Orange Pi Zero 3

[leon332157]

Basic information

• Board URL (official): http://www.orangepi.org/html/hardWare/computerAndMicrocontrollers/details/Orange-Pi-Zero-3.html
• Board purchased from: Amazon US
• Board purchase date: 12/28/2023
• Board specs (as tested): 4GB + Expansion Board, 64GB PNY Elite-X MicroSD, no heatsink
• Board price (as tested): $38 without tax

Linux/system information

Official Ubuntu Image

orangepi@orangepizero3:~$ neofetch
            .-/+oossssoo+/-.               orangepi@orangepizero3
        `:+ssssssssssssssssss+:`           ----------------------
      -+ssssssssssssssssssyyssss+-         OS: Ubuntu 22.04.3 LTS aarch64
    .ossssssssssssssssssdMMMNysssso.       Host: OrangePi Zero3
   /ssssssssssshdmmNNmmyNMMMMhssssss/      Kernel: 6.1.31-sun50iw9
  +ssssssssshmydMMMMMMMNddddyssssssss+     Uptime: 14 mins
 /sssssssshNMMMyhhyyyyhmNMMMNhssssssss/    Packages: 1531 (dpkg)
.ssssssssdMMMNhsssssssssshNMMMdssssssss.   Shell: bash 5.1.16
+sssshhhyNMMNyssssssssssssyNMMMysssssss+   Terminal: /dev/pts/0
ossyNMMMNyMMhsssssssssssssshmmmhssssssso   CPU: (4) @ 1.512GHz
ossyNMMMNyMMhsssssssssssssshmmmhssssssso   Memory: 451MiB / 3930MiB
+sssshhhyNMMNyssssssssssssyNMMMysssssss+
.ssssssssdMMMNhsssssssssshNMMMdssssssss.
 /sssssssshNMMMyhhyyyyhdNMMMNhssssssss/
  +sssssssssdmydMMMMMMMMddddyssssssss+
   /ssssssssssshdmNNNNmyNMMMMhssssss/
    .ossssssssssssssssssdMMMNysssso.
      -+sssssssssssssssssyyyssss+-
        `:+ssssssssssssssssss+:`
            .-/+oossssoo+/-.


Linux orangepizero3 6.1.31-sun50iw9 #1.0.2 SMP Thu Sep 28 13:55:18 CST 2023 aarch64 aarch64 aarch64 GNU/Linux

Benchmark results

CPU

• Geekbench 6: (155 single/ 457 multi -(https://browser.geekbench.com/v6/cpu/4279497))
• TODO Gflops (geerlingguy/top500-benchmark HPL result)

Power

• Idle power draw (at wall): ~1 W
• Maximum simulated power draw (stress-ng --matrix 0): ~2 W
• During Geekbench multicore benchmark: ~2W
• During top500 HPL benchmark: TODO W

Disk

PNY Elite-X 64GB micro SD

Benchmark	Result
fio 1M sequential read	TODO MB/s
iozone 1M random read	TODO MB/s
iozone 1M random write	TODO MB/s
iozone 4K random read	TODO MB/s
iozone 4K random write	TODO MB/s

Network

iperf3 results:

• iperf3 -c $SERVER_IP: TODO Mbps
• iperf3 --reverse -c $SERVER_IP: TODO Mbps
• iperf3 --bidir -c $SERVER_IP: TODO Mbps up, TODO Mbps down

GPU

• TODO: Haven't determined standardized benchmark yet. See Issue #2.

Memory

tinymembench results:

Click to expand memory benchmark result

tinymembench v0.4.10 (simple benchmark for memory throughput and latency)

==========================================================================
== Memory bandwidth tests ==
== ==
== Note 1: 1MB = 1000000 bytes ==
== Note 2: Results for 'copy' tests show how many bytes can be ==
== copied per second (adding together read and writen ==
== bytes would have provided twice higher numbers) ==
== Note 3: 2-pass copy means that we are using a small temporary buffer ==
== to first fetch data into it, and only then write it to the ==
== destination (source -> L1 cache, L1 cache -> destination) ==
== Note 4: If sample standard deviation exceeds 0.1%, it is shown in ==
== brackets ==

C copy backwards : 1507.2 MB/s (0.6%)
C copy backwards (32 byte blocks) : 1524.4 MB/s (0.2%)
C copy backwards (64 byte blocks) : 1538.0 MB/s (0.4%)
C copy : 1464.8 MB/s (1.2%)
C copy prefetched (32 bytes step) : 1082.4 MB/s
C copy prefetched (64 bytes step) : 1000.3 MB/s
C 2-pass copy : 1294.4 MB/s
C 2-pass copy prefetched (32 bytes step) : 913.7 MB/s
C 2-pass copy prefetched (64 bytes step) : 773.7 MB/s
C fill : 5991.7 MB/s (0.3%)
C fill (shuffle within 16 byte blocks) : 5990.3 MB/s
C fill (shuffle within 32 byte blocks) : 5986.2 MB/s
C fill (shuffle within 64 byte blocks) : 5992.5 MB/s (0.1%)
NEON 64x2 COPY : 1533.9 MB/s (0.3%)
NEON 64x2x4 COPY : 1549.2 MB/s
NEON 64x1x4_x2 COPY : 1209.8 MB/s (1.0%)
NEON 64x2 COPY prefetch x2 : 340.1 MB/s
NEON 64x2x4 COPY prefetch x1 : 1598.2 MB/s
NEON 64x2 COPY prefetch x1 : 1656.7 MB/s
NEON 64x2x4 COPY prefetch x1 : 1598.3 MB/s

standard memcpy : 1548.2 MB/s (0.1%)
standard memset : 6000.6 MB/s (0.2%)

NEON LDP/STP copy : 1523.8 MB/s (0.5%)
NEON LDP/STP copy pldl2strm (32 bytes step) : 955.5 MB/s (1.2%)
NEON LDP/STP copy pldl2strm (64 bytes step) : 1160.9 MB/s (0.3%)
NEON LDP/STP copy pldl1keep (32 bytes step) : 1768.4 MB/s
NEON LDP/STP copy pldl1keep (64 bytes step) : 1768.0 MB/s
NEON LD1/ST1 copy : 1523.4 MB/s (0.7%)
NEON STP fill : 5995.0 MB/s (0.3%)
NEON STNP fill : 3854.1 MB/s (0.5%)
ARM LDP/STP copy : 1530.3 MB/s (0.6%)
ARM STP fill : 5999.8 MB/s (0.3%)
ARM STNP fill : 3904.9 MB/s (0.8%)

==========================================================================
== Memory latency test ==
== ==
== Average time is measured for random memory accesses in the buffers ==
== of different sizes. The larger is the buffer, the more significant ==
== are relative contributions of TLB, L1/L2 cache misses and SDRAM ==
== accesses. For extremely large buffer sizes we are expecting to see ==
== page table walk with several requests to SDRAM for almost every ==
== memory access (though 64MiB is not nearly large enough to experience ==
== this effect to its fullest). ==
== ==
== Note 1: All the numbers are representing extra time, which needs to ==
== be added to L1 cache latency. The cycle timings for L1 cache ==
== latency can be usually found in the processor documentation. ==
== Note 2: Dual random read means that we are simultaneously performing ==
== two independent memory accesses at a time. In the case if ==
== the memory subsystem can't handle multiple outstanding ==
== requests, dual random read has the same timings as two ==
== single reads performed one after another. ==

block size : single random read / dual random read, [MADV_NOHUGEPAGE]
1024 : 0.0 ns / 0.0 ns
2048 : 0.0 ns / 0.0 ns
4096 : 0.0 ns / 0.0 ns
8192 : 0.0 ns / 0.0 ns
16384 : 0.0 ns / 0.0 ns
32768 : 0.0 ns / 0.0 ns
65536 : 4.3 ns / 7.3 ns
131072 : 6.6 ns / 10.4 ns
262144 : 7.7 ns / 11.7 ns
524288 : 8.3 ns / 12.4 ns
1048576 : 10.1 ns / 14.8 ns
2097152 : 94.1 ns / 142.7 ns
4194304 : 141.2 ns / 186.7 ns
8388608 : 165.0 ns / 201.7 ns
16777216 : 178.7 ns / 211.1 ns

33554432 : 186.9 ns / 215.3 ns
67108864 : 191.3 ns / 217.2 ns

block size : single random read / dual random read, [MADV_HUGEPAGE]
1024 : 0.0 ns / 0.0 ns
2048 : 0.0 ns / 0.0 ns
4096 : 0.0 ns / 0.0 ns
8192 : 0.0 ns / 0.0 ns
16384 : 0.0 ns / 0.0 ns
32768 : 0.0 ns / 0.0 ns
65536 : 4.3 ns / 7.3 ns
131072 : 6.6 ns / 10.4 ns
262144 : 7.7 ns / 11.7 ns
524288 : 8.3 ns / 12.3 ns
1048576 : 10.0 ns / 14.6 ns
2097152 : 93.4 ns / 141.5 ns
4194304 : 135.3 ns / 178.2 ns
8388608 : 155.1 ns / 189.3 ns
16777216 : 164.3 ns / 193.2 ns
33554432 : 169.3 ns / 196.0 ns
67108864 : 172.0 ns / 197.9 ns

sbc-bench results

Run sbc-bench and paste a link to the results here: gist

Phoronix Test Suite

Results from pi-general-benchmark.sh:

• pts/encode-mp3: TODO sec
• pts/x264 4K: TODO fps
• pts/x264 1080p: TODO fps
• pts/phpbench: TODO
• pts/build-linux-kernel (defconfig): TODO sec

[JuniorJPDJ]

Can I please ask you to do iperf3 test? I'm interested in ethernet speed.

[leon332157]

Can I please ask you to do iperf3 test? I'm interested in ethernet speed.

Sorry, I no longer have access to the device, but I would imagine it's similar to other h618 devices.