SHARE
TWEET

OPi Zero Plus with more mature Armbian

a guest Nov 17th, 2017 184 Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
  1. root@orangepizeroplus:~/tinymembench# ./tinymembench
  2. tinymembench v0.4.9 (simple benchmark for memory throughput and latency)
  3.  
  4. ==========================================================================
  5. == Memory bandwidth tests                                               ==
  6. ==                                                                      ==
  7. == Note 1: 1MB = 1000000 bytes                                          ==
  8. == Note 2: Results for 'copy' tests show how many bytes can be          ==
  9. ==         copied per second (adding together read and writen           ==
  10. ==         bytes would have provided twice higher numbers)              ==
  11. == Note 3: 2-pass copy means that we are using a small temporary buffer ==
  12. ==         to first fetch data into it, and only then write it to the   ==
  13. ==         destination (source -> L1 cache, L1 cache -> destination)    ==
  14. == Note 4: If sample standard deviation exceeds 0.1%, it is shown in    ==
  15. ==         brackets                                                     ==
  16. ==========================================================================
  17.  
  18.  C copy backwards                                     :    857.0 MB/s (1.7%)
  19.  C copy backwards (32 byte blocks)                    :    852.2 MB/s (1.2%)
  20.  C copy backwards (64 byte blocks)                    :    859.7 MB/s (0.9%)
  21.  C copy                                               :    854.5 MB/s (1.3%)
  22.  C copy prefetched (32 bytes step)                    :    683.1 MB/s
  23.  C copy prefetched (64 bytes step)                    :    763.3 MB/s
  24.  C 2-pass copy                                        :    864.5 MB/s (0.6%)
  25.  C 2-pass copy prefetched (32 bytes step)             :    638.3 MB/s
  26.  C 2-pass copy prefetched (64 bytes step)             :    351.8 MB/s (0.2%)
  27.  C fill                                               :   2252.3 MB/s
  28.  C fill (shuffle within 16 byte blocks)               :   2252.1 MB/s (0.4%)
  29.  C fill (shuffle within 32 byte blocks)               :   2252.4 MB/s (1.0%)
  30.  C fill (shuffle within 64 byte blocks)               :   2253.0 MB/s (0.4%)
  31.  ---
  32.  standard memcpy                                      :    875.1 MB/s (0.6%)
  33.  standard memset                                      :   2252.7 MB/s
  34.  ---
  35.  NEON LDP/STP copy                                    :    865.7 MB/s (0.6%)
  36.  NEON LDP/STP copy pldl2strm (32 bytes step)          :    653.8 MB/s (0.6%)
  37.  NEON LDP/STP copy pldl2strm (64 bytes step)          :    774.2 MB/s
  38.  NEON LDP/STP copy pldl1keep (32 bytes step)          :    908.9 MB/s
  39.  NEON LDP/STP copy pldl1keep (64 bytes step)          :    909.2 MB/s
  40.  NEON LD1/ST1 copy                                    :    862.7 MB/s (1.3%)
  41.  NEON STP fill                                        :   2252.5 MB/s (0.6%)
  42.  NEON STNP fill                                       :   1881.2 MB/s (3.1%)
  43.  ARM LDP/STP copy                                     :    867.0 MB/s (0.4%)
  44.  ARM STP fill                                         :   2251.8 MB/s
  45.  ARM STNP fill                                        :   1876.4 MB/s (1.5%)
  46.  
  47. ==========================================================================
  48. == Memory latency test                                                  ==
  49. ==                                                                      ==
  50. == Average time is measured for random memory accesses in the buffers   ==
  51. == of different sizes. The larger is the buffer, the more significant   ==
  52. == are relative contributions of TLB, L1/L2 cache misses and SDRAM      ==
  53. == accesses. For extremely large buffer sizes we are expecting to see   ==
  54. == page table walk with several requests to SDRAM for almost every      ==
  55. == memory access (though 64MiB is not nearly large enough to experience ==
  56. == this effect to its fullest).                                         ==
  57. ==                                                                      ==
  58. == Note 1: All the numbers are representing extra time, which needs to  ==
  59. ==         be added to L1 cache latency. The cycle timings for L1 cache ==
  60. ==         latency can be usually found in the processor documentation. ==
  61. == Note 2: Dual random read means that we are simultaneously performing ==
  62. ==         two independent memory accesses at a time. In the case if    ==
  63. ==         the memory subsystem can't handle multiple outstanding       ==
  64. ==         requests, dual random read has the same timings as two       ==
  65. ==         single reads performed one after another.                    ==
  66. ==========================================================================
  67.  
  68. block size : single random read / dual random read, [MADV_NOHUGEPAGE]
  69.       1024 :    0.0 ns          /     0.0 ns
  70.       2048 :    0.0 ns          /     0.0 ns
  71.       4096 :    0.0 ns          /     0.0 ns
  72.       8192 :    0.0 ns          /     0.0 ns
  73.      16384 :    0.0 ns          /     0.0 ns
  74.      32768 :    0.0 ns          /     0.0 ns
  75.      65536 :    6.8 ns          /    11.5 ns
  76.     131072 :   10.4 ns          /    16.0 ns
  77.     262144 :   12.3 ns          /    17.7 ns
  78.     524288 :   14.6 ns          /    20.4 ns
  79.    1048576 :  101.0 ns          /   156.7 ns
  80.    2097152 :  147.5 ns          /   203.6 ns
  81.    4194304 :  178.4 ns          /   229.0 ns
  82.    8388608 :  194.8 ns          /   240.7 ns
  83.   16777216 :  205.0 ns          /   248.2 ns
  84.   33554432 :  211.0 ns          /   252.8 ns
  85.   67108864 :  214.7 ns          /   256.1 ns
  86.  
  87. block size : single random read / dual random read, [MADV_HUGEPAGE]
  88.       1024 :    0.0 ns          /     0.0 ns
  89.       2048 :    0.0 ns          /     0.0 ns
  90.       4096 :    0.0 ns          /     0.0 ns
  91.       8192 :    0.0 ns          /     0.0 ns
  92.      16384 :    0.0 ns          /     0.0 ns
  93.      32768 :    0.0 ns          /     0.0 ns
  94.      65536 :    6.8 ns          /    11.6 ns
  95.     131072 :   10.4 ns          /    15.9 ns
  96.     262144 :   12.3 ns          /    17.7 ns
  97.     524288 :   14.6 ns          /    20.3 ns
  98.    1048576 :  101.0 ns          /   156.8 ns
  99.    2097152 :  147.5 ns          /   203.7 ns
  100.    4194304 :  178.4 ns          /   229.1 ns
  101.    8388608 :  194.8 ns          /   240.7 ns
  102.   16777216 :  204.8 ns          /   247.9 ns
  103.   33554432 :  211.0 ns          /   252.8 ns
  104.   67108864 :  214.8 ns          /   256.3 ns
  105.  
  106.  
  107. root@orangepizeroplus:~# 7zr b
  108.  
  109. 7-Zip (a) [64] 16.02 : Copyright (c) 1999-2016 Igor Pavlov : 2016-05-21
  110. p7zip Version 16.02 (locale=en_US.UTF-8,Utf16=on,HugeFiles=on,64 bits,4 CPUs LE)
  111.  
  112. LE
  113. CPU Freq:   414  1006  1006  1005  1006  1006  1006  1005
  114.  
  115. RAM size:     482 MB,  # CPU hardware threads:   4
  116. RAM usage:    450 MB,  # Benchmark threads:      4
  117.  
  118.                        Compressing  |                  Decompressing
  119. Dict     Speed Usage    R/U Rating  |      Speed Usage    R/U Rating
  120.          KiB/s     %   MIPS   MIPS  |      KiB/s     %   MIPS   MIPS
  121.  
  122. 22:       1557   306    495   1515  |      44917   399    961   3832
  123. 23:       1606   325    503   1637  |      43543   396    952   3768
  124. 24:       1305   307    457   1404  |      40686   389    919   3572
  125. ----------------------------------  | ------------------------------
  126. Avr:             313    485   1519  |              394    944   3724
  127. Tot:             354    714   2621
  128.  
  129.  
  130. root@orangepizeroplus:~# /bin/bash /tmp/sysbench.sh
  131. 408:     execution time (avg/stddev):   89.2554/0.00
  132. 648:     execution time (avg/stddev):   56.1463/0.00
  133. 816:     execution time (avg/stddev):   44.3941/0.00
  134. 912:     execution time (avg/stddev):   39.7057/0.00
  135. 960:     execution time (avg/stddev):   37.7316/0.00
  136. 1008:     execution time (avg/stddev):   35.9167/0.00
  137. 408:     execution time (avg/stddev):   22.3622/0.00
  138. 648:     execution time (avg/stddev):   14.1378/0.00
  139. 816:     execution time (avg/stddev):   11.1106/0.00
  140. 912:     execution time (avg/stddev):   9.9382/0.00
  141. 960:     execution time (avg/stddev):   9.4391/0.00
  142. 1008:     execution time (avg/stddev):   8.9818/0.00
  143.  
  144.  
  145. for i in 128 192 256 ; do openssl speed -elapsed -evp aes-${i}-cbc ; done
  146. type             16 bytes     64 bytes    256 bytes   1024 bytes   8192 bytes
  147. aes-128-cbc      69173.49k   218179.56k   457685.25k   655786.67k   749043.71k
  148. aes-192-cbc      66168.97k   196154.67k   379023.02k   509089.11k   565190.66k
  149. aes-256-cbc      64564.66k   183042.71k   332124.33k   427910.83k   466774.70k
RAW Paste Data
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy. OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!
 
Top