Guest User

CUDA 5.0 SDK NBody Ocelot Debug Log

a guest
Jul 7th, 2015
31
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 12.77 KB | None | 0 0
  1. lbraun@ceg01:/local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody$ cuda-gdb --args nbody_ocelot --benchmark
  2. NVIDIA (R) CUDA Debugger
  3. 5.0 release
  4. Portions Copyright (C) 2007-2012 NVIDIA Corporation
  5. GNU gdb (GDB) 7.2
  6. Copyright (C) 2010 Free Software Foundation, Inc.
  7. License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
  8. This is free software: you are free to change and redistribute it.
  9. There is NO WARRANTY, to the extent permitted by law. Type "show copying"
  10. and "show warranty" for details.
  11. This GDB was configured as "x86_64-unknown-linux-gnu".
  12. For bug reporting instructions, please see:
  13. <http://www.gnu.org/software/gdb/bugs/>...
  14. Reading symbols from /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/nbody_ocelot...(no debugging symbols found)...done.
  15. (cuda-gdb) run
  16. Starting program: /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/nbody_ocelot --benchmark
  17. [Thread debugging using libthread_db enabled]
  18. [New Thread 0x7fffec28e700 (LWP 28122)]
  19. Run "nbody -benchmark [-numbodies=<numBodies>]" to measure perfomance.
  20. -fullscreen (run n-body simulation in fullscreen mode)
  21. -fp64 (use double precision floating point values for simulation)
  22. -hostmem (stores simulation data in host memory)
  23. -benchmark (run benchmark to measure performance)
  24. -numbodies=<N> (number of bodies (>= 1) to run in simulation)
  25. -device=<d> (where d=0,1,2.... for the CUDA device to use)
  26. -numdevices=<i> (where i=(number of CUDA devices > 0) to use for simulation)
  27. -compare (compares simulation results running once on the default GPU and once on the CPU)
  28. -cpu (run n-body simulation on the CPU)
  29. -tipsy=<file.bin> (load a tipsy model file for simulation)
  30.  
  31. > Windowed mode
  32. > Simulation data stored in video memory
  33. > Single precision floating point simulation
  34. > 1 Devices used for simulation
  35. [New Thread 0x7fffeba8d700 (LWP 28123)]
  36. [Thread 0x7fffeba8d700 (LWP 28123) exited]
  37. [New Thread 0x7fffeba8d700 (LWP 28124)]
  38. [Thread 0x7fffeba8d700 (LWP 28124) exited]
  39. [New Thread 0x7fffeba8d700 (LWP 28125)]
  40. [Thread 0x7fffeba8d700 (LWP 28125) exited]
  41. GPU Device 0: "Ocelot PTX Emulator" with compute capability 2.1
  42.  
  43. [New Thread 0x7fffeba8d700 (LWP 28126)]
  44. [Thread 0x7fffeba8d700 (LWP 28126) exited]
  45. [New Thread 0x7fffeba8d700 (LWP 28127)]
  46. [Thread 0x7fffeba8d700 (LWP 28127) exited]
  47. > Compute 2.1 CUDA device: [Ocelot PTX Emulator]
  48. [New Thread 0x7fffeba8d700 (LWP 28128)]
  49. [Thread 0x7fffeba8d700 (LWP 28128) exited]
  50. [New Thread 0x7fffeba8d700 (LWP 28129)]
  51. all enabled
  52. (0.699931) X86TraceGenerator.cpp:771: New kernel launched
  53. (0.699972) X86TraceGenerator.cpp:772: compute version:2.0
  54. (0.699993) X86TraceGenerator.cpp:773: grid 4 x 1 x 1
  55. (0.700021) X86TraceGenerator.cpp:774: block 256 x 1 x 1
  56. (0.700041) X86TraceGenerator.cpp:775: number of warps per block:8
  57. (0.700067) X86TraceGenerator.cpp:776: number of total warps:32
  58. (0.700079) X86TraceGenerator.cpp:777: # threads per block : 256
  59. (0.700090) X86TraceGenerator.cpp:778: number of register per thread:0
  60. (0.700106) X86TraceGenerator.cpp:779: number of shared memory per thread:0
  61. (0.700119) X86TraceGenerator.cpp:817: max blocks per core : 6
  62. (0.704504) X86TraceGenerator.cpp:1078: mkdir -p /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/macsim_Trace/_Z15integrateBodiesIfLb0EEvPN4vec4IT_E4TypeES4_S4_jjffi_0/ (status 0)
  63.  
  64. (0.704586) X86TraceGenerator.cpp:1079: errno is 2 message is No such file or directory
  65.  
  66. (16.163317) X86TraceGenerator.cpp:771: New kernel launched
  67. (16.163355) X86TraceGenerator.cpp:772: compute version:2.0
  68. (16.163368) X86TraceGenerator.cpp:773: grid 4 x 1 x 1
  69. (16.163381) X86TraceGenerator.cpp:774: block 256 x 1 x 1
  70. (16.163393) X86TraceGenerator.cpp:775: number of warps per block:8
  71. (16.163404) X86TraceGenerator.cpp:776: number of total warps:32
  72. (16.163416) X86TraceGenerator.cpp:777: # threads per block : 256
  73. (16.163427) X86TraceGenerator.cpp:778: number of register per thread:0
  74. (16.163438) X86TraceGenerator.cpp:779: number of shared memory per thread:0
  75. (16.163458) X86TraceGenerator.cpp:817: max blocks per core : 6
  76. (16.167410) X86TraceGenerator.cpp:1078: mkdir -p /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/macsim_Trace/_Z15integrateBodiesIfLb0EEvPN4vec4IT_E4TypeES4_S4_jjffi_1/ (status 0)
  77.  
  78. (16.167461) X86TraceGenerator.cpp:1079: errno is 0 message is Success
  79.  
  80. (31.551816) X86TraceGenerator.cpp:771: New kernel launched
  81. (31.551859) X86TraceGenerator.cpp:772: compute version:2.0
  82. (31.551879) X86TraceGenerator.cpp:773: grid 4 x 1 x 1
  83. (31.551900) X86TraceGenerator.cpp:774: block 256 x 1 x 1
  84. (31.551928) X86TraceGenerator.cpp:775: number of warps per block:8
  85. (31.551953) X86TraceGenerator.cpp:776: number of total warps:32
  86. (31.551976) X86TraceGenerator.cpp:777: # threads per block : 256
  87. (31.551999) X86TraceGenerator.cpp:778: number of register per thread:0
  88. (31.552022) X86TraceGenerator.cpp:779: number of shared memory per thread:0
  89. (31.552047) X86TraceGenerator.cpp:817: max blocks per core : 6
  90. (31.556119) X86TraceGenerator.cpp:1078: mkdir -p /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/macsim_Trace/_Z15integrateBodiesIfLb0EEvPN4vec4IT_E4TypeES4_S4_jjffi_2/ (status 0)
  91.  
  92. (31.556209) X86TraceGenerator.cpp:1079: errno is 0 message is Success
  93.  
  94. (46.961537) X86TraceGenerator.cpp:771: New kernel launched
  95. (46.961581) X86TraceGenerator.cpp:772: compute version:2.0
  96. (46.961601) X86TraceGenerator.cpp:773: grid 4 x 1 x 1
  97. (46.961623) X86TraceGenerator.cpp:774: block 256 x 1 x 1
  98. (46.961649) X86TraceGenerator.cpp:775: number of warps per block:8
  99. (46.961675) X86TraceGenerator.cpp:776: number of total warps:32
  100. (46.961698) X86TraceGenerator.cpp:777: # threads per block : 256
  101. (46.961722) X86TraceGenerator.cpp:778: number of register per thread:0
  102. (46.961745) X86TraceGenerator.cpp:779: number of shared memory per thread:0
  103. (46.961770) X86TraceGenerator.cpp:817: max blocks per core : 6
  104. (46.965670) X86TraceGenerator.cpp:1078: mkdir -p /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/macsim_Trace/_Z15integrateBodiesIfLb0EEvPN4vec4IT_E4TypeES4_S4_jjffi_3/ (status 0)
  105.  
  106. (46.965721) X86TraceGenerator.cpp:1079: errno is 0 message is Success
  107.  
  108. (62.341825) X86TraceGenerator.cpp:771: New kernel launched
  109. (62.341866) X86TraceGenerator.cpp:772: compute version:2.0
  110. (62.341887) X86TraceGenerator.cpp:773: grid 4 x 1 x 1
  111. (62.341911) X86TraceGenerator.cpp:774: block 256 x 1 x 1
  112. (62.341935) X86TraceGenerator.cpp:775: number of warps per block:8
  113. (62.341960) X86TraceGenerator.cpp:776: number of total warps:32
  114. (62.341984) X86TraceGenerator.cpp:777: # threads per block : 256
  115. (62.342006) X86TraceGenerator.cpp:778: number of register per thread:0
  116. (62.342030) X86TraceGenerator.cpp:779: number of shared memory per thread:0
  117. (62.342054) X86TraceGenerator.cpp:817: max blocks per core : 6
  118. (62.345955) X86TraceGenerator.cpp:1078: mkdir -p /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/macsim_Trace/_Z15integrateBodiesIfLb0EEvPN4vec4IT_E4TypeES4_S4_jjffi_4/ (status 0)
  119.  
  120. (62.346010) X86TraceGenerator.cpp:1079: errno is 0 message is Success
  121.  
  122. (77.762645) X86TraceGenerator.cpp:771: New kernel launched
  123. (77.762684) X86TraceGenerator.cpp:772: compute version:2.0
  124. (77.762704) X86TraceGenerator.cpp:773: grid 4 x 1 x 1
  125. (77.762727) X86TraceGenerator.cpp:774: block 256 x 1 x 1
  126. (77.762752) X86TraceGenerator.cpp:775: number of warps per block:8
  127. (77.762774) X86TraceGenerator.cpp:776: number of total warps:32
  128. (77.762798) X86TraceGenerator.cpp:777: # threads per block : 256
  129. (77.762824) X86TraceGenerator.cpp:778: number of register per thread:0
  130. (77.762847) X86TraceGenerator.cpp:779: number of shared memory per thread:0
  131. (77.762874) X86TraceGenerator.cpp:817: max blocks per core : 6
  132. (77.765837) X86TraceGenerator.cpp:1078: mkdir -p /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/macsim_Trace/_Z15integrateBodiesIfLb0EEvPN4vec4IT_E4TypeES4_S4_jjffi_5/ (status 0)
  133.  
  134. (77.765885) X86TraceGenerator.cpp:1079: errno is 0 message is Success
  135.  
  136. (93.150533) X86TraceGenerator.cpp:771: New kernel launched
  137. (93.150571) X86TraceGenerator.cpp:772: compute version:2.0
  138. (93.150591) X86TraceGenerator.cpp:773: grid 4 x 1 x 1
  139. (93.150612) X86TraceGenerator.cpp:774: block 256 x 1 x 1
  140. (93.150638) X86TraceGenerator.cpp:775: number of warps per block:8
  141. (93.150662) X86TraceGenerator.cpp:776: number of total warps:32
  142. (93.150686) X86TraceGenerator.cpp:777: # threads per block : 256
  143. (93.150709) X86TraceGenerator.cpp:778: number of register per thread:0
  144. (93.150732) X86TraceGenerator.cpp:779: number of shared memory per thread:0
  145. (93.150757) X86TraceGenerator.cpp:817: max blocks per core : 6
  146. (93.153666) X86TraceGenerator.cpp:1078: mkdir -p /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/macsim_Trace/_Z15integrateBodiesIfLb0EEvPN4vec4IT_E4TypeES4_S4_jjffi_6/ (status 0)
  147.  
  148. (93.153715) X86TraceGenerator.cpp:1079: errno is 0 message is Success
  149.  
  150. (108.538777) X86TraceGenerator.cpp:771: New kernel launched
  151. (108.538831) X86TraceGenerator.cpp:772: compute version:2.0
  152. (108.538846) X86TraceGenerator.cpp:773: grid 4 x 1 x 1
  153. (108.538859) X86TraceGenerator.cpp:774: block 256 x 1 x 1
  154. (108.538871) X86TraceGenerator.cpp:775: number of warps per block:8
  155. (108.538883) X86TraceGenerator.cpp:776: number of total warps:32
  156. (108.538895) X86TraceGenerator.cpp:777: # threads per block : 256
  157. (108.538906) X86TraceGenerator.cpp:778: number of register per thread:0
  158. (108.538918) X86TraceGenerator.cpp:779: number of shared memory per thread:0
  159. (108.538931) X86TraceGenerator.cpp:817: max blocks per core : 6
  160. (108.541826) X86TraceGenerator.cpp:1078: mkdir -p /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/macsim_Trace/_Z15integrateBodiesIfLb0EEvPN4vec4IT_E4TypeES4_S4_jjffi_7/ (status 0)
  161.  
  162. (108.541878) X86TraceGenerator.cpp:1079: errno is 0 message is Success
  163.  
  164. (123.948039) X86TraceGenerator.cpp:771: New kernel launched
  165. (123.948076) X86TraceGenerator.cpp:772: compute version:2.0
  166. (123.948089) X86TraceGenerator.cpp:773: grid 4 x 1 x 1
  167. (123.948102) X86TraceGenerator.cpp:774: block 256 x 1 x 1
  168. (123.948113) X86TraceGenerator.cpp:775: number of warps per block:8
  169. (123.948125) X86TraceGenerator.cpp:776: number of total warps:32
  170. (123.948137) X86TraceGenerator.cpp:777: # threads per block : 256
  171. (123.948149) X86TraceGenerator.cpp:778: number of register per thread:0
  172. (123.948160) X86TraceGenerator.cpp:779: number of shared memory per thread:0
  173. (123.948179) X86TraceGenerator.cpp:817: max blocks per core : 6
  174. (123.951005) X86TraceGenerator.cpp:1078: mkdir -p /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/macsim_Trace/_Z15integrateBodiesIfLb0EEvPN4vec4IT_E4TypeES4_S4_jjffi_8/ (status 0)
  175.  
  176. (123.951056) X86TraceGenerator.cpp:1079: errno is 0 message is Success
  177.  
  178. (139.448141) X86TraceGenerator.cpp:771: New kernel launched
  179. (139.448179) X86TraceGenerator.cpp:772: compute version:2.0
  180. (139.448193) X86TraceGenerator.cpp:773: grid 4 x 1 x 1
  181. (139.448206) X86TraceGenerator.cpp:774: block 256 x 1 x 1
  182. (139.448217) X86TraceGenerator.cpp:775: number of warps per block:8
  183. (139.448229) X86TraceGenerator.cpp:776: number of total warps:32
  184. (139.448241) X86TraceGenerator.cpp:777: # threads per block : 256
  185. (139.448252) X86TraceGenerator.cpp:778: number of register per thread:0
  186. (139.448264) X86TraceGenerator.cpp:779: number of shared memory per thread:0
  187. (139.448277) X86TraceGenerator.cpp:817: max blocks per core : 6
  188. (139.452406) X86TraceGenerator.cpp:1078: mkdir -p /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/macsim_Trace/_Z15integrateBodiesIfLb0EEvPN4vec4IT_E4TypeES4_S4_jjffi_9/ (status 0)
  189.  
  190. (139.452491) X86TraceGenerator.cpp:1079: errno is 0 message is Success
  191.  
  192. (154.893865) X86TraceGenerator.cpp:771: New kernel launched
  193. (154.893908) X86TraceGenerator.cpp:772: compute version:2.0
  194. (154.893922) X86TraceGenerator.cpp:773: grid 4 x 1 x 1
  195. (154.893935) X86TraceGenerator.cpp:774: block 256 x 1 x 1
  196. (154.893947) X86TraceGenerator.cpp:775: number of warps per block:8
  197. (154.893959) X86TraceGenerator.cpp:776: number of total warps:32
  198. (154.893971) X86TraceGenerator.cpp:777: # threads per block : 256
  199. (154.893983) X86TraceGenerator.cpp:778: number of register per thread:0
  200. (154.893994) X86TraceGenerator.cpp:779: number of shared memory per thread:0
  201. (154.894014) X86TraceGenerator.cpp:817: max blocks per core : 6
  202. (154.898086) X86TraceGenerator.cpp:1078: mkdir -p /local/lbraun/CUDA_5.0_SKD/5_Simulations/nbody/macsim_Trace/_Z15integrateBodiesIfLb0EEvPN4vec4IT_E4TypeES4_S4_jjffi_10/ (status 0)
  203.  
  204. (154.898160) X86TraceGenerator.cpp:1079: errno is 0 message is Success
  205.  
  206. 1024 bodies, total time for 10 iterations: 154364.375 ms
  207. = 0.000 billion interactions per second
  208. = 0.001 single-precision GFLOP/s at 20 flops per interaction
  209. [Thread 0x7fffeba8d700 (LWP 28129) exited]
  210. [Thread 0x7fffec28e700 (LWP 28122) exited]
  211.  
  212. Program received signal SIGSEGV, Segmentation fault.
  213. 0x00007ffff3a37213 in llvm::StringRef::operator[](unsigned long) const () at StringRef.h:192
  214. 192 return Data[Index];
Advertisement
Add Comment
Please, Sign In to add comment