Benchmarks

Linpack
Build root@linaro-alip:~/benchmarks# cc -Ofast -o linpack linpack.c -lm -mcpu=cortex-a8 -march=armv7-a -mfpu=neon -mfloat-abi=hard -funsafe-math-optimizations -fno-fast-math linpack.c: In function ‘main’: linpack.c:78:14: warning: ignoring return value of ‘fgets’, declared with attribute warn_unused_result [-Wunused-result] Results root@linaro-alip:~/benchmarks# ./linpack Enter array size (q to quit) [200]: Memory required: 315K.

LINPACK benchmark, Double precision. Machine precision: 15 digits. Array size 200 X 200. Average rolled and unrolled performance:

Reps Time(s) DGEFA  DGESL  OVERHEAD    KFLOPS

16  0.61  88.52%   6.56%   4.92%  37885.057      32   1.21  85.12%   2.48%  12.40%  41459.119      64   2.43  93.83%   2.47%   3.70%  37561.254     128   4.86  91.77%   2.47%   5.76%  38381.368     256   9.70  92.06%   2.89%   5.05%  38173.000     512  19.41  91.29%   2.47%   6.23%  38634.432

Whetstone/Dhrystone
TODO

OpenSSL
Linaro-alip armhf OpenSSL 1.0.1 14 Mar 2012 built on: Tue Aug 21 05:35:49 UTC 2012 options:bn(64,32) rc4(ptr,char) des(idx,cisc,16,long) aes(partial) blowfish(ptr) compiler: cc -fPIC -DOPENSSL_PIC -DZLIB -DOPENSSL_THREADS -D_REENTRANT -DDSO_DLFCN -DHAVE_DLFCN_H -DL_ENDIAN -DTERMIO -g -O2 -fstack-protector --param=ssp-buffer-size=4 -Wformat -Wformat-security -Werror=format-security -D_FORTIFY_SOURCE=2 -Wl,-Bsymbolic-functions -Wl,-z,relro -Wa,--noexecstack -Wall -DOPENSSL_NO_TLS1_2_CLIENT -DOPENSSL_MAX_TLS1_2_CIPHER_LENGTH=50 The 'numbers' are in 1000s of bytes per second processed. type            16 bytes     64 bytes    256 bytes   1024 bytes   8192 bytes md2                 0.00         0.00         0.00         0.00         0.00 mdc2                0.00         0.00         0.00         0.00         0.00 md4              4539.13k    23584.98k    68988.33k   133520.04k   184363.69k md5              5140.49k    17237.58k    46162.43k    79220.05k   100848.98k hmac(md5)        6296.96k    20580.39k    51788.37k    83395.93k   101282.91k sha1             5056.81k    15672.85k    36537.09k    54699.01k    64102.40k rmd160           4733.01k    14162.58k    31460.95k    45231.10k    51950.93k rc4             67049.00k    74935.98k    78372.86k    79348.39k    79623.51k des cbc         17689.04k    18793.72k    19138.82k    19248.13k    19292.16k des ede3         6748.10k     6951.38k     6998.10k     7015.77k     6950.87k idea cbc            0.00         0.00         0.00         0.00         0.00 seed cbc        20640.20k    21906.09k    22347.52k    22450.52k    22500.69k rc2 cbc         13089.00k    13998.74k    14224.73k    14294.36k    14164.76k rc5-32/12 cbc       0.00         0.00         0.00         0.00         0.00 blowfish cbc    26759.62k    29755.75k    30726.06k    30958.59k    31053.14k cast cbc        25870.12k    28393.51k    29254.23k    29501.78k    29570.39k aes-128 cbc     19582.69k    20855.45k    21258.07k    21348.35k    21392.04k aes-192 cbc     16902.33k    17731.03k    18009.26k    18094.42k    18117.97k aes-256 cbc     14778.66k    15419.55k    15636.82k    15683.58k    15712.26k camellia-128 cbc   26162.67k    28201.17k    28923.31k    29136.90k    28918.58k camellia-192 cbc   20555.46k    22316.52k    22863.19k    22990.17k    23046.83k camellia-256 cbc   20704.67k    22316.39k    22846.72k    23003.48k    23044.10k sha256           4130.87k     9683.05k    17185.11k    21408.43k    23093.25k sha512            804.45k     3218.84k     4525.99k     6147.07k     6873.09k whirlpool        1201.69k     2457.88k     3979.18k     4716.20k     4917.93k aes-128 ige     18517.42k    19858.50k    20280.58k    20406.61k    20838.75k aes-192 ige     15950.20k    17003.69k    17323.18k    17393.32k    17408.00k aes-256 ige     14102.48k    14868.65k    15100.93k    15172.95k    15174.31k ghash           14806.49k    15383.55k    15564.03k    15625.22k    15652.18k sign   verify    sign/s verify/s rsa 512 bits 0.002293s 0.000203s    436.1   4920.6 rsa 1024 bits 0.012441s 0.000617s    80.4   1621.2 rsa 2048 bits 0.075263s 0.002055s    13.3    486.7 rsa 4096 bits 0.499048s 0.007148s     2.0    139.9 sign   verify    sign/s verify/s dsa 512 bits 0.002058s 0.002299s    485.9    435.0 dsa 1024 bits 0.006101s 0.006964s   163.9    143.6 dsa 2048 bits 0.020326s 0.023641s    49.2     42.3 sign   verify    sign/s verify/s 160 bit ecdsa (secp160r1)  0.0010s   0.0045s    977.2    222.1 192 bit ecdsa (nistp192)  0.0011s   0.0046s    950.8    218.4 224 bit ecdsa (nistp224)  0.0014s   0.0062s    739.1    160.2 256 bit ecdsa (nistp256)  0.0016s   0.0079s    613.0    126.5 384 bit ecdsa (nistp384)  0.0036s   0.0184s    281.4     54.3 521 bit ecdsa (nistp521)  0.0096s   0.0510s    103.9     19.6 163 bit ecdsa (nistk163)  0.0021s   0.0080s    473.6    125.3 233 bit ecdsa (nistk233)  0.0044s   0.0155s    228.5     64.3 283 bit ecdsa (nistk283)  0.0067s   0.0286s    150.2     35.0 409 bit ecdsa (nistk409)  0.0178s   0.0667s     56.3     15.0 571 bit ecdsa (nistk571)  0.0426s   0.1538s     23.5      6.5 163 bit ecdsa (nistb163)  0.0021s   0.0086s    472.9    116.0 233 bit ecdsa (nistb233)  0.0043s   0.0173s    230.3     57.9 283 bit ecdsa (nistb283)  0.0067s   0.0320s    149.7     31.2 409 bit ecdsa (nistb409)  0.0178s   0.0759s     56.1     13.2 571 bit ecdsa (nistb571)  0.0428s   0.1760s     23.3      5.7 op     op/s 160 bit ecdh (secp160r1)  0.0038s    264.8 192 bit ecdh (nistp192)  0.0038s    263.9 224 bit ecdh (nistp224)  0.0052s    191.9 256 bit ecdh (nistp256)  0.0066s    151.4 384 bit ecdh (nistp384)  0.0152s     66.0 521 bit ecdh (nistp521)  0.0422s     23.7 163 bit ecdh (nistk163)  0.0040s    253.0 233 bit ecdh (nistk233)  0.0077s    130.0 283 bit ecdh (nistk283)  0.0142s     70.6 409 bit ecdh (nistk409)  0.0331s     30.2 571 bit ecdh (nistk571)  0.0760s     13.2 163 bit ecdh (nistb163)  0.0042s    235.8 233 bit ecdh (nistb233)  0.0085s    117.0 283 bit ecdh (nistb283)  0.0158s     63.1 409 bit ecdh (nistb409)  0.0378s     26.5 571 bit ecdh (nistb571)  0.0879s     11.4 Place your optimized hardfloat result here.

ioquake3
libv places here results of framebuffer ioquake3 with logs.

Video decoding
See CedarXVideoRenderingChart

A13 Benchmarks
A13 needs own CPU benchmarks because DDR3 bus is crippled.