原创 ARM嵌入式平台性能测试

By Toradex 秦海

在新项目需要选择一个全新的基于ARM嵌入式处理器平台的时候,难免会需要对新平台的性能进行评估,这时候有几种思路可以进行参考,一是ARM芯片厂家发布的性能指标,不过大多数是基于理论情况;二是购买同样平台的开发板移植应用进行实测,效果最直接但是可能需要花费较大精力和时间;那么这个时候也可以考虑使用针对性的benchmark软件在目标平台上面进行性能测试,算是一个折衷的方法,其结果有一定参考意义但由于影响benchmark软件结果的因素不仅仅是硬件本身,还有不同的BSP以及软件设定等,因此在这些设定一致性越大的前提下其结果的参考意义才越大,否则很可能结果不是预期想要的甚至南辕北辙.

 

基于上面思路,本文统一采用Toradex工业产品等级 ARM计算机模块以及其官方发布的最新版Linux BSPV2.5Beta3最为测试基准平台,同时将对结果影响比较大的CPU主频和显示输出分辨率尽可能保持一致来进行测试,测试样本分别是基于NVIDIA Tegra2的Colibri T20 512M, 基于NXP i.MX6DL 的Colibri i.MX6DL 512M以及基于NXP Vybrid的Colibri VF61 256M;其中前两个均为双核Cortex-A9 ARM核心,第三个为Cortex-A5和M4异构双核核心,不过这里只测试A5.

 

1). 本文涉及的硬件平台测试项目及工具如下

a). 硬件平台

上述三种接口兼容的Colibri ARM 计算机模块以及一块Colibri Eva Board

b). 测试项目及对应工具

- CPU测试: nbench

- Memory测试: stream

- Storage测试: dd, hdparm

- Ethernet测试: iperf

- CPU压力测试: stress

- GPU压力测试: glmark2

注:所涉及工具除glmark2均已经在BSP中预装.

 

2). 测试进程以及结果

a). 预设

参考这里为两个A9平台关闭DVFS(dynamic voltage and frequency switching), Colibri T20 CPU主频设定为1GHz, Colibri i.MX6DL CPU主频设定为800MHz, Colibri VF61不支持DVFS则无需设定;

显示分辨率所有平台均统一设置为默认值640x480.

b). CPU测试

进入/usr/bin运行下面命令

# nbench

 

- Colibri T20结果如下

=============LINUX DATA BELOW============= 

CPU                 : Dual                                                      

L2 Cache            :                                                          

OS                  : Linux 3.1.10-V2.5b3+gc8ead50                             

C compiler          : arm-angstrom-linux-gnueabi-gcc                            

libc                : static                                                   

MEMORY INDEX        : 5.042                                                    

INTEGER INDEX       : 5.245                                                     

FLOATING-POINT INDEX: 6.401                                                    

Baseline (LINUX)    : AMD K6/233*, 512 KB L2-cache, gcc 2.7.2.3, libc-5.4.38

--------------------------------------------------------------------------

 

- Colibri i.MX6DL 结果如下

==============LINUX DATA BELOW=========

CPU                 : Dual ARMv7 Processor rev 10 (v7l)                        

L2 Cache            :                                                          

OS                  : Linux 3.14.28-V2.5b3+g0632def                            

C compiler          : arm-angstrom-linux-gnueabi-gcc                           

libc                : static                                                   

MEMORY INDEX        : 4.028                                                    

INTEGER INDEX       : 4.177                                                    

FLOATING-POINT INDEX: 5.137                                                    

Baseline (LINUX)    : AMD K6/233*, 512 KB L2-cache, gcc 2.7.2.3, libc-5.4.38

----------------------------------------------------------------------------

 

Colibri VF61 结果如下

==============LINUX DATA BELOW=========

CPU                 : ARMv7 Processor rev 1 (v7l)                               

L2 Cache            :                                                          

OS                  : Linux 4.1.15-v2.5b3+ge6d111c                             

C compiler          : arm-angstrom-linux-gnueabi-gcc                           

libc                : static                                                   

MEMORY INDEX        : 1.896                                                    

INTEGER INDEX       : 2.337                                                    

FLOATING-POINT INDEX: 2.139                                                    

Baseline (LINUX)    : AMD K6/233*, 512 KB L2-cache, gcc 2.7.2.3, libc-5.4.38

---------------------------------------------------------------------

nbench结果为单个CPU性能,可以看出T20和i.MX6同为A9核心基本处于统一水平,T20因为主频略高要有一定优势,而VF61因为是A5核心同时主频低则相对要差一些.另外系统还内置了另一个CPU测试工具lmbench,这里就不详述了.

 

c). Memory测试

运行下面命令

# stream

 

- Colibri T20结果如下

==================================

STREAM copy latency: 33.38 nanoseconds                                         

STREAM copy bandwidth: 479.33 MB/sec                                           

STREAM scale latency: 35.58 nanoseconds                                        

STREAM scale bandwidth: 449.65 MB/sec                                          

STREAM add latency: 41.73 nanoseconds                                          

STREAM add bandwidth: 575.10 MB/sec                                            

STREAM triad latency: 42.90 nanoseconds                                        

STREAM triad bandwidth: 559.44 MB/sec

---------------------------------------------------------

 

- Colibri i.MX6DL 结果如下

=================================

STREAM copy latency: 18.33 nanoseconds     

STREAM copy bandwidth: 873.08 MB/sec                                            

STREAM scale latency: 23.45 nanoseconds                                        

STREAM scale bandwidth: 682.30 MB/sec                                          

STREAM add latency: 26.90 nanoseconds               

STREAM add bandwidth: 892.26 MB/sec              

STREAM triad latency: 25.58 nanoseconds   

STREAM triad bandwidth: 938.16 MB/sec 

------------------------------------------------------

- Colibri VF61 结果如下

=================================

STREAM copy latency: 30.53 nanoseconds                                         

STREAM copy bandwidth: 524.09 MB/sec   

STREAM scale latency: 30.78 nanoseconds   

STREAM scale bandwidth: 519.82 MB/sec   

STREAM add latency: 134.66 nanoseconds     

STREAM add bandwidth: 178.23 MB/sec 

STREAM triad latency: 149.24 nanoseconds   

STREAM triad bandwidth: 160.81 MB/sec

-----------------------------------------------------------

 

d). Storage测试

./ 由于T20和VF61直接使用了Nand Flash,无法使用hdparm测试,所以我们统一采用我们采用dd来测试模块自带flash存储.

运行下面命令

sync;time -p bash -c "(dd if=/dev/zero bs=1024 count=100000 of=/test.file;sync)"   //测试写速度

echo 3 > /proc/sys/vm/drop_caches ;time dd if=/test.file of=/dev/null bs=1024              //测试读速度

 

- Colibri T20结果如下

读取测试,约为14.7MB/sec

=======================

100000+0 records in 

100000+0 records out  

real    0m6.795s

user    0m0.030s

sys     0m1.830s

-----------------------------------------

写入测试,约为9MB/sec

========================

100000+0 records in

100000+0 records out 

real 11.08

user 0.01

sys 2.19         

-----------------------------------------

 

- Colibri i.MX6DL结果如下

读取测试,约为43.5MB/sec

========================

100000+0 records in 

100000+0 records out 

real    0m2.306s

user    0m0.020s   

sys     0m0.680s

--------------------------------------------

写入测试,约为10MB/sec

=========================

100000+0 records in

100000+0 records out 

real 10.07

user 0.09

sys 3.64

-------------------------------------------

 

- Colibri VF61 结果如下

读取测试,约为24MB/sec

========================

[ 1178.378483] sh (407): drop_caches: 3 

100000+0 records in 

100000+0 records out  

real    0m4.161s

user    0m0.100s 

sys     0m3.180s

------------------------------------------

写入测试,约为12.8MB/sec

========================

100000+0 records in 

100000+0 records out 

real 7.78 

user 0.13 

sys 3.85

-----------------------------------

 

./ 使用hdparm测试外部8G SD卡读取速度

运行下面命令

hdparm -t /dev/mmcblk1p1

 

- Colibri T20结果如下

====================

/dev/mmcblk0p1:                                                                

 Timing buffered disk reads:  52 MB in  3.02 seconds =  17.22 MB/sec

------------------------------------

 

- Colibri i.MX6DL 结果如下

====================

/dev/mmcblk1p1:                                                                

 Timing buffered disk reads:  56 MB in  3.09 seconds =  18.13 MB/sec

------------------------------------

 

- Colibri VF61 结果如下

=====================

/dev/mmcblk0p1:                                                                

 Timing buffered disk reads:  54 MB in  3.07 seconds =  17.60 MB/sec

-------------------------------------

 

e). Ethernet测试

将测试目标板和Linux主机连接到同一局域网,目标板为100M网口.

在Linux主机端运行下面命令(以TCP测试为例,也可以更改参数进行其他测试)

iperf -s

在目标板上面运行下面命令

iperf -c $hostip -t 60 -P 8

 

- Colibri T20结果如下

=========================

[SUM]  0.0-60.1 sec   676 MBytes  94.3 Mbits/sec

------------------------------------------

 

- Colibri i.MX6DL 结果如下

=======================

[SUM]  0.0-60.2 sec   677 MBytes  94.4 Mbits/sec

---------------------------------------

 

- Colibri VF61 结果如下

=======================

[SUM]  0.0-60.1 sec   674 MBytes  94.2 Mbits/sec

---------------------------------------

 

f). CPU压力测试

在三个平台上面分别运行下面命令

# stress -c 2

在另一终端中使用”top”命令查看CPU使用状态,两个CPU均已经满负荷

g). GPU压力测试

首先需要安装glmark2工具,这里通过Toradex openembedded环境编译出了相关的ipk安装包,具体环境配置可以参考这里, 这里以Colibri i.MX6平台为例.

安装流程

opkg install libpng12_1.2.51-r0_armv7at2hf-vfp-neon.ipk

opkg install glmark2_2014.03-r0_armv7at2hf-vfp-neon-mx6qdl.ipk

运行

glmark2-es2

=======================================================                        

    glmark2 2014.03   

=======================================================                        

    OpenGL Information 

    GL_VENDOR:     Vivante Corporation  

    GL_RENDERER:   Vivante GC880 

    GL_VERSION:    OpenGL ES 3.0 V5.0.11.p4.25762  

=======================================================                        

[build] use-vbo=false: FPS: 495 FrameTime: 2.020 ms 

[build] use-vbo=true: FPS: 908 FrameTime: 1.101 ms 

[texture] texture-filter=nearest: FPS: 702 FrameTime: 1.425 ms 

[texture] texture-filter=linear: FPS: 664 FrameTime: 1.506 ms                  

[texture] texture-filter=mipmap: FPS: 704 FrameTime: 1.420 ms   

[shading] shading=gouraud: FPS: 485 FrameTime: 2.062 ms    

[shading] shading=blinn-phong-inf: FPS: 248 FrameTime: 4.032 ms     

[shading] shading=phong: FPS: 151 FrameTime: 6.623 ms 

[shading] shading=cel: FPS: 114 FrameTime: 8.772 ms   

[bump] bump-render=high-poly: FPS: 159 FrameTime: 6.289 ms 

[bump] bump-render=normals: FPS: 426 FrameTime: 2.347 ms  

[bump] bump-render=height: FPS: 340 FrameTime: 2.941 ms                        

[effect2d] kernel=0,1,0;1,-4,1;0,1,0;: FPS: 104 FrameTime: 9.615 ms            

[effect2d] kernel=1,1,1,1,1;1,1,1,1,1;1,1,1,1,1;: FPS: 37 FrameTime: 27.027 ms 

[pulsar] light=false:quads=5:texture=false: FPS: 601 FrameTime: 1.664 ms       

[desktop] blur-radius=5:effect=blur:passes=1:separable=true:windows=4: FPS: 52 F

rameTime: 19.231 ms 

[desktop] effect=shadow:windows=4: FPS: 212 FrameTime: 4.717 ms

[buffer] columns=200:interleave=false:update-dispersion=0.9:update-fraction=0.5:

update-method=map: FPS: 52 FrameTime: 19.231 ms 

[buffer] columns=200:interleave=false:update-dispersion=0.9:update-fraction=0.5:

update-method=subdata: FPS: 51 FrameTime: 19.608 ms                            

[buffer] columns=200:interleave=true:update-dispersion=0.9:update-fraction=0.5:u

pdate-method=map: FPS: 62 FrameTime: 16.129 ms                                 

[ideas] speed=duration: FPS: 46 FrameTime: 21.739 ms                           

[jellyfish] <default>: FPS: 89 FrameTime: 11.236 ms                             

[terrain] <default>: FPS: 4 FrameTime: 250.000 ms                              

[shadow] <default>: FPS: 175 FrameTime: 5.714 ms                               

[refract] <default>: FPS: 27 FrameTime: 37.037 ms                               

[conditionals] fragment-steps=0:vertex-steps=0: FPS: 427 FrameTime: 2.342 ms   

[conditionals] fragment-steps=5:vertex-steps=0: FPS: 93 FrameTime: 10.753 ms   

[conditionals] fragment-steps=0:vertex-steps=5: FPS: 383 FrameTime: 2.611 ms   

[function] fragment-complexity=low:fragment-steps=5: FPS: 173 FrameTime: 5.780 m

s

[function] fragment-complexity=medium:fragment-steps=5: FPS: 51 FrameTime: 19.60

8 ms

[loop] fragment-loop=false:fragment-steps=5:vertex-steps=5: FPS: 156 FrameTime:

6.410 ms

[loop] fragment-steps=5:fragment-uniform=false:vertex-steps=5: FPS: 156 FrameTim

e: 6.410 ms 

[loop] fragment-steps=5:fragment-uniform=true:vertex-steps=5: FPS: 82 FrameTime:

 12.195 ms

=======================================================                        

                                  glmark2 Score: 255 

=======================================================