Hello All, I'm trying to include the OpenCL thorns to try and get WaveToyOpenCL to run. When compiling, I run into the following errors. COMPILING arrangements/CactusUtils/OpenCLRunTime/src/kernel-info.cc "/home/ram0311/Cactus/arrangements/Carpet/CarpetLib/src/typeprops.hh", line 62: warning: statement is unreachable return -1; ^
"/home/ram0311/Cactus/arrangements/Carpet/CarpetLib/src/typeprops.hh", line 73: warning: statement is unreachable return -1; ^
"/home/ram0311/Cactus/arrangements/Carpet/CarpetLib/src/typeprops.hh", line 84: warning: statement is unreachable return -1; ^
"/home/ram0311/Cactus/arrangements/CactusUtils/OpenCLRunTime/src/device.hh", line 19: catastrophic error: cannot open source file "CL/opencl.h" # include <CL/opencl.h> ^
1 catastrophic error detected in the compilation of "/home/ram0311/Cactus/configs/opencl/build/OpenCLRunTime/kernel-info.cc". Compilation terminated. make[3]: *** [kernel-info.cc.o] Error 2 make[2]: *** [make.checked] Error 2 make[1]: *** [/home/ram0311/Cactus/configs/opencl/lib/libthorn_OpenCLRunTime.a] Error 2 I've removed the comments from the einsteintoolkit manifest to update to include everything in the thorns. I had the same error when compiling the OpenCL thorn as well.
On Fri, May 01, 2015 at 10:14:29AM -0500, Christopher Ramirez wrote:
cannot open source file "CL/opencl.h"# include <CL/opencl.h> ^
1 catastrophic error detected in the compilation of "/home/ram0311/Cactus/configs/opencl/build/OpenCLRunTime/kernel-info.cc". Compilation terminated.
I've removed the comments from the einsteintoolkit manifest to update to include everything in the thorns. I had the same error when compiling the OpenCL thorn as well.
Do you have the file CL/opencl.h installed? This is typically distributed as part of an opencl installation, either by a GPU implementation like the one from Nvidia, or for CPUs by AMD or Intel.
Frank
Yes, the cuda toolkit is installed, and from my understanding, opencl is included with it.
On Mon, May 4, 2015 at 9:09 AM, Frank Loeffler knarf@cct.lsu.edu wrote:
On Fri, May 01, 2015 at 10:14:29AM -0500, Christopher Ramirez wrote:
cannot open source file "CL/opencl.h"# include <CL/opencl.h> ^
1 catastrophic error detected in the compilation of "/home/ram0311/Cactus/configs/opencl/build/OpenCLRunTime/kernel-info.cc". Compilation terminated.
I've removed the comments from the einsteintoolkit manifest to update to include everything in the thorns. I had the same error when compiling the OpenCL thorn as well.
Do you have the file CL/opencl.h installed? This is typically distributed as part of an opencl installation, either by a GPU implementation like the one from Nvidia, or for CPUs by AMD or Intel.
Frank
On Mon, May 04, 2015 at 09:11:23AM -0500, Christopher Ramirez wrote:
Yes, the cuda toolkit is installed, and from my understanding, opencl is included with it.
In that case it would be helpful to get a full log of the build process (make sim VERBOSE=yes), and the location of the CL/opencl.h file it should have found, and the option list you used.
Especially interesting would be whether you set variables like OPENCL_DIR, OPENCL_INC_DIRS, OPENCL_LIB_DIRS, or OPENCL_LIBS.
Frank
These are the options, and I've attached a logfile. F90 = pgf90 F77 = pgf77 #F90 = ifort #F77 = ifort #CXX = pgCC #CC = pgcc CXX = icpc CC = icc
HDF5_DIR = /share/apps/hdf5-1.8.12
LAPACK = yes LAPACK_DIR = /home/garrison/ifort64/lib LAPACK_LIBS = acml ifcoremt_pic imf irc svml
OPENCL_DIR = /share/apps/cuda-toolkit/6.5/ OPENCL_INC_DIRS = /share/apps/cuda-toolkit/6.5/include/CL OPENCL_LIB_DIRS = /share/apps/cuda-toolkit/6.5/lib64
#MPI = CUSTOM MPI_DIR = /share/apps/openmpi-1.6.5 MPI_INC_DIRS = /share/apps/openmpi-1.6.5/include MPI_LIB_DIRS = /share/apps/openmpi-1.6.5/lib MPI_LIBS = mpi mpi_cxx open-rte open-pal dl nsl util
FFTW = yes FFTW_DIR = /home/garrison/fftw3 FFTW_LIBS = fftw3_threads fftw3_mpi $(MPI_LIBS) fftw3 m
OPTIMISE = yes FFLAGS = -O3 -fast -Mipa=fast,inline -tp=x64 CPPFLAGS = -DCCTK_DISABLE_OMP_COLLAPSE FPPFLAGS = -DCCTK_DISABLE_OMP_COLLAPSE #C_OPTIMISE_FLAGS = -O3 -fast -Mipa=fast,inline -tp=x64 #CXX_OPTIMISE_FLAGS = -O3 -fast -Mipa=fast,inline -tp=x64 C_OPTIMISE_FLAGS = -Os -ip -pthread -no-prec-div CXX_OPTIMISE_FLAGS = -Os -ip -pthread -no-prec-div F77_OPTIMISE_FLAGS = -O3 -fast -Mipa=fast,inline -tp=x64 F90_OPTIMISE_FLAGS = -O3 -fast -Mipa=fast,inline -tp=x64 #F77_OPTIMISE_FLAGS = -Os -ip -no-prec-div #F90_OPTIMISE_FLAGS = -Os -ip -no-prec-div
PTHREADS = yes VERBOSE = yes
#DEBUG=all
On Mon, May 4, 2015 at 9:21 AM, Frank Loeffler knarf@cct.lsu.edu wrote:
On Mon, May 04, 2015 at 09:11:23AM -0500, Christopher Ramirez wrote:
Yes, the cuda toolkit is installed, and from my understanding, opencl is included with it.
In that case it would be helpful to get a full log of the build process (make sim VERBOSE=yes), and the location of the CL/opencl.h file it should have found, and the option list you used.
Especially interesting would be whether you set variables like OPENCL_DIR, OPENCL_INC_DIRS, OPENCL_LIB_DIRS, or OPENCL_LIBS.
Frank
On Mon, May 04, 2015 at 03:04:49PM -0500, Christopher Ramirez wrote:
OPENCL_INC_DIRS = /share/apps/cuda-toolkit/6.5/include/CL
I believe that this should be /share/apps/cuda-toolkit/6.5/include. The "CL" is supposed to be used in the #include statement (and also is in your error message.)
Frank
users@lists.einsteintoolkit.org
-
Christopher Ramirez -
Frank Loeffler