Create a GPU-enabled version of qsim (Options 1 and 2 only) Modifying the above if cuQuantum was installed to a different directory. Set the CUQUANTUM_DIR and CUQUANTUM_ROOT environment variables, export CUQUANTUM_DIR=/opt/nvidia/cuquantum/Įxport CUQUANTUM_ROOT=/opt/nvidia/cuquantum/ Specifically, this is the appropriate installer. Install cuQuantum SDK/cuStateVec (Option 2 only) sudo apt install cmake & sudo apt install pip & pip install pybind11ĥ. This step might take a few minutes toĬomplete. Install the tools required to build qsim. Run source ~/.bashrc to activate the new environment search path echo "export PATH=/usr/local//bin$" > ~/.bashrc With the CUDA directory that you discovered in the previous step. You can run the followingĬommand to append the path to your ~/.bashrc file. In this case, the directory is cuda-11.4.Īdd the CUDA toolkit path to your environment. The output of the command should resemble theįollowing: bin cuda cuda-11 cuda-11.4 etc games include lib man sbin share src The toolkit is the highest number that looks like the patternĬuda-XX.Y. You canĬheck whether it is installed by checking whether the CUDA toolkitĭirectory exists as described in step 3.) sudo apt install -y nvidia-cuda-toolkitĪdd your CUDA toolkit to the environment search path (Options 1 and 2 only)ĭiscover the directory of the CUDA toolkit that you installed. ![]() ![]() (This may have already been installed along with the driver. ![]() Complete the steps provided in the following Enable your virtual machine to use the GPU (Options 1, 2, and 3) When the command completes successfully, your prompt changes from your local You can verify your environment by using the gcloud config listĬonnect to your VM by using SSH.You need to provide the gcloud tool with detailsĪbout your VM, such as the project name and the region where your VM is After installation, run the gcloud init command to initialize the GoogleĬloud environment.Use SSH in the gcloud tool to communicate with your VM. Prepare your computer (Options 1, 2, and 3) Choosing the right machine family and typeĢ.When Google Cloud finishes creating the VM, you can see your VM listed in the In the Firewall section, ensure that both the Allow HTTP trafficĬheckbox and the Allow HTTPS traffic checkboxs are selected.The instructions above override steps 3 through 5 in the Create a Linux VM.In the Version option, choose 20.04 LTS.In the Operating System option, choose Ubuntu.In the Boot disk section, click the Change button:.Select the GPU Type and Number of GPUs that you would like to use.Select the tab for the GPU machine family.Instance section, ensure that your VM has the following properties: In addition to the guidance specified in the Create a Linux VM Create a virtual machine (Options 1, 2, and 3) Some commands might require you to add sudo before the command.įor example, if a step asks you to type icecream -fancy, you might need to Note: The later steps in this tutorial require you to enter several commands at theĬommand line. The headers for each step note which of these three options they apply to. The following steps depend on which option you pick. If you plan to do multi-GPU simulations, then you using cuQuantum Appliance, which runs in a Docker container and hasĪ modified version of qsim.using NVIDIA's cuQuantum as a backend for the latest version of.As discussed there, you have a choice among 3 options: In order to decide which type of GPU you would like to use and how many GPUs you Support are also relevant if you are interested in running GPU simulations locallyīefore starting this tutorial, we recommend reading the choosing hardware guide The instructions for compiling qsim with GPU ![]() In this tutorial, you configure and test a virtual machine (VM) to run GPU-based
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |