Difference between revisions of "Cuda"

From Ghoulwiki
Jump to: navigation, search
 
(troubleshooting)
 
(25 intermediate revisions by the same user not shown)
Line 1: Line 1:
<pre><nowiki>
+
== troubleshooting ==
N=16384
 
DATASIZE_IN_RAW=576kb
 
DATASIZE_IN_STATE=64kb
 
DATASIZE_IN_INDEX=18kb
 
DATASIZE_IN_TOTAL=658kb
 
DATASIZE_OUT_TOTAL=16384kb
 
assert(INDEXPOS_0(I0) == INDEXSTART_1-1)=1
 
assert(INDEXPOS_1(I0-1,I0) == INDEXSTART_2-1)=1
 
assert(INDEXPOS_2(I0-1,I0-1,I0) == INDEX_END-1)=1
 
assert(sz < 255)=1
 
-2.453896,-2.369326,-2.369326,...,3.864799
 
INDEXPOS_0(0 )=0.000000
 
INDEXPOS_0(I0 )=16.000000
 
INDEXPOS_1(0,0)=17.000000
 
INDEXPOS_1(0,I0)=33.000000
 
INDEXPOS_1(1,0)=34.000000
 
INDEXPOS_1(1,I0)=50.000000
 
pIndex[INDEXPOS_0(0 )]=-2.453896
 
pIndex[INDEXPOS_0(I0 )]=3.864799
 
index0 = -2.453896,-1.726156,...,3.864799
 
SZ=4
 
self = -1.788016,-2.257454,-2.724891,-2.724891,...
 
x=0 [-2.5;-1.7]
 
  y=0 [-2.3;-2.1]
 
    z=0 [-2.8;-2.7]
 
        inner 0 = 0.000000
 
        inner 1 = 5.901756
 
        inner 2 = 11.745769
 
        inner 3 = 19.288576
 
    z=1 [-2.7;-2.5]
 
        inner 4 = 17.572510
 
        inner 5 = 16.600601
 
        inner 6 = 24.219767
 
        inner 7 = 8.167437
 
    z=2 [-2.5;-2.4]
 
        inner 8 = 18.507490
 
        inner 9 = 7.554741
 
        inner 10 = 20.370079
 
        inner 11 = 29.691578
 
    z=3 [-2.4;-2.4]
 
        inner 12 = 22.642988
 
        inner 13 = 11.601787
 
        inner 14 = 13.652305
 
        inner 15 = 18.196127
 
    z=4 [-2.4;-2.3]
 
        inner 16 = 14.000830
 
        inner 17 = 12.065138
 
        inner 18 = 24.476425
 
        inner 19 = 23.872925
 
    z=5 [-2.3;-2.3]
 
        inner 20 = 12.756110
 
        inner 21 = 15.190945
 
        inner 22 = 9.769132
 
        inner 23 = 8.995293
 
    z=6 [-2.3;-2.3]
 
        inner 24 = 11.085899
 
        inner 25 = 10.686364
 
        inner 26 = 23.381184
 
        inner 27 = 11.656428
 
    z=7 [-2.3;-2.3]
 
        inner 28 = 32.430786
 
        inner 29 = 8.369833
 
        inner 30 = 23.406630
 
        inner 31 = 15.185813
 
    z=8 [-2.3;-2.2]
 
        inner 32 = 10.964545
 
        inner 33 = 14.118701
 
        inner 34 = 18.430721
 
        inner 35 = 35.430370
 
  y=1 [-2.1;-2.0]
 
    z=0 [-2.4;-2.3]
 
        inner 64 = 16.223408
 
        inner 65 = 16.639528
 
        inner 66 = 14.283614
 
        inner 67 = 42.721340
 
    z=1 [-2.3;-2.3]
 
        inner 68 = 7.783429
 
        inner 69 = 13.231225
 
        inner 70 = 11.384384
 
        inner 71 = 50.390957
 
    z=2 [-2.3;-2.3]
 
        inner 72 = 25.590431
 
        inner 73 = 45.739227
 
        inner 74 = 10.842459
 
        inner 75 = 20.392258
 
    z=3 [-2.3;-2.2]
 
        inner 76 = 12.485866
 
        inner 77 = 9.493233
 
        inner 78 = 12.459182
 
        inner 79 = 14.626216
 
    z=4 [-2.2;-2.2]
 
        inner 80 = 11.382857
 
        inner 81 = 8.399722
 
        inner 82 = 25.005053
 
        inner 83 = 19.014940
 
    z=5 [-2.2;-2.2]
 
        inner 84 = 29.822359
 
        inner 85 = 13.966319
 
        inner 86 = 16.870075
 
        inner 87 = 10.419142
 
  y=2 [-2.0;-1.9]
 
    z=0 [-2.3;-2.2]
 
        inner 128 = 10.847272
 
        inner 129 = 12.658548
 
        inner 130 = 18.869101
 
        inner 131 = 20.591751
 
  y=3 [-1.9;-1.9]
 
  y=4 [-1.9;-1.8]
 
  y=5 [-1.8;-1.7]
 
x=1 [-1.7;-1.5]
 
  y=0 [-2.2;-2.0]
 
    z=0 [-2.6;-2.5]
 
        inner 1024 = 7.998069
 
        inner 1025 = 3.119650
 
        inner 1026 = 5.771182
 
        inner 1027 = 5.366159
 
    z=1 [-2.5;-2.4]
 
        inner 1028 = 15.597795
 
        inner 1029 = 16.404339
 
        inner 1030 = 9.193154
 
        inner 1031 = 24.535093
 
    z=2 [-2.4;-2.4]
 
        inner 1032 = 24.469870
 
        inner 1033 = 11.403264
 
        inner 1034 = 34.110180
 
        inner 1035 = 14.567740
 
    z=3 [-2.4;-2.4]
 
        inner 1036 = 11.105278
 
        inner 1037 = 24.348482
 
        inner 1038 = 42.786793
 
        inner 1039 = 11.546680
 
    z=4 [-2.4;-2.3]
 
        inner 1040 = 29.355791
 
        inner 1041 = 13.012123
 
        inner 1042 = 4.781135
 
        inner 1043 = 11.303662
 
    z=5 [-2.3;-2.3]
 
        inner 1044 = 18.599432
 
        inner 1045 = 11.701448
 
        inner 1046 = 17.839315
 
        inner 1047 = 15.079315
 
    z=6 [-2.3;-2.2]
 
        inner 1048 = 26.009691
 
        inner 1049 = 8.960336
 
        inner 1050 = 23.570415
 
        inner 1051 = 56.983021
 
    z=7 [-2.2;-2.2]
 
        inner 1052 = 33.761017
 
        inner 1053 = 11.753607
 
        inner 1054 = 31.582930
 
        inner 1055 = 18.510578
 
  y=1 [-2.0;-1.9]
 
    z=0 [-2.3;-2.3]
 
        inner 1088 = 21.843861
 
        inner 1089 = 12.935850
 
        inner 1090 = 64.940254
 
        inner 1091 = 42.734600
 
    z=1 [-2.3;-2.2]
 
        inner 1092 = 30.705534
 
        inner 1093 = 12.135798
 
        inner 1094 = 12.449890
 
        inner 1095 = 12.329914
 
    z=2 [-2.2;-2.2]
 
        inner 1096 = 31.151951
 
        inner 1097 = 32.529907
 
        inner 1098 = 14.172465
 
        inner 1099 = 12.578788
 
  y=2 [-1.9;-1.8]
 
    z=0 [-2.2;-2.2]
 
        inner 1152 = 13.478780
 
        inner 1153 = 32.812008
 
        inner 1154 = 20.965910
 
        inner 1155 = 28.627789
 
  y=3 [-1.8;-1.8]
 
  y=4 [-1.8;-1.7]
 
x=2 [-1.5;-1.3]
 
  y=0 [-2.2;-1.9]
 
    z=0 [-2.6;-2.5]
 
        inner 2048 = 28.749586
 
        inner 2049 = 36.384407
 
        inner 2050 = 9.435517
 
        inner 2051 = 10.165879
 
    z=1 [-2.5;-2.4]
 
        inner 2052 = 28.975939
 
        inner 2053 = 17.722677
 
        inner 2054 = 5.991668
 
        inner 2055 = 7.278506
 
    z=2 [-2.4;-2.4]
 
        inner 2056 = 28.724413
 
        inner 2057 = 13.053309
 
        inner 2058 = 13.563144
 
        inner 2059 = 14.046345
 
    z=3 [-2.4;-2.3]
 
        inner 2060 = 35.615978
 
        inner 2061 = 15.967229
 
        inner 2062 = 9.546773
 
        inner 2063 = 24.217566
 
    z=4 [-2.3;-2.3]
 
        inner 2064 = 53.290894
 
        inner 2065 = 9.825660
 
        inner 2066 = 15.643993
 
        inner 2067 = 10.022723
 
    z=5 [-2.3;-2.3]
 
        inner 2068 = 59.701759
 
        inner 2069 = 20.153185
 
        inner 2070 = 10.990539
 
        inner 2071 = 23.136860
 
    z=6 [-2.3;-2.3]
 
        inner 2072 = 6.848102
 
        inner 2073 = 54.616154
 
        inner 2074 = 8.828905
 
        inner 2075 = 8.405998
 
    z=7 [-2.3;-2.2]
 
        inner 2076 = 23.348570
 
        inner 2077 = 15.214012
 
        inner 2078 = 9.893643
 
        inner 2079 = 22.549686
 
    z=8 [-2.2;-2.2]
 
        inner 2080 = 35.303177
 
        inner 2081 = 13.472959
 
        inner 2082 = 27.748701
 
        inner 2083 = 19.738178
 
  y=1 [-1.9;-1.8]
 
    z=0 [-2.3;-2.2]
 
        inner 2112 = 34.979721
 
        inner 2113 = 24.496271
 
        inner 2114 = 19.322412
 
        inner 2115 = 9.607713
 
    z=1 [-2.2;-2.2]
 
        inner 2116 = 44.412495
 
        inner 2117 = 22.303303
 
        inner 2118 = 12.305737
 
        inner 2119 = 51.542202
 
  y=2 [-1.8;-1.7]
 
x=3 [-1.3;-1.2]
 
  y=0 [-2.2;-1.9]
 
    z=0 [-2.5;-2.4]
 
        inner 3072 = 32.804501
 
        inner 3073 = 5.819980
 
        inner 3074 = 21.022861
 
        inner 3075 = 12.083915
 
    z=1 [-2.4;-2.3]
 
        inner 3076 = 13.468491
 
        inner 3077 = 16.011194
 
        inner 3078 = 31.638832
 
        inner 3079 = 33.021862
 
    z=2 [-2.3;-2.3]
 
        inner 3080 = 11.166696
 
        inner 3081 = 6.983787
 
        inner 3082 = 9.400255
 
        inner 3083 = 6.579343
 
    z=3 [-2.3;-2.3]
 
        inner 3084 = 15.449165
 
        inner 3085 = 38.091919
 
        inner 3086 = 31.973207
 
        inner 3087 = 8.912704
 
    z=4 [-2.3;-2.3]
 
        inner 3088 = 16.650330
 
        inner 3089 = 9.273459
 
        inner 3090 = 28.364801
 
        inner 3091 = 15.845580
 
    z=5 [-2.3;-2.3]
 
        inner 3092 = 24.548090
 
        inner 3093 = 23.099260
 
        inner 3094 = 7.603713
 
        inner 3095 = 13.797179
 
    z=6 [-2.3;-2.3]
 
        inner 3096 = 11.609632
 
        inner 3097 = 16.984091
 
        inner 3098 = 9.855360
 
        inner 3099 = 40.032089
 
    z=7 [-2.3;-2.2]
 
        inner 3100 = 33.886070
 
        inner 3101 = 6.892903
 
        inner 3102 = 11.529577
 
        inner 3103 = 23.990860
 
  y=1 [-1.9;-1.7]
 
    z=0 [-2.2;-2.2]
 
        inner 3136 = 15.759767
 
        inner 3137 = 10.188901
 
        inner 3138 = 12.234061
 
        inner 3139 = 19.372662
 
atom[0]=5118 atom[1]=0 iNumResults=5118 kMaxResults=2097152
 
check...
 
check:iNumResults=5118 maxc=14 for i=4176
 
  
Press ENTER to exit...
+
* compiling cuda samples : error message "... cannot be declared weak" : gcc-4.4 is not supported,
</nowiki></pre>
+
** http://carlosscheidegger.wordpress.com/2009/11/16/cuda-2-3-on-ubuntu-9-10/
 +
** add “–compiler-bindir=/usr/bin/gcc-4.3″ to NVCCFLAGS in your makefiles
 +
** cuda/shared/common.mk
 +
** cuda//C/common/common.mk
 +
 
 +
 
 +
* running example : segfault
 +
** cuda driver not installed ?
 +
** try :  make emu=1
 +
** try :  make dbg=1 emu=1
 +
** gdb ... backtrace:  0xb7fa7ccd in cudaGetDeviceProperties () from /usr/local/cuda/lib/libcudart.so.2
 +
 
 +
 
 +
* error : /usr/bin/ld: cannot find -lglut
 +
** solution : apt-get install libglut3-dev
 +
 
 +
 
 +
* error (during launch) : error while loading shared libraries: libcudart.so.2: cannot open shared object file: No such file or directory
 +
** solution : /etc/ld.so.conf
 +
** add line : /usr/local/cuda/lib
 +
** start /sbin/ldconfig
 +
 
 +
== old ==
 +
 
 +
[[cuda_old_notes]]

Latest revision as of 00:16, 29 November 2009

troubleshooting


  • running example : segfault
    • cuda driver not installed ?
    • try : make emu=1
    • try : make dbg=1 emu=1
    • gdb ... backtrace: 0xb7fa7ccd in cudaGetDeviceProperties () from /usr/local/cuda/lib/libcudart.so.2


  • error : /usr/bin/ld: cannot find -lglut
    • solution : apt-get install libglut3-dev


  • error (during launch) : error while loading shared libraries: libcudart.so.2: cannot open shared object file: No such file or directory
    • solution : /etc/ld.so.conf
    • add line : /usr/local/cuda/lib
    • start /sbin/ldconfig

old

cuda_old_notes