Announcement

Collapse
No announcement yet.

AMD EPYC 9554 & EPYC 9654 Benchmarks - Outstanding Performance For Linux HPC/Servers

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • t.s.
    replied
    Originally posted by coder View Post
    1. Which interview?
    2. I doubt they'll go all the way to A76, much less A76 + A55. The issue is that Pi is still targeting a lower price bracket and will use a cheaper process node. My guess is 4x A75, as not only is the A76 bigger, but the A75 actually has more performance per mm2 (Source: https://www.anandtech.com/show/12785...7nm-powerhouse), therefore better performance/$.
    This interview: https://www.tomshardware.com/news/ra...es-next-gen-pi
    Yes, he didn't told what CPU they'll use. But my bet is still at A76, as we see that almost no SBC use A75. But yes, maybe they'll go A75 as they usually use older, bigger node.​

    Originally posted by coder View Post
    I think SBC makers probably view standardization as a threat -- at least the more premium ones. Sadly, the Raspberry Pi is a standard in itself, which is fine for tinkering and projects, but its port layout isn't ideal for something like a mini-desktop computer.

    Also, I'm not sure if anyone "owns" the standard PC form factors, in which case there might be licensing terms or costs.

    BTW, mini-STX is the other form factor I forgot to mention. It's similar to the 5x5 NUC form factor.

    Actually, the ODROID-N2's port layout isn't too bad. I have an aluminum case from KKSB (not the current one, but a previous revision), and all the ports are on the front or back. Currently, I have cables connected only to the back side, making it somewhat NUC-like.
    Well, it's just better business decisions, as it's more profitable that way. Not against it. When they see money in standardization, they'll go that route. As for RPi size, well, it's caused by no having a standards. So everyone just use what they think is cute/cool/cheaper.

    The PC form factor have no licensing AFAIK..

    I have a mini-STX, Asrock Deskmini X300. I think it's on the bigger side, but is perfect for socketable CPU. Something like mini business pc's like optiplex, elitedesk, or thinkcentre is perfect too. But ARM boards didn't have something like humongous fan, can be passive cooled. So I prefer 4x4, 4x5 or 4.6, as this kind of size's more flexible, we can use it for laptop too.

    Leave a comment:


  • coder
    replied
    Originally posted by t.s. View Post
    there'll be Raspberry Pi 5 too, according to Eben's interview. My guess: they'll use Cortex-A76 + A-55 too.
    1. Which interview?
    2. I doubt they'll go all the way to A76, much less A76 + A55. The issue is that Pi is still targeting a lower price bracket and will use a cheaper process node. My guess is 4x A75, as not only is the A76 bigger, but the A75 actually has more performance per mm2 (Source: https://www.anandtech.com/show/12785...7nm-powerhouse), therefore better performance/$.

    Originally posted by t.s. View Post
    Ditto for standard size. It can be nano-ITX, or whatever size (but not too big). If we have standards, then we can have case like x86. How nice if it came true.
    I think SBC makers probably view standardization as a threat -- at least the more premium ones. Sadly, the Raspberry Pi is a standard in itself, which is fine for tinkering and projects, but its port layout isn't ideal for something like a mini-desktop computer.

    Also, I'm not sure if anyone "owns" the standard PC form factors, in which case there might be licensing terms or costs.

    BTW, mini-STX is the other form factor I forgot to mention. It's similar to the 5x5 NUC form factor.

    Actually, the ODROID-N2's port layout isn't too bad. I have an aluminum case from KKSB (not the current one, but a previous revision), and all the ports are on the front or back. Currently, I have cables connected only to the back side, making it somewhat NUC-like.

    Leave a comment:


  • t.s.
    replied
    Originally posted by coder View Post
    Indeed. However, I'm in no hurry. I'm curious to see if HardKernel will release an ODROID based on the RK3588, or similar. Maybe they'll use their H-series form factor, since those have a bigger passive heatsink and can accommodate a M.2 SSD.
    Me too! But still no news from HK for RK3588 SBC. And there'll be Raspberry Pi 5 too, according to Eben's interview. My guess: they'll use Cortex-A76 + A-55 too.

    Originally posted by coder View Post
    And although I really like what Firefly did, it's just too expensive for what it is. I feel like they over-engineered it, with that whole daughter board aspect.

    BTW, I really wish we could get some momentum behind one of the standard form factors, like nano-ITX or 5x5.
    Yeah. Don't know why they do that. Premium price for ITX size and upgradeable RAM and Storage.

    Ditto for standard size. It can be nano-ITX, or whatever size (but not too big). If we have standards, then we can have case like x86. How nice if it came true. Me, I prefer something like framework board (more compact, but more thick). I'll very much like it if I can use my board as a laptop, or for desktop.

    Leave a comment:


  • coder
    replied
    Originally posted by t.s. View Post
    I've tried ... N2 (idle ~2w) surprisingly capable and quite quick opening apps, despite using microSD.
    100% agree. I got the eMMC module, and the N2+ gives the most desktop-like user experience I've had from a SBC.

    Originally posted by t.s. View Post
    The problem, especially N2 is the 4GB RAM. Now, with something like OPi5 and Rock5B that have up to 16GB, my dream to have a ~2 watt desktop will come true soon-ish.
    Indeed. However, I'm in no hurry. I'm curious to see if HardKernel will release an ODROID based on the RK3588, or similar. Maybe they'll use their H-series form factor, since those have a bigger passive heatsink and can accommodate a M.2 SSD.

    And although I really like what Firefly did, it's just too expensive for what it is. I feel like they over-engineered it, with that whole daughter board aspect.


    BTW, I really wish we could get some momentum behind one of the standard form factors, like nano-ITX or 5x5.

    Leave a comment:


  • t.s.
    replied
    Originally posted by coder View Post
    Here's an excerpt of that table, including some of the more notable entries:

    Device /
    details
    Clockspeed Kernel Distro 7-zip multi 7-zip single AES memcpy memset kH/s
    Radxa ROCK 5B 2350/1830 MHz 5.10 Focal arm64 16450 3146 1337540 10830 29220 25.31
    Pentium N6005 3300/2000 MHz 6.0 Jammy amd64 10810 3485 922000 9600 11300 20.15
    ODROID-N2+ 2400/2015 MHz 5.14 Hirsute arm64 9780 2386 1366090 4030 7120 -
    Raspberry Pi 4 B 1800 MHz 5.15 Jammy armhf 6300 1844 82750 1190 3110 -
    Raspberry Pi 3 B+ normal 4.14 Raspbian Stretch 3040 856 36600 1050 1500 -


    I was trying to find a good way to copy-paste tables into a post, but without success. Finally, it occurred to me to save a spreadsheet as HTML and then open it with VIM and run a few substitutions. Works, but annoying. If I had to do it a lot, I'd write an XSLT script.
    I've tried RPi3+, RPi4B, N2. RPi4B (idle ~4w) and N2 (idle ~2w) surprisingly capable and quite quick opening apps, despite using microSD. The problem, especially N2 is the 4GB RAM. Now, with something like OPi5 and Rock5B that have up to 16GB, my dream to have a ~2 watt desktop will come true soon-ish. Well, must wait for the GPU driver, ~1-2 years.

    Leave a comment:


  • t.s.
    replied
    Originally posted by coder View Post
    Wow! Thanks for the link! That's some great data! I just wish the user interface were a bit more friendly. I see no way to sort by column value or export as a spreadsheet.

    I don't know where you're getting efficiency numbers, because neither that chart nor the full logs seem to have efficiency or power.

    However, the N6005 indeed managed to win at single-threaded 7-zip. As for multi-threaded performance, I'd be curious to know how much the 4x A55's are adding to the Rock 5B's numbers. I know it's a little bit moot, but it would be enlightening to know how Cortex-A76 compares with Tremont, especially ISO-clock or ISO-power.
    You're welcome.

    For the efficiency number, it's not included there. But you can find the estimated number here for Rock5B (RK3588) (https://forum.radxa.com/t/rock-5b-de...tion/10483/400). For other number, sorry, just pulled out from my memory, but IIRC, I read it at one of the RK3588 SBC articles from cnx-software.com.

    N6005 win because their turbo boost, I think. If the Cortex A-76 clocked to ~2.8GHz, I think it'll tied. Here https://forum.radxa.com/t/rock-5b-de...ation/10483/56 for the A55 perf.

    Leave a comment:


  • Michael
    replied
    Originally posted by coder View Post
    Current preorder price is $75 for the 8 GB model. I have offered to donate one to the site, if Michael is interested. He just needs to PM me the pre-checkout total and I'll paypal the $.
    Thanks, currently though waiting to hear back from OrangePi... They messaged me on Twitter asking if I'd write a news about it, I asked them then about any review sample.

    Leave a comment:


  • coder
    replied
    Here's an excerpt of that table, including some of the more notable entries:

    Device /
    details
    Clockspeed Kernel Distro 7-zip multi 7-zip single AES memcpy memset kH/s
    Radxa ROCK 5B 2350/1830 MHz 5.10 Focal arm64 16450 3146 1337540 10830 29220 25.31
    Pentium N6005 3300/2000 MHz 6.0 Jammy amd64 10810 3485 922000 9600 11300 20.15
    ODROID-N2+ 2400/2015 MHz 5.14 Hirsute arm64 9780 2386 1366090 4030 7120 -
    Raspberry Pi 4 B 1800 MHz 5.15 Jammy armhf 6300 1844 82750 1190 3110 -
    Raspberry Pi 3 B+ normal 4.14 Raspbian Stretch 3040 856 36600 1050 1500 -


    I was trying to find a good way to copy-paste tables into a post, but without success. Finally, it occurred to me to save a spreadsheet as HTML and then open it with VIM and run a few substitutions. Works, but annoying. If I had to do it a lot, I'd write an XSLT script.
    Last edited by coder; 20 November 2022, 06:07 PM.

    Leave a comment:


  • coder
    replied
    Originally posted by t.s. View Post
    As for Intel atom/ celeron level, the multithread score still below RK3588 perf (https://github.com/ThomasKaiser/sbc-...ter/Results.md).
    Wow! Thanks for the link! That's some great data! I just wish the user interface were a bit more friendly. I see no way to sort by column value or export as a spreadsheet.

    Originally posted by t.s. View Post
    Their power/perf efficiency too.
    I don't know where you're getting efficiency numbers, because neither that chart nor the full logs seem to have efficiency or power.

    However, the N6005 indeed managed to win at single-threaded 7-zip. As for multi-threaded performance, I'd be curious to know how much the 4x A55's are adding to the Rock 5B's numbers. I know it's a little bit moot, but it would be enlightening to know how Cortex-A76 compares with Tremont, especially ISO-clock or ISO-power.

    Originally posted by t.s. View Post
    Edit: and you could pre-order orangepi 5 4-8-16GB from aliexpress now. They'll send it in December. Quite cheap.
    Current preorder price is $75 for the 8 GB model. I have offered to donate one to the site, if Michael is interested. He just needs to PM me the pre-checkout total and I'll paypal the $.


    However, from what I can tell, it has a fan header but they offer no heatsink or fan specifically for it. My best guess is that the SoC package is about 17 mm on a side, with the dotted line around it measuring 19 mm on a side. I think you could fit a 20 mm x 20 mm copper heatsink, like this one:

    Last edited by coder; 20 November 2022, 05:42 PM.

    Leave a comment:


  • coder
    replied
    Originally posted by Paradigm Shifter View Post
    Yeah, I know they don't right now... but there's a first time for everything, and with Genoa appearing to stomp a new hole in the current Xeon range, we can only guess what Sapphire Rapids will bring. Hopefully not stupid stuff like exceeding TDP.
    You should be able to simply look at the specified TDPs, to see the elevated power consumption of this generation. These are customers who really don't like surprises, because more power consumption than specified would blow a hole in their TCO calculations and could exceed the capacity of their cooling & electrical infrastructure.

    Leave a comment:

Working...
X