composable_kernel/script/tools/ck-docker

#!/bin/bash
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
# SPDX-License-Identifier: MIT

# CK Docker Tool - Build and test composable_kernel in Docker with ROCm support

set -e
set -o pipefail

# Find script directory and load common utilities
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "${SCRIPT_DIR}/common.sh"

# Initialize configuration
PROJECT_ROOT=$(get_project_root "${SCRIPT_DIR}")
CONTAINER_NAME=$(get_container_name "${PROJECT_ROOT}")

# Help message
show_help() {
    cat << EOF
CK Docker Tool - Build and test composable_kernel in Docker

Usage: ck-docker <command> [options]

Container Management:
  start [name]            Start Docker container
  stop [name]             Stop and remove container
  status [name]           Check container status
  shell [name]            Open shell in container

Build/Test (delegates to core tools inside container):
  configure [opts]        Run ck-configure in container
  build [opts]            Run ck-build in container
  test [opts]             Run ck-test in container
  exec <cmd>              Run arbitrary command in container

Examples:
  ck-docker start
  ck-docker configure --preset dev-gfx950
  ck-docker build test_amdgcn_mma
  ck-docker test test_amdgcn_mma --filter '*Fp16*'
  ck-docker shell
  ck-docker exec rocminfo

Environment:
  CK_CONTAINER_NAME - Override default container name (default: ck_<username>_<branch>)
  CK_DOCKER_IMAGE   - Override Docker image (default: rocm/composable_kernel:ck_ub24.04_rocm7.0.1)
EOF
}

# Start container
cmd_start() {
    local name="${1:-${CONTAINER_NAME}}"
    local docker_image=$(get_docker_image)

    # Check if container exists and is running
    if container_exists "${name}"; then
        if container_is_running "${name}"; then
            echo "Container '${name}' is already running"
            return 0
        else
            echo "Starting existing container '${name}'..."
            docker start "${name}"
            echo "Container started"
            return 0
        fi
    fi

    echo "Creating new Docker container '${name}'..."
    docker run -d \
        --name "${name}" \
        --device=/dev/kfd --device=/dev/dri \
        --security-opt seccomp=unconfined \
        --group-add video \
        -v "${PROJECT_ROOT}":/workspace \
        -w /workspace \
        "${docker_image}" \
        tail -f /dev/null

    echo "Container '${name}' started successfully"
    docker exec "${name}" bash -c "echo 'Working directory:' && pwd"
}

# Configure (delegate to ck-configure in container)
cmd_configure() {
    ensure_container_running "${CONTAINER_NAME}" "${SCRIPT_DIR}"
    docker exec "${CONTAINER_NAME}" /workspace/script/tools/ck-configure "$@"
}

# Build (delegate to ck-build in container)
cmd_build() {
    ensure_container_running "${CONTAINER_NAME}" "${SCRIPT_DIR}"
    docker exec "${CONTAINER_NAME}" /workspace/script/tools/ck-build "$@"
}

# Test (delegate to ck-test in container)
cmd_test() {
    ensure_container_running "${CONTAINER_NAME}" "${SCRIPT_DIR}"
    docker exec "${CONTAINER_NAME}" /workspace/script/tools/ck-test "$@"
}

# Execute arbitrary command in container
cmd_exec() {
    if [ $# -eq 0 ]; then
        error "command required"
        echo "Usage: ck-docker exec <command>"
        return 1
    fi

    ensure_container_running "${CONTAINER_NAME}" "${SCRIPT_DIR}"

    local docker_flags=()
    [ -t 0 ] && [ -t 1 ] && docker_flags+=("-it")

    # Auto-detect Python commands and enable unbuffered output for live streaming
    local is_python=false
    for arg in "$@"; do
        if [[ "$arg" == "python" || "$arg" == "python3" || "$arg" == *.py ]]; then
            is_python=true
            break
        fi
    done

    if [ "$is_python" = true ]; then
        docker_flags+=("-e" "PYTHONUNBUFFERED=1")
    fi

    docker exec "${docker_flags[@]}" "${CONTAINER_NAME}" "$@"
}

# Shell
cmd_shell() {
    local name="${1:-${CONTAINER_NAME}}"

    # Check if container is running
    if ! container_is_running "${name}"; then
        echo "Container '${name}' not running. Starting..."
        cmd_start "${name}"
    fi

    echo "Opening shell in '${name}' (type 'exit' to leave)..."
    docker exec -it "${name}" bash
}

# Status
cmd_status() {
    local name="${1:-}"
    local docker_image=$(get_docker_image)

    if [ -z "$name" ]; then
        echo "Composable Kernel Docker Containers:"
        echo "---"
        docker ps -a --filter "ancestor=${docker_image}" \
            --format "table {{.Names}}\t{{.Status}}\t{{.CreatedAt}}" || echo "No containers found"
    else
        # Check container status
        if container_is_running "${name}"; then
            echo "Container '${name}' is RUNNING"
            docker ps --filter "name=^${name}$" --format "table {{.Names}}\t{{.Status}}\t{{.Image}}"
            echo ""
            echo "GPU Information:"
            docker exec "${name}" bash -c "rocm-smi --showproductname 2>/dev/null | head -10 || echo 'No GPU detected'"
        elif container_exists "${name}"; then
            echo "Container '${name}' exists but is STOPPED"
            echo "Start with: ck-docker start ${name}"
        else
            echo "Container '${name}' does NOT exist"
            echo "Create with: ck-docker start ${name}"
        fi
    fi
}

# Stop
cmd_stop() {
    local name="${1:-${CONTAINER_NAME}}"

    # Check if container exists
    if container_exists "${name}"; then
        echo "Stopping and removing container '${name}'..."
        docker stop "${name}" 2>/dev/null || true
        docker rm "${name}" 2>/dev/null || true
        echo "Container stopped and removed"
    else
        echo "Container '${name}' does not exist"
    fi
}

# Main command dispatcher
case "${1:-}" in
    start)
        shift
        cmd_start "$@"
        ;;
    configure)
        shift
        cmd_configure "$@"
        ;;
    build)
        shift
        cmd_build "$@"
        ;;
    test)
        shift
        cmd_test "$@"
        ;;
    exec)
        shift
        cmd_exec "$@"
        ;;
    shell)
        shift
        cmd_shell "$@"
        ;;
    status)
        shift
        cmd_status "$@"
        ;;
    stop)
        shift
        cmd_stop "$@"
        ;;
    help|--help|-h)
        show_help
        ;;
    *)
        echo "Unknown command: ${1:-}"
        echo ""
        show_help
        exit 1
        ;;
esac