Openssl has a strange speed

[serj-47]

• S905x3
• TOX1

Debian GNU/Linux 11 (bullseye)
..
Linux armbian 6.1.55-ophub #1 SMP Sat Sep 23 07:37:26 EDT 2023 aarch64 GNU/Linux

cat /proc/cpuinfo
processor : 0
model name : ARMv8 Processor rev 0 (v8l)
BogoMIPS : 48.00
Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm lrcpc dcpop asimddp
CPU implementer : 0x41
CPU architecture: 8
CPU variant : 0x1
CPU part : 0xd05
CPU revision : 0
...

When I run openssl speed aes-256-cbc in the console, I get low results:
...
root@armbian:~# openssl speed aes-256-cbc
Doing aes-256 cbc for 3s on 16 size blocks: 10210845 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 64 size blocks: 2747026 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 256 size blocks: 703276 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 1024 size blocks: 176809 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 8192 size blocks: 22131 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 16384 size blocks: 11057 aes-256 cbc's in 3.00s
OpenSSL 1.1.1w 11 Sep 2023
built on: Wed Sep 13 19:21:33 2023 UTC
options:bn(64,64) rc4(char) des(int) aes(partial) blowfish(ptr)
compiler: gcc -fPIC -pthread -Wa,--noexecstack -Wall -Wa,--noexecstack -g -O2 -ffile-prefix-map=/build/reproducible-path/openssl-1.1.1w=. -fstack-protector-strong -Wformat -Werror=format-security -DOPENSSL_USE_NODELETE -DOPENSSL_PIC -DOPENSSL_CPUID_OBJ -DOPENSSL_BN_ASM_MONT -DSHA1_ASM -DSHA256_ASM -DSHA512_ASM -DKECCAK1600_ASM -DVPAES_ASM -DECP_NISTZ256_ASM -DPOLY1305_ASM -DNDEBUG -Wdate-time -D_FORTIFY_SOURCE=2
The 'numbers' are in 1000s of bytes per second processed.
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes 16384 bytes
aes-256 cbc 54457.84k 58603.22k 60012.89k 60350.81k 60432.38k 60385.96k

For comparison, I also have another tvbox with the same s905x3 processor that runs on coreelec firmware. I tested openssl speed aes-256-cbc on it and the results are much higher:

openssl speed aes-256-cbc
Doing aes-256-cbc for 3s on 16 size blocks: 27220155 aes-256-cbc's in 3.00s
Doing aes-256-cbc for 3s on 64 size blocks: 17752825 aes-256-cbc's in 3.00s
Doing aes-256-cbc for 3s on 256 size blocks: 7347953 aes-256-cbc's in 3.00s
Doing aes-256-cbc for 3s on 1024 size blocks: 2233218 aes-256-cbc's in 3.00s
Doing aes-256-cbc for 3s on 8192 size blocks: 297553 aes-256-cbc's in 3.00s
Doing aes-256-cbc for 3s on 16384 size blocks: 149534 aes-256-cbc's in 3.00s
version: 3.0.12
built on: Fri Jan 12 17:48:39 2024 UTC
options: bn(64,32)
compiler: /home/portisch/CE/CoreELEC/build.CoreELEC-Amlogic-ng.arm-20/toolchain/bin/armv8a-libreelec-linux-gnueabihf-gcc -fPIC -pthread -Wa,--noexecstack -march=armv8-a+crc -mtune=cortex-a53 -mabi=aapcs-linux -Wno-psabi -Wa,-mno-warn-deprecated -mfloat-abi=hard -mfpu=neon-fp-armv8 -Wall -pipe -O2 -fomit-frame-pointer -DNDEBUG -march=armv8-a+crc -mtune=cortex-a53 -mabi=aapcs-linux -Wno-psabi -Wa,-mno-warn-deprecated -mfloat-abi=hard -mfpu=neon-fp-armv8 -Wall -pipe -O2 -fomit-frame-pointer -fuse-ld=gold -DOPENSSL_USE_NODELETE -DOPENSSL_PIC -DOPENSSL_BUILDING_OPENSSL -DNDEBUG -DNDEBUG
CPUINFO: OPENSSL_armcap=0x3d The 'numbers' are in 1000s of bytes per second processed. type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes 16384 bytes
aes-256-cbc 145174.16k 378726.93k 627025.32k 762271.74k 812518.06k 816655.02k