少女：小女子听闻这飞腾可是大有来头，政府银行学校都在用，应该很厉害叭？
曦儿：姐姐这就给你测个，正好姐姐这有块RK3399的板子，一起给你比比~
可能有集美接触过类似的开发板，树莓派、香橙派、香蕉派等等，但飞腾派大概还是第一次接触，前面已经成功烧入镜像并启动系统，是不是迫不及待想试试这颇负盛名的飞腾派好不好用呢？毕竟，是骡子是马拉出来溜溜才知道~
板子的硬件规格在前文中有介绍，在此不再过多赘述，查阅硬件参数可知，飞腾派所使用的D2000Q采用了2+2的核心设计，其中2个是1.8GHz主频的FTC664大核（0x664，D2000上FTC663的演进版本），剩下两个则是1.5GHz主频的FTC310小核（0x303，理论上应该叫FTC303才对，或是过往曾叫过这个名字）
飞腾并没有公布几款处理器核心的微架构，一些文章和测评中提到过FTC663同频性能大致与A72相若，作为演进版本的FTC664大概不会差距太大，至于FTC310，并没有太多公开资料，但个人认为应该和A53差不多，正好开发板中常用的瑞芯微RK3399有着相近的主频和大小结构（只是多了2个A53小核），具备可比较性而无需反复换算
前文中给飞腾派烧录的系统镜像是OpenKylin 1.01(yangtze)，但目前暂时没有找到适配RK3399的OpenKylin系统镜像，为便于测试，选用Firefly提供的Ubuntu 20.04 LTS(focal)系统
OpenKylin采用基于Wayland的UKUI，这是一款现代化的桌面环境，而Firefly给RK3399打包的Ubuntu镜像默认使用LXQt，一种基于Qt而主要面向嵌入式应用的简易桌面，二者资源占用大相径庭，为了保证测试公平，更换为来自Ubuntu Kylin的UKUI桌面环境
openkylin@phytiumPi:~$ cat /etc/*-release
DISTRIB_ID=openKylin
DISTRIB_RELEASE=1.0.1
DISTRIB_CODENAME=yangtze
DISTRIB_DESCRIPTION="openKylin 1.0.1"
NAME="openKylin"
FULL_NAME="openKylin"
VERSION="1.0.1 (yangtze)"
VERSION_US="1.0.1 (yangtze)"
ID=openkylin
PRETTY_NAME="openKylin 1.0.1"
VERSION_ID="1.0.1"
HOME_URL="https://www.openkylin.top/"
VERSION_CODENAME=yangtze
PRODUCT_FEATURES=3
openkylin@phytiumPi:~$ uname -a
Linux phytiumPi 5.4.18-63+ #2 SMP PREEMPT Wed Aug 30 13:10:19 CST 2023 aarch64 aarch64 aarch64 GNU/Linux
D2000Q OpenKylin 1.0.1使用系统默认5.4.18版本内核
firefly@firefly:~$ cat /etc/*-release
DISTRIB_ID=Ubuntu
DISTRIB_RELEASE=20.04
DISTRIB_CODENAME=focal
DISTRIB_DESCRIPTION="Ubuntu 20.04.6 LTS"
NAME="Ubuntu Kylin"
VERSION="20.04.6 LTS (Focal Fossa)"
ID=ubuntu
ID_LIKE=debian
PRETTY_NAME="Ubuntu 20.04.6 LTS"
VERSION_ID="20.04"
HOME_URL="https://www.ubuntu.com/"
SUPPORT_URL="https://help.ubuntu.com/"
BUG_REPORT_URL="https://bugs.launchpad.net/ubuntu/"
PRIVACY_POLICY_URL="https://www.ubuntu.com/legal/terms-and-policies/privacy-policy"
VERSION_CODENAME=focal
UBUNTU_CODENAME=focal
firefly@firefly:~$ uname -a
Linux firefly 4.4.194 #267 SMP Thu Mar 30 11:31:00 CST 2023 aarch64 aarch64 aarch64 GNU/Linux
RK3399 Ubuntu 20.04使用瑞芯微SDK的4.4.194版本内核
UnixBench是一个类Unix（Unix，BSD，Linux，macOS）系统下的开源性能测试工具，它提供了对类Unix系统性能的基本指标，被广泛用于测试各种Linux设备的性能。
主要测试项目包括整数运算、浮点运算、文件拷贝、管道、上下文交互、进程创建、系统调用和脚本执行等
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: phytiumpi: GNU/Linux
OS: GNU/Linux -- 5.4.18-63+ -- #2 SMP PREEMPT Wed Aug 30 13:10:19 CST 2023
Machine: aarch64 (aarch64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Phytium,FT-E2000/Little (100.0 bogomips)
CPU 1: Phytium,FT-E2000/Little (100.0 bogomips)
CPU 2: Phytium,FT-E2000/Big (100.0 bogomips)
CPU 3: Phytium,FT-E2000/Big (100.0 bogomips)
08:25:30 up 1:26, 1 user, load average: 2.09, 2.30, 2.58; runlevel 2023-08-25
---
Benchmark Run: 三 12月 13 2023 08:25:30 - 08:53:26
4 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 9571238.1 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2097.6 MWIPS (9.6 s, 7 samples)
Execl Throughput 916.4 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 173785.9 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 42175.5 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 482523.6 KBps (30.0 s, 2 samples)
Pipe Throughput 604900.0 lps (10.0 s, 7 samples)
Pipe-based Context Switching 62391.2 lps (10.0 s, 7 samples)
Process Creation 2149.8 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2434.1 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1101.7 lpm (60.0 s, 2 samples)
System Call Overhead 558560.5 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 9571238.1 820.2
Double-Precision Whetstone 55.0 2097.6 381.4
Execl Throughput 43.0 916.4 213.1
File Copy 1024 bufsize 2000 maxblocks 3960.0 173785.9 438.9
File Copy 256 bufsize 500 maxblocks 1655.0 42175.5 254.8
File Copy 4096 bufsize 8000 maxblocks 5800.0 482523.6 831.9
Pipe Throughput 12440.0 604900.0 486.3
Pipe-based Context Switching 4000.0 62391.2 156.0
Process Creation 126.0 2149.8 170.6
Shell Scripts (1 concurrent) 42.4 2434.1 574.1
Shell Scripts (8 concurrent) 6.0 1101.7 1836.2
System Call Overhead 15000.0 558560.5 372.4
========
System Benchmarks Index Score 421.6
---
Benchmark Run: 三 12月 13 2023 08:53:26 - 09:21:57
4 CPUs in system; running 4 parallel copies of tests
Dhrystone 2 using register variables 56289798.2 lps (10.0 s, 7 samples)
Double-Precision Whetstone 10459.2 MWIPS (10.0 s, 7 samples)
Execl Throughput 4955.6 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 720457.2 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 214458.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1888381.4 KBps (30.0 s, 2 samples)
Pipe Throughput 3061262.9 lps (10.0 s, 7 samples)
Pipe-based Context Switching 315403.2 lps (10.0 s, 7 samples)
Process Creation 10631.6 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 9250.1 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1262.2 lpm (60.1 s, 2 samples)
System Call Overhead 2315710.7 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 56289798.2 4823.5
Double-Precision Whetstone 55.0 10459.2 1901.7
Execl Throughput 43.0 4955.6 1152.5
File Copy 1024 bufsize 2000 maxblocks 3960.0 720457.2 1819.3
File Copy 256 bufsize 500 maxblocks 1655.0 214458.0 1295.8
File Copy 4096 bufsize 8000 maxblocks 5800.0 1888381.4 3255.8
Pipe Throughput 12440.0 3061262.9 2460.8
Pipe-based Context Switching 4000.0 315403.2 788.5
Process Creation 126.0 10631.6 843.8
Shell Scripts (1 concurrent) 42.4 9250.1 2181.6
Shell Scripts (8 concurrent) 6.0 1262.2 2103.7
System Call Overhead 15000.0 2315710.7 1543.8
========
System Benchmarks Index Score 1769.3
飞腾派测试结果，单核421.6分/四核1769.3分
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: firefly: GNU/Linux
OS: GNU/Linux -- 4.4.194 -- #267 SMP Thu Mar 30 11:31:00 CST 2023
Machine: aarch64 (aarch64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: (48.0 bogomips)
CPU 1: (48.0 bogomips)
CPU 2: (48.0 bogomips)
CPU 3: (48.0 bogomips)
CPU 4: (48.0 bogomips)
CPU 5: (48.0 bogomips)
03:03:07 up 2:56, 2 users, load average: 0.39, 0.60, 0.64; runlevel 2023-12-13
---
Benchmark Run: 三 12月 13 2023 03:03:07 - 03:31:21
6 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 16697938.0 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3220.2 MWIPS (9.9 s, 7 samples)
Execl Throughput 2148.7 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 277280.4 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 97053.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 692535.6 KBps (30.0 s, 2 samples)
Pipe Throughput 745032.6 lps (10.0 s, 7 samples)
Pipe-based Context Switching 90938.6 lps (10.0 s, 7 samples)
Process Creation 5554.3 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 4124.8 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1325.0 lpm (60.0 s, 2 samples)
System Call Overhead 708854.3 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 16697938.0 1430.8
Double-Precision Whetstone 55.0 3220.2 585.5
Execl Throughput 43.0 2148.7 499.7
File Copy 1024 bufsize 2000 maxblocks 3960.0 277280.4 700.2
File Copy 256 bufsize 500 maxblocks 1655.0 97053.0 586.4
File Copy 4096 bufsize 8000 maxblocks 5800.0 692535.6 1194.0
Pipe Throughput 12440.0 745032.6 598.9
Pipe-based Context Switching 4000.0 90938.6 227.3
Process Creation 126.0 5554.3 440.8
Shell Scripts (1 concurrent) 42.4 4124.8 972.8
Shell Scripts (8 concurrent) 6.0 1325.0 2208.3
System Call Overhead 15000.0 708854.3 472.6
========
System Benchmarks Index Score 694.1
---
Benchmark Run: 三 12月 13 2023 03:31:21 - 03:59:49
6 CPUs in system; running 6 parallel copies of tests
Dhrystone 2 using register variables 62069586.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 13610.2 MWIPS (10.0 s, 7 samples)
Execl Throughput 4826.3 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 905840.5 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 290217.8 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1912889.0 KBps (30.0 s, 2 samples)
Pipe Throughput 3370496.3 lps (10.0 s, 7 samples)
Pipe-based Context Switching 118665.4 lps (10.0 s, 7 samples)
Process Creation 12487.6 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 10769.1 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1513.2 lpm (60.1 s, 2 samples)
System Call Overhead 4289161.2 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 62069586.5 5318.7
Double-Precision Whetstone 55.0 13610.2 2474.6
Execl Throughput 43.0 4826.3 1122.4
File Copy 1024 bufsize 2000 maxblocks 3960.0 905840.5 2287.5
File Copy 256 bufsize 500 maxblocks 1655.0 290217.8 1753.6
File Copy 4096 bufsize 8000 maxblocks 5800.0 1912889.0 3298.1
Pipe Throughput 12440.0 3370496.3 2709.4
Pipe-based Context Switching 4000.0 118665.4 296.7
Process Creation 126.0 12487.6 991.1
Shell Scripts (1 concurrent) 42.4 10769.1 2539.9
Shell Scripts (8 concurrent) 6.0 1513.2 2522.1
System Call Overhead 15000.0 4289161.2 2859.4
========
System Benchmarks Index Score 1940.5
RK3399测试结果，单(大)核694.1分/六核1940.5分
测试结果显示飞腾派单核性能只有A72的0.6倍，当然这里面很可能有其他因素的影响，如RK3399因时间较早，板子上还是MLC eMMC，性能高于一般SD卡，文件读写项下拉分
这里发现了一个有趣的现象，飞腾派单核性能极度接近于总分的四分之一，按此分数估算，大小核性能差距不大，若这个421实际是小核成绩的话，意味着小核不仅远超A53，也超过A55甚至低频A510的一般水平，若实际如此说明FTC310很可能微架构和FTC663/664基本相同，只是缩减了一些东西
Geekbench6是由加拿大Primate Labs开发的跨平台性能测试工具，但更多还是偏向移动端，不少新款手机的参数都是从此泄露的
Phytium-Pi Board 2023 vs Firefly-RK3399 Board (Linux Opensource)
由于这块早期版本的RK3399板子只有2GB内存，Geekbench这种偏移动端的测试用例有不少Workload是内存敏感型（图像处理及渲染等一大堆），导致多核测试结果失真，可对比4G内存的RK3399
可以看出，FTC664同频性能的确与A72相近，部分项目稍微低些
由于多出两个A53小核，正常情况下RK3399的总分会高于飞腾派
OpenSSL命令行自带了个测试工具，用于测试处理器的加解密速度
openkylin@phytiumpi:~$ openssl speed aes
Doing aes-128-cbc for 3s on 16 size blocks: 30628719 aes-128-cbc's in 2.99s
Doing aes-128-cbc for 3s on 64 size blocks: 11677120 aes-128-cbc's in 2.99s
Doing aes-128-cbc for 3s on 256 size blocks: 6849505 aes-128-cbc's in 2.99s
Doing aes-128-cbc for 3s on 1024 size blocks: 2691896 aes-128-cbc's in 3.00s
Doing aes-128-cbc for 3s on 8192 size blocks: 405470 aes-128-cbc's in 3.00s
Doing aes-128-cbc for 3s on 16384 size blocks: 205242 aes-128-cbc's in 2.99s
Doing aes-192-cbc for 3s on 16 size blocks: 13553612 aes-192-cbc's in 2.99s
Doing aes-192-cbc for 3s on 64 size blocks: 10774453 aes-192-cbc's in 3.00s
Doing aes-192-cbc for 3s on 256 size blocks: 5850229 aes-192-cbc's in 3.00s
Doing aes-192-cbc for 3s on 1024 size blocks: 2118900 aes-192-cbc's in 3.00s
Doing aes-192-cbc for 3s on 8192 size blocks: 305971 aes-192-cbc's in 2.99s
Doing aes-192-cbc for 3s on 16384 size blocks: 154649 aes-192-cbc's in 3.00s
Doing aes-256-cbc for 3s on 16 size blocks: 13329440 aes-256-cbc's in 3.00s
Doing aes-256-cbc for 3s on 64 size blocks: 10229055 aes-256-cbc's in 2.99s
Doing aes-256-cbc for 3s on 256 size blocks: 5199274 aes-256-cbc's in 3.00s
Doing aes-256-cbc for 3s on 1024 size blocks: 1793441 aes-256-cbc's in 3.00s
Doing aes-256-cbc for 3s on 8192 size blocks: 252999 aes-256-cbc's in 3.00s
Doing aes-256-cbc for 3s on 16384 size blocks: 127667 aes-256-cbc's in 3.00s
version: 3.0.8
built on: Wed Apr 19 09:27:20 2023 UTC
options: bn(64,64)
compiler: gcc -fPIC -pthread -Wa,--noexecstack -Wall -DOPENSSL_TLS_SECURITY_LEVEL=2 -Wa,--noexecstack -DOPENSSL_USE_NODELETE -DOPENSSL_PIC -DOPENSSL_BUILDING_OPENSSL -DNDEBUG
CPUINFO: OPENSSL_armcap=0xfd
The 'numbers' are in 1000s of bytes per second processed.
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes 16384 bytes
aes-128-cbc 163899.50k 249945.04k 586445.91k 918833.83k 1107203.41k 1124643.79k
aes-192-cbc 72527.69k 229855.00k 499219.54k 723251.20k 838299.14k 844589.74k
aes-256-cbc 71090.35k 218949.67k 443671.38k 612161.19k 690855.94k 697232.04k
openkylin@phytiumpi:~$ openssl speed sha1
Doing sha1 for 3s on 16 size blocks: 2782594 sha1's in 2.98s
Doing sha1 for 3s on 64 size blocks: 2536937 sha1's in 3.00s
Doing sha1 for 3s on 256 size blocks: 2108079 sha1's in 3.00s
Doing sha1 for 3s on 1024 size blocks: 1253386 sha1's in 3.00s
Doing sha1 for 3s on 8192 size blocks: 265046 sha1's in 3.00s
Doing sha1 for 3s on 16384 size blocks: 138562 sha1's in 3.00s
version: 3.0.8
built on: Wed Apr 19 09:27:20 2023 UTC
options: bn(64,64)
compiler: gcc -fPIC -pthread -Wa,--noexecstack -Wall -DOPENSSL_TLS_SECURITY_LEVEL=2 -Wa,--noexecstack -DOPENSSL_USE_NODELETE -DOPENSSL_PIC -DOPENSSL_BUILDING_OPENSSL -DNDEBUG
CPUINFO: OPENSSL_armcap=0xfd
The 'numbers' are in 1000s of bytes per second processed.
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes 16384 bytes
sha1 14940.10k 54121.32k 179889.41k 427822.42k 723752.28k 756733.27k
openkylin@phytiumpi:~$ openssl speed sha512
Doing sha512 for 3s on 16 size blocks: 1164594 sha512's in 2.99s
Doing sha512 for 3s on 64 size blocks: 1169720 sha512's in 3.00s
Doing sha512 for 3s on 256 size blocks: 900894 sha512's in 2.99s
Doing sha512 for 3s on 1024 size blocks: 542076 sha512's in 3.00s
Doing sha512 for 3s on 8192 size blocks: 115165 sha512's in 3.00s
Doing sha512 for 3s on 16384 size blocks: 60512 sha512's in 2.99s
version: 3.0.8
built on: Wed Apr 19 09:27:20 2023 UTC
options: bn(64,64)
compiler: gcc -fPIC -pthread -Wa,--noexecstack -Wall -DOPENSSL_TLS_SECURITY_LEVEL=2 -Wa,--noexecstack -DOPENSSL_USE_NODELETE -DOPENSSL_PIC -DOPENSSL_BUILDING_OPENSSL -DNDEBUG
CPUINFO: OPENSSL_armcap=0xfd
The 'numbers' are in 1000s of bytes per second processed.
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes 16384 bytes
sha512 6231.94k 24954.03k 77133.40k 185028.61k 314477.23k 331581.47k
飞腾派测试结果
firefly@firefly:~$ openssl speed aes
Doing aes-128 cbc for 3s on 16 size blocks: 15636793 aes-128 cbc's in 3.00s
Doing aes-128 cbc for 3s on 64 size blocks: 4218557 aes-128 cbc's in 3.00s
Doing aes-128 cbc for 3s on 256 size blocks: 1069101 aes-128 cbc's in 3.00s
Doing aes-128 cbc for 3s on 1024 size blocks: 269223 aes-128 cbc's in 3.00s
Doing aes-128 cbc for 3s on 8192 size blocks: 33748 aes-128 cbc's in 3.00s
Doing aes-128 cbc for 3s on 16384 size blocks: 16877 aes-128 cbc's in 3.00s
Doing aes-192 cbc for 3s on 16 size blocks: 13615098 aes-192 cbc's in 2.99s
Doing aes-192 cbc for 3s on 64 size blocks: 3576241 aes-192 cbc's in 2.98s
Doing aes-192 cbc for 3s on 256 size blocks: 915210 aes-192 cbc's in 3.00s
Doing aes-192 cbc for 3s on 1024 size blocks: 230315 aes-192 cbc's in 3.00s
Doing aes-192 cbc for 3s on 8192 size blocks: 28839 aes-192 cbc's in 3.00s
Doing aes-192 cbc for 3s on 16384 size blocks: 14414 aes-192 cbc's in 3.00s
Doing aes-256 cbc for 3s on 16 size blocks: 11925620 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 64 size blocks: 3143317 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 256 size blocks: 793604 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 1024 size blocks: 199712 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 8192 size blocks: 25000 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 16384 size blocks: 12496 aes-256 cbc's in 3.00s
OpenSSL 1.1.1f 31 Mar 2020
built on: Tue Oct 10 09:03:48 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 -fdebug-prefix-map=/build/openssl-R3RAvN/openssl-1.1.1f=. -fstack-protector-strong -Wformat -Werror=format-security -DOPENSSL_TLS_SECURITY_LEVEL=2 -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-128 cbc 83396.23k 89995.88k 91229.95k 91894.78k 92154.54k 92170.92k
aes-192 cbc 72856.71k 76805.18k 78097.92k 78614.19k 78749.70k 78719.66k
aes-256 cbc 63603.31k 67057.43k 67720.87k 68168.36k 68266.67k 68244.82k
firefly@firefly:~$ openssl speed sha1
Doing sha1 for 3s on 16 size blocks: 19374573 sha1's in 3.00s
Doing sha1 for 3s on 64 size blocks: 13680091 sha1's in 3.00s
Doing sha1 for 3s on 256 size blocks: 7340622 sha1's in 3.00s
Doing sha1 for 3s on 1024 size blocks: 2575383 sha1's in 3.00s
Doing sha1 for 3s on 8192 size blocks: 364376 sha1's in 3.00s
Doing sha1 for 3s on 16384 size blocks: 183730 sha1's in 3.00s
OpenSSL 1.1.1f 31 Mar 2020
built on: Tue Oct 10 09:03:48 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 -fdebug-prefix-map=/build/openssl-R3RAvN/openssl-1.1.1f=. -fstack-protector-strong -Wformat -Werror=format-security -DOPENSSL_TLS_SECURITY_LEVEL=2 -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
sha1 103331.06k 291841.94k 626399.74k 879064.06k 994989.40k 1003410.77k
firefly@firefly:~$ openssl speed sha512
Doing sha512 for 3s on 16 size blocks: 4557225 sha512's in 3.00s
Doing sha512 for 3s on 64 size blocks: 4588415 sha512's in 3.00s
Doing sha512 for 3s on 256 size blocks: 1768218 sha512's in 3.00s
Doing sha512 for 3s on 1024 size blocks: 625711 sha512's in 3.00s
Doing sha512 for 3s on 8192 size blocks: 89221 sha512's in 3.00s
Doing sha512 for 3s on 16384 size blocks: 44840 sha512's in 3.00s
OpenSSL 1.1.1f 31 Mar 2020
built on: Tue Oct 10 09:03:48 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 -fdebug-prefix-map=/build/openssl-R3RAvN/openssl-1.1.1f=. -fstack-protector-strong -Wformat -Werror=format-security -DOPENSSL_TLS_SECURITY_LEVEL=2 -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
sha512 24305.20k 97886.19k 150887.94k 213576.02k 243632.81k 244886.19k
RK3399测试结果
飞腾派大多时候都比RK3399要快一些，尤其是SHA512，但是SHA1则RK3399略胜一筹
举报
更多回帖
