Installing GMAC

GMAC is a user-level library that implements an Asymmetric Distributed Shared Memory model to be used by CUDA programs. An ADSM model allows CPU code to access data hosted in accelerator (GPU) memory.

GMAC is being developed by the Operating System Group at the Universitat Politecnica de Catalunya and the IMPACT Research Group at theUniversity of Illinois

 

_________________________________________________________

To install gmac,

1. Download the latest version of gmac to date: gmac-0.0.10.tar.gz

2. Unzip gmac-0.0.10.tar.gz using the following command

gunzip gmac-0.0.10.tar.gz
 tar -xvf gmac-0.0.10.tar

3. Go inside the directory gmac-0.0.10 and make another directory build to separate the installation files from the source.

cd gmac-0.0.10
 mkdir build

4. Go inside the directory build and run configuration file

cd build
 ../configure

5. Install using make all install command

sudo make all install

________________________________________________________________________________

I am installing gmac on a 32 bit UNIX machine with gcc 4.3 and CUDA 3.0.

After installing from the Makefile I encountered the following error

/usr/bin/ld: cannot find -lcuda
collect2: ld returned 1 exit status
make[5]: *** [libgmac.la] Error 1
make[5]: Leaving directory `/home/imacbuntu/Projects/gmac-0.0.10/build/
src/gmac'
make[4]: *** [all-recursive] Error 1
make[4]: Leaving directory `/home/imacbuntu/Projects/gmac-0.0.10/build/
src/gmac'
make[3]: *** [all] Error 2
make[3]: Leaving directory `/home/imacbuntu/Projects/gmac-0.0.10/build/
src/gmac'
make[2]: *** [all-recursive] Error 1
make[2]: Leaving directory `/home/imacbuntu/Projects/gmac-0.0.10/build/
src'
make[1]: *** [all] Error 2
make[1]: Leaving directory
`/home/imacbuntu/Projects/gmac-0.0.10/build/
src'
make: *** [all-recursive] Error 1

 

The error has something to do with the library of cuda,

when I tried to link the libcuda.so in /usr/lib by performing the following command, installation of gmac became successful.

sudo ln -s /usr/lib/nvidia-current/libcuda.so /usr/lib/libcuda.so



Sources: http://code.google.com/p/adsm/