if there are plan in AMD for a product in this segment? i mean a very low clocked Zen/ARM custom core + few polairs/vega cores SoC bit bellow 100$in a rpi(ish) format or with a micro motherboard will murder everything on this market specially since it will be fully supported out of the box.(specially since Qualcomm/Intel and nVidia are extremely expensive for this market)

I'm really tired of broken ARM boards with half working undebugable blobs, wink eye to AMD

[bridgman]

Can't comment, sorry.

[dungeon]

Compared this with my 3 years old Athlon 5350, todays Debian Sid blah, blah:

http://openbenchmarking.org/result/1...RI-1703199RI22

Clearly winning 7/10 tests to TX2 or 9/10 against TX1 and on remaining 3 or 1 quite close

[Zajec]

Is there some rack mountable board on the photo? Which one is it?

[NotMine999]

Can someone ask to bridgman if there are plan in AMD for a product in this segment? i mean a very low clocked Zen/ARM custom core + few polairs/vega cores SoC bit bellow 100$in a rpi(ish) format or with a micro motherboard will murder everything on this market specially since it will be fully supported out of the box.(specially since Qualcomm/Intel and nVidia are extremely expensive for this market)

I'm really tired of broken ARM boards with half working undebugable blobs, wink eye to AMD

What? And waste what person-power hours and precious capital dollars AMD may still have on "high volume, low margin" devices like consumer ARM devices what may generate a low ROI?

Where is the market for "a very low clocked Zen/ARM custom core + few polairs/vega cores SoC"? That sounds so much like a niche market to me. Then there is the development time to make, support, and market a "Franken-CPU" like that and whose only competition might be the NVIDIA products in this review.

I would rather see AMD focus on getting Zen and it's server variants out in the market in a strong & stable way that has some "staying power", and then plow the proceeds back into strengthening the company's R&D, marketing, and support assets. There is such a thing as spreading a company's assets too thin by getting into too many "distantly related" product lines.

As for the assorted ARM devices in this review that are still stuck in Linux 3.x kernel history, other than proprietary video functions, could the problem also be a lack of developer interest (Linux kernel development work, applications development work, etc.) in those devices? It's fairly clear to me that the vendors of most of those devices, unlike RPi & NVIDIA, do not have the resources to "push" their products in the marketplace. I think the facts are clear that RaspberryPi has made a big splash in the market by finding a valid and underserved market segment (computing education using "open" tools), and then garnered lots of "mindshare" from developers and the community in general as people saw many possibilities in the device. That is a tough position to compete against.

NVIDIA has "some deep pockets" so it can support it's Jetson family. NVIDIA's GPU assets are valuable and can be leveraged into making Jetson an "interesting" niche compute product.

[Michael]

Is there some rack mountable board on the photo? Which one is it?

Just a 1U micro/pico ATX that can accomodate two systems is where I run my Jetsons

[jrch2k8]

What? And waste what person-power hours and precious capital dollars AMD may still have on "high volume, low margin" devices like consumer ARM devices what may generate a low ROI?

Where is the market for "a very low clocked Zen/ARM custom core + few polairs/vega cores SoC"? That sounds so much like a niche market to me. Then there is the development time to make, support, and market a "Franken-CPU" like that and whose only competition might be the NVIDIA products in this review.

I would rather see AMD focus on getting Zen and it's server variants out in the market in a strong & stable way that has some "staying power", and then plow the proceeds back into strengthening the company's R&D, marketing, and support assets. There is such a thing as spreading a company's assets too thin by getting into too many "distantly related" product lines.

As for the assorted ARM devices in this review that are still stuck in Linux 3.x kernel history, other than proprietary video functions, could the problem also be a lack of developer interest (Linux kernel development work, applications development work, etc.) in those devices? It's fairly clear to me that the vendors of most of those devices, unlike RPi & NVIDIA, do not have the resources to "push" their products in the marketplace. I think the facts are clear that RaspberryPi has made a big splash in the market by finding a valid and underserved market segment (computing education using "open" tools), and then garnered lots of "mindshare" from developers and the community in general as people saw many possibilities in the device. That is a tough position to compete against.

NVIDIA has "some deep pockets" so it can support it's Jetson family. NVIDIA's GPU assets are valuable and can be leveraged into making Jetson an "interesting" niche compute product.

that is just the thing, i agree here but AMD already have products for this and it would not be a franken CPU either since it designed to scale from very low power to servers and GCN is already used on embedded(that for some reason are not available easily to buy).

IoT goes from cell phones, routers, industrial to rpi like boards and it uses pretty much the same SoC, it just changes the delivery format(the board itself) and as someone that works with this products and know many people on the industrial low power sector, i can tell you this WE HATE ARM TO THEIR BONES and i mean hate like "wow we are surprised nobody have gone to qualcomm with a machine gun and go crazy" hate. I can tell you ARM is the most unsupported shitty piece of hardware junk you can get your hands on(but is the only thing we have).

If today you decide to create an embedded device for market release in Q1 2018, you will spend prolly 3 or 4 weeks on C/C++ doing the actual code of the product and the rest of the year until 3 hours before release, you will be fighting the SoC everyday, 10h a day, you will refactor your OS at least 7 times, spend 6 months debugging(to find out is driver bugs that won't ever get fixed), 3 months begging your SoC provider for a fix that will never come, at least 3 meetings in this timeframe will end up being you wanting to quit and ipads/laptops flying in the room, until 1 month before release management settle and let you chop half the product features to bypass the miriad of driver bugs you encountered and finally release a product you won't ever want to touch with a 18m pole to update it again just to move to the next nightmare for 2019 release.

Intel and nVidia are IoT developers wet dream but sadly their offers are so out of market that management cannot afford to use them due to costs and here is where AMD can find a very interesting market and gain developer support to go for the mobile market on android later on (be it AArch64 or x86)

[Death Knight]

Better to test Orange PI PC2 which uses H5 CPU using A53 core.

[Michael]

Better to test Orange PI PC2 which uses H5 CPU using A53 core.

Sure, if I had the PC2....

[mitcoes]

Atoms X5 and x7 and perhaps the 7700k should be used as reference in this tests. The 7700k is being used as "100" in some benchmarks as it seems is very popular and well known.