aws-bootstrap-g4dn 0.3.0__py3-none-any.whl → 0.5.0__py3-none-any.whl

aws_bootstrap/cli.py

@@ -29,6 +29,7 @@ from .ssh import (
     private_key_path,
     query_gpu_info,
     remove_ssh_host,
+    resolve_instance_id,
     run_remote_setup,
     wait_for_ssh,
 )
@@ -277,7 +278,7 @@ def launch(
     click.echo()
     click.secho("  VSCode Remote SSH:", fg="cyan")
     click.secho(
-        f"    code --folder-uri vscode-remote://ssh-remote+{alias}/home/{config.ssh_user}",
+        f"    code --folder-uri vscode-remote://ssh-remote+{alias}/home/{config.ssh_user}/workspace",
         bold=True,
     )
 
@@ -288,7 +289,7 @@ def launch(
 
     click.echo()
     click.secho("  Terminate:", fg="cyan")
-    click.secho(f"    aws-bootstrap terminate {instance_id} --region {config.region}", bold=True)
+    click.secho(f"    aws-bootstrap terminate {alias} --region {config.region}", bold=True)
     click.echo()
 
 
@@ -410,7 +411,7 @@ def status(region, profile, gpu, instructions):
 
             click.secho("    VSCode Remote SSH:", fg="cyan")
             click.secho(
-                f"      code --folder-uri vscode-remote://ssh-remote+{alias}/home/{user}",
+                f"      code --folder-uri vscode-remote://ssh-remote+{alias}/home/{user}/workspace",
                 bold=True,
             )
 
@@ -419,7 +420,8 @@ def status(region, profile, gpu, instructions):
 
     click.echo()
     first_id = instances[0]["InstanceId"]
-    click.echo("  To terminate:  " + click.style(f"aws-bootstrap terminate {first_id}", bold=True))
+    first_ref = ssh_hosts.get(first_id, first_id)
+    click.echo("  To terminate:  " + click.style(f"aws-bootstrap terminate {first_ref}", bold=True))
     click.echo()
 
 
@@ -427,18 +429,28 @@ def status(region, profile, gpu, instructions):
 @click.option("--region", default="us-west-2", show_default=True, help="AWS region.")
 @click.option("--profile", default=None, help="AWS profile override.")
 @click.option("--yes", "-y", is_flag=True, default=False, help="Skip confirmation prompt.")
-@click.argument("instance_ids", nargs=-1)
+@click.argument("instance_ids", nargs=-1, metavar="[INSTANCE_ID_OR_ALIAS]...")
 def terminate(region, profile, yes, instance_ids):
     """Terminate instances created by aws-bootstrap.
 
-    Pass specific instance IDs to terminate, or omit to terminate all
-    aws-bootstrap instances in the region.
+    Pass specific instance IDs or SSH aliases (e.g. aws-gpu1) to terminate,
+    or omit to terminate all aws-bootstrap instances in the region.
     """
     session = boto3.Session(profile_name=profile, region_name=region)
     ec2 = session.client("ec2")
 
     if instance_ids:
-        targets = list(instance_ids)
+        targets = []
+        for value in instance_ids:
+            resolved = resolve_instance_id(value)
+            if resolved is None:
+                raise CLIError(
+                    f"Could not resolve '{value}' to an instance ID.\n\n"
+                    "  It is not a valid instance ID or a known SSH alias."
+                )
+            if resolved != value:
+                info(f"Resolved alias '{value}' -> {resolved}")
+            targets.append(resolved)
     else:
         instances = find_tagged_instances(ec2, "aws-bootstrap-g4dn")
         if not instances:

aws_bootstrap/resources/gpu_benchmark.py

@@ -628,7 +628,9 @@ def configure_precision(device: torch.device, requested: PrecisionMode) -> Preci
     return PrecisionMode.FP32
 
 
-def print_system_info(requested_precision: PrecisionMode) -> tuple[torch.device, PrecisionMode]:
+def print_system_info(
+    requested_precision: PrecisionMode, force_cpu: bool = False
+) -> tuple[torch.device, PrecisionMode]:
     """Print system and CUDA information, return device and actual precision mode."""
     print("\n" + "=" * 60)
     print("System Information")
@@ -636,7 +638,7 @@ def print_system_info(requested_precision: PrecisionMode) -> tuple[torch.device,
     print(f"PyTorch version: {torch.__version__}")
     print(f"Python version: {sys.version.split()[0]}")
 
-    if torch.cuda.is_available():
+    if torch.cuda.is_available() and not force_cpu:
         device = torch.device("cuda")
         print("CUDA available: Yes")
         print(f"CUDA version: {torch.version.cuda}")
@@ -666,8 +668,11 @@ def print_system_info(requested_precision: PrecisionMode) -> tuple[torch.device,
     else:
         device = torch.device("cpu")
         actual_precision = PrecisionMode.FP32
-        print("CUDA available: No (running on CPU)")
-        print("WARNING: GPU benchmark results will not be representative!")
+        if force_cpu:
+            print("CPU-only mode requested (--cpu flag)")
+        else:
+            print("CUDA available: No (running on CPU)")
+        print("Running on CPU for benchmarking")
 
     print("=" * 60)
     return device, actual_precision
@@ -724,10 +729,15 @@ def main() -> None:
         action="store_true",
         help="Run CUDA/cuBLAS diagnostic tests before benchmarking",
     )
+    parser.add_argument(
+        "--cpu",
+        action="store_true",
+        help="Force CPU-only execution (for CPU vs GPU comparison)",
+    )
     args = parser.parse_args()
 
     requested_precision = PrecisionMode(args.precision)
-    device, actual_precision = print_system_info(requested_precision)
+    device, actual_precision = print_system_info(requested_precision, force_cpu=args.cpu)
 
     # Run diagnostics if requested
     if args.diagnose:

aws_bootstrap/resources/launch.json

@@ -0,0 +1,42 @@
+{
+    // CUDA debug configurations for VSCode
+    // Deployed to: ~/workspace/.vscode/launch.json
+    //
+    // Usage: Open any .cu file, press F5 to build and debug
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "CUDA: Build and Debug Active File",
+            "type": "cuda-gdb",
+            "request": "launch",
+            "program": "${fileDirname}/${fileBasenameNoExtension}",
+            "args": [],
+            "cwd": "${fileDirname}",
+            "miDebuggerPath": "__CUDA_GDB_PATH__",
+            "stopAtEntry": false,
+            "preLaunchTask": "nvcc: build active file (debug)"
+        },
+        {
+            "name": "CUDA: Build and Debug (stop at main)",
+            "type": "cuda-gdb",
+            "request": "launch",
+            "program": "${fileDirname}/${fileBasenameNoExtension}",
+            "args": [],
+            "cwd": "${fileDirname}",
+            "miDebuggerPath": "__CUDA_GDB_PATH__",
+            "stopAtEntry": true,
+            "preLaunchTask": "nvcc: build active file (debug)"
+        },
+        {
+            "name": "CUDA: Run Active File (no debug)",
+            "type": "cuda-gdb",
+            "request": "launch",
+            "program": "${fileDirname}/${fileBasenameNoExtension}",
+            "args": [],
+            "cwd": "${fileDirname}",
+            "miDebuggerPath": "__CUDA_GDB_PATH__",
+            "stopAtEntry": false,
+            "preLaunchTask": "nvcc: build active file (release)"
+        }
+    ]
+}

aws_bootstrap/resources/remote_setup.sh

@@ -7,7 +7,7 @@ echo "=== aws-bootstrap-g4dn remote setup ==="
 
 # 1. Verify GPU
 echo ""
-echo "[1/5] Verifying GPU and CUDA..."
+echo "[1/6] Verifying GPU and CUDA..."
 if command -v nvidia-smi &>/dev/null; then
     nvidia-smi --query-gpu=name,driver_version,memory.total --format=csv,noheader
 else
@@ -20,15 +20,40 @@ else
     echo "WARNING: nvcc not found (CUDA toolkit may not be installed)"
 fi
 
+# Make Nsight Systems (nsys) available on PATH if installed under /opt/nvidia
+if ! command -v nsys &>/dev/null; then
+    NSIGHT_DIR="/opt/nvidia/nsight-systems"
+    if [ -d "$NSIGHT_DIR" ]; then
+        # Fix permissions — the parent dir is often root-only (drwx------)
+        sudo chmod o+rx "$NSIGHT_DIR"
+        # Find the latest version directory (lexicographic sort)
+        NSYS_VERSION=$(ls -1 "$NSIGHT_DIR" | sort -V | tail -1)
+        if [ -n "$NSYS_VERSION" ] && [ -x "$NSIGHT_DIR/$NSYS_VERSION/bin/nsys" ]; then
+            NSYS_BIN="$NSIGHT_DIR/$NSYS_VERSION/bin"
+            if ! grep -q "nsight-systems" ~/.bashrc 2>/dev/null; then
+                echo "export PATH=\"$NSYS_BIN:\$PATH\"" >> ~/.bashrc
+            fi
+            export PATH="$NSYS_BIN:$PATH"
+            echo "  Nsight Systems $NSYS_VERSION added to PATH ($NSYS_BIN)"
+        else
+            echo "  WARNING: Nsight Systems directory found but no nsys binary"
+        fi
+    else
+        echo "  Nsight Systems not found at $NSIGHT_DIR"
+    fi
+else
+    echo "  nsys already on PATH: $(command -v nsys)"
+fi
+
 # 2. Install utilities
 echo ""
-echo "[2/5] Installing utilities..."
+echo "[2/6] Installing utilities..."
 sudo apt-get update -qq
 sudo apt-get install -y -qq htop tmux tree jq
 
 # 3. Set up Python environment with uv
 echo ""
-echo "[3/5] Setting up Python environment with uv..."
+echo "[3/6] Setting up Python environment with uv..."
 if ! command -v uv &>/dev/null; then
     curl -LsSf https://astral.sh/uv/install.sh | sh
 fi
@@ -153,7 +178,7 @@ echo "  Jupyter config written to $JUPYTER_CONFIG_DIR/jupyter_lab_config.py"
 
 # 4. Jupyter systemd service
 echo ""
-echo "[4/5] Setting up Jupyter systemd service..."
+echo "[4/6] Setting up Jupyter systemd service..."
 LOGIN_USER=$(whoami)
 
 sudo tee /etc/systemd/system/jupyter.service > /dev/null << SVCEOF
@@ -180,7 +205,7 @@ echo "  Jupyter service started (port 8888)"
 
 # 5. SSH keepalive
 echo ""
-echo "[5/5] Configuring SSH keepalive..."
+echo "[5/6] Configuring SSH keepalive..."
 if ! grep -q "ClientAliveInterval" /etc/ssh/sshd_config; then
     echo "ClientAliveInterval 60" | sudo tee -a /etc/ssh/sshd_config > /dev/null
     echo "ClientAliveCountMax 10" | sudo tee -a /etc/ssh/sshd_config > /dev/null
@@ -190,5 +215,58 @@ else
     echo "  SSH keepalive already configured"
 fi
 
+# 6. VSCode workspace setup
+echo ""
+echo "[6/6] Setting up VSCode workspace..."
+mkdir -p ~/workspace/.vscode
+
+# Detect cuda-gdb path
+CUDA_GDB_PATH=""
+if command -v cuda-gdb &>/dev/null; then
+    CUDA_GDB_PATH=$(command -v cuda-gdb)
+elif [ -x /usr/local/cuda/bin/cuda-gdb ]; then
+    CUDA_GDB_PATH="/usr/local/cuda/bin/cuda-gdb"
+else
+    # Try glob for versioned CUDA installs
+    for p in /usr/local/cuda-*/bin/cuda-gdb; do
+        if [ -x "$p" ]; then
+            CUDA_GDB_PATH="$p"
+        fi
+    done
+fi
+if [ -z "$CUDA_GDB_PATH" ]; then
+    echo "  WARNING: cuda-gdb not found — using placeholder in launch.json"
+    CUDA_GDB_PATH="cuda-gdb"
+else
+    echo "  cuda-gdb: $CUDA_GDB_PATH"
+fi
+
+# Detect GPU SM architecture
+GPU_ARCH=""
+if command -v nvidia-smi &>/dev/null; then
+    COMPUTE_CAP=$(nvidia-smi --query-gpu=compute_cap --format=csv,noheader 2>/dev/null | head -1 | tr -d '[:space:]')
+    if [ -n "$COMPUTE_CAP" ]; then
+        GPU_ARCH="sm_$(echo "$COMPUTE_CAP" | tr -d '.')"
+    fi
+fi
+if [ -z "$GPU_ARCH" ]; then
+    echo "  WARNING: Could not detect GPU arch — defaulting to sm_75"
+    GPU_ARCH="sm_75"
+else
+    echo "  GPU arch: $GPU_ARCH"
+fi
+
+# Copy example CUDA source into workspace
+cp /tmp/saxpy.cu ~/workspace/saxpy.cu
+echo "  Deployed saxpy.cu"
+
+# Deploy launch.json with cuda-gdb path
+sed "s|__CUDA_GDB_PATH__|${CUDA_GDB_PATH}|g" /tmp/launch.json > ~/workspace/.vscode/launch.json
+echo "  Deployed launch.json"
+
+# Deploy tasks.json with GPU architecture
+sed "s|__GPU_ARCH__|${GPU_ARCH}|g" /tmp/tasks.json > ~/workspace/.vscode/tasks.json
+echo "  Deployed tasks.json"
+
 echo ""
 echo "=== Remote setup complete ==="

aws_bootstrap/resources/saxpy.cu

@@ -0,0 +1,49 @@
+/**
+ * SAXPY Example, CUDA Style
+ * Source: https://developer.nvidia.com/blog/easy-introduction-cuda-c-and-c/
+ *
+ * This is included as an example CUDA C++ source file to try out the VS Code launch configuration we include on the host machine.
+ *
+ */
+#include <stdio.h>
+
+__global__
+void saxpy(int n, float a, float *x, float *y)
+{
+  int i = blockIdx.x*blockDim.x + threadIdx.x;
+  if (i < n) y[i] = a*x[i] + y[i];
+}
+
+int main(void)
+{
+  int N = 1<<20;
+  float *x, *y, *d_x, *d_y;
+  x = (float*)malloc(N*sizeof(float));
+  y = (float*)malloc(N*sizeof(float));
+
+  cudaMalloc(&d_x, N*sizeof(float));
+  cudaMalloc(&d_y, N*sizeof(float));
+
+  for (int i = 0; i < N; i++) {
+    x[i] = 1.0f;
+    y[i] = 2.0f;
+  }
+
+  cudaMemcpy(d_x, x, N*sizeof(float), cudaMemcpyHostToDevice);
+  cudaMemcpy(d_y, y, N*sizeof(float), cudaMemcpyHostToDevice);
+
+  // Perform SAXPY on 1M elements
+  saxpy<<<(N+255)/256, 256>>>(N, 2.0f, d_x, d_y);
+
+  cudaMemcpy(y, d_y, N*sizeof(float), cudaMemcpyDeviceToHost);
+
+  float maxError = 0.0f;
+  for (int i = 0; i < N; i++)
+    maxError = max(maxError, abs(y[i]-4.0f));
+  printf("Max error: %f\n", maxError);
+
+  cudaFree(d_x);
+  cudaFree(d_y);
+  free(x);
+  free(y);
+}

aws_bootstrap/resources/tasks.json

@@ -0,0 +1,48 @@
+{
+    // CUDA build tasks for VSCode
+    // Deployed to: ~/workspace/.vscode/tasks.json
+    "version": "2.0.0",
+    "tasks": [
+        {
+            "label": "nvcc: build active file (debug)",
+            "type": "shell",
+            "command": "nvcc",
+            "args": [
+                "-g",                           // Host debug symbols
+                "-G",                           // Device (GPU) debug symbols
+                "-O0",                          // No optimization
+                "-arch=__GPU_ARCH__",            // GPU arch (auto-detected)
+                "-o",
+                "${fileDirname}/${fileBasenameNoExtension}",
+                "${file}"
+            ],
+            "options": {
+                "cwd": "${fileDirname}"
+            },
+            "problemMatcher": ["$nvcc"],
+            "group": {
+                "kind": "build",
+                "isDefault": true
+            },
+            "detail": "Compile active .cu file with debug symbols (-g -G)"
+        },
+        {
+            "label": "nvcc: build active file (release)",
+            "type": "shell",
+            "command": "nvcc",
+            "args": [
+                "-O3",
+                "-arch=__GPU_ARCH__",
+                "-o",
+                "${fileDirname}/${fileBasenameNoExtension}",
+                "${file}"
+            ],
+            "options": {
+                "cwd": "${fileDirname}"
+            },
+            "problemMatcher": ["$nvcc"],
+            "group": "build",
+            "detail": "Compile active .cu file optimized (no debug)"
+        }
+    ]
+}

aws_bootstrap/ssh.py

@@ -159,6 +159,42 @@ def run_remote_setup(
         click.secho(f"  SCP failed: {nb_result.stderr}", fg="red", err=True)
         return False
 
+    # SCP the CUDA example source
+    saxpy_path = script_path.parent / "saxpy.cu"
+    click.echo("  Uploading saxpy.cu...")
+    saxpy_result = subprocess.run(
+        ["scp", *ssh_opts, *scp_port_opts, str(saxpy_path), f"{user}@{host}:/tmp/saxpy.cu"],
+        capture_output=True,
+        text=True,
+    )
+    if saxpy_result.returncode != 0:
+        click.secho(f"  SCP failed: {saxpy_result.stderr}", fg="red", err=True)
+        return False
+
+    # SCP the VSCode launch.json
+    launch_json_path = script_path.parent / "launch.json"
+    click.echo("  Uploading launch.json...")
+    launch_result = subprocess.run(
+        ["scp", *ssh_opts, *scp_port_opts, str(launch_json_path), f"{user}@{host}:/tmp/launch.json"],
+        capture_output=True,
+        text=True,
+    )
+    if launch_result.returncode != 0:
+        click.secho(f"  SCP failed: {launch_result.stderr}", fg="red", err=True)
+        return False
+
+    # SCP the VSCode tasks.json
+    tasks_json_path = script_path.parent / "tasks.json"
+    click.echo("  Uploading tasks.json...")
+    tasks_result = subprocess.run(
+        ["scp", *ssh_opts, *scp_port_opts, str(tasks_json_path), f"{user}@{host}:/tmp/tasks.json"],
+        capture_output=True,
+        text=True,
+    )
+    if tasks_result.returncode != 0:
+        click.secho(f"  SCP failed: {tasks_result.stderr}", fg="red", err=True)
+        return False
+
     # SCP the script
     click.echo("  Uploading remote_setup.sh...")
     scp_result = subprocess.run(
@@ -338,6 +374,34 @@ def list_ssh_hosts(config_path: Path | None = None) -> dict[str, str]:
     return result
 
 
+_INSTANCE_ID_RE = re.compile(r"^i-[0-9a-f]{8,17}$")
+
+
+def _is_instance_id(value: str) -> bool:
+    """Return ``True`` if *value* looks like an EC2 instance ID (``i-`` + hex)."""
+    return _INSTANCE_ID_RE.match(value) is not None
+
+
+def resolve_instance_id(value: str, config_path: Path | None = None) -> str | None:
+    """Resolve *value* to an EC2 instance ID.
+
+    If *value* already looks like an instance ID (``i-`` prefix followed by hex
+    digits) it is returned as-is.  Otherwise it is treated as an SSH host alias
+    and looked up in the managed SSH config blocks.
+
+    Returns the instance ID on success, or ``None`` if the alias was not found.
+    """
+    if _is_instance_id(value):
+        return value
+
+    hosts = list_ssh_hosts(config_path)
+    # Reverse lookup: alias -> instance_id
+    for iid, alias in hosts.items():
+        if alias == value:
+            return iid
+    return None
+
+
 @dataclass
 class SSHHostDetails:
     """Connection details parsed from an SSH config stanza."""

aws_bootstrap/tests/test_cli.py

@@ -170,6 +170,58 @@ def test_terminate_with_confirm(mock_terminate, mock_find, mock_session, mock_re
     assert mock_terminate.call_args[0][1] == ["i-abc123"]
 
 
+@patch("aws_bootstrap.cli.remove_ssh_host", return_value=None)
+@patch("aws_bootstrap.cli.boto3.Session")
+@patch("aws_bootstrap.cli.terminate_tagged_instances")
+@patch("aws_bootstrap.cli.resolve_instance_id", return_value="i-abc123")
+def test_terminate_by_alias(mock_resolve, mock_terminate, mock_session, mock_remove_ssh):
+    mock_terminate.return_value = [
+        {
+            "InstanceId": "i-abc123",
+            "PreviousState": {"Name": "running"},
+            "CurrentState": {"Name": "shutting-down"},
+        }
+    ]
+    runner = CliRunner()
+    result = runner.invoke(main, ["terminate", "--yes", "aws-gpu1"])
+    assert result.exit_code == 0
+    assert "Resolved alias 'aws-gpu1' -> i-abc123" in result.output
+    assert "Terminated 1" in result.output
+    mock_resolve.assert_called_once_with("aws-gpu1")
+    mock_terminate.assert_called_once()
+    assert mock_terminate.call_args[0][1] == ["i-abc123"]
+
+
+@patch("aws_bootstrap.cli.boto3.Session")
+@patch("aws_bootstrap.cli.resolve_instance_id", return_value=None)
+def test_terminate_unknown_alias_errors(mock_resolve, mock_session):
+    runner = CliRunner()
+    result = runner.invoke(main, ["terminate", "--yes", "aws-gpu99"])
+    assert result.exit_code != 0
+    assert "Could not resolve 'aws-gpu99'" in result.output
+
+
+@patch("aws_bootstrap.cli.remove_ssh_host", return_value=None)
+@patch("aws_bootstrap.cli.boto3.Session")
+@patch("aws_bootstrap.cli.terminate_tagged_instances")
+@patch("aws_bootstrap.cli.resolve_instance_id", return_value="i-abc123")
+def test_terminate_by_instance_id_passthrough(mock_resolve, mock_terminate, mock_session, mock_remove_ssh):
+    """Instance IDs are passed through without resolution message."""
+    mock_resolve.return_value = "i-abc123"
+    mock_terminate.return_value = [
+        {
+            "InstanceId": "i-abc123",
+            "PreviousState": {"Name": "running"},
+            "CurrentState": {"Name": "shutting-down"},
+        }
+    ]
+    runner = CliRunner()
+    result = runner.invoke(main, ["terminate", "--yes", "i-abc123"])
+    assert result.exit_code == 0
+    assert "Resolved alias" not in result.output
+    assert "Terminated 1" in result.output
+
+
 @patch("aws_bootstrap.cli.boto3.Session")
 @patch("aws_bootstrap.cli.find_tagged_instances")
 def test_terminate_cancelled(mock_find, mock_session):
@@ -565,7 +617,7 @@ def test_status_instructions_shown_by_default(mock_find, mock_spot, mock_session
     assert result.exit_code == 0
     assert "ssh aws-gpu1" in result.output
     assert "ssh -NL 8888:localhost:8888 aws-gpu1" in result.output
-    assert "vscode-remote://ssh-remote+aws-gpu1/home/ubuntu" in result.output
+    assert "vscode-remote://ssh-remote+aws-gpu1/home/ubuntu/workspace" in result.output
     assert "python ~/gpu_benchmark.py" in result.output
 
 

aws_bootstrap/tests/test_ssh_config.py

@@ -6,6 +6,7 @@ import stat
 from pathlib import Path
 
 from aws_bootstrap.ssh import (
+    _is_instance_id,
     _next_alias,
     _read_ssh_config,
     add_ssh_host,
@@ -13,6 +14,7 @@ from aws_bootstrap.ssh import (
     get_ssh_host_details,
     list_ssh_hosts,
     remove_ssh_host,
+    resolve_instance_id,
 )
 
 
@@ -331,3 +333,77 @@ def test_get_ssh_host_details_default_port(tmp_path):
     details = get_ssh_host_details("i-abc123", config_path=cfg)
     assert details is not None
     assert details.port == 22
+
+
+# ---------------------------------------------------------------------------
+# Instance ID detection
+# ---------------------------------------------------------------------------
+
+
+def test_is_instance_id_valid_short():
+    assert _is_instance_id("i-abcdef01") is True
+
+
+def test_is_instance_id_valid_long():
+    assert _is_instance_id("i-0123456789abcdef0") is True
+
+
+def test_is_instance_id_rejects_alias():
+    assert _is_instance_id("aws-gpu1") is False
+
+
+def test_is_instance_id_rejects_empty():
+    assert _is_instance_id("") is False
+
+
+def test_is_instance_id_rejects_prefix_only():
+    assert _is_instance_id("i-") is False
+
+
+def test_is_instance_id_rejects_uppercase():
+    assert _is_instance_id("i-ABCDEF01") is False
+
+
+def test_is_instance_id_rejects_too_short():
+    assert _is_instance_id("i-abc") is False
+
+
+# ---------------------------------------------------------------------------
+# resolve_instance_id
+# ---------------------------------------------------------------------------
+
+
+def test_resolve_passthrough_instance_id(tmp_path):
+    """Instance IDs are returned as-is without consulting SSH config."""
+    cfg = _config_path(tmp_path)
+    cfg.parent.mkdir(parents=True, exist_ok=True)
+    cfg.write_text("")
+    result = resolve_instance_id("i-0123456789abcdef0", config_path=cfg)
+    assert result == "i-0123456789abcdef0"
+
+
+def test_resolve_alias_to_instance_id(tmp_path):
+    cfg = _config_path(tmp_path)
+    add_ssh_host("i-abc12345", "1.2.3.4", "ubuntu", KEY_PATH, config_path=cfg)
+    result = resolve_instance_id("aws-gpu1", config_path=cfg)
+    assert result == "i-abc12345"
+
+
+def test_resolve_alias_multiple_hosts(tmp_path):
+    cfg = _config_path(tmp_path)
+    add_ssh_host("i-111aaa11", "1.1.1.1", "ubuntu", KEY_PATH, config_path=cfg)
+    add_ssh_host("i-222bbb22", "2.2.2.2", "ubuntu", KEY_PATH, config_path=cfg)
+    assert resolve_instance_id("aws-gpu1", config_path=cfg) == "i-111aaa11"
+    assert resolve_instance_id("aws-gpu2", config_path=cfg) == "i-222bbb22"
+
+
+def test_resolve_unknown_alias_returns_none(tmp_path):
+    cfg = _config_path(tmp_path)
+    cfg.parent.mkdir(parents=True, exist_ok=True)
+    cfg.write_text("")
+    assert resolve_instance_id("aws-gpu99", config_path=cfg) is None
+
+
+def test_resolve_nonexistent_config_returns_none(tmp_path):
+    cfg = tmp_path / "no_such_file"
+    assert resolve_instance_id("aws-gpu1", config_path=cfg) is None

{aws_bootstrap_g4dn-0.3.0.dist-info → aws_bootstrap_g4dn-0.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aws-bootstrap-g4dn
-Version: 0.3.0
+Version: 0.5.0
 Summary: Bootstrap AWS EC2 GPU instances for hybrid local-remote development
 Author: Adam Ever-Hadani
 License-Expression: MIT
@@ -49,7 +49,7 @@ ssh aws-gpu1                  # You're in, venv activated, PyTorch works
 ### 🎯 Target Workflows
 
 1. **Jupyter server-client** — Jupyter runs on the instance, connect from your local browser
-2. **VSCode Remote SSH** — `ssh aws-gpu1` just works with the Remote SSH extension
+2. **VSCode Remote SSH** — opens `~/workspace` with pre-configured CUDA debug/build tasks and an example `.cu` file
 3. **NVIDIA Nsight remote debugging** — GPU debugging over SSH
 
 ---
@@ -162,6 +162,7 @@ The setup script runs automatically on the instance after SSH becomes available:
 | **GPU smoke test notebook** | Copies `gpu_smoke_test.ipynb` to `~/gpu_smoke_test.ipynb` (open in JupyterLab) |
 | **Jupyter** | Configures and starts JupyterLab as a systemd service on port 8888 |
 | **SSH keepalive** | Configures server-side keepalive to prevent idle disconnects |
+| **VSCode workspace** | Creates `~/workspace/.vscode/` with `launch.json` and `tasks.json` (auto-detected `cuda-gdb` path and GPU arch), plus an example `saxpy.cu` |
 
 ### 📊 GPU Benchmark
 
@@ -200,6 +201,28 @@ ssh -i ~/.ssh/id_ed25519 -NL 8888:localhost:8888 ubuntu@<public-ip>
 
 A **GPU smoke test notebook** (`~/gpu_smoke_test.ipynb`) is pre-installed on every instance. Open it in JupyterLab to interactively verify the CUDA stack, run FP32/FP16 matmuls, train a small CNN on MNIST, and visualise training loss and GPU memory usage.
 
+### 🖥️ VSCode Remote SSH
+
+The remote setup creates a `~/workspace` folder with pre-configured CUDA debug and build tasks:
+
+```
+~/workspace/
+├── .vscode/
+│   ├── launch.json   # CUDA debug configs (cuda-gdb path auto-detected)
+│   └── tasks.json    # nvcc build tasks (GPU arch auto-detected, e.g. sm_75)
+└── saxpy.cu          # Example CUDA source — open and press F5 to debug
+```
+
+Connect directly from your terminal:
+
+```bash
+code --folder-uri vscode-remote://ssh-remote+aws-gpu1/home/ubuntu/workspace
+```
+
+Then install the [Nsight VSCE extension](https://marketplace.visualstudio.com/items?itemName=NVIDIA.nsight-vscode-edition) on the remote when prompted. Open `saxpy.cu`, set a breakpoint, and press F5.
+
+See [Nsight remote profiling guide](docs/nsight-remote-profiling.md) for more details on CUDA debugging and profiling workflows.
+
 ### 📋 Listing Resources
 
 ```bash
@@ -238,8 +261,14 @@ aws-bootstrap status --region us-east-1
 # Terminate all aws-bootstrap instances (with confirmation prompt)
 aws-bootstrap terminate
 
-# Terminate specific instances
-aws-bootstrap terminate i-abc123 i-def456
+# Terminate by SSH alias (resolved via ~/.ssh/config)
+aws-bootstrap terminate aws-gpu1
+
+# Terminate by instance ID
+aws-bootstrap terminate i-abc123
+
+# Mix aliases and instance IDs
+aws-bootstrap terminate aws-gpu1 i-def456
 
 # Skip confirmation prompt
 aws-bootstrap terminate --yes
@@ -251,7 +280,7 @@ aws-bootstrap terminate --yes
 CUDA: 12.8 (driver supports up to 13.0)
 ```
 
-SSH aliases are managed automatically — they're created on `launch`, shown in `status`, and cleaned up on `terminate`. Aliases use sequential numbering (`aws-gpu1`, `aws-gpu2`, etc.) and never reuse numbers from previous instances.
+SSH aliases are managed automatically — they're created on `launch`, shown in `status`, and cleaned up on `terminate`. Aliases use sequential numbering (`aws-gpu1`, `aws-gpu2`, etc.) and never reuse numbers from previous instances. You can use aliases anywhere you'd use an instance ID, e.g. `aws-bootstrap terminate aws-gpu1`.
 
 ## EC2 vCPU Quotas
 
@@ -322,7 +351,7 @@ aws-bootstrap launch --instance-type t3.medium --ami-filter "ubuntu/images/hvm-s
 | GPU instance pricing | [instances.vantage.sh](https://instances.vantage.sh/aws/ec2/g4dn.xlarge) |
 | Spot instance quotas | [AWS docs](https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/using-spot-limits.html) |
 | Deep Learning AMIs | [AWS docs](https://docs.aws.amazon.com/dlami/latest/devguide/what-is-dlami.html) |
-| Nvidia Nsight remote debugging | [Nvidia docs](https://docs.nvidia.com/nsight-visual-studio-edition/3.2/Content/Setup_Remote_Debugging.htm) |
+| Nsight remote GPU profiling | [Guide](docs/nsight-remote-profiling.md) — Nsight Compute, Nsight Systems, and Nsight VSCE on EC2 |
 
 Tutorials on setting up a CUDA environment on EC2 GPU instances:
 

aws_bootstrap_g4dn-0.5.0.dist-info/RECORD

@@ -0,0 +1,27 @@
+aws_bootstrap/__init__.py,sha256=kl_jvrunGyIyizdRqAP6ROb5P1BBrXX5PTq5gq1ipU0,82
+aws_bootstrap/cli.py,sha256=N2hT0XEC-4k5Cs3iGfA_xt_onc__NMNmh8fCaV4frgc,21076
+aws_bootstrap/config.py,sha256=TeCOYDlijT-KD5SFIzc-VvBhOqcq9YCgen9NK63rka8,895
+aws_bootstrap/ec2.py,sha256=LHpzW91ayK45gsWV_B4LanSZIhWggqTsL31qHUceiaA,12274
+aws_bootstrap/gpu.py,sha256=WTnHR0s3mQHDlnzqRgqAC6omWz7nT5YtGpcs0Bf88jk,692
+aws_bootstrap/ssh.py,sha256=0acHNX7IG6PUvp6T72l9kHTwUs5sVXFAyJXvUfA3qnE,20131
+aws_bootstrap/resources/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+aws_bootstrap/resources/gpu_benchmark.py,sha256=1eFt_3MXvoLhs9HahrRPhbxvtdjFaXG2Ty3GEg7Gud0,29366
+aws_bootstrap/resources/gpu_smoke_test.ipynb,sha256=XvAOEIPa5H9ri5mRZqOdknmwOwKNvCME6DzBGuhRYfg,10698
+aws_bootstrap/resources/launch.json,sha256=ZOcvHLy3-zBOqRTtFzuyn-_2tB64yuEn8PrJOoZ-PgE,1484
+aws_bootstrap/resources/remote_setup.sh,sha256=z_YGdzwEHWInkE3dZVbBNa0F_joTeVhnOpCYOj1CK30,8331
+aws_bootstrap/resources/requirements.txt,sha256=gpYl1MFCfWXiAhbIUgAjuTHONz3MKci25msIyOkMmUk,75
+aws_bootstrap/resources/saxpy.cu,sha256=1BSESEwGGCx3KWx9ZJ8jiPHQ42KzQN6i2aP0I28bPsA,1178
+aws_bootstrap/resources/tasks.json,sha256=6U8pB1N8YIWgUCfFet4ne3nYnI92tWv5D5kPiQG3Zlg,1576
+aws_bootstrap/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+aws_bootstrap/tests/test_cli.py,sha256=m_4tIX0xYZ8BxDkHPGAWiPAKo4vETaTSKSJbyn3K1Cg,34731
+aws_bootstrap/tests/test_config.py,sha256=arvET6KNl4Vqsz0zFrSdhciXGU688bfsvCr3dSpziN0,1050
+aws_bootstrap/tests/test_ec2.py,sha256=Jmqsjv973hxXbZWfGgECtm6aa2156Lzji227sYMBuMg,10547
+aws_bootstrap/tests/test_gpu.py,sha256=rbMuda_sIVbaCzkWXoLv9YIfnWztgRoP7NuVL8XHrUY,3871
+aws_bootstrap/tests/test_ssh_config.py,sha256=YYtv82zBBLGioTo58iC31_5jUli1s0eoGV9VRCobOgY,14059
+aws_bootstrap/tests/test_ssh_gpu.py,sha256=dRp86Og-8GqiATSff3rxhu83mBZdGgqI4UOnoC00Ln0,1454
+aws_bootstrap_g4dn-0.5.0.dist-info/licenses/LICENSE,sha256=Hen77Mt8sazSQJ9DgrmZuAvDwo2vc5JAkR_avuFV-CM,1067
+aws_bootstrap_g4dn-0.5.0.dist-info/METADATA,sha256=t8m53ZodJlZyMffeSu3Wk5bMt-Dm_Jl3q_HTbRLQbYE,13728
+aws_bootstrap_g4dn-0.5.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+aws_bootstrap_g4dn-0.5.0.dist-info/entry_points.txt,sha256=T8FXfOgmLEvFi8DHaFJ3tCzId9J3_d2Y6qT98OXxCjA,57
+aws_bootstrap_g4dn-0.5.0.dist-info/top_level.txt,sha256=mix9gZRs8JUv0OMSB_rwdGcRnTKzsKgHrE5fyAn5zJw,14
+aws_bootstrap_g4dn-0.5.0.dist-info/RECORD,,

aws_bootstrap_g4dn-0.3.0.dist-info/RECORD

@@ -1,24 +0,0 @@
-aws_bootstrap/__init__.py,sha256=kl_jvrunGyIyizdRqAP6ROb5P1BBrXX5PTq5gq1ipU0,82
-aws_bootstrap/cli.py,sha256=H7Lud1PWk0O5zKGf1StARCEahrMErickuHXsWk42j3A,20481
-aws_bootstrap/config.py,sha256=TeCOYDlijT-KD5SFIzc-VvBhOqcq9YCgen9NK63rka8,895
-aws_bootstrap/ec2.py,sha256=LHpzW91ayK45gsWV_B4LanSZIhWggqTsL31qHUceiaA,12274
-aws_bootstrap/gpu.py,sha256=WTnHR0s3mQHDlnzqRgqAC6omWz7nT5YtGpcs0Bf88jk,692
-aws_bootstrap/ssh.py,sha256=RK5Ahiwpol9-4MUvurKyNa1JorQW9VkkNtSSfPzryrU,17851
-aws_bootstrap/resources/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aws_bootstrap/resources/gpu_benchmark.py,sha256=2uoss2bZGhg7c3D7Hg1-EJlOVDtzAH4co1ahSvF_lVU,29080
-aws_bootstrap/resources/gpu_smoke_test.ipynb,sha256=XvAOEIPa5H9ri5mRZqOdknmwOwKNvCME6DzBGuhRYfg,10698
-aws_bootstrap/resources/remote_setup.sh,sha256=n1joNO-6EizLsz2BPOPruFhe90kEQ9Np2SBhYXnOJRs,5648
-aws_bootstrap/resources/requirements.txt,sha256=gpYl1MFCfWXiAhbIUgAjuTHONz3MKci25msIyOkMmUk,75
-aws_bootstrap/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aws_bootstrap/tests/test_cli.py,sha256=vyoVVqSakC7Y2BCEFpyf2ghTUvT-QWBQC9-yvEFz3gw,32554
-aws_bootstrap/tests/test_config.py,sha256=arvET6KNl4Vqsz0zFrSdhciXGU688bfsvCr3dSpziN0,1050
-aws_bootstrap/tests/test_ec2.py,sha256=Jmqsjv973hxXbZWfGgECtm6aa2156Lzji227sYMBuMg,10547
-aws_bootstrap/tests/test_gpu.py,sha256=rbMuda_sIVbaCzkWXoLv9YIfnWztgRoP7NuVL8XHrUY,3871
-aws_bootstrap/tests/test_ssh_config.py,sha256=iQDd3hJ8to-2-QHW26Brtglfl0q0P6sCE6U_itxoNyY,11609
-aws_bootstrap/tests/test_ssh_gpu.py,sha256=dRp86Og-8GqiATSff3rxhu83mBZdGgqI4UOnoC00Ln0,1454
-aws_bootstrap_g4dn-0.3.0.dist-info/licenses/LICENSE,sha256=Hen77Mt8sazSQJ9DgrmZuAvDwo2vc5JAkR_avuFV-CM,1067
-aws_bootstrap_g4dn-0.3.0.dist-info/METADATA,sha256=tfsBYTSqVQf8A46P22qwdFsb_ur-Ge57hQfuDaj0mgE,12417
-aws_bootstrap_g4dn-0.3.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-aws_bootstrap_g4dn-0.3.0.dist-info/entry_points.txt,sha256=T8FXfOgmLEvFi8DHaFJ3tCzId9J3_d2Y6qT98OXxCjA,57
-aws_bootstrap_g4dn-0.3.0.dist-info/top_level.txt,sha256=mix9gZRs8JUv0OMSB_rwdGcRnTKzsKgHrE5fyAn5zJw,14
-aws_bootstrap_g4dn-0.3.0.dist-info/RECORD,,