ARM vs x86

Most people in here have a lot more experience in the server thing than me so like I have always been told, ask people who are smarter than you. After getting ( and pretty much idling) way to many servers to learn and play I can't help but be drawn to the arm server that oracle has on it's free tier. I have compared it to almost all the other ones I have gotten on here and it seems to be more "more bang for ht buck" as it were. Is it that arm processors handle loads better than x86 processors or is it more of a Oracle has such massive resources behind the instances that make it seem that way? From reading it looks like the cost/performance of an arm is better on paper but I am curious what you guys have seen in the real world.

Comments

  • depends on your workload, and what are you trying to do.

    If your software require you a hard AVX2, SSE4, MMX .etc requirement, you will never get this done in ARM cpu as it simply won't run, or paying your developer to use arm-equivalent instruction become not economical.

    but if you're just a basic bitch using it as general purpose-whatever (like running mainstream software), you might as well not notice it.
    your rsync / syncthing runs on arm?, great, then use it as arm is cheaper.

    Fuck this 24/7 internet spew of trivia and celebrity bullshit.

  • @Encoders said: f you're just a basic bitch

    I'm 100% a basic bitch. My entire lab at home is ARM. My router is a Nano Pi R2S, just moved my NAS over to an ODROID-HC4, my compute is a 4-unit ODROID-MC1 cluster (*arr stack, deluge, plex, LNMP stack with dokuwiki), and my remote syslog/pi-hole/wifi controller is an ODROID-HC1.

    Low power, silent, sips power, no heat, etc. I love it.

    Thanked by (1)yoursunny
  • Not_OlesNot_Oles Hosting ProviderContent Writer

    @schism Have you tried Oracle Free Tier?

    I hope everyone gets the servers they want!

  • @schism said:
    Most people in here have a lot more experience in the server thing than me so like I have always been told, ask people who are smarter than you. After getting ( and pretty much idling) way to many servers to learn and play I can't help but be drawn to the arm server that oracle has on it's free tier. I have compared it to almost all the other ones I have gotten on here and it seems to be more "more bang for ht buck" as it were. Is it that arm processors handle loads better than x86 processors or is it more of a Oracle has such massive resources behind the instances that make it seem that way? From reading it looks like the cost/performance of an arm is better on paper but I am curious what you guys have seen in the real world.

    I have used both Oracle's ARM offering as well as cheap x86 CPUs like atom. ARM definitely wins there.

    If you compare Raspberry Pi, which runs on ARM with a Celeron x86 CPU, of course x86 wins there.

    So it comes down to exact CPU models & specs.

    If you are running anything that requires specific x86 or x64 support, stay away from ARM. In all other cases, give the new ARM CPUs a try. They are a lot better then older ARM CPUs like those used in Raspberry Pi.

    Just a reminder that both Android and iPhones uses ARM CPUs. Now Apple's M1 chipsets also uses ARM CPU, which are (supposedly) faster then their intel x86 or x64 counterparts.

    Artificial intelligence is no match for our natural stupidity.

    Time flies like an arrow; fruit flies like a banana.

  • @Not_Oles said:
    @schism Have you tried Oracle Free Tier?

    Yes sir which is what made me ask the question. For the little bit of playing around I do it kind of made me wonder so I asked.

    Thanked by (1)Not_Oles
  • @Encoders said:
    depends on your workload, and what are you trying to do.

    If your software require you a hard AVX2, SSE4, MMX .etc requirement, you will never get this done in ARM cpu as it simply won't run, or paying your developer to use arm-equivalent instruction become not economical.

    but if you're just a basic bitch using it as general purpose-whatever (like running mainstream software), you might as well not notice it.
    your rsync / syncthing runs on arm?, great, then use it as arm is cheaper.

    I had not considered the cpu specific stuff. I really don't have a use case other than playing around with them so I had not come across any issues like that. Thanks for pointing it out.

  • @somik said:

    @schism said:
    Most people in here have a lot more experience in the server thing than me so like I have always been told, ask people who are smarter than you. After getting ( and pretty much idling) way to many servers to learn and play I can't help but be drawn to the arm server that oracle has on it's free tier. I have compared it to almost all the other ones I have gotten on here and it seems to be more "more bang for ht buck" as it were. Is it that arm processors handle loads better than x86 processors or is it more of a Oracle has such massive resources behind the instances that make it seem that way? From reading it looks like the cost/performance of an arm is better on paper but I am curious what you guys have seen in the real world.

    I have used both Oracle's ARM offering as well as cheap x86 CPUs like atom. ARM definitely wins there.

    If you compare Raspberry Pi, which runs on ARM with a Celeron x86 CPU, of course x86 wins there.

    So it comes down to exact CPU models & specs.

    If you are running anything that requires specific x86 or x64 support, stay away from ARM. In all other cases, give the new ARM CPUs a try. They are a lot better then older ARM CPUs like those used in Raspberry Pi.

    Just a reminder that both Android and iPhones uses ARM CPUs. Now Apple's M1 chipsets also uses ARM CPU, which are (supposedly) faster then their intel x86 or x64 counterparts.

    So it does seem like it's an architecture issue. I don't know about the apple chipset (I'm a nix guy so I prefer to give my money to FOSS places) however I will say most of the stenography stuff I have played with has run fast in termux on my pixel 6 than on my i7 laptop.

  • @schism said:

    @somik said:

    @schism said:
    Most people in here have a lot more experience in the server thing than me so like I have always been told, ask people who are smarter than you. After getting ( and pretty much idling) way to many servers to learn and play I can't help but be drawn to the arm server that oracle has on it's free tier. I have compared it to almost all the other ones I have gotten on here and it seems to be more "more bang for ht buck" as it were. Is it that arm processors handle loads better than x86 processors or is it more of a Oracle has such massive resources behind the instances that make it seem that way? From reading it looks like the cost/performance of an arm is better on paper but I am curious what you guys have seen in the real world.

    I have used both Oracle's ARM offering as well as cheap x86 CPUs like atom. ARM definitely wins there.

    If you compare Raspberry Pi, which runs on ARM with a Celeron x86 CPU, of course x86 wins there.

    So it comes down to exact CPU models & specs.

    If you are running anything that requires specific x86 or x64 support, stay away from ARM. In all other cases, give the new ARM CPUs a try. They are a lot better then older ARM CPUs like those used in Raspberry Pi.

    Just a reminder that both Android and iPhones uses ARM CPUs. Now Apple's M1 chipsets also uses ARM CPU, which are (supposedly) faster then their intel x86 or x64 counterparts.

    So it does seem like it's an architecture issue. I don't know about the apple chipset (I'm a nix guy so I prefer to give my money to FOSS places) however I will say most of the stenography stuff I have played with has run fast in termux on my pixel 6 than on my i7 laptop.

    x86 and x64 is said to have a lot of instruction overhead that they need to support instruction sets from all the way back to the 80s. ARM doesn't have it so it processes instructions faster. However as it is designed to be more energy efficient, it needs more cores to keep up with the latest x86 or x64 CPUs. But when it comes to older x86 cpu vs newer ARM cpus, ARM wins most of the time.

    Let me give you a very simple example.

    For compiling a java project into a jar executable file, it took 170 seconds on my older x64 cpu, while it took 40 seconds on Oracle's ARM CPU. These were run on 2 seperate VPS, both with 4 cores allocated to it along with 8 GB of ram.

    Artificial intelligence is no match for our natural stupidity.

    Time flies like an arrow; fruit flies like a banana.

  • edited June 2023

    Benchmarked it.

    Benchmark by KangServer.id
    Performed: April 18th 2023
    
    ----------------------------------------------------------------------------
    ***** Passmark's PerformanceTest *****
    ----------------------------------------------------------------------------
                    Hetzner CAX31 - 11.99 EURO      | Hetzner CPX31 - 13.1 EURO
                         8 vCPU 16GB RAM            |      4 vCPU 8GB RAM   
    ----------------------------------------------------------------------------
    Single Threaded:        1320                    |          2045
    CPU Mark       :        6224                    |          8232
    ----------------------------------------------------------------------------
    
    ----------------------------------------------------------------------------
    ***** Geekbench 5 *****
    ----------------------------------------------------------------------------
                    Hetzner CAX31 - 11.99 EURO      | Hetzner CPX31 - 13.1 EURO
                         8 vCPU 16GB RAM            |      4 vCPU 8GB RAM   
    ----------------------------------------------------------------------------
    Single Core:               803                  |           974
    Multi Core :              5909                  |          3686
    https://browser.geekbench.com/v5/cpu/21076774   | https://browser.geekbench.com/v5/cpu/21076766
    ----------------------------------------------------------------------------
    
    ----------------------------------------------------------------------------
    ***** Geekbench 6 *****
    ----------------------------------------------------------------------------
                    Hetzner CAX31 - 11.99 EURO      | Hetzner CPX31 - 13.1 EURO
                         8 vCPU 16GB RAM            |      4 vCPU 8GB RAM   
    ----------------------------------------------------------------------------
    Single Core:              1034                  |          1242
    Multi Core :              5649                  |          4006
    https://browser.geekbench.com/v6/cpu/960880     | https://browser.geekbench.com/v6/cpu/960862
    ----------------------------------------------------------------------------
    
    ----------------------------------------------------------------------------
    ***** UnixBench *****
    ----------------------------------------------------------------------------
                    Hetzner CAX31 - 11.99 EURO      | Hetzner CPX31 - 13.1 EURO
                         8 vCPU 16GB RAM            |      4 vCPU 8GB RAM   
    ----------------------------------------------------------------------------
    Single SBIS:             1288.1                 |         1850.2
    Multi SBIS :             8948.2                 |         6825.2
    ----------------------------------------------------------------------------
    
    ----------------------------------------------------------------------------
    ***** PTS PostgreSQL (pgbench) *****
    Scaling Factor: 100 | Clients: 100 | Mode: Read-Only
    ----------------------------------------------------------------------------
                    Hetzner CAX31 - 11.99 EURO      | Hetzner CPX31 - 13.1 EURO
                         8 vCPU 16GB RAM            |      4 vCPU 8GB RAM   
    ----------------------------------------------------------------------------
    Score      :           133666 TPS               |       138406 TPS  
    Avg Latency:            0.748 ms                |        0.723 ms
    ----------------------------------------------------------------------------
    
    ----------------------------------------------------------------------------
    ***** PTS Nginx Benchmark *****
    Connections: 1000
    ----------------------------------------------------------------------------
                    Hetzner CAX31 - 11.99 EURO      | Hetzner CPX31 - 13.1 EURO
                         8 vCPU 16GB RAM            |      4 vCPU 8GB RAM  
    ----------------------------------------------------------------------------
    Score                 21617.43 RPS              |      19791.11 TPS
    ----------------------------------------------------------------------------
    
    ----------------------------------------------------------------------------
    ***** PTS Apache HTTP Server *****
    Connections: 1000
    ----------------------------------------------------------------------------
                    Hetzner CAX31 - 11.99 EURO      | Hetzner CPX31 - 13.1 EURO
                         8 vCPU 16GB RAM            |      4 vCPU 8GB RAM  
    ----------------------------------------------------------------------------
    Score:                23250.16 RPS              |      25327.43 TPS
    ----------------------------------------------------------------------------
    
    ----------------------------------------------------------------------------
    ***** PTS PHPBench *****
    ----------------------------------------------------------------------------
                    Hetzner CAX31 - 11.99 EURO      | Hetzner CPX31 - 13.1 EURO
                         8 vCPU 16GB RAM            |      4 vCPU 8GB RAM   
    ----------------------------------------------------------------------------
    Score:                   530440                 |         650093
    ----------------------------------------------------------------------------
    
    ----------------------------------------------------------------------------
    ***** PTS Redis *****
    Test options: SET & GET | Parallel Connections: 50
    ----------------------------------------------------------------------------
                    Hetzner CAX31 - 11.99 EURO      | Hetzner CPX31 - 13.1 EURO
                         8 vCPU 16GB RAM            |      4 vCPU 8GB RAM         
    ----------------------------------------------------------------------------
    GET:                 1575098.00 RPS             |        2149429.92 RPS
    SET:                 1156443.41 RPS             |        1600233.71 RPS
    ----------------------------------------------------------------------------
    
    ----------------------------------------------------------------------------
    ***** PTS MariaDB (mysqlslap) *****
    Clients: 1024
    ----------------------------------------------------------------------------
                    Hetzner CAX31 - 11.99 EURO      | Hetzner CPX31 - 13.1 EURO
                         8 vCPU 16GB RAM            |      4 vCPU 8GB RAM        
    ----------------------------------------------------------------------------
    Score:                  188 QPS                 |          223 QPS
    ----------------------------------------------------------------------------
    
    ----------------------------------------------------------------------------
    *** PTS 7-Zip Compression ***
    ----------------------------------------------------------------------------
                    Hetzner CAX31 - 11.99 EURO      | Hetzner CPX31 - 13.1 EURO
                         8 vCPU 16GB RAM            |      4 vCPU 8GB RAM   
    ----------------------------------------------------------------------------
    Compression  :         35697 MIPS               |       25581 MIPS
    Decompression:         32493 MIPS               |       16605 MIPS
    ----------------------------------------------------------------------------
    
    ----------------------------------------------------------------------------
    Hetzner CAX31 - 11.99 EURO
          8 vCPU 16GB RAM
          
    fio Disk Speed Tests (Mixed R/W 50/50):
    ---------------------------------
    Block Size | 4k            (IOPS) | 64k           (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 115.29 MB/s  (28.8k) | 1.11 GB/s    (17.4k)
    Write      | 115.21 MB/s  (28.8k) | 1.15 GB/s    (17.9k)
    Total      | 230.50 MB/s  (57.6k) | 2.26 GB/s    (35.4k)
               |                      |
    Block Size | 512k          (IOPS) | 1m            (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 1.88 GB/s     (3.6k) | 2.29 GB/s     (2.2k)
    Write      | 2.04 GB/s     (3.9k) | 2.56 GB/s     (2.5k)
    Total      | 3.92 GB/s     (7.6k) | 4.85 GB/s     (4.7k)
    
    ----------------------------------------------------------------------
     I/O Speed(1st run) : 1.0 GB/s
     I/O Speed(2nd run) : 979 MB/s
     I/O Speed(3rd run) : 1.1 GB/s
     I/O Speed(average) : 1043.1 MB/s
    ----------------------------------------------------------------------
    
    ----------------------------------------------------------------------
    Hetzner CPX31 - 13.1 EURO
          4 vCPU 8GB RAM
          
    fio Disk Speed Tests (Mixed R/W 50/50):
    ---------------------------------
    Block Size | 4k            (IOPS) | 64k           (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 132.48 MB/s  (33.1k) | 1.66 GB/s    (25.9k)
    Write      | 132.83 MB/s  (33.2k) | 1.67 GB/s    (26.1k)
    Total      | 265.32 MB/s  (66.3k) | 3.33 GB/s    (52.0k)
               |                      |
    Block Size | 512k          (IOPS) | 1m            (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 2.39 GB/s     (4.6k) | 2.36 GB/s     (2.3k)
    Write      | 2.52 GB/s     (4.9k) | 2.52 GB/s     (2.4k)
    Total      | 4.92 GB/s     (9.6k) | 4.88 GB/s     (4.7k)
    
    ----------------------------------------------------------------------
     I/O Speed(1st run) : 1.4 GB/s
     I/O Speed(2nd run) : 1.5 GB/s
     I/O Speed(3rd run) : 1.5 GB/s
     I/O Speed(average) : 1501.9 MB/s
    ----------------------------------------------------------------------
    

    I don't know about real-word performance, as i never used it for production.

    Thanked by (1)FrankZ

    📱: Samsung Galaxy | 💻: Windows 11

  • Plex will want that Intel power.

  • @hornet said:
    Plex will want that Intel power.

    HW video encoding/decoding is a hot mess depending on the SoC manufacturer (Allwinner is probably the worst offender as they never upstream their changes on mainstream Linux)

    Thanked by (1)rajprakash
  • @rubenmdh said:

    @hornet said:
    Plex will want that Intel power.

    HW video encoding/decoding is a hot mess depending on the SoC manufacturer (Allwinner is probably the worst offender as they never upstream their changes on mainstream Linux)

    Ah, yes, but flagship android phones seems to be somewhat competent at encoding/decoding video streams. They still will need a lot more optimizations but since ffmpeg seems to have support for arm64, i think it should run nicely on a proper ARM cpu.

    Anyone got a ARM box to try it out?

    Artificial intelligence is no match for our natural stupidity.

    Time flies like an arrow; fruit flies like a banana.

  • @somik said:

    @rubenmdh said:

    @hornet said:
    Plex will want that Intel power.

    HW video encoding/decoding is a hot mess depending on the SoC manufacturer (Allwinner is probably the worst offender as they never upstream their changes on mainstream Linux)

    Ah, yes, but flagship android phones seems to be somewhat competent at encoding/decoding video streams. They still will need a lot more optimizations but since ffmpeg seems to have support for arm64, i think it should run nicely on a proper ARM cpu.

    Anyone got a ARM box to try it out?

    Are you in a place where you can get a free Oracle service? I definitely did not mean to disparage RISC/ARM offerings. I actually love their idea. I blame the industry for not encouraging/forcing beautiful, open drivers and hardware encoding/decoding of all the video and audio standards.

Sign In or Register to comment.