Criar e executar um job que usa GPUs

import com.google.cloud.batch.v1.AllocationPolicy;
import com.google.cloud.batch.v1.AllocationPolicy.Accelerator;
import com.google.cloud.batch.v1.AllocationPolicy.InstancePolicy;
import com.google.cloud.batch.v1.AllocationPolicy.InstancePolicyOrTemplate;
import com.google.cloud.batch.v1.BatchServiceClient;
import com.google.cloud.batch.v1.CreateJobRequest;
import com.google.cloud.batch.v1.Job;
import com.google.cloud.batch.v1.LogsPolicy;
import com.google.cloud.batch.v1.Runnable;
import com.google.cloud.batch.v1.Runnable.Script;
import com.google.cloud.batch.v1.TaskGroup;
import com.google.cloud.batch.v1.TaskSpec;
import com.google.protobuf.Duration;
import java.io.IOException;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;

public class CreateGpuJob {

  public static void main(String[] args)
      throws IOException, ExecutionException, InterruptedException, TimeoutException {
    // TODO(developer): Replace these variables before running the sample.
    // Project ID or project number of the Google Cloud project you want to use.
    String projectId = "YOUR_PROJECT_ID";
    // Name of the region you want to use to run the job. Regions that are
    // available for Batch are listed on: https://cloud.google.com/batch/docs/get-started#locations
    String region = "europe-central2";
    // The name of the job that will be created.
    // It needs to be unique for each project and region pair.
    String jobName = "JOB_NAME";
    // Optional. When set to true, Batch fetches the drivers required for the GPU type
    // that you specify in the policy field from a third-party location,
    // and Batch installs them on your behalf. If you set this field to false (default),
    // you need to install GPU drivers manually to use any GPUs for this job.
    boolean installGpuDrivers = false;
    // Accelerator-optimized machine types are available to Batch jobs. See the list
    // of available types on: https://cloud.google.com/compute/docs/accelerator-optimized-machines
    String machineType = "g2-standard-4";

    createGpuJob(projectId, region, jobName, installGpuDrivers, machineType);
  }

  // Create a job that uses GPUs
  public static Job createGpuJob(String projectId, String region, String jobName,
                                  boolean installGpuDrivers, String machineType)
      throws IOException, ExecutionException, InterruptedException, TimeoutException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests.
    try (BatchServiceClient batchServiceClient = BatchServiceClient.create()) {
      // Define what will be done as part of the job.
      Runnable runnable =
          Runnable.newBuilder()
              .setScript(
                  Script.newBuilder()
                      .setText(
                          "echo Hello world! This is task ${BATCH_TASK_INDEX}. "
                                  + "This job has a total of ${BATCH_TASK_COUNT} tasks.")
                      // You can also run a script from a file. Just remember, that needs to be a
                      // script that's already on the VM that will be running the job.
                      // Using setText() and setPath() is mutually exclusive.
                      // .setPath("/tmp/test.sh")
                      .build())
              .build();

      TaskSpec task = TaskSpec.newBuilder()
                  // Jobs can be divided into tasks. In this case, we have only one task.
                  .addRunnables(runnable)
                  .setMaxRetryCount(2)
                  .setMaxRunDuration(Duration.newBuilder().setSeconds(3600).build())
                  .build();

      // Tasks are grouped inside a job using TaskGroups.
      // Currently, it's possible to have only one task group.
      TaskGroup taskGroup = TaskGroup.newBuilder()
          .setTaskCount(3)
          .setParallelism(1)
          .setTaskSpec(task)
          .build();

      // Policies are used to define on what kind of virtual machines the tasks will run.
      // Read more about machine types here: https://cloud.google.com/compute/docs/machine-types
      InstancePolicy instancePolicy =
          InstancePolicy.newBuilder().setMachineType(machineType).build();  

      // Policies are used to define on what kind of virtual machines the tasks will run on.
      AllocationPolicy allocationPolicy =
          AllocationPolicy.newBuilder()
              .addInstances(
                  InstancePolicyOrTemplate.newBuilder()
                      .setInstallGpuDrivers(installGpuDrivers)
                      .setPolicy(instancePolicy)
                      .build())
              .build();

      Job job =
          Job.newBuilder()
              .addTaskGroups(taskGroup)
              .setAllocationPolicy(allocationPolicy)
              .putLabels("env", "testing")
              .putLabels("type", "script")
              // We use Cloud Logging as it's an out of the box available option.
              .setLogsPolicy(
                  LogsPolicy.newBuilder().setDestination(LogsPolicy.Destination.CLOUD_LOGGING))
              .build();

      CreateJobRequest createJobRequest =
          CreateJobRequest.newBuilder()
              // The job's parent is the region in which the job will run.
              .setParent(String.format("projects/%s/locations/%s", projectId, region))
              .setJob(job)
              .setJobId(jobName)
              .build();

      Job result =
          batchServiceClient
              .createJobCallable()
              .futureCall(createJobRequest)
              .get(5, TimeUnit.MINUTES);

      System.out.printf("Successfully created the job: %s", result.getName());

      return result;
    }
  }
}

// Imports the Batch library
const batchLib = require('@google-cloud/batch');
const batch = batchLib.protos.google.cloud.batch.v1;

// Instantiates a client
const batchClient = new batchLib.v1.BatchServiceClient();

/**
 * TODO(developer): Update these variables before running the sample.
 */
// Project ID or project number of the Google Cloud project you want to use.
const projectId = await batchClient.getProjectId();
// Name of the region you want to use to run the job. Regions that are
// available for Batch are listed on: https://cloud.google.com/batch/docs/get-started#locations
const region = 'europe-central2';
// The name of the job that will be created.
// It needs to be unique for each project and region pair.
const jobName = 'batch-gpu-job';
// The GPU type. You can view a list of the available GPU types
// by using the `gcloud compute accelerator-types list` command.
const gpuType = 'nvidia-l4';
// The number of GPUs of the specified type.
const gpuCount = 1;
// Optional. When set to true, Batch fetches the drivers required for the GPU type
// that you specify in the policy field from a third-party location,
// and Batch installs them on your behalf. If you set this field to false (default),
// you need to install GPU drivers manually to use any GPUs for this job.
const installGpuDrivers = false;
// Accelerator-optimized machine types are available to Batch jobs. See the list
// of available types on: https://cloud.google.com/compute/docs/accelerator-optimized-machines
const machineType = 'g2-standard-4';

// Define what will be done as part of the job.
const runnable = new batch.Runnable({
  script: new batch.Runnable.Script({
    commands: ['-c', 'echo Hello world! This is task ${BATCH_TASK_INDEX}.'],
  }),
});

const task = new batch.TaskSpec({
  runnables: [runnable],
  maxRetryCount: 2,
  maxRunDuration: {seconds: 3600},
});

// Tasks are grouped inside a job using TaskGroups.
const group = new batch.TaskGroup({
  taskCount: 3,
  taskSpec: task,
});

// Policies are used to define on what kind of virtual machines the tasks will run on.
// In this case, we tell the system to use "g2-standard-4" machine type.
// Read more about machine types here: https://cloud.google.com/compute/docs/machine-types
const instancePolicy = new batch.AllocationPolicy.InstancePolicy({
  machineType,
  // Accelerator describes Compute Engine accelerators to be attached to the VM
  accelerators: [
    new batch.AllocationPolicy.Accelerator({
      type: gpuType,
      count: gpuCount,
      installGpuDrivers,
    }),
  ],
});

const allocationPolicy = new batch.AllocationPolicy.InstancePolicyOrTemplate({
  instances: [{installGpuDrivers, policy: instancePolicy}],
});

const job = new batch.Job({
  name: jobName,
  taskGroups: [group],
  labels: {env: 'testing', type: 'script'},
  allocationPolicy,
  // We use Cloud Logging as it's an option available out of the box
  logsPolicy: new batch.LogsPolicy({
    destination: batch.LogsPolicy.Destination.CLOUD_LOGGING,
  }),
});
// The job's parent is the project and region in which the job will run
const parent = `projects/${projectId}/locations/${region}`;

async function callCreateBatchGPUJob() {
  // Construct request
  const request = {
    parent,
    jobId: jobName,
    job,
  };

  // Run request
  const [response] = await batchClient.createJob(request);
  console.log(JSON.stringify(response));
}

await callCreateBatchGPUJob();

from google.cloud import batch_v1


def create_gpu_job(project_id: str, region: str, job_name: str) -> batch_v1.Job:
    """
    This method shows how to create a sample Batch Job that will run
    a simple command on Cloud Compute instances on GPU machines.

    Args:
        project_id: project ID or project number of the Cloud project you want to use.
        region: name of the region you want to use to run the job. Regions that are
            available for Batch are listed on: https://cloud.google.com/batch/docs/get-started#locations
        job_name: the name of the job that will be created.
            It needs to be unique for each project and region pair.

    Returns:
        A job object representing the job created.
    """
    client = batch_v1.BatchServiceClient()

    # Define what will be done as part of the job.
    task = batch_v1.TaskSpec()
    runnable = batch_v1.Runnable()
    runnable.script = batch_v1.Runnable.Script()
    runnable.script.text = "echo Hello world! This is task ${BATCH_TASK_INDEX}. This job has a total of ${BATCH_TASK_COUNT} tasks."
    # You can also run a script from a file. Just remember, that needs to be a script that's
    # already on the VM that will be running the job. Using runnable.script.text and runnable.script.path is mutually
    # exclusive.
    # runnable.script.path = '/tmp/test.sh'
    task.runnables = [runnable]

    # We can specify what resources are requested by each task.
    resources = batch_v1.ComputeResource()
    resources.cpu_milli = 2000  # in milliseconds per cpu-second. This means the task requires 2 whole CPUs.
    resources.memory_mib = 16  # in MiB
    task.compute_resource = resources

    task.max_retry_count = 2
    task.max_run_duration = "3600s"

    # Tasks are grouped inside a job using TaskGroups.
    # Currently, it's possible to have only one task group.
    group = batch_v1.TaskGroup()
    group.task_count = 4
    group.task_spec = task

    # Policies are used to define on what kind of virtual machines the tasks will run on.
    # In this case, we tell the system to use "g2-standard-4" machine type.
    # Read more about machine types here: https://cloud.google.com/compute/docs/machine-types
    policy = batch_v1.AllocationPolicy.InstancePolicy()
    policy.machine_type = "g2-standard-4"

    instances = batch_v1.AllocationPolicy.InstancePolicyOrTemplate()
    instances.policy = policy
    instances.install_gpu_drivers = True
    allocation_policy = batch_v1.AllocationPolicy()
    allocation_policy.instances = [instances]

    job = batch_v1.Job()
    job.task_groups = [group]
    job.allocation_policy = allocation_policy
    job.labels = {"env": "testing", "type": "container"}
    # We use Cloud Logging as it's an out of the box available option
    job.logs_policy = batch_v1.LogsPolicy()
    job.logs_policy.destination = batch_v1.LogsPolicy.Destination.CLOUD_LOGGING

    create_request = batch_v1.CreateJobRequest()
    create_request.job = job
    create_request.job_id = job_name
    # The job's parent is the region in which the job will run
    create_request.parent = f"projects/{project_id}/locations/{region}"

    return client.create_job(create_request)

import com.google.cloud.batch.v1.AllocationPolicy;
import com.google.cloud.batch.v1.AllocationPolicy.Accelerator;
import com.google.cloud.batch.v1.AllocationPolicy.InstancePolicy;
import com.google.cloud.batch.v1.AllocationPolicy.InstancePolicyOrTemplate;
import com.google.cloud.batch.v1.BatchServiceClient;
import com.google.cloud.batch.v1.CreateJobRequest;
import com.google.cloud.batch.v1.Job;
import com.google.cloud.batch.v1.LogsPolicy;
import com.google.cloud.batch.v1.Runnable;
import com.google.cloud.batch.v1.Runnable.Script;
import com.google.cloud.batch.v1.TaskGroup;
import com.google.cloud.batch.v1.TaskSpec;
import com.google.protobuf.Duration;
import java.io.IOException;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;

public class CreateGpuJobN1 {

  public static void main(String[] args)
      throws IOException, ExecutionException, InterruptedException, TimeoutException {
    // TODO(developer): Replace these variables before running the sample.
    // Project ID or project number of the Google Cloud project you want to use.
    String projectId = "YOUR_PROJECT_ID";
    // Name of the region you want to use to run the job. Regions that are
    // available for Batch are listed on: https://cloud.google.com/batch/docs/get-started#locations
    String region = "europe-central2";
    // The name of the job that will be created.
    // It needs to be unique for each project and region pair.
    String jobName = "JOB_NAME";
    // Optional. When set to true, Batch fetches the drivers required for the GPU type
    // that you specify in the policy field from a third-party location,
    // and Batch installs them on your behalf. If you set this field to false (default),
    // you need to install GPU drivers manually to use any GPUs for this job.
    boolean installGpuDrivers = false;
    // The GPU type. You can view a list of the available GPU types
    // by using the `gcloud compute accelerator-types list` command.
    String gpuType = "nvidia-tesla-t4";
    // The number of GPUs of the specified type.
    int gpuCount = 2;

    createGpuJob(projectId, region, jobName, installGpuDrivers, gpuType, gpuCount);
  }

  // Create a job that uses GPUs
  public static Job createGpuJob(String projectId, String region, String jobName,
                                  boolean installGpuDrivers, String gpuType, int gpuCount)
      throws IOException, ExecutionException, InterruptedException, TimeoutException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests.
    try (BatchServiceClient batchServiceClient = BatchServiceClient.create()) {
      // Define what will be done as part of the job.
      Runnable runnable =
          Runnable.newBuilder()
              .setScript(
                  Script.newBuilder()
                      .setText(
                          "echo Hello world! This is task ${BATCH_TASK_INDEX}. "
                                  + "This job has a total of ${BATCH_TASK_COUNT} tasks.")
                      // You can also run a script from a file. Just remember, that needs to be a
                      // script that's already on the VM that will be running the job.
                      // Using setText() and setPath() is mutually exclusive.
                      // .setPath("/tmp/test.sh")
                      .build())
              .build();

      TaskSpec task = TaskSpec.newBuilder()
                  // Jobs can be divided into tasks. In this case, we have only one task.
                  .addRunnables(runnable)
                  .setMaxRetryCount(2)
                  .setMaxRunDuration(Duration.newBuilder().setSeconds(3600).build())
                  .build();

      // Tasks are grouped inside a job using TaskGroups.
      // Currently, it's possible to have only one task group.
      TaskGroup taskGroup = TaskGroup.newBuilder()
          .setTaskCount(3)
          .setParallelism(1)
          .setTaskSpec(task)
          .build();

      // Accelerator describes Compute Engine accelerators to be attached to the VM.
      Accelerator accelerator = Accelerator.newBuilder()
          .setType(gpuType)
          .setCount(gpuCount)
          .build();

      // Policies are used to define on what kind of virtual machines the tasks will run on.
      AllocationPolicy allocationPolicy =
          AllocationPolicy.newBuilder()
              .addInstances(
                  InstancePolicyOrTemplate.newBuilder()
                      .setInstallGpuDrivers(installGpuDrivers)
                      .setPolicy(InstancePolicy.newBuilder().addAccelerators(accelerator))
                      .build())
              .build();

      Job job =
          Job.newBuilder()
              .addTaskGroups(taskGroup)
              .setAllocationPolicy(allocationPolicy)
              .putLabels("env", "testing")
              .putLabels("type", "script")
              // We use Cloud Logging as it's an out of the box available option.
              .setLogsPolicy(
                  LogsPolicy.newBuilder().setDestination(LogsPolicy.Destination.CLOUD_LOGGING))
              .build();

      CreateJobRequest createJobRequest =
          CreateJobRequest.newBuilder()
              // The job's parent is the region in which the job will run.
              .setParent(String.format("projects/%s/locations/%s", projectId, region))
              .setJob(job)
              .setJobId(jobName)
              .build();

      Job result =
          batchServiceClient
              .createJobCallable()
              .futureCall(createJobRequest)
              .get(5, TimeUnit.MINUTES);

      System.out.printf("Successfully created the job: %s", result.getName());

      return result;
    }
  }
}

// Imports the Batch library
const batchLib = require('@google-cloud/batch');
const batch = batchLib.protos.google.cloud.batch.v1;

// Instantiates a client
const batchClient = new batchLib.v1.BatchServiceClient();

/**
 * TODO(developer): Update these variables before running the sample.
 */
// Project ID or project number of the Google Cloud project you want to use.
const projectId = await batchClient.getProjectId();
// Name of the region you want to use to run the job. Regions that are
// available for Batch are listed on: https://cloud.google.com/batch/docs/get-started#locations
const region = 'europe-central2';
// The name of the job that will be created.
// It needs to be unique for each project and region pair.
const jobName = 'batch-gpu-job-n1';
// The GPU type. You can view a list of the available GPU types
// by using the `gcloud compute accelerator-types list` command.
const gpuType = 'nvidia-tesla-t4';
// The number of GPUs of the specified type.
const gpuCount = 1;
// Optional. When set to true, Batch fetches the drivers required for the GPU type
// that you specify in the policy field from a third-party location,
// and Batch installs them on your behalf. If you set this field to false (default),
// you need to install GPU drivers manually to use any GPUs for this job.
const installGpuDrivers = false;
// Accelerator-optimized machine types are available to Batch jobs. See the list
// of available types on: https://cloud.google.com/compute/docs/accelerator-optimized-machines
const machineType = 'n1-standard-16';

// Define what will be done as part of the job.
const runnable = new batch.Runnable({
  script: new batch.Runnable.Script({
    commands: ['-c', 'echo Hello world! This is task ${BATCH_TASK_INDEX}.'],
  }),
});

const task = new batch.TaskSpec({
  runnables: [runnable],
  maxRetryCount: 2,
  maxRunDuration: {seconds: 3600},
});

// Tasks are grouped inside a job using TaskGroups.
const group = new batch.TaskGroup({
  taskCount: 3,
  taskSpec: task,
});

// Policies are used to define on what kind of virtual machines the tasks will run on.
// In this case, we tell the system to use "g2-standard-4" machine type.
// Read more about machine types here: https://cloud.google.com/compute/docs/machine-types
const instancePolicy = new batch.AllocationPolicy.InstancePolicy({
  machineType,
  // Accelerator describes Compute Engine accelerators to be attached to the VM
  accelerators: [
    new batch.AllocationPolicy.Accelerator({
      type: gpuType,
      count: gpuCount,
      installGpuDrivers,
    }),
  ],
});

const allocationPolicy = new batch.AllocationPolicy.InstancePolicyOrTemplate({
  instances: [{installGpuDrivers, policy: instancePolicy}],
});

const job = new batch.Job({
  name: jobName,
  taskGroups: [group],
  labels: {env: 'testing', type: 'script'},
  allocationPolicy,
  // We use Cloud Logging as it's an option available out of the box
  logsPolicy: new batch.LogsPolicy({
    destination: batch.LogsPolicy.Destination.CLOUD_LOGGING,
  }),
});
// The job's parent is the project and region in which the job will run
const parent = `projects/${projectId}/locations/${region}`;

async function callCreateBatchGPUJobN1() {
  // Construct request
  const request = {
    parent,
    jobId: jobName,
    job,
  };

  // Run request
  const [response] = await batchClient.createJob(request);
  console.log(JSON.stringify(response));
}

await callCreateBatchGPUJobN1();

from google.cloud import batch_v1


def create_gpu_job(
    project_id: str, region: str, zone: str, job_name: str
) -> batch_v1.Job:
    """
    This method shows how to create a sample Batch Job that will run
    a simple command on Cloud Compute instances on GPU machines.

    Args:
        project_id: project ID or project number of the Cloud project you want to use.
        region: name of the region you want to use to run the job. Regions that are
            available for Batch are listed on: https://cloud.google.com/batch/docs/get-started#locations
        zone: name of the zone you want to use to run the job. Important in regard to GPUs availability.
            GPUs availability can be found here: https://cloud.google.com/compute/docs/gpus/gpu-regions-zones
        job_name: the name of the job that will be created.
            It needs to be unique for each project and region pair.

    Returns:
        A job object representing the job created.
    """
    client = batch_v1.BatchServiceClient()

    # Define what will be done as part of the job.
    task = batch_v1.TaskSpec()
    runnable = batch_v1.Runnable()
    runnable.script = batch_v1.Runnable.Script()
    runnable.script.text = "echo Hello world! This is task ${BATCH_TASK_INDEX}. This job has a total of ${BATCH_TASK_COUNT} tasks."
    # You can also run a script from a file. Just remember, that needs to be a script that's
    # already on the VM that will be running the job. Using runnable.script.text and runnable.script.path is mutually
    # exclusive.
    # runnable.script.path = '/tmp/test.sh'
    task.runnables = [runnable]

    # We can specify what resources are requested by each task.
    resources = batch_v1.ComputeResource()
    resources.cpu_milli = 2000  # in milliseconds per cpu-second. This means the task requires 2 whole CPUs.
    resources.memory_mib = 16  # in MiB
    task.compute_resource = resources

    task.max_retry_count = 2
    task.max_run_duration = "3600s"

    # Tasks are grouped inside a job using TaskGroups.
    # Currently, it's possible to have only one task group.
    group = batch_v1.TaskGroup()
    group.task_count = 4
    group.task_spec = task

    # Policies are used to define on what kind of virtual machines the tasks will run on.
    # Read more about machine types here: https://cloud.google.com/compute/docs/machine-types
    policy = batch_v1.AllocationPolicy.InstancePolicy()
    policy.machine_type = "n1-standard-16"

    accelerator = batch_v1.AllocationPolicy.Accelerator()
    # Note: not every accelerator is compatible with instance type
    # Read more here: https://cloud.google.com/compute/docs/gpus#t4-gpus
    accelerator.type_ = "nvidia-tesla-t4"
    accelerator.count = 1

    policy.accelerators = [accelerator]
    instances = batch_v1.AllocationPolicy.InstancePolicyOrTemplate()
    instances.policy = policy
    instances.install_gpu_drivers = True
    allocation_policy = batch_v1.AllocationPolicy()
    allocation_policy.instances = [instances]

    location = batch_v1.AllocationPolicy.LocationPolicy()
    location.allowed_locations = ["zones/us-central1-b"]
    allocation_policy.location = location

    job = batch_v1.Job()
    job.task_groups = [group]
    job.allocation_policy = allocation_policy
    job.labels = {"env": "testing", "type": "container"}
    # We use Cloud Logging as it's an out of the box available option
    job.logs_policy = batch_v1.LogsPolicy()
    job.logs_policy.destination = batch_v1.LogsPolicy.Destination.CLOUD_LOGGING

    create_request = batch_v1.CreateJobRequest()
    create_request.job = job
    create_request.job_id = job_name
    # The job's parent is the region in which the job will run
    create_request.parent = f"projects/{project_id}/locations/{region}"

    return client.create_job(create_request)