Guest User

OPi Zero Plus with FriendlyELEC Xenial image

a guest
Nov 15th, 2017
113
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
  1. FriendlyELEC's arm64 Ubuntu Xenial for NEO Plus 2 (kernel 4.11.2, no cpufreq support but running at 816 MHz, DRAM clocked at 672 MHz obviously):
  2.  
  3. root@NanoPi-M1-Plus2:~/tinymembench# ./tinymembench
  4. tinymembench v0.4.9 (simple benchmark for memory throughput and latency)
  5.  
  6. ==========================================================================
  7. == Memory bandwidth tests ==
  8. == ==
  9. == Note 1: 1MB = 1000000 bytes ==
  10. == Note 2: Results for 'copy' tests show how many bytes can be ==
  11. == copied per second (adding together read and writen ==
  12. == bytes would have provided twice higher numbers) ==
  13. == Note 3: 2-pass copy means that we are using a small temporary buffer ==
  14. == to first fetch data into it, and only then write it to the ==
  15. == destination (source -> L1 cache, L1 cache -> destination) ==
  16. == Note 4: If sample standard deviation exceeds 0.1%, it is shown in ==
  17. == brackets ==
  18. ==========================================================================
  19.  
  20. C copy backwards : 866.4 MB/s (1.1%)
  21. C copy backwards (32 byte blocks) : 867.0 MB/s (1.2%)
  22. C copy backwards (64 byte blocks) : 884.9 MB/s (0.8%)
  23. C copy : 891.3 MB/s (1.0%)
  24. C copy prefetched (32 bytes step) : 718.2 MB/s
  25. C copy prefetched (64 bytes step) : 812.4 MB/s
  26. C 2-pass copy : 871.3 MB/s
  27. C 2-pass copy prefetched (32 bytes step) : 649.6 MB/s
  28. C 2-pass copy prefetched (64 bytes step) : 336.3 MB/s (0.2%)
  29. C fill : 2193.5 MB/s
  30. C fill (shuffle within 16 byte blocks) : 2194.5 MB/s
  31. C fill (shuffle within 32 byte blocks) : 2194.6 MB/s
  32. C fill (shuffle within 64 byte blocks) : 2193.1 MB/s
  33. ---
  34. standard memcpy : 906.7 MB/s
  35. standard memset : 2195.6 MB/s
  36. ---
  37. NEON LDP/STP copy : 897.6 MB/s (0.4%)
  38. NEON LDP/STP copy pldl2strm (32 bytes step) : 683.5 MB/s (0.6%)
  39. NEON LDP/STP copy pldl2strm (64 bytes step) : 798.6 MB/s
  40. NEON LDP/STP copy pldl1keep (32 bytes step) : 951.5 MB/s
  41. NEON LDP/STP copy pldl1keep (64 bytes step) : 952.1 MB/s
  42. NEON LD1/ST1 copy : 900.9 MB/s
  43. NEON STP fill : 2195.3 MB/s
  44. NEON STNP fill : 1994.3 MB/s (0.4%)
  45. ARM LDP/STP copy : 898.3 MB/s (0.3%)
  46. ARM STP fill : 2194.8 MB/s
  47. ARM STNP fill : 1996.3 MB/s (0.3%)
  48.  
  49. ==========================================================================
  50. == Framebuffer read tests. ==
  51. == ==
  52. == Many ARM devices use a part of the system memory as the framebuffer, ==
  53. == typically mapped as uncached but with write-combining enabled. ==
  54. == Writes to such framebuffers are quite fast, but reads are much ==
  55. == slower and very sensitive to the alignment and the selection of ==
  56. == CPU instructions which are used for accessing memory. ==
  57. == ==
  58. == Many x86 systems allocate the framebuffer in the GPU memory, ==
  59. == accessible for the CPU via a relatively slow PCI-E bus. Moreover, ==
  60. == PCI-E is asymmetric and handles reads a lot worse than writes. ==
  61. == ==
  62. == If uncached framebuffer reads are reasonably fast (at least 100 MB/s ==
  63. == or preferably >300 MB/s), then using the shadow framebuffer layer ==
  64. == is not necessary in Xorg DDX drivers, resulting in a nice overall ==
  65. == performance improvement. For example, the xf86-video-fbturbo DDX ==
  66. == uses this trick. ==
  67. ==========================================================================
  68.  
  69. NEON LDP/STP copy (from framebuffer) : 165.7 MB/s
  70. NEON LDP/STP 2-pass copy (from framebuffer) : 156.6 MB/s
  71. NEON LD1/ST1 copy (from framebuffer) : 43.0 MB/s
  72. NEON LD1/ST1 2-pass copy (from framebuffer) : 42.5 MB/s
  73. ARM LDP/STP copy (from framebuffer) : 85.5 MB/s
  74. ARM LDP/STP 2-pass copy (from framebuffer) : 83.2 MB/s
  75.  
  76. ==========================================================================
  77. == Memory latency test ==
  78. == ==
  79. == Average time is measured for random memory accesses in the buffers ==
  80. == of different sizes. The larger is the buffer, the more significant ==
  81. == are relative contributions of TLB, L1/L2 cache misses and SDRAM ==
  82. == accesses. For extremely large buffer sizes we are expecting to see ==
  83. == page table walk with several requests to SDRAM for almost every ==
  84. == memory access (though 64MiB is not nearly large enough to experience ==
  85. == this effect to its fullest). ==
  86. == ==
  87. == Note 1: All the numbers are representing extra time, which needs to ==
  88. == be added to L1 cache latency. The cycle timings for L1 cache ==
  89. == latency can be usually found in the processor documentation. ==
  90. == Note 2: Dual random read means that we are simultaneously performing ==
  91. == two independent memory accesses at a time. In the case if ==
  92. == the memory subsystem can't handle multiple outstanding ==
  93. == requests, dual random read has the same timings as two ==
  94. == single reads performed one after another. ==
  95. ==========================================================================
  96.  
  97. block size : single random read / dual random read, [MADV_NOHUGEPAGE]
  98. 1024 : 0.0 ns / 0.0 ns
  99. 2048 : 0.0 ns / 0.0 ns
  100. 4096 : 0.0 ns / 0.0 ns
  101. 8192 : 0.0 ns / 0.0 ns
  102. 16384 : 0.0 ns / 0.0 ns
  103. 32768 : 0.1 ns / 0.1 ns
  104. 65536 : 8.3 ns / 14.2 ns
  105. 131072 : 12.8 ns / 19.7 ns
  106. 262144 : 15.1 ns / 21.9 ns
  107. 524288 : 17.6 ns / 25.5 ns
  108. 1048576 : 104.5 ns / 162.5 ns
  109. 2097152 : 151.3 ns / 210.6 ns
  110. 4194304 : 184.0 ns / 237.0 ns
  111. 8388608 : 201.8 ns / 250.0 ns
  112. 16777216 : 212.7 ns / 258.8 ns
  113. 33554432 : 219.2 ns / 265.6 ns
  114. 67108864 : 222.8 ns / 269.2 ns
  115.  
  116. block size : single random read / dual random read, [MADV_HUGEPAGE]
  117. 1024 : 0.0 ns / 0.0 ns
  118. 2048 : 0.0 ns / 0.0 ns
  119. 4096 : 0.0 ns / 0.0 ns
  120. 8192 : 0.0 ns / 0.0 ns
  121. 16384 : 0.0 ns / 0.0 ns
  122. 32768 : 0.1 ns / 0.1 ns
  123. 65536 : 8.3 ns / 14.2 ns
  124. 131072 : 12.8 ns / 19.7 ns
  125. 262144 : 15.1 ns / 21.9 ns
  126. 524288 : 17.7 ns / 24.8 ns
  127. 1048576 : 104.5 ns / 162.5 ns
  128. 2097152 : 151.4 ns / 210.6 ns
  129. 4194304 : 184.3 ns / 237.5 ns
  130. 8388608 : 201.9 ns / 250.4 ns
  131. 16777216 : 212.6 ns / 258.7 ns
  132. 33554432 : 219.2 ns / 265.6 ns
  133. 67108864 : 222.9 ns / 269.5 ns
  134.  
  135.  
  136. sysbench --test=cpu --cpu-max-prime=20000 run --num-threads=4:
  137. execution time (avg/stddev): 11.2186/0.00
  138.  
  139.  
  140. root@NanoPi-M1-Plus2:~/tinymembench# 7zr b
  141.  
  142. 7-Zip (A) 9.20 Copyright (c) 1999-2010 Igor Pavlov 2010-11-18
  143. p7zip Version 9.20 (locale=en_US.UTF-8,Utf16=on,HugeFiles=on,4 CPUs)
  144.  
  145. RAM size: 482 MB, # CPU hardware threads: 4
  146. RAM usage: 434 MB, # Benchmark threads: 4
  147.  
  148. Dict Compressing | Decompressing
  149. Speed Usage R/U Rating | Speed Usage R/U Rating
  150. KB/s % MIPS MIPS | KB/s % MIPS MIPS
  151.  
  152. 22: 1165 296 383 1133 | 30716 399 694 2771
  153. 23: 1158 302 390 1180 | 30260 399 694 2769
  154. Killed
  155.  
  156.  
  157. for i in 128 192 256 ; do openssl speed -elapsed -evp aes-${i}-cbc ; done
  158. type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes
  159. aes-128-cbc 102619.34k 274383.85k 458681.60k 570289.15k 613662.72k
  160. aes-192-cbc 95828.78k 236630.63k 366491.39k 436039.34k 461564.59k
  161. aes-256-cbc 91768.22k 213249.41k 313543.59k 363093.33k 380613.97k
  162.  
  163.  
  164. root@NanoPi-M1-Plus2:~# iperf3 -c 192.168.83.61 -t 60 && iperf3 -R -c 192.168.83.61 -t 60
  165. Connecting to host 192.168.83.61, port 5201
  166. [ 4] local 192.168.83.63 port 44298 connected to 192.168.83.61 port 5201
  167. [ ID] Interval Transfer Bandwidth Retr Cwnd
  168. [ 4] 0.00-1.01 sec 82.6 MBytes 690 Mbits/sec 0 156 KBytes
  169. [ 4] 1.01-2.01 sec 82.5 MBytes 691 Mbits/sec 0 164 KBytes
  170. [ 4] 2.01-3.00 sec 85.5 MBytes 722 Mbits/sec 0 334 KBytes
  171. [ 4] 3.00-4.00 sec 102 MBytes 852 Mbits/sec 0 389 KBytes
  172. [ 4] 4.00-5.00 sec 102 MBytes 853 Mbits/sec 0 389 KBytes
  173. [ 4] 5.00-6.00 sec 101 MBytes 844 Mbits/sec 0 389 KBytes
  174. [ 4] 6.00-7.00 sec 102 MBytes 856 Mbits/sec 0 389 KBytes
  175. [ 4] 7.00-8.00 sec 101 MBytes 845 Mbits/sec 0 389 KBytes
  176. [ 4] 8.00-9.00 sec 102 MBytes 853 Mbits/sec 0 389 KBytes
  177. [ 4] 9.00-10.00 sec 101 MBytes 844 Mbits/sec 0 389 KBytes
  178. [ 4] 10.00-11.00 sec 101 MBytes 846 Mbits/sec 0 389 KBytes
  179. [ 4] 11.00-12.00 sec 100 MBytes 839 Mbits/sec 0 389 KBytes
  180. [ 4] 12.00-13.00 sec 100 MBytes 842 Mbits/sec 0 389 KBytes
  181. [ 4] 13.00-14.00 sec 101 MBytes 848 Mbits/sec 0 389 KBytes
  182. [ 4] 14.00-15.00 sec 102 MBytes 854 Mbits/sec 0 389 KBytes
  183. [ 4] 15.00-16.00 sec 101 MBytes 850 Mbits/sec 0 389 KBytes
  184. [ 4] 16.00-17.00 sec 102 MBytes 855 Mbits/sec 0 389 KBytes
  185. [ 4] 17.00-18.00 sec 101 MBytes 849 Mbits/sec 0 389 KBytes
  186. [ 4] 18.00-19.00 sec 101 MBytes 846 Mbits/sec 0 389 KBytes
  187. [ 4] 19.00-20.00 sec 102 MBytes 860 Mbits/sec 0 389 KBytes
  188. [ 4] 20.00-21.00 sec 101 MBytes 845 Mbits/sec 0 389 KBytes
  189. [ 4] 21.00-22.00 sec 102 MBytes 855 Mbits/sec 0 389 KBytes
  190. [ 4] 22.00-23.00 sec 102 MBytes 856 Mbits/sec 0 389 KBytes
  191. [ 4] 23.00-24.00 sec 101 MBytes 844 Mbits/sec 0 389 KBytes
  192. [ 4] 24.00-25.00 sec 102 MBytes 855 Mbits/sec 0 389 KBytes
  193. [ 4] 25.00-26.00 sec 102 MBytes 854 Mbits/sec 0 389 KBytes
  194. [ 4] 26.00-27.00 sec 102 MBytes 852 Mbits/sec 0 389 KBytes
  195. [ 4] 27.00-28.00 sec 101 MBytes 849 Mbits/sec 0 389 KBytes
  196. [ 4] 28.00-29.00 sec 102 MBytes 853 Mbits/sec 0 389 KBytes
  197. [ 4] 29.00-30.00 sec 101 MBytes 850 Mbits/sec 0 389 KBytes
  198. [ 4] 30.00-31.00 sec 101 MBytes 851 Mbits/sec 0 389 KBytes
  199. [ 4] 31.00-32.00 sec 102 MBytes 854 Mbits/sec 0 389 KBytes
  200. [ 4] 32.00-33.00 sec 101 MBytes 851 Mbits/sec 0 389 KBytes
  201. [ 4] 33.00-34.00 sec 102 MBytes 855 Mbits/sec 0 389 KBytes
  202. [ 4] 34.00-35.00 sec 101 MBytes 851 Mbits/sec 0 389 KBytes
  203. [ 4] 35.00-36.00 sec 101 MBytes 851 Mbits/sec 0 389 KBytes
  204. [ 4] 36.00-37.00 sec 102 MBytes 852 Mbits/sec 0 389 KBytes
  205. [ 4] 37.00-38.00 sec 102 MBytes 854 Mbits/sec 0 389 KBytes
  206. [ 4] 38.00-39.00 sec 102 MBytes 853 Mbits/sec 0 389 KBytes
  207. [ 4] 39.00-40.00 sec 102 MBytes 852 Mbits/sec 0 389 KBytes
  208. [ 4] 40.00-41.00 sec 102 MBytes 853 Mbits/sec 0 389 KBytes
  209. [ 4] 41.00-42.00 sec 101 MBytes 846 Mbits/sec 0 389 KBytes
  210. [ 4] 42.00-43.00 sec 101 MBytes 847 Mbits/sec 0 389 KBytes
  211. [ 4] 43.00-44.00 sec 101 MBytes 846 Mbits/sec 0 389 KBytes
  212. [ 4] 44.00-45.00 sec 103 MBytes 861 Mbits/sec 0 570 KBytes
  213. [ 4] 45.00-46.00 sec 101 MBytes 843 Mbits/sec 0 570 KBytes
  214. [ 4] 46.00-47.00 sec 103 MBytes 860 Mbits/sec 0 570 KBytes
  215. [ 4] 47.00-48.00 sec 101 MBytes 848 Mbits/sec 0 570 KBytes
  216. [ 4] 48.00-49.00 sec 102 MBytes 853 Mbits/sec 0 570 KBytes
  217. [ 4] 49.00-50.00 sec 102 MBytes 855 Mbits/sec 0 570 KBytes
  218. [ 4] 50.00-51.00 sec 102 MBytes 853 Mbits/sec 0 570 KBytes
  219. [ 4] 51.00-52.00 sec 101 MBytes 851 Mbits/sec 0 570 KBytes
  220. [ 4] 52.00-53.00 sec 102 MBytes 855 Mbits/sec 0 570 KBytes
  221. [ 4] 53.00-54.00 sec 103 MBytes 863 Mbits/sec 0 570 KBytes
  222. [ 4] 54.00-55.00 sec 102 MBytes 853 Mbits/sec 0 570 KBytes
  223. [ 4] 55.00-56.00 sec 101 MBytes 848 Mbits/sec 0 570 KBytes
  224. [ 4] 56.00-57.00 sec 102 MBytes 854 Mbits/sec 0 570 KBytes
  225. [ 4] 57.00-58.00 sec 102 MBytes 855 Mbits/sec 0 570 KBytes
  226. [ 4] 58.00-59.00 sec 102 MBytes 859 Mbits/sec 0 570 KBytes
  227. [ 4] 59.00-60.00 sec 102 MBytes 852 Mbits/sec 0 570 KBytes
  228. - - - - - - - - - - - - - - - - - - - - - - - - -
  229. [ ID] Interval Transfer Bandwidth Retr
  230. [ 4] 0.00-60.00 sec 5.89 GBytes 844 Mbits/sec 0 sender
  231. [ 4] 0.00-60.00 sec 5.89 GBytes 844 Mbits/sec receiver
  232.  
  233. iperf Done.
  234. Connecting to host 192.168.83.61, port 5201
  235. Reverse mode, remote host 192.168.83.61 is sending
  236. [ 4] local 192.168.83.63 port 44302 connected to 192.168.83.61 port 5201
  237. [ ID] Interval Transfer Bandwidth
  238. [ 4] 0.00-1.00 sec 112 MBytes 941 Mbits/sec
  239. [ 4] 1.00-2.00 sec 112 MBytes 940 Mbits/sec
  240. [ 4] 2.00-3.00 sec 112 MBytes 940 Mbits/sec
  241. [ 4] 3.00-4.00 sec 112 MBytes 940 Mbits/sec
  242. [ 4] 4.00-5.00 sec 112 MBytes 940 Mbits/sec
  243. [ 4] 5.00-6.00 sec 112 MBytes 940 Mbits/sec
  244. [ 4] 6.00-7.00 sec 112 MBytes 940 Mbits/sec
  245. [ 4] 7.00-8.00 sec 112 MBytes 940 Mbits/sec
  246. [ 4] 8.00-9.00 sec 112 MBytes 940 Mbits/sec
  247. [ 4] 9.00-10.00 sec 112 MBytes 940 Mbits/sec
  248. [ 4] 10.00-11.00 sec 112 MBytes 940 Mbits/sec
  249. [ 4] 11.00-12.00 sec 112 MBytes 940 Mbits/sec
  250. [ 4] 12.00-13.00 sec 112 MBytes 940 Mbits/sec
  251. [ 4] 13.00-14.00 sec 112 MBytes 940 Mbits/sec
  252. [ 4] 14.00-15.00 sec 112 MBytes 940 Mbits/sec
  253. [ 4] 15.00-16.00 sec 112 MBytes 940 Mbits/sec
  254. [ 4] 16.00-17.00 sec 112 MBytes 940 Mbits/sec
  255. [ 4] 17.00-18.00 sec 112 MBytes 940 Mbits/sec
  256. [ 4] 18.00-19.00 sec 112 MBytes 940 Mbits/sec
  257. [ 4] 19.00-20.00 sec 112 MBytes 940 Mbits/sec
  258. [ 4] 20.00-21.00 sec 78.0 MBytes 654 Mbits/sec
  259. [ 4] 21.00-22.00 sec 94.8 MBytes 795 Mbits/sec
  260. [ 4] 22.00-23.00 sec 112 MBytes 940 Mbits/sec
  261. [ 4] 23.00-24.00 sec 111 MBytes 935 Mbits/sec
  262. [ 4] 24.00-25.00 sec 112 MBytes 940 Mbits/sec
  263. [ 4] 25.00-26.00 sec 112 MBytes 940 Mbits/sec
  264. [ 4] 26.00-27.00 sec 112 MBytes 940 Mbits/sec
  265. [ 4] 27.00-28.00 sec 112 MBytes 940 Mbits/sec
  266. [ 4] 28.00-29.00 sec 112 MBytes 940 Mbits/sec
  267. [ 4] 29.00-30.00 sec 112 MBytes 940 Mbits/sec
  268. [ 4] 30.00-31.00 sec 112 MBytes 940 Mbits/sec
  269. [ 4] 31.00-32.00 sec 112 MBytes 940 Mbits/sec
  270. [ 4] 32.00-33.00 sec 112 MBytes 940 Mbits/sec
  271. [ 4] 33.00-34.00 sec 112 MBytes 940 Mbits/sec
  272. [ 4] 34.00-35.00 sec 112 MBytes 940 Mbits/sec
  273. [ 4] 35.00-36.00 sec 112 MBytes 940 Mbits/sec
  274. [ 4] 36.00-37.00 sec 112 MBytes 940 Mbits/sec
  275. [ 4] 37.00-38.00 sec 112 MBytes 940 Mbits/sec
  276. [ 4] 38.00-39.00 sec 112 MBytes 940 Mbits/sec
  277. [ 4] 39.00-40.00 sec 112 MBytes 937 Mbits/sec
  278. [ 4] 40.00-41.00 sec 112 MBytes 940 Mbits/sec
  279. [ 4] 41.00-42.00 sec 112 MBytes 940 Mbits/sec
  280. [ 4] 42.00-43.00 sec 112 MBytes 940 Mbits/sec
  281. [ 4] 43.00-44.00 sec 112 MBytes 940 Mbits/sec
  282. [ 4] 44.00-45.00 sec 112 MBytes 940 Mbits/sec
  283. [ 4] 45.00-46.00 sec 93.2 MBytes 782 Mbits/sec
  284. [ 4] 46.00-47.00 sec 67.3 MBytes 562 Mbits/sec
  285. [ 4] 47.00-48.00 sec 95.9 MBytes 807 Mbits/sec
  286. [ 4] 48.00-49.00 sec 112 MBytes 940 Mbits/sec
  287. [ 4] 49.00-50.00 sec 112 MBytes 940 Mbits/sec
  288. [ 4] 50.00-51.00 sec 112 MBytes 940 Mbits/sec
  289. [ 4] 51.00-52.00 sec 112 MBytes 939 Mbits/sec
  290. [ 4] 52.00-53.00 sec 112 MBytes 940 Mbits/sec
  291. [ 4] 53.00-54.00 sec 112 MBytes 940 Mbits/sec
  292. [ 4] 54.00-55.00 sec 112 MBytes 940 Mbits/sec
  293. [ 4] 55.00-56.00 sec 112 MBytes 940 Mbits/sec
  294. [ 4] 56.00-57.00 sec 112 MBytes 940 Mbits/sec
  295. [ 4] 57.00-58.00 sec 112 MBytes 940 Mbits/sec
  296. [ 4] 58.00-59.00 sec 112 MBytes 940 Mbits/sec
  297. [ 4] 59.00-60.00 sec 112 MBytes 940 Mbits/sec
  298. - - - - - - - - - - - - - - - - - - - - - - - - -
  299. [ ID] Interval Transfer Bandwidth
  300. [ 4] 0.00-60.00 sec 6.44 GBytes 922 Mbits/sec sender
  301. [ 4] 0.00-60.00 sec 6.44 GBytes 922 Mbits/sec receiver
  302.  
  303. iperf Done.
RAW Paste Data