Changes between Version 7 and Version 8 of GPUApp
- Timestamp:
- Jul 2, 2010, 5:14:35 PM (14 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
GPUApp
v7 v8 6 6 7 7 == Windows == #windows 8 * '''NVIDIA Cuda''' (BOINC-NVCuda sample app for Windows can be found at "/boinc/samples/nvcuda/") 8 9 === NVIDIA Cuda === 10 11 BOINC-NVCuda sample app for Windows can be found at "/boinc/samples/nvcuda/". 12 9 13 {{{ 10 14 cuda_kernel.cu; cuda.cu; cuda_config.h 11 15 }}} 12 16 The example_app_nvcuda.vcproj can be found at "boin/win_build/". Note that NVIDIA Cuda SDK 3.0 or older supports device emulation mode. If your machine doesn't have a Cuda-enabled GPU, then you should build the sample app in the device emulation mode. Do so by setting "Build -> Configuration Manger -> Configuration" to either Emudebug|Emurelease. It comes to our attention that while compiling the sample app, the linker tries to link both the debug and release libraries, and thus causing the following errors: 13 17 {{{ 14 18 LIBCMTD.lib(dbgheap.obj) : error LNK2005: __heap_alloc already defined in LIBCMT.lib(malloc.obj) … … 17 21 ... 18 22 }}} 19 23 One solution to this problem is to set the Hyprid Cuda/C++ Runtime Library point to "Multi-Threaded Debug (/MTd)". Do so by right click on the project. Set "Properties -> Configuration Properties -> Cuda Build Rule v3.0.14 -> Hybrid CUDA/C++ Options -> Runtime Library" to "Multi-Threaded Debug (/MTd)". 20 24 21 25 The executable file can be found at "boinc/win_build/Build/Win32/build_mode/" (build_mode could be release, debug, emurelease or emudebug). 22 26 23 * '''NVIDIA OpenCL''' (BOINC-NVOpenCL sample app for Windows can be found at "/boin/samples/nvopencl/") 27 === NVIDIA OpenCL === 28 29 BOINC-NVOpenCL sample app for Windows can be found at "/boin/samples/nvopencl/". 30 24 31 {{{ 25 32 nvopencl.hpp; nvopencl.cpp; nvopencl_kernels.cl 26 33 }}} 27 34 The example_app_nvopencl.vcproj can be found at "boin/win_build/". OpenCL doesn't have emulation mode, but it could run on CPU alone by specifying CL_DEVICE_TYPE_CPU or CL_DEVICE_TYPE_ALL when creating an OpenCL context. 28 35 29 36 The Runtime Library needs to be reset to point to "Multi-threaded Debug (/MTd)" to avoid linking issues. Do so by right click on the project. Set "Properties -> Configuration Properties -> C/C++ -> Code Generation -> Runtime Library" to "Multi-threaded Debug (/MTd)". 30 37 31 * '''ATI Stream OpenCL''' (BOINC-ATIOpenCL sample app for Windows can be found at "/boin/samples/atiopencl/") 38 === ATI Stream OpenCL === 39 40 BOINC-ATIOpenCL sample app for Windows can be found at "/boin/samples/atiopencl/". 41 32 42 {{{ 33 43 atiopencl.hpp; atiopencl.cpp; atiopencl_kernels.cl 34 44 }}} 35 45 The example_app_atiopencl.vcproj can be found at "boin/win_build/". It is identical to NVIDIA OpenCL. Prior to build the app, make sure you have already reset the Runtime Library to point to "Multi-threaded Debug (/MTd)". 36 46 37 47 == Linux == #linux 38 48 39 * '''NVIDIA Cuda''' (BOINC-NVCuda sample app for Linux can be found at "/boinc/samples/nvcuda/") 49 === NVIDIA Cuda === 50 BOINC-NVCuda sample app for Linux can be found at "/boinc/samples/nvcuda/". 51 40 52 {{{ 41 53 Makefile; common.mk; cuda_kernel.cu; cuda.cu; cuda_config.h; readme.txt 42 54 }}} 43 55 44 Before running Makefile, you will need to install gcc 4.3 and g++ 4.3. This is because the NVIDIA Cuda SDK 3.0 has not yet worked with gcc 4.0 and g++ 4.0. There should be no issue compiling cuda files with gcc 4.3 and g++ 4.3 on newer NVIDIA Cuda SDK versions. For a successful compilation, please follow these steps: 56 Before running Makefile, you will need to install gcc 4.3 and g++ 4.3. This is because the NVIDIA Cuda SDK 3.0 has not yet worked with gcc 4.0 and g++ 4.0. There should be no issue compiling cuda files with gcc 4.3 and g++ 4.3 on newer NVIDIA Cuda SDK versions. For a successful compilation, please follow these steps: 57 45 58 {{{ 46 59 1) Install gcc-4.3 and g++-4.3: … … 56 69 $ ln -s $(which gcc-4.3) gcc 57 70 }}} 58 The Makefile for Linux is made with the assumption that the NVIDIA Cuda SDK is installed at the default location "$(ROOT)/home/USER_NAME/NVIDIA_GPU_Computing_SDK/". On my Linux machine, for example, it would be "$(ROOT)/home/tuanle/NVIDIA_GPU_Computing_SDK/". Since the absolute path is used in Makefile, you will probably need to edit file "common.mk" before compiling the sample app. Do so by looking for "/home/tuanle/NVIDIA_GPU_Computing_SDK" in file "common.mk" and replace this path with an appropriate path on your machine.59 71 60 What if your machine doesn't have an NVIDIA Cuda-enabled GPU? Then, you can compile and run your app in emulation mode. As far as we know, NVIDIA Cuda SDK 3.1 no longer supports emulation mode. Thus, you will need to install an older Cuda SDK version, like version 3.0, on your machine. To make an executable file in emulation mode, simply type "make emu=1".72 The Makefile for Linux is made with the assumption that the NVIDIA Cuda SDK is installed at the default location "$(ROOT)/home/USER_NAME/NVIDIA_GPU_Computing_SDK/". On my Linux machine, for example, it would be "$(ROOT)/home/tuanle/NVIDIA_GPU_Computing_SDK/". Since the absolute path is used in Makefile, you will probably need to edit file "common.mk" before compiling the sample app. Do so by looking for "/home/tuanle/NVIDIA_GPU_Computing_SDK" in file "common.mk" and replace this path with an appropriate path on your machine. 61 73 62 Also, note that you will need to define some environment variables before running the executable file. 74 What if your machine doesn't have an NVIDIA Cuda-enabled GPU? Then, you can compile and run your app in emulation mode. As far as we know, NVIDIA Cuda SDK 3.1 no longer supports emulation mode. Thus, you will need to install an older Cuda SDK version, like version 3.0, on your machine. To make an executable file in emulation mode, simply type "make emu=1". 75 76 Also, note that you will need to define some environment variables before running the executable file. 63 77 {{{ 64 78 export PATH=/usr/local/cuda/bin:$PATH … … 66 80 }}} 67 81 68 * '''NVIDIA OpenCL''' (BOINC-NVOpenCL sample app for Linux can be found at "/boin/samples/nvopencl/") 82 === NVIDIA OpenCL === 83 84 BOINC-NVOpenCL sample app for Linux can be found at "/boin/samples/nvopencl/". 85 69 86 {{{ 70 87 Makefile; common_opencl; nvopencl.h; nvopencl.cpp; nvopencl_kernels; readme.txt 71 88 }}} 72 89 It appears that NVIDIA OpenCL SDK is missing shared library file libOpenCL.so which is needed at compile time. This library file comes with the kernel driver package which can be installed only when your machine has an NVIDIA Cuda-enabled GPU. Thus, any attempt to compile OpenCL sample codes on a non-cuda-enabled GPU machine might result in the following error: 73 90 {{{ 74 91 /usr/bin/ld: cannot find -lOpenCL 75 92 }}} 76 93 The Makefile for Linux is made with the assumption that the NVIDIA Cuda SDK is installed at the default location "$(ROOT)/home/USER_NAME/NVIDIA_GPU_Computing_SDK/". On my Linux machine, for example, it would be "$(ROOT)/home/tuanle/NVIDIA_GPU_Computing_SDK/". Since the absolute path is used in Makefile, you will probably need to edit file "common.mk" before compiling the sample app. Do so by looking for "/home/tuanle/NVIDIA_GPU_Computing_SDK" in file "common.mk" and replace this path with an appropriate path on your machine. 77 94 78 * '''ATI Stream OpenCL''' (BOINC-ATIOpenCL sample app for Linux can be found at "/boin/samples/atiopencl/") 95 === ATI Stream OpenCL === 96 97 BOINC-ATIOpenCL sample app for Linux can be found at "/boin/samples/atiopencl/". 98 79 99 {{{ 80 100 Makefile; atiopencl.h; atiopencl.cpp; atiopencl_kernels; readme.txt 81 101 }}} 82 102 The Makefile for Linux is made with the assumption that the ATI Stream OpenCL SDK version 2.1 for 32-bit Linux and Boinc are installed in the same parent directory, i.e. "ati-stream-sdk-v.2.1-lnx32" directory and "boinc" directory are both installed at "$(ROOT)/home/" directory. If you are using the SDK v2.1 for 64-bit Linux, or if Boinc and the OpenCL SDK are not installed in the same parent directory, then Makefile needs to be edited prior to any compilation. Do so by looking for 83 103 {{{ 84 104 … … 95 115 in file "Makefile" and replace these paths with appropriate paths on your machine. 96 116 97 117 Most problems related to running the ATI Stream OpenCL executable files can be found in ATI_Stream_SDK_Installation_Notes.pdf section 2.2. Here are the two most common run-time errors: 98 118 99 119 1) ./atiopencl: error while loading shared libraries: libOpenCL.so: cannot open shared object file: No such file or directory -> Solution: … … 126 146 == Mac OS X == #mac 127 147 128 * '''NVIDIA Cuda''' (BOINC-Cuda sample app for Mac OS X can be found at "/boinc/samples/nvcuda/") 148 === NVIDIA Cuda === 149 150 BOINC-Cuda sample app for Mac OS X can be found at "/boinc/samples/nvcuda/" 151 129 152 {{{ 130 153 Makefile_mac; common_mac.mk; cuda_kernel_mac.cu; cuda_mac.c; cuda_config.h; readme_mac.txt 131 154 }}} 132 155 133 134 135 156 Unlike Windows and Linux, the 'nvcc' cuda compiler for Mac has some trouble compiling .cu files that 157 contain both BOINC and Cuda codes. Any attempt to compile such .cu files might result in errors like 158 these: 136 159 {{{ 137 160 /usr/lib/gcc/i686-apple-darwin9/4.0.1/include/mmintrin.h(55): error: identifier "__builtin_ia32_emms" is undefined … … 140 163 ... 141 164 }}} 142 143 144 145 165 The solution that we came up with is to compile BOINC and Cuda seperately, meaning that compile .c files that have BOINC codes with 166 gcc and compile .u files that have Cuda codes such as kernel definitions with nvcc (This can simply be done by putting .cu and .c 167 file names at corresponding "CUFILES := " and "CCFILES := " entries in Makefile_mac). To handle the results computed by the kernels, 168 you will need to write external functions. The function definitions that make kernel calls will be put in .cu file while the function headers with "extern" prefix are put in .c file and can be called in main function or elsewhere. 146 169 147 170 What if your machine doesn't have an NVIDIA Cuda-enabled GPU? Then, you can compile and run your app in emulation mode. As far as we know, NVIDIA Cuda SDK 3.1 no longer supports emulation mode. Thus, you will need to install an older Cuda SDK version, like version 3.0, on your machine. To make an executable file in emulation mode, simply type "make -f Makefile_mac emu=1". 148 171 149 172 Also, note that you will need to define some environment variables before running the executable file. 150 173 {{{ 151 174 export PATH=/usr/local/cuda/bin:$PATH … … 153 176 }}} 154 177 155 178 One last thing to mention, the makefile for Mac is made with the assumption that the NVIDIA Cuda SDK is installed at the default location: "$ROOT/Developer/GPU Computing/" on Mac. If it is installed at a different location on your machine, then you will need to edit file "common_mac.mk". Do so by looking for "ROOTDIR ?= /Developer/GPU\ Computing" in file "common_mac.mk" and replace this path with an appropriate path on your machine.
