https://elinux.org/api.php?action=feedcontributions&user=Aradke&feedformat=atom
eLinux.org - User contributions [en]
2024-03-19T06:41:44Z
User contributions
MediaWiki 1.31.0
https://elinux.org/index.php?title=RPi_Performance&diff=156152
RPi Performance
2012-07-29T06:53:46Z
<p>Aradke: /* Results */</p>
<hr />
<div>{{Template:RPi_Software}}<br />
<br />
<br />
=CPU=<br />
==Linpack==<br />
<br />
The Arm has been tested using the linpack benchmark from [http://www.netlib.org/benchmark/linpackc.new], built with gcc with -O3 (Optimisation level 3). Run with array size 200.<br />
<br />
With software floating point<br />
<br />
===Source===<br />
[http://www.netlib.org/benchmark/linpackc.new]<br />
<br />
===Compile/Run===<br />
<pre><br />
cc -O3 -o linpack linpack.c -lm<br />
linpack.c: In function ‘main’:<br />
linpack.c:69: warning: return type of ‘main’ is not ‘int’<br />
./linpack<br />
Enter array size (q to quit) [200]: 200<br />
</pre><br />
<br />
<br />
===Results===<br />
Crippled<br />
<pre><br />
Memory required: 315K.<br />
<br />
LINPACK benchmark, Double precision.<br />
Machine precision: 15 digits.<br />
Array size 200 X 200.<br />
Average rolled and unrolled performance:<br />
<br />
Reps Time(s) DGEFA DGESL OVERHEAD KFLOPS<br />
2 0.53 92.45% 1.89% 5.66% 5493.333<br />
4 1.07 92.52% 2.80% 4.67% 5385.621<br />
8 2.12 92.45% 2.36% 5.19% 5466.003<br />
16 4.24 92.45% 2.83% 4.72% 5438.944<br />
32 8.49 92.11% 2.71% 5.18% 5459.213<br />
64 16.98 92.05% 2.89% 5.06% 5452.440<br />
</pre><br />
<br />
Hardware floating point (-mfloat-abi=softfp)<br />
<pre><br />
Memory required: 315K.<br />
LINPACK benchmark, Double precision.<br />
Machine precision: 15 digits.<br />
Array size 200 X 200.<br />
Average rolled and unrolled performance:<br />
<br />
Reps Time(s) DGEFA DGESL OVERHEAD KFLOPS<br />
8 0.51 90.20% 3.92% 5.88% 22888.889<br />
16 1.02 89.22% 4.90% 5.88% 22888.889<br />
32 2.05 90.24% 3.41% 6.34% 22888.889<br />
64 4.08 91.42% 2.94% 5.64% 22829.437<br />
128 8.16 91.54% 2.94% 5.51% 22799.827<br />
256 16.31 91.35% 2.76% 5.89% 22903.800<br />
</pre><br />
<br />
Full hardware floating point on Raspbian (-mfloat-abi=hard -mfpu=vfp) and arm_freq=700<br />
<pre><br />
Memory required: 315K.<br />
LINPACK benchmark, Double precision.<br />
Machine precision: 15 digits.<br />
Array size 200 X 200.<br />
Average rolled and unrolled performance:<br />
<br />
Reps Time(s) DGEFA DGESL OVERHEAD KFLOPS<br />
16 0.58 89.66% 3.45% 6.90% 40691.358<br />
32 1.17 87.18% 4.27% 8.55% 41071.651<br />
64 2.32 88.36% 3.02% 8.62% 41459.119<br />
128 4.67 88.22% 3.43% 8.35% 41071.651<br />
256 9.33 88.85% 3.32% 7.82% 40880.620<br />
512 18.63 89.00% 2.95% 8.05% 41047.675<br />
</pre><br />
<br />
Full hardware floating point on Raspbian (-mfloat-abi=hard -mfpu=vfp) and arm_freq=1000 and core_freq=500<br />
<pre><br />
Memory required: 315K.<br />
LINPACK benchmark, Double precision.<br />
Machine precision: 15 digits.<br />
Array size 200 X 200.<br />
Average rolled and unrolled performance:<br />
<br />
Reps Time(s) DGEFA DGESL OVERHEAD KFLOPS<br />
32 0.79 89.87% 0.00% 10.13% 61896.714<br />
64 1.58 89.24% 1.27% 9.49% 61463.869<br />
128 3.16 90.19% 1.90% 7.91% 60407.789<br />
256 6.32 88.13% 3.80% 8.07% 60511.761<br />
512 12.65 87.83% 3.56% 8.62% 60825.836<br />
<br />
</pre><br />
<br />
==Whetstone/Dhrystone==<br />
<br />
All code compiled with gcc options -float-abi=softfp -O3<br />
<br />
===Source===<br />
Code for these tests can be found here http://www.rowley.co.uk/arm/whet_dhry.zip. <br />
Or if 404 this code might be analogous http://freespace.virgin.net/roy.longbottom/benchnt.zip<br />
<br />
<br />
===Compile/Run===<br />
<pre><br />
?<br />
</pre><br />
<br />
<br />
===Results===<br />
Dhrystone<br />
<pre><br />
Microseconds for one run through Dhrystone: 1.2<br />
<br />
Dhrystones per Second: 809061.5 <br />
</pre><br />
<br />
<br />
Whetstone Crippled <br />
<pre><br />
Loops: 1000, Iterations: 10, Duration: 24 sec.<br />
<br />
C Converted Double Precision Whetstones: 41.7 MIPS<br />
</pre><br />
<br />
Rebuilding the Whetstone test code with 'gcc -mfpu -float-abi=softfp' gives better results:<br />
<pre><br />
<br />
Loops: 1000, Iterations: 100, Duration: 106 sec.<br />
C Converted Double Precision Whetstones: 94.3 MIPS<br />
</pre><br />
<br />
However, the majority of compute time is spent in the SQRT function, which for the above test was built without -mfpu=vfp. Using a library with vfp give the following much improved result :<br />
<pre><br />
Loops: 1000, Iterations: 100, Duration: 15 sec.<br />
C Converted Double Precision Whetstones: 666.7 MIPS<br />
</pre><br />
<br />
==OpenSSL==<br />
<br />
===Source===<br />
[http://www.openssl.org/source/]<br />
<br />
===Compile/Run===<br />
<pre><br />
openssl version;<br />
openssl speed;<br />
</pre><br />
<br />
===Results===<br />
<pre><br />
OpenSSL 0.9.8o 01 Jun 2010<br />
built on: Thu Aug 26 18:56:26 UTC 2010<br />
options:bn(64,32) md2(int) rc4(ptr,int) des(idx,risc1,4,long) aes(partial) blowfish(idx)<br />
compiler: gcc -fPIC -DOPENSSL_PIC -DZLIB -DOPENSSL_THREADS -D_REENTRANT -DDSO_DLFCN -DHAVE_DLFCN_H -DL_ENDIAN -DTERMIO -O2 -Wa,--noexecstack -g -Wall<br />
available timing options: TIMES TIMEB HZ=100 [sysconf value]<br />
timing function used: times<br />
The 'numbers' are in 1000s of bytes per second processed.<br />
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes<br />
md2 148.81k 372.18k 624.81k 769.95k 832.90k<br />
mdc2 0.00 0.00 0.00 0.00 0.00<br />
md4 615.30k 2468.76k 7612.19k 16707.01k 28104.86k<br />
md5 380.13k 1501.12k 4800.77k 11312.81k 21682.77k<br />
hmac(md5) 1022.28k 3480.23k 9587.80k 17492.25k 25441.78k<br />
sha1 303.72k 1092.39k 3106.50k 6302.57k 9852.39k<br />
rmd160 244.29k 849.04k 2414.53k 4747.26k 7513.00k<br />
rc4 14658.70k 16836.49k 17462.03k 17628.21k 17522.08k<br />
des cbc 2913.17k 3221.30k 3289.77k 3360.09k 3367.21k<br />
des ede3 1149.87k 1188.59k 1198.46k 1206.00k 1208.25k<br />
idea cbc 0.00 0.00 0.00 0.00 0.00<br />
seed cbc 0.00 0.00 0.00 0.00 0.00<br />
rc2 cbc 2812.71k 3012.02k 3054.19k 3077.82k 3076.12k<br />
rc5-32/12 cbc 0.00 0.00 0.00 0.00 0.00<br />
blowfish cbc 6091.32k 7007.89k 7250.62k 7288.21k 7163.88k<br />
cast cbc 5068.25k 6020.03k 6345.71k 6367.64k 6260.44k<br />
aes-128 cbc 3205.76k 3497.72k 3616.00k 3652.49k 3665.85k<br />
aes-192 cbc 2730.65k 2981.88k 3073.20k 3102.38k 3111.86k<br />
aes-256 cbc 2383.90k 2596.12k 2659.91k 2702.13k 2732.50k<br />
camellia-128 cbc 0.00 0.00 0.00 0.00 0.00<br />
camellia-192 cbc 0.00 0.00 0.00 0.00 0.00<br />
camellia-256 cbc 0.00 0.00 0.00 0.00 0.00<br />
sha256 679.98k 1629.47k 2905.43k 3708.32k 4175.45k<br />
sha512 41.02k 163.83k 232.63k 318.20k 353.81k<br />
aes-128 ige 3089.03k 3579.08k 3698.68k 3689.14k 3578.18k<br />
aes-192 ige 2641.68k 3019.45k 3111.38k 3144.95k 3035.70k<br />
aes-256 ige 2334.50k 2632.35k 2705.04k 2735.69k 2687.74k<br />
sign verify sign/s verify/s<br />
rsa 512 bits 0.013747s 0.001193s 72.7 838.4<br />
rsa 1024 bits 0.063481s 0.002742s 15.8 364.7<br />
rsa 2048 bits 0.321250s 0.007378s 3.1 135.5<br />
rsa 4096 bits 1.805000s 0.022528s 0.6 44.4<br />
sign verify sign/s verify/s<br />
dsa 512 bits 0.011690s 0.013597s 85.5 73.5<br />
dsa 1024 bits 0.027233s 0.031683s 36.7 31.6<br />
dsa 2048 bits 0.073897s 0.087304s 13.5 11.5<br />
</pre><br />
<br />
=GPU=<br />
The RaspberryPi appears to handle h264 1080p movie from USB to HDMI at least 4MB/s.<br />
<br />
The Admin "JamesH" said it would handle "basically 1080p30, high profile, >40Mb/s." (5MB/s) in h264<br />
<br />
And about WVGA(480p30) or 720p20 in VP8/WEBM<br />
<br />
<br />
<br />
==ioquake3==<br />
<br />
===Source===<br />
https://github.com/raspberrypi/quake3<br />
<br />
===Compile/Run===<br />
- Download source, compile as delivered<br />
- Start game<br />
- Runs at display's native res, in my case 1280x1024<br />
- Bitdepth stuck at 16bpp, not sure how to change, values in q3config.cfg seem to be ignored<br />
- In-game console commands:<br />
\timedemo 1<br />
\demo four<br />
<br />
===Results===<br />
armel "driver info" : http://i.imgur.com/wtYhB.jpg<br />
armel timedemo score: http://i.imgur.com/i2TkN.jpg<br />
20.2fps<br />
<br />
armhf "driver info" : http://i.imgur.com/8nqa1.jpg<br />
armhf timedemo score: http://i.imgur.com/dUu0g.jpg<br />
28.5fps<br />
<br />
<br />
[[Category: RaspberryPi]]<br />
<br />
=IO=<br />
<br />
==USB bus==<br />
*All IO uses the same bus so the combination of all IO can not exceed the the bus speed of an as yet hypothetical 60MB/s<br />
*A test with a fast USB-Stick showed that Raspberry Pi can achieve about 30 MB/s:<br />
<pre>root@raspberrypi:~# dd if=/dev/sda of=/dev/null bs=32M count=10 iflag=direct<br />
10+0 records in<br />
10+0 records out<br />
335544320 bytes (336 MB) copied, 10.6428 s, 31.5 MB/s<br />
</pre><br />
<br />
==SD card==<br />
*TODO test<br />
<br />
'''Note: the dd test should probably use i/oflags=direct for reads and writes. But that will change the results recorded to date'''<br />
===Compile/Run===<br />
<pre><br />
# write<br />
dd if=/dev/zero of=~/test.tmp bs=500K count=1024 <br />
# read<br />
dd if=~/test.tmp of=/dev/null bs=500K count=1024 <br />
# cleanup<br />
rm ~/test.tmp<br />
# find out which kernel you're running<br />
uname -a<br />
</pre><br />
<br />
===Results===<br />
* Depends on SD card used http://elinux.org/RaspberryPiBoardVerifiedPeripherals#SD_cards<br />
<br />
{| border="1" class="sortable"<br />
! SD Card !! Read (MB/s) !! Write (MB/s) !! class="unsortable" | Distro !! class="unsortable" | Kernel !! class="unsortable" | Notes<br />
|-<br />
| ADATA 32GB SDHC Class 10 (ASDH32GCL10-R) || 20.1 || 6.4 || 2012-06-18-wheezy-beta || Linux raspberrypi 3.1.9+ #152 PREEMPT Fri Jul 6 18:47:16 BST 2012 armv6l GNU/Linux ||<br />
|-<br />
| Extrememory SDHC 16GB class 10 || 4.7 || 4.5 || Debian Wheezy "Raspbian" || Linux raspbian 3.1.9+ #52 ||<br />
|-<br />
| Extrememory SDHC 16GB class 10 || 11.3 || 5.4 || Debian Wheezy "Raspbian" || Linux raspbian 3.1.9+ #101 || init_emmc_clock=200000000 in config.txt<br />
|-<br />
| Extrememory SDHC 16GB class 10 || 18.2 || 6.3 || Debian Wheezy "Raspbian" || Linux raspbian 3.1.9+ custom || kernel and firmware as of 17.06.2012, no extra option in config.txt<br />
|-<br />
| Extrememory SDHC 16GB class 10 <br/>(man:0x000012 oem:0x3456 name:F0F0F hwrev:0x1 fwrev:0x0) || 16.9 || 10.7 || archlinuxarm-13-06-2012 || Linux alarmpi 3.1.9-25-ARCH+ #1 PREEMPT || <br />
|-<br />
| Extrememory SDHC 32GB class 10 <br/>(man:0x000003 oem:0x5344 name:SMI hwrev:0x1 fwrev:0x0) || 18.7 || 16.5 || archlinuxarm-13-06-2012 || Linux alarmpi 3.1.9-25-ARCH+ #1 PREEMPT || <br />
|-<br />
| Fugi SDHC 32GB class 10 (P10NM00580A) || 12.7 || 19.8 || Debian Wheezy Raspbian || Linux raspbian 3.1.9+ #168 || man:0x000073 oem:0x4247 name:NCard hwrev:0x1 fwrev:0x0 ||<br />
|-<br />
| Integral SDHC 16GB class 10 ||17.7 || 19.6 || Debian Wheezy Raspbian || Linux raspbian 3.1.9+ #168 ||<br />
|-<br />
| Kingston SDHC 4GB class 4 ||4.5 ||4.1 ||Debian Squeeze "debian6-19-04-2012" ||Linux raspberrypi 3.1.9+ #52 Tue May 8 23:49:32 BST 2012 ||<br />
|-<br />
|Kingston SDHC 4GB class 4 ||4.2 ||2.5 ||archlinuxarm-19-04-2012 ||Linux alarmpi 3.1.9-13+ #6 Thu May 10 00:48:37 UTC 2012 ||Identical card to one above. One to look into, as I was expecting Arch to be faster...<br />
|-<br />
|Kingston uSDHC 4GB class 4 ||4.0 ||3.8 ||Debian Squeeze ||Linux 3.1.9+ #90 ||<br />
|-<br />
|Kingston uSDHC 8GB class 4 (SDC4/8GB) ||4.7 ||3.7 ||archlinuxarm-29-04-2012 ||Linux alarmpi 3.1.9+ #66 Thu May 17 16:56:20 BST 2012 ||[http://dl.dropbox.com/u/268147/rpi/Kingston_uSD_8GB_CDM_Bench.zip CrystalDiskMark results (FAT32)] This is my only card that can be counted on to boot up on each plug-in.<br />
|-<br />
|Kingston SDHC 8GB class 4 (SD4/8GB) ||4.6 ||3.0 ||archlinuxarm-29-04-2012 ||Linux alarmpi 3.1.9+ #66 Thu May 17 16:56:20 BST 2012 ||[http://dl.dropbox.com/u/268147/rpi/Kingston_SD4-8GB_CDM_Bench.zip CrystalDiskMark results (FAT32)]<br />
|-<br />
|Kingston SDHC 8GB class 4 (SD4/8GB) ||13.2 ||3.4 || Hexxeh Raspbian r3 ||Linux raspbian 3.1.9+ #202 PREEMPT Wed Jul 25 22:11:06 BST 2012 armv6l GNU/Linux || man:0x000002 oem:0x544d name:SA08G hwrev:0x1 fwrev:0x0<br />
|-<br />
|Kingston SDHC 32GB class 10 ||10.8 ||8.1 ||Fedora 17 ARM snapshot 07 May 2012 ||Linux fedora-arm 3.1.9 #1 ||mmc0: note - long write sync 1453000ns - 14608 its. - kernel/module problems?<br />
|-<br />
|Kingston SDHC 32GB class 10 ||4.7 ||4.1 ||Fedora 17 ARM nightly snapshot ||Linux fedora-arm 3.1.9+ #101 PREEMPT Mon Jun 4 17:19:44 BST 2012 ||custom kernel from raspberrypi github - no more mmc0 sync problems<br />
|-<br />
|Kingston SDHC 32GB class 10 ||4.6 ||3.5 ||Debian Squeeze "debian6-19-04-2012" ||Linux raspberrypi 3.1.9+ #90 ||<br />
|-<br />
|Panasonic SDHC 8GB class 6 ||4.8 ||4.4 || || ||<br />
|-<br />
|Panasonic SDHC 8GB class 4 ||11.1 || 9.7 || Debian Wheezy "Rasbpian" || Linux rpi 3.1.9+ #168 PREEMPT Sat Jul 14 18:56:31 BST 2012 armv6l GNU/Linux ||<br />
|-<br />
|Patriot microSDHC 16GB Class 10 (PSF16GMSHC10) ||9.5 ||5.2 ||Fedora 14 ||Linux raspi 3.1.9+ #101 ||init_emmc_clock=200000000 in config.txt<br />
|-<br />
|Samsung SDHC 16GB Class 10 (MB-SPAGA) ||10.7 ||8.8 ||Fedora 17 ARM snapshot 07 May 2012 - GUI release ||Linux fedora-arm 3.1.9 #1 ||Had "long write sync" errors, slow boot times and then system instability using USB port on Macbook, switched to iPhone charger (5V 1A) and warning disappeared<br />
|-<br />
|Samsung SDHC 16GB Class 10 (MB-SPAGA) ||19.6 ||18.7 || Debian Wheezy "Raspbian" ||Linux raspberrypi 3.1.9+ #168 PREEMPT Sat Jul 14 18:56:31 BST 2012 armvl GNU/Linux ||(Same user / card as above, definitely notable that Raspbian is superior)<br />
|-<br />
|Samsung microSDHC 16GB Class 10 (MB-MPAGA/US) || 19.8 || 15.8 || Debian Wheezy "Raspbian" || Linux pisces 3.1.9+ #155 PREEMPT Mon Jul 9 12:49:19 BST 2012 armv6l GNU/Linux || -<br />
|-<br />
|Samsung microSDHC 16GB Class 4 (MB-MS4GA/US) || 19.2 || 5.5 || Debian Wheezy "Raspbian" || ? || -<br />
|-<br />
|SanDisk microSD 2GB ||4.7 ||4.2 ||archlinuxarm-29-04-2012 ||Linux alarmpi 3.1.9+ #66 Thu May 17 16:56:20 BST 2012 ||[http://dl.dropbox.com/u/268147/rpi/SanDisk_2GB_uSD_CDM_Bench.zip CrystalDiskMark results (FAT32)] Card has no serial/is likely a fake.<br />
|-<br />
|SanDisk Ultra SDHC 4GB class 4 ||4.7 ||4.4 ||Raspbian Wheezy || Linux raspberry-pi 3.1.9+ #1 PREEMPT Wed Jun 6 16:26:14 CEST 2012 armv6l GNU/Linux || man:0x000003 oem:0x5344 name:SD04G hwrev:0x8 fwrev:0x0 ||<br />
|-<br />
|SanDisk SDHC 8GB class 4 ||11.1 ||5.6 ||Raspbian Wheezy || Linux raspberrypi 3.1.9+ #202 PREEMPT || After Hexxeh rpi-update. <br />man:0x000003 oem:0x5344 name:SD08G hwrev:0x8 fwrev:0x0<br />
|-<br />
|SanDisk SDHC 8GB class 4 ||4.7 ||3.2 ||Debian Squeeze || ||<br />
|-<br />
|SanDisk Ultra SDHC I 8GB class 6 "30MB/s*" ||19.5 || 7.6 ||archlinuxarm || 3.1.9-22-ARCH+ #1 PREEMPT Sun Jun 17 13:54:30 UTC 2012 || "mmc0: error -84 whilst initialising SD card" at bootup, but works fine<br />
|-<br />
|SanDisk Ultra SDHC I 8GB class 10 "30MB/s*" ||19.3 || 3.2 ||Raspbian Wheezy || 3.1.9+ #168 PREEMPT Sat Jul 14 18:56:31 BST 2012 ||<br />
|-<br />
|SanDisk Ultra SDHC II 16GB class 2 "15MB/s*" ||16.7 || 16.2 || Raspbian Wheezy || 3.1.9+ #168 PREEMPT Sat Jul 14 18:56:31 BST 2012 || man:0x000003 oem:0x5344 name:SD16G hwrev:0x8 fwrev:0x0<br />
|-<br />
|SanDisk Ultra SDHC 16GB class 10 UHS-1 "30Mb/s" (SDSDU-016G-U46) ||20.9 ||18.1 ||Raspbian Wheezy || Linux raspberrypi 3.1.9+ #202 PREEMPT || After Hexxeh rpi-update. <br />man:0x000003 oem:0x5344 name:SU16G hwrev:0x8 fwrev:0x0<br />
|-<br />
|SanDisk Extreme SDHC I 8GB class 10 "30MB/s" || 17.7 || 19.7 || Archlinuxarm 2012-06-13 || Linux raspi 3.1.9-28-ARCH+ #1 PREEMPT Fri Jul 6 23:07:26 UTC 2012 armv6l GNU/Linux ||<br />
|-<br />
|SanDisk SDHC 32GB class 6 ||4.6 ||4.8 || || ||<br />
|-<br />
|SanDisk uSDXC 64GB class 6 ||4.9 ||3.8 ||archlinuxarm-29-04-2012 ||Linux alarmpi 3.1.9+ #66 Thu May 17 16:56:20 BST 2012 ||[http://dl.dropbox.com/u/268147/rpi/SanDisk_64GB_uSDXC_CDM_Bench.zip CrystalDiskMark results (FAT32)]<br />
|-<br />
|TDK microSDHC 4GB, Class 4 (80-56-10301-004G) ||11.2 ||4.7 ||Debian Wheezy "Raspbian" (2012-07-15) ||3.1.9+ #168 PREEMPT Sat Jul 14 18:56:31 BST 2012 ||<br />
|-<br />
|Transcend SDHC 8GB class 6 ||5.8 ||5.8 || || || |<br />
|-<br />
|Transcend SDHC 8GB Class 6 (TS8GSDHC6) ||4.6 ||4.0 ||Debian Squeeze "debian6-19-04-2012" ||Linux raspberrypi 3.1.9+ #90 Wed Apr 18 18:23:05 BST 2012 armv61 GNU/Linux ||Tested with dd. Card doesn't maintain the promised minimum class speed.<br />
|-<br />
|Transcend SDHC 8GB Class 4 (TS8GSDHC4) ||11.1 ||8.1 ||Debian Wheezy "Rasbpian" ||Linux raspberrypi 3.1.9+ #168 PREEMPT Sat Jul 14 18:56:31 BST 2012 armv6l GNU/Linux ||man:0x000003 oem:0x5344 name:SD08G hwrev:0x8 fwrev:0x0<br />
|-<br />
|Transcend microSDHC 8GB Kit, Class 4 (TS8GUSDHC4)||4.7 ||3.7 ||Raspbian Wheezy || Linux raspberry-pi 3.1.9+ #1 PREEMPT Wed Jun 6 16:26:14 CEST 2012 armv6l GNU/Linux || man:0x000003 oem:0x5344 name:SU08G hwrev:0x8 fwrev:0x0 ||<br />
|-<br />
|Transcend SDHC 4GB Class 6 ||9.8 ||8.8 ||Fedora Remix FC14 ||Linux raspi 3.1.9 #1 PREEMPT Sat Mar 3 21:58:00 UTC 2012 armv6l armv6l armv6l GNU/Linux ||Not sure why this setup is faster than others, test results repeatable.<br />
|-<br />
|Transcend SDHC 16GB Class 10 ||20.3 ||11.9 ||Debian Wheezy "Rasbpian" || Linux raspberry-pi 3.1.9-cutdown+ #173 ||<br />
|-<br />
|Sandisk Extreme Pro SDHC 16GB Class 10 UHS-I (SDSDXPA-016G-A75) ||4.7 ||4.8 ||debian6-19-04-2012 ||Linux Raspi 3.1.9+ #66 Thu May 17 16:56:20 BST 2012 || Followed [http://www.element14.com/community/message/51493?tstart=0#51493 a forum post] to install newest kernel from git repo.<br />
|-<br />
|SanDisk Extreme Pro SDHC 16GB Class 10||20.8||18.6||Debian Wheezy "Raspbian"||Linux raspberrypi 3.1.9+ #125 PREEMPT Sun Jun 17 16:09:36 BST 2012 armv6l GNU/Linux||<br />
|-<br />
|Sandisk Ultra SDHC I Class 6 ("30MB/s") ||4.7 ||4.8 ||Debian Wheezy "Raspbian" ||3.2.18+ #3 PREEMPT ||Feels faster than my Kingston 4GB Class 4 card.<br />
|-<br />
|WINTEC FileMate Professional SDHC 16GB Class 10 (3FMSD16GBC10-R) ||4.6 ||4.5 ||Debian Squeeze "debian6-19-04-2012" ||Linux raspberrypi 3.1.9+ #95 PREEMPT Thu May 31 13:21:40 BST 2012 armv6l GNU/Linux ||After installing new kernel with rpi-update on 2012-06-01<br />
|-<br />
|Lexar SDHC 8GB Class 4 "Multi-use" ||18.9 ||6.8 ||Debian Wheezy "Raspbian" ||3.1.9+ #110 PREEMPT || <br />
|-<br />
|Lexar SDHC 8GB Class 6 "PLATINUM II" ||19.7 ||10.1 ||Debian Wheezy "Raspbian" || 3.1.9+ #168 PREEMPT || <br />
|-<br />
|Lexar SDHC 16GB Class 10 "PLATINUM II" ||5.3 ||4.8 ||Debian Wheezy/sid || Linux raspberrypi 3.2.19-rpi1+ #3 || <br />
|-<br />
|Lexar SDHC 16GB Class 10 "PLATINUM II" ||18.9 ||9.0 ||Debian Wheezy "Raspbian" || Linux raspbian 3.1.9+ #168 PREEMPT || Same card as 'Lexar SDHC 16GB Class 10 "PLATINUM II"' above - imaged with Raspbian<br />
|<br />
|-<br />
|Mushkin SDHC 16GB Class 10 MKNSDHCC10-16GB ||19.7 ||10.9 ||2012-07-15-wheezy-raspbian ||3.1.9+ #168 PREEMPT || <br />
|-<br />
|Panasonic SDHC 4GB Class 10 UHS-I ||11.2 ||6.2 ||Debian Wheezy "Raspbian" ||3.1.9+ #144 PREEMPT || Panasonic RP-SDU04GE1K<br />
|}<br />
<br />
==NIC==<br />
<br />
===Compile/Run===<br />
On LAN server:<br />
<pre>iperf -s</pre><br />
<br />
On Raspberry Pi:<br />
<pre>iperf -t 60 -c <SERVER_IP_ADDRESS> -d</pre><br />
<br />
===Results===<br />
{| border="1"<br />
! Bandwidth (Mbit/s)<br />
! CPU usage (top)<br />
! Distro<br />
! Kernel<br />
! Notes<br />
|-<br />
|52.1 + 46.4<br />
|5.1%us, 66.2%sy, 28.7%si<br />
|Debian Squeeze "debian6-19-04-2012"<br />
|Linux raspberrypi 3.1.9+ #95 PREEMPT<br />
|<br />
|-<br />
|91.8 + 36.8<br />
|1.6%us, 60.8%sy, 37.5%si<br />
|Debian Wheezy "Raspbian"<br />
|Linux raspbian 3.1.9+ #101 PREEMPT<br />
|<br />
|-<br />
|65.1 + 48.8<br />
|1.3%us, 61.9%sy, 36.8%si<br />
|Arch Linux 2012-04-29<br />
|Linux alarmpi 3.1.9-12+ #5 Sat Apr 28 04:49:38 UTC 2012 armv6l ARMv6-compatible processor rev 7 (v6l) BCM2708 GNU/Linux<br />
|Remote host connected at gigabit<br />
|-<br />
|69.5 + 29.1<br />
|0.6%us, 55.5%sy, 40.0%si<br />
|Debian Wheezy "Raspbian"<br />
|Linux rpi 3.1.9+ #168 PREEMPT<br />
|Remote connected at gigabit, values for si between 30 and 55 %<br />
|}<br />
<br />
===Additional Observations===<br />
<br />
Using netperf -H [netserver host IP] with Debian Wheezy and changing the CPU clock rate, the TCP performance increased linearly from 61 Mb/s at 500 MHz to 80.6 Mb/s at 900 MHz.<br />
<br />
Performance seems to improve considerably by dropping MTU from the default 1500 to 1488. However, this has caused kernel instabilities with Debian Squeeze images (debian6-19-04-2012). It is unknown if this performance benefit is also gained on other images, or if these kernel instabilities have been resolved.<br />
<br />
=Power=<br />
<br />
This table lists how much power is drawn over the 5V power cable whilst performing various tasks.<br />
<br />
{|class="wikitable"<br />
! Task !! Power use (mA) !! Notes<br />
|-<br />
| Booting (without peripherals) || 120-400 || Taken from Agilent lab power supply readings. No composite/keyboard/mouse/network connected. HDMI was enabled but the cable was disconnected.<br />
|-<br />
| Idling (HDMI on, network on) || 370 || Taken from Agilent lab power supply readings. No composite/keyboard/mouse connected.<br />
|-<br />
| Idling (HDMI on, network off) || 320 || Taken from Agilent lab power supply readings. No composite/keyboard/mouse/network connected.<br />
|-<br />
| 1080p video playback || 750 || About 3h on 4 AA batteries<br />
|-<br />
| Text editing || - || Same as idling<br />
|-<br />
| Compiling C code || ? ||<br />
|-<br />
| Running a Python program || ? ||<br />
|-<br />
| Playing Quake III || ? ||<br />
|}<br />
<br />
{{Template:Raspberry Pi}}</div>
Aradke