Difference between revisions of "Cuda"

From Ghoulwiki
Jump to: navigation, search
(→‎troubleshooting)
 
(5 intermediate revisions by the same user not shown)
Line 1: Line 1:
−
* http://zwischenwelt.org/svn/robertdiplarbeit
+
== troubleshooting ==
−
* [[CudaVsNested]]
 
−
* [[CudaLog]]
 
  
 +
* compiling cuda samples : error message "... cannot be declared weak" : gcc-4.4 is not supported,
 +
** 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
  
−
* http://www.litec-computer.de/PC-Komponenten/Grafikkarten/PCI-express/nVidia/Gigabyte-GV-NX85T256H-8500GT-512MB-Dual-DVI-TV-out-passiv::13515.html
 
−
* http://www.litec-computer.de/PC-Komponenten/Grafikkarten/PCI-express/nVidia/ASUS-EN8500GT-SILENT-MAGIC-HTD-512MB-DVI-TV-out-passiv::13117.html
 
−
* beachten : keine 88 (kann kein atomic), nur 85 oder 86, möglichst viel ram (512mb) , keine karten mit "Nur 128-bit Speicherinterface"
 
  
−
* svn+ssh://ghoulsblade@zwischenwelt.org/var/svn/robertprojarbeit
+
* running example : segfault
−
* http://zwischenwelt.org/svn/robertprojarbeit
+
** cuda driver not installed ?
−
* http://zwischenwelt.org/svn/robertdiplarbeit
+
** try :  make emu=1
 +
** try :   make dbg=1 emu=1
 +
** gdb ... backtrace: 0xb7fa7ccd in cudaGetDeviceProperties () from /usr/local/cuda/lib/libcudart.so.2
  
−
* nvidia-cuda-forum http://forums.nvidia.com/index.php?showforum=62  (search for 8600)
 
−
* nvidia-cuda-hp http://developer.nvidia.com/object/cuda.html
 
−
* FAQ : http://forums.nvidia.com/index.php?showtopic=36286&hl=8600  (many interesting programming tips)
 
−
* SIMD : http://en.wikipedia.org/wiki/Vector_processor
 
−
* samples http://developer.download.nvidia.com/compute/cuda/sdk/website/samples.html
 
−
* cuda 1.0 announcement 26.june : http://forums.nvidia.com/index.php?showtopic=39030&hl=8600
 
  
 +
* 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]]
−
*  $(CUDA_BIN_PATH)\nvcc.exe -arch sm_11 -ccbin "$(VCInstallDir)bin" -c -DWIN32 -D_CONSOLE -D_MBCS -Xcompiler /EHsc,/W3,/nologo,/Wp64,/O2,/Zi,/MT -I"$(CUDA_INC_PATH)" -I./ -I../../common/inc -o $(ConfigurationName)\myproj.obj myproj.cu
 
−
 
 
−
== success 11.10.2007 ==
 
−
 
 
−
  gpu/cpu=    0.5  ok  err<=0.5% N=263250 size=9MB IO=15 i3:0,0 tgpu=43.3s tcpu=93.0
 
−
  gpu/cpu=    0.6  ok  err<=0.5% N=2621440 size=90MB IO=32 i3:1,1 tgpu=595.5s tcpu=1074.1
 
−
 
 
−
== new card laptop ==
 
−
 
 
−
<pre>
 
−
name : GeForce 9500M GS
 
−
    523584k totalGlobalMem
 
−
        16k sharedMemPerBlock
 
−
        8k regsPerBlock
 
−
        32 warpSize
 
−
      256k memPitch
 
−
      512 maxThreadsPerBlock
 
−
      512 maxThreadsDim[0]
 
−
      512 maxThreadsDim[1]
 
−
        64 maxThreadsDim[2]
 
−
        63k maxGridSize[0]
 
−
        63k maxGridSize[1]
 
−
        1 maxGridSize[2]
 
−
        64k totalConstMem
 
−
        1 major
 
−
        1 minor
 
−
      927k clockRate
 
−
      256 textureAlignment
 
−
 
 
−
</pre>
 
−
 
 
−
 
 
−
== old cards, 256 mb ==
 
−
<pre>
 
−
##### ##### ##### ##### #####device 0
 
−
name : GeForce 8500 GT
 
−
    261888k totalGlobalMem
 
−
        16k sharedMemPerBlock
 
−
        8k regsPerBlock
 
−
        32 warpSize
 
−
      256k memPitch
 
−
      512 maxThreadsPerBlock
 
−
      512 maxThreadsDim[0]
 
−
      512 maxThreadsDim[1]
 
−
        64 maxThreadsDim[2]
 
−
        63k maxGridSize[0]
 
−
        63k maxGridSize[1]
 
−
        1 maxGridSize[2]
 
−
        64k totalConstMem
 
−
        1 major
 
−
        1 minor
 
−
      1371k clockRate
 
−
      256 textureAlignment
 
−
##### ##### ##### ##### #####device 1
 
−
name : GeForce 8500 GT
 
−
    261824k totalGlobalMem
 
−
        16k sharedMemPerBlock
 
−
        8k regsPerBlock
 
−
        32 warpSize
 
−
      256k memPitch
 
−
      512 maxThreadsPerBlock
 
−
      512 maxThreadsDim[0]
 
−
      512 maxThreadsDim[1]
 
−
        64 maxThreadsDim[2]
 
−
        63k maxGridSize[0]
 
−
        63k maxGridSize[1]
 
−
        1 maxGridSize[2]
 
−
        64k totalConstMem
 
−
        1 major
 
−
        1 minor
 
−
      1371k clockRate
 
−
      256 textureAlignment
 
−
</pre>
 
−
 
 
−
== new cards, 512 mb ==
 
−
 
 
−
<pre>
 
−
##### ##### ##### ##### #####device 0
 
−
name : GeForce 8500 GT
 
−
    524032k totalGlobalMem
 
−
        16k sharedMemPerBlock
 
−
        8k regsPerBlock
 
−
        32 warpSize
 
−
      256k memPitch
 
−
      512 maxThreadsPerBlock
 
−
      512 maxThreadsDim[0]
 
−
      512 maxThreadsDim[1]
 
−
        64 maxThreadsDim[2]
 
−
        63k maxGridSize[0]
 
−
        63k maxGridSize[1]
 
−
        1 maxGridSize[2]
 
−
        64k totalConstMem
 
−
        1 major
 
−
        1 minor
 
−
      896k clockRate
 
−
      256 textureAlignment
 
−
##### ##### ##### ##### #####device 1
 
−
name : GeForce 8500 GT
 
−
    523968k totalGlobalMem
 
−
        16k sharedMemPerBlock
 
−
        8k regsPerBlock
 
−
        32 warpSize
 
−
      256k memPitch
 
−
      512 maxThreadsPerBlock
 
−
      512 maxThreadsDim[0]
 
−
      512 maxThreadsDim[1]
 
−
        64 maxThreadsDim[2]
 
−
        63k maxGridSize[0]
 
−
        63k maxGridSize[1]
 
−
        1 maxGridSize[2]
 
−
        64k totalConstMem
 
−
        1 major
 
−
        1 minor
 
−
      896k clockRate
 
−
      256 textureAlignment
 
−
</pre>
 
−
 
 
−
== sample output ==
 
−
 
 
−
<pre>
 
−
N=65536
 
−
SX=2048
 
−
SY=64
 
−
SZ=2
 
−
I0=32
 
−
DATASIZE_IN_RAW=2304kb
 
−
DATASIZE_IN_STATE=256kb
 
−
DATASIZE_IN_INDEX=136kb
 
−
DATASIZE_IN_TOTAL=2696kb
 
−
DATASIZE_OUT_TOTAL=16384kb
 
−
0.74 sec : reading data from file
 
−
assert passed : (INDEXPOS_0(I0) == INDEXSTART_1-1)
 
−
assert passed : (INDEXPOS_1(I0-1,I0) == INDEXSTART_2-1)
 
−
assert passed : (INDEXPOS_2(I0-1,I0-1,I0) == INDEX_END-1)
 
−
assert passed : (sz < 255)
 
−
-2.478893,-2.459100,-2.459100,...,4.097229
 
−
0.09 sec : generating index data
 
−
0.02 sec : allocate and init device mem
 
−
9.55 sec : exec kernel on device
 
−
0.00 sec : receive results from device
 
−
atom[0]=57100 atom[1]=0 iNumResults=57100 kMaxResults=2097152
 
−
check : with index on cpu...
 
−
check : with index on cpu: iNumResults=57100
 
−
17.29 sec : check : with index on cpu
 
−
 
 
−
Press ENTER to exit...
 
−
</pre>
 
−
coarse-strong-ultra-100-96_10000.txt
 
−
 
 
−
== big file : 750 mb ==
 
−
 
 
−
<pre>
 
−
N=65536
 
−
SX=2048
 
−
SY=64
 
−
SZ=2
 
−
I0=32
 
−
DATASIZE_IN_RAW=2304kb
 
−
DATASIZE_IN_STATE=256kb
 
−
DATASIZE_IN_INDEX=136kb
 
−
DATASIZE_IN_TOTAL=2696kb
 
−
DATASIZE_OUT_TOTAL=16384kb
 
−
line 1:coarse-strong-ultra-000000 000 0.04820 0.05043 0.05505 0.04887 0.05384 0.
 
−
05995 0.06215 0.06603 0.06615 0.06679 0.06202 0.06686 0.06654 0.06499 0.06705 0.
 
−
05835 0.05513 0.05442 0.05398 0.04658 0.05066 0.05162 0.04627 0.04324 0.04433 0.
 
−
04061 0.03673 0.04281 0.04078 0.03822 0.03821 0.03952 0.03648 0.03312 0.03402 0.
 
−
03277 0.03029 0.04310 0.04202 0.04168 0.03964 0.04356 0.04193 0.03870 0.04995 0.
 
−
04837 0.04460 0.04857 0.04831 0.04714 0.04734 0.05127 0.05319 0.05641 0.05886 0.
 
−
05365 0.05752 0.05877 0.05435 0.05526
 
−
line 2:0.05103 0.05033 0.04347 0.04750 0.04574 0.03781 0.03926 0.03612 0.03374 0
 
−
.03207 0.03060 0.02828 0.02507 0.02721 0.02558 0.02493 0.03374 0.02920 0.03031 0
 
−
.02906 0.03283 0.03207 0.03207 0.04170 0.04342 0.04020 0.04298 0.04131 0.04298 0
 
−
.04404 0.04810 0.04727 0.04491 0.04764 0.04301 0.04383 0.04317 0.04511 0.04545 0
 
−
.04818 0.04908 0.04463 0.04620 0.04699 0.04360 0.04529 0.04346 0.04122 0.04011 0
 
−
.03737 0.03293 0.02865 0.02832 0.02520 0.02255 0.02125 0.02035 0.01192 0.01107 0
 
−
.00685 0.01059 0.01442 0.01595 0.02073
 
−
line 3: 0.01839 0.01905 0.02360 0.02169 0.02749 0.02954 0.03428 0.03788 0.03793
 
−
0.04286 0.03990 0.04313 0.04426 0.04382 0.04529 0.04475 0.04587 0.04372 0.04377
 
−
0.04492 0.04141 0.04456 0.04552 0.04159 0.04223 0.03591 0.03698 0.03614 0.03736
 
−
0.03934 0.03516 0.03583 0.02827 0.02601 0.02256 0.02111 0.02014 0.02016 0.02150
 
−
0.01603 0.01632 0.01486 0.01818 0.01843 0.02040 0.02465 0.02337 0.02405 0.02452
 
−
0.02435 0.02745 0.02855 0.03582 0.03742 0.04081 0.04198 0.03672 0.03736 0.03749
 
−
0.03917 0.04121 0.04257 0.04485 0.0417
 
−
line 4:5 0.04121 0.04167 0.03555 0.03806 0.03863 0.03748 0.03451 0.03039 0.02957
 
−
0.02493 0.02768 0.03054 0.02767 0.02438 0.02099 0.01713 0.01462 0.01508 0.01577
 
−
0.01737 0.01791 0.02091 0.02171 0.02182 0.02522 0.02480 0.02493 0.02913 0.02996
 
−
0.03269 0.03296 0.03631 0.03866 0.03451 0.04187 0.03918 0.04450 0.04598 0.04060
 
−
0.04482 0.03857 0.04485 0.04499 0.04898 0.05087 0.04374 0.04700 0.04478 0.04084
 
−
0.04081 0.04103 0.04135 0.03853 0.03664 0.03382 0.02755 0.02830 0.02619 0.02489
 
−
0.02267 0.01911 0.01841 0.01437 0.015
 
−
line 5:69 0.01486 0.01429 0.01689 0.02116 0.02161 0.02497 0.02357 0.02480 0.0248
 
−
6 0.02717 0.03292 0.03393 0.03558 0.03961 0.04140 0.03921 0.03968 0.03907 0.0418
 
−
6 0.04094 0.04488 0.04213 0.04043 0.04132 0.04242 0.04413 0.04329 0.04607 0.0437
 
−
9 0.04371 0.04105 0.03754 0.03824 0.03826 0.03761 0.03649 0.03190 0.03074 0.0221
 
−
8 0.02409 0.02173 0.01948 0.01822 0.01906 0.02054 0.01712 0.01795 0.01876 0.0171
 
−
6 0.02161 0.02460 0.02727 0.02947 0.02950 0.03441 0.03185 0.03891 0.03999 0.0409
 
−
8 0.04559 0.04661 0.04359 0.04212 0.04
 
−
total lines : 1507200
 
−
Drücken Sie eine beliebige Taste . . .
 
−
</pre>
 
−
 
 
−
 
 
−
 
 
−
== big test 1 (without last index on device) ==
 
−
 
 
−
<pre>
 
−
N=1048576
 
−
SX=32768
 
−
SY=1024
 
−
SZ=32
 
−
I0=32
 
−
DATASIZE_IN_RAW=36864kb
 
−
DATASIZE_IN_STATE=4096kb
 
−
DATASIZE_IN_INDEX=136kb
 
−
DATASIZE_IN_TOTAL=41096kb
 
−
DATASIZE_OUT_TOTAL=16384kb
 
−
ReadTextData data/Corel_ColorMoments_9d.ascii : 68040 lines of real data, added
 
−
980536 lines of random data
 
−
WARNING ! iRealNumLines=68040 does not match the hardcoded N=1048576
 
−
1.08 sec : reading data from file
 
−
assert passed : (INDEXPOS_0(I0) == INDEXSTART_1-1)
 
−
assert passed : (INDEXPOS_1(I0-1,I0) == INDEXSTART_2-1)
 
−
assert passed : (INDEXPOS_2(I0-1,I0-1,I0) == INDEX_END-1)
 
−
assert passed : (sz < 255)
 
−
-2.478893,-2.478893,-2.478893,...,4.097229
 
−
1.86 sec : generating index data
 
−
0.06 sec : allocate and init device mem
 
−
764.99 sec : exec kernel on device
 
−
0.00 sec : receive results from device
 
−
atom[0]=60051 atom[1]=0 iNumResults=60051 kMaxResults=2097152
 
−
check : with index on cpu...
 
−
check : with index on cpu: iNumResults=60051
 
−
357.94 sec : check : with index on cpu
 
−
 
 
−
Press ENTER to exit...
 
−
</pre>
 
−
 
 
−
== big data with all index levels  used in device ==
 
−
<pre>
 
−
N=1048576
 
−
SX=32768
 
−
SY=1024
 
−
SZ=32
 
−
I0=32
 
−
DATASIZE_IN_RAW=36864kb
 
−
DATASIZE_IN_STATE=4096kb
 
−
DATASIZE_IN_INDEX=136kb
 
−
DATASIZE_IN_TOTAL=41096kb
 
−
DATASIZE_OUT_TOTAL=16384kb
 
−
ReadTextData data/Corel_ColorMoments_9d.ascii : 68040 lines of real data, added
 
−
980536 lines of random data
 
−
WARNING ! iRealNumLines=68040 does not match the hardcoded N=1048576
 
−
0.96 sec : reading data from file
 
−
assert passed : (INDEXPOS_0(I0) == INDEXSTART_1-1)
 
−
assert passed : (INDEXPOS_1(I0-1,I0) == INDEXSTART_2-1)
 
−
assert passed : (INDEXPOS_2(I0-1,I0-1,I0) == INDEX_END-1)
 
−
assert passed : (sz < 255)
 
−
-2.478893,-2.478893,-2.478893,...,4.097229
 
−
1.86 sec : generating index data
 
−
0.06 sec : allocate and init device mem
 
−
354.73 sec : exec kernel on device
 
−
0.00 sec : receive results from device
 
−
atom[0]=60051 atom[1]=0 iNumResults=60051 kMaxResults=2097152
 
−
check : with index on cpu...
 
−
check : with index on cpu: iNumResults=60051
 
−
357.97 sec : check : with index on cpu
 
−
 
 
−
Press ENTER to exit...
 
−
</pre>
 
−
 
 
−
== big data with I0:16 : device is faster than cpu ==
 
−
 
 
−
<pre>
 
−
N=1048576
 
−
SX=65536
 
−
SY=4096
 
−
SZ=256
 
−
I0=16
 
−
DATASIZE_IN_RAW=36864kb
 
−
DATASIZE_IN_STATE=4096kb
 
−
DATASIZE_IN_INDEX=18kb
 
−
DATASIZE_IN_TOTAL=40978kb
 
−
DATASIZE_OUT_TOTAL=16384kb
 
−
ReadTextData data/Corel_ColorMoments_9d.ascii : 68040 lines of real data, added
 
−
980536 lines of random data
 
−
WARNING ! iRealNumLines=68040 does not match the hardcoded N=1048576
 
−
0.95 sec : reading data from file
 
−
assert passed : (INDEXPOS_0(I0) == INDEXSTART_1-1)
 
−
assert passed : (INDEXPOS_1(I0-1,I0) == INDEXSTART_2-1)
 
−
assert passed : (INDEXPOS_2(I0-1,I0-1,I0) == INDEX_END-1)
 
−
assert FAILED : (sz < 255)
 
−
-2.478893,-2.478893,-2.478893,...,4.097229
 
−
1.91 sec : generating index data
 
−
0.06 sec : allocate and init device mem
 
−
393.60 sec : exec kernel on device
 
−
0.00 sec : receive results from device
 
−
atom[0]=60051 atom[1]=0 iNumResults=60051 kMaxResults=2097152
 
−
check : with index on cpu...
 
−
check : with index on cpu: iNumResults=60051
 
−
520.65 sec : check : with index on cpu
 
−
 
 
−
Press ENTER to exit...
 
−
 
 
−
</pre>
 
−
 
 
−
<pre>
 
−
gpu/cpu=    0.4  N=65536 size=2MB IO=16 gpu_idx3=0 cpu_idx3=0 time_gpu=10.6s time_cpu=24.8
 
−
gpu/cpu=    0.4  N=65536 size=2MB IO=16 gpu_idx3=0 cpu_idx3=0 time_gpu=10.6s time_cpu=25.3
 
−
gpu/cpu=    0.9  N=32768 size=1MB IO=32 gpu_idx3=0 cpu_idx3=0 time_gpu=3.1s time_cpu=3.4
 
−
gpu/cpu=    0.7  N=32768 size=1MB IO=32 gpu_idx3=0 cpu_idx3=0 time_gpu=2.9s time_cpu=4.3
 
−
</pre>
 

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

Retrieved from "https://ghoulsblade.schattenkind.net/wiki/index.php?title=Cuda&oldid=3525"