评测丨用数字带你综合体验海思3519A性能
2021年09月26日 17:19 发布者：哦哈哟
1. 1 OK3519 BSP整体测评OK3519A 采用Hi3519AV100，该芯片支持 H.265/H.264编解码，编码/解码性能高达4K*2K@60fps/1080p@240fps，集成了海思第四代ISP，支持WDR、多级降噪、六轴防抖及多种图像增强和矫正算法，内置高性能全景拼接引擎，集成了智能加速引擎包括IVE，DSP，NNIE，DPU，可进行图片分类，目标检测等。适用于适用于医疗，金融，防控等多个领域的计算机视觉。整理来说，OK3519A 视频编解码，视频输入方面的性能强大，集成了智能加速引擎，提供了高效且丰富的计算资源。海思提供了大量的库文件，应用可调用海思的库实现。飞凌优化了原厂BSP，移植了QT5.9.4，支持鼠标和触摸屏。目前QT显示功能与海思原生测试冲突，不能直接同时使用。如果希望同时使用，需从代码上去掉对MPI和VB的重复初始化。默认出厂程序HDMI显示，加载QT主界面，如下图：https://www.forlinx.com/file.php?f=202009/f_2c769a041581baab18b307edc53872f5&t=png&o=&s=&v=1601196153OK3519A 支持MIPI-DSI和HDMI屏幕接口，HDMI支持4K输出。2种方式切换屏幕：uboot菜单动态控制和烧写系统时环境变量指定。QT与命令行demo，均有测试例程，客户可参考，添加自己的应用。减少开发时间。1. 2 OK3519 A 接口功能简介
串口支持odd、even、mark、space校验，实测波特率可9600到1500000。网络支持SSH/SFTP/WEB服务。支持移远ec20 4G模块，华为ME909S 4G 模块。MIPI-DSI屏显示（1024x600分辨率ARGB1555输出显示，ft5x06和gt911触摸），支持背光调节。支持RX-RTC8010。音频支持2路AI输入，1路AO输出，支持HDMI音频输出，支持VQE。默认支持索尼的imx290和imx334。支持MIPI-CSI（OV5640）预览到HDMI上。https://www.forlinx.com/file.php?f=202009/f_f288f9766899a97bf19150b52c16ba3a&t=png&o=&s=&v=1601197062
支持PCIE接口（与USB3.0 共用资源，默认为USB3.0）。支持看门狗功能。支持SPI接口，一路片选。支持原厂MPP例程。支持SD卡烧写，支持ext4 烧写，速度快。多种启动方式：SPI NAND flash（支持yaffs文件系统，24位ECC）、eMMC启动（ext4文件系统）。1.3 OK3519 性能测试1.3. 1. USB2.0 读写速度测试存储设备不同，测试结果存在差异。写入测试：$dd if=/dev/zero of=/run/media/sda1/test bs=1M count=500 conv=fsynchttps://www.forlinx.com/file.php?f=202009/f_42c49b324aadf2baf33b52e64235ba93&t=png&o=&s=&v=1601197077
读取测试：$dd if=/run/media/sda1/test of=/dev/null bs=1Mhttps://www.forlinx.com/file.php?f=202009/f_25c04bff7cfe49ccbf41bfd586bca4cc&t=png&o=&s=&v=1601197088
1.3.2 USB3.0 读写速度测试存储设备不同，测试结果存在差异。写入测试：$dd if=/dev/zero of=/run/media/sda1/test bs=1M count=500 conv=fsynchttps://www.forlinx.com/file.php?f=202009/f_ec90fd1b95ee78f0fe0f23797125039a&t=png&o=&s=&v=1601197096
读取测试：$dd if=/run/media/sda1/test of=/dev/null bs=1Mhttps://www.forlinx.com/file.php?f=202009/f_27982592aaa58f40cebe04bb976cac8b&t=png&o=&s=&v=1601197103
1.3.3 SD卡读写测试SD卡支持Default Speed(DS)/High Speed(HS) /ddr50 /SDR12 /SDR25 /SDR50 /SDR104模式。实测工作在SDR50时的读写速度。https://www.forlinx.com/file.php?f=202009/f_e50d5ba8ad04a3ef29426f33e80c4451&t=png&o=&s=&v=1601197111
写入测试：$dd if=/dev/zero of=/run/media/mmcblk1/test bs=1M count=500 conv=fsynchttps://www.forlinx.com/file.php?f=202009/f_39772fb796011f82f2474a6b876b0ed1&t=png&o=&s=&v=1601197119
读取测试：$dd if=/run/media/mmcblk1/test of=/dev/null bs=1Mhttps://www.forlinx.com/file.php?f=202009/f_6735015512b5283ae88227c7f7a1d8e4&t=png&o=&s=&v=1601197127
1.3.4 eMMC读写测试eMMC采用HS400模式，以读写ext4文件系统速度为例，如下：写入测试：$ dd if=/dev/zero of=/test bs=1M count=100 conv=fsynchttps://www.forlinx.com/file.php?f=202009/f_94c17bc7b38a4581e4d721699c829cc4&t=png&o=&s=&v=1601197139
读取测试：$dd if=/test of=/dev/null bs=1Mhttps://www.forlinx.com/file.php?f=202009/f_68036ce6e18f89efa19c5a4b77b69ffa&t=png&o=&s=&v=16011971461.3.5 有线网络吞吐量测试组网环境如下：https://www.forlinx.com/file.php?f=202009/f_5d056819583d20d48f08c8a73e59841b&t=png&o=&s=&v=1601197154
TCP发送吞吐量测试：PC机做服务器：ipeRF3.ext -sOK3519上测试：iperf3 -c 192.168.2.72 -t 10 -i 1Connecting to host 192.168.2.72, port 5201[ 4] local 192.168.2.147 port 35524 connected to 192.168.2.72 port 5201[ ID] Interval Transfer Bandwidth Retr Cwnd[ 4] 0.00-1.00 sec 108 MBytes 908 Mbits/sec 12 191 KBytes[ 4] 1.00-2.00 sec 112 MBytes 941 Mbits/sec 4 154 KBytes[ 4] 2.00-3.00 sec 112 MBytes 941 Mbits/sec 1 218 KBytes[ 4] 3.00-4.00 sec 110 MBytes 925 Mbits/sec 7 211 KBytes[ 4] 4.00-5.00 sec 112 MBytes 939 Mbits/sec 4 164 KBytes[ 4] 5.00-6.01 sec 112 MBytes 932 Mbits/sec 4 215 KBytes[ 4] 6.01-7.00 sec 112 MBytes 942 Mbits/sec 0 215 KBytes[ 4] 7.00-8.01 sec 113 MBytes 941 Mbits/sec 1 225 KBytes[ 4] 8.01-9.00 sec 112 MBytes 939 Mbits/sec 2 238 KBytes[ 4] 9.00-10.00 sec 112 MBytes 941 Mbits/sec 1 211 KBytes- - - - - - - - - - - - - - - - - - - - - - - - -[ ID] Interval Transfer Bandwidth Retr[ 4] 0.00-10.00 sec 1.09 GBytes 935 Mbits/sec 36 sender[ 4] 0.00-10.00 sec 1.09 GBytes 933 Mbits/sec receiver
iperf Done.TCP接收与UDP发送接收，其他测试方法类似。1.3.6 Coremark 跑分2K performance run parameters for coremark.CoreMark Size : 666Total ticks : 18799Total time (secs): 18.799000Iterations/Sec : 5851.375073Iterations : 110000Compiler version : GCC6.3.0Compiler flags : -O3 -funroll-all-loops --param max-inline-insns-auto=550 -DPERFORMANCE_RUN=1 -lrtMemory location : Please put data memory location here(e.g. code in flash, data on heap etc)seedcrc : 0xe9f5crclist : 0xe714crcmatrix : 0x1fd7crcstate : 0x8e3acrcfinal : 0x33ffCorrect operation validated. See README.md for run and reporting rules.CoreMark 1.0 : 5851.375073 / GCC6.3.0 -O3 -funroll-all-loops --param max-inline-insns-auto=550 -DPERFORMANCE_RUN=1 -lrt / Heap1.3.7 Dhrystone测试/run/media/mmcblk1p1 # echo 50000000 | ./dhrystoneDhrystone Benchmark, Version 2.1 (Language: C)Please give the number of runs through the benchmark:Execution starts, 50000000 runs through DhrystoneExecution endsFinal values of the variables used in the benchmark:Int_Glob: 5 should be: 5Bool_Glob: 1 should be: 1Ch_1_Glob: A should be: ACh_2_Glob: B should be: BArr_1_Glob: 7 should be: 7Arr_2_Glob: 50000010 should be: Number_Of_Runs + 10Ptr_Glob-> Ptr_Comp: 648336 should be: (implementation-dependent) Discr: 0 should be: 0 Enum_Comp: 2 should be: 2 Int_Comp: 17 should be: 17 Str_Comp: DHRYSTONE PROGRAM, SOME STRING should be: DHRYSTONE PROGRAM, SOME STRINGNext_Ptr_Glob-> Ptr_Comp: 648336 should be: (implementation-dependent), same as above Discr: 0 should be: 0 Enum_Comp: 1 should be: 1 Int_Comp: 18 should be: 18 Str_Comp: DHRYSTONE PROGRAM, SOME STRING should be: DHRYSTONE PROGRAM, SOME STRINGInt_1_Loc: 5 should be: 5Int_2_Loc: 13 should be: 13Int_3_Loc: 7 should be: 7Enum_Loc: 1 should be: 1Str_1_Loc: DHRYSTONE PROGRAM, 1'ST STRING should be: DHRYSTONE PROGRAM, 1'ST STRINGStr_2_Loc: DHRYSTONE PROGRAM, 2'ND STRING should be: DHRYSTONE PROGRAM, 2'ND STRING
Register option selected? YESmicroseconds for one run through Dhrystone: 0.2Dhrystones per Second: 4989727.1VAX MIPS rating = 2839.913原文链接：https://www.forlinx.com/article_view_519.html