Update Exercises_Instructions.md

Author: csccva

Exercises_Instructions.md

@@ -156,18 +156,17 @@ This is another SYCL  implementation with support for many type of devices. No s
 
 Set up the environment:
 
-    module purge
-    module use /scratch/project_2012125/cristian/spack/share/spack/modules/linux-rhel8-x86_64_v3/
-    module load hipsycl/24.06.0-gcc-10.4.0-4nny2ja
     module load gcc/10.4.0
+    module load cuda/12.6.0
+    module load openmpi/4.1.5-cuda # Needed for using GPU-aware MPI
     export LD_LIBRARY_PATH=$CUDA_HOME/lib64:$LD_LIBRARY_PATH
     export LD_LIBRARY_PATH=/appl/spack/v020/install-tree/gcc-8.5.0/gcc-10.4.0-2oazqj/lib64/:$LD_LIBRARY_PATH
-    export LD_PRELOAD=/scratch/project_2012125/cristian/spack/opt/spack/linux-rhel8-x86_64_v3/gcc-10.4.0/llvm-18.1.8-bgdmsbegf2oymsvhmukkr22s2cjb4zxz/lib/libomp.so
-
+    export export LD_PRELOAD=/projappl/project_2015315/apps/LLVM/lib/x86_64-unknown-linux-gnu/libomp.so
+    
 
 Compile sycl code:
 
-    acpp -fuse-ld=lld -O3 -L/appl/spack/v020/install-tree/gcc-8.5.0/gcc-10.4.0-2oazqj/lib64/ --acpp-targets="omp.accelerated;cuda:sm_80" <sycl_code>.cpp
+    acpp -fuse-ld=lld -O3 -L/appl/spack/v020/install-tree/gcc-8.5.0/gcc-10.4.0-2oazqj/lib64/   --acpp-targets="omp.accelerated;cuda:sm_80"   -lstdc++  <sycl_code>.cpp
 
 #### AdaptiveCpp on LUMI