Pular para o conteúdo principal

Remove the B200 GPU baseboard

Follow instructions in this section to remove the B200 GPU baseboard. The procedure must be executed by a trained technician.

About this task

Attention
  • Read Installation Guidelines and Safety inspection checklist to ensure that you work safely.
  • Power off the server and peripheral devices and disconnect the power cords and all external cables. See Power off the server.
  • If the server is installed in a rack, remove the server from the rack. See Remove the server from rack.
  • Two people and one lifting device on site that can support up to 400 lb (181 kg) are required to perform this procedure. If you do not already have a lifting device available, Lenovo offers the Genie Lift GL-8 material lift that can be purchased at Data Center Solution Configurator. Make sure to include the Foot-release brake and the Load Platform when ordering the Genie Lift GL-8 material lift.
Note
Make sure you have the required tools listed below available to properly replace the component:
  • Torx T15 head screwdriver
  • 2 x Torx T15 200mm extension bit
  • Phillips #1 head screwdriver
  • Phillips #2 head screwdriver
  • Alcohol cleaning pad
  • 2 x B200 PCM
  • 2 x B200 SXM6 PAD-1
  • 2 x B200 SXM6 PAD-2
  • B200 GPU F&R Shipping bkt Kit
  • B200 GPU Service Kit
  • B200 Retimer nvswitch Service Kit
  • B200 Retimer NVswitch Shipping Kit
  • B200 NVSWITCH PCM
  • B200 NVSWITCH PAD-1
  • B200 NVSWITCH PAD-2
  • B200 GPU baseboard handle
  • Torx T25 150mm extension bit (for GPU baseboard handles)
B200 (GPU & Retimer NVSwitch) (service & shipping bkt) Kit are reusable and mandatory when servicing GPUs and GPU cold plate modules. It is recommended to keep them at the facility where the server operates for future replacement needs.
Note
Make sure you have the required tools listed below available to properly replace the component:
  • Torque screwdriver which can be set to 0.6 newton-meters, 5.3 inch-pounds
The following illustration shows the B200 GPU numbering and corresponding slot numbering in XCC.
Figure 1. B200 GPU numbering
B200 GPU numbering
Physical GPU socketSlot numbering in XCCLogical number in nvidia-smi

GPU 1

Slot 21

4

GPU 2

Slot 24

7

GPU 3

Slot 22

5

GPU 4

Slot 23

6

GPU 5

Slot 17

0

GPU 6

Slot 20

3

GPU 7

Slot 18

1

GPU 8

Slot 19

2

Procedure

  1. Make preparation for this task.
    1. Remove the front top cover. See Remove the front top cover.
    2. Remove the rear top cover. See Remove the rear top cover.
    3. Remove the fan cage. See Remove the fan cage (trained technician only).
    4. Remove the CPU complex. See Remove the CPU complex.
    5. Remove the power complex. See Remove the power complex.
    6. Disconnect the cables from the GPU baseboard.
    7. Disconnect and remove the cables routed through the GPU complex, if necessary. Before disconnecting the cables, make a list of each cable and record the connectors the cable is connected to. Refer to Internal cable routing.
    8. Remove the rear B200 GPU cold plate module. See Remove the rear B200 GPU cold plate module.
    9. Remove the front B200 GPU cold plate module. See Remove the front B200 GPU cold plate module.
    10. Remove the NVswitch and retimer cold plate module. See Remove the B200 NVSwitch and retimer cold plate module.
  2. Disengage the PCIe switch shuttle from the chassis.
    1. Press the two blue release latches.
    2. Rotate the two release levers until they are perpendicular to the PCIe switch shuttle.
    3. Pull the PCIe switch shuttle forward until it stops.
      Important
      Push the two release levers back until they lock into place after pulling out the PCIe switch shuttle to avoid damage.
      Figure 2. PCIe switch shuttle removal to stop position
      PCIe switch shuttle removal to stop position
  3. Unfasten the two M3 screws to remove the GPU connector protective bracket.
    Figure 3. Removing the GPU connector protective bracket
    Removing the GPU connector protective bracket
  4. Unfasten the two M3 screws to remove the CX-7 adapter card protective bracket.
    Figure 4. Removing CX-7 adapter card protective bracket
    Removing CX-7 adapter card protective bracket
  5. Unfasten the three M3 screws to remove the hose guide from the chassis. Repeat to remove the hose guide on the other side.
    Figure 5. Removing hose guide
    Removing hose guide
  6. Unfasten the eighteen Torx T15 captive screws on the GPU baseboard.
    Note
    Loosen or tighten the screws with a torque screwdriver set to the proper torque. For reference, the torque required for the screws to be fully loosen or tighten is 0.6±0.024 newton-meters, 5.3±0.212 inch-pounds.
    Figure 6. Screw removal
    Screw removal
  7. Remove the GPU complex.
    1. Install the handles. Attach the Torx T25 extension bit to the screwdriver. Align the handles with the screw holes and lower them onto the GPU baseboard; then, fasten the four M4 screws (4 x M4, 0.5 newton-meters, 4.3 inch-pounds) to secure the handles to the GPU baseboard.
      Figure 7. Installing the handles
      Installing the handles
    2. Hold the two handles (1), and lift the GPU complex out of the chassis.
    Attention
    Make sure two people stand on either side of the GPU complex, and lift it by holding the two handles.
    Figure 8. Removing the GPU complex
    Removing the GPU complex
    Note
    Keep the handles attached to the GPU complex if it is to be shipped for RMA procedure.
  8. Remove the handles if necessary. Carefully lay the GPU complex on a flat, static protective surface; then, attach the Torx T25 extension bit to the screwdriver and unfasten the four M4 screws that secure the handles to the baseboard. Lift the handles to remove them from the baseboard.
    Note
    Keep the handles attached to the GPU complex if it is to be shipped for RMA procedure.
    Figure 9. Removing handles
    Removing handles
  9. Remove the GPUs from the GPU baseboard. Simultaneously loosen the two diagonal Torx T15 screws with the screwdriver set to the proper torque.
    1. Carefully lay the GPU complex on a flat, static protective surface.
    2. Set the torque screwdriver to 0.6 newton-meters, 5.3 inch-pounds to simultaneously loosen the two diagonal screws; then, simultaneously loosen the two diagonal screws.
      Figure 10. Removing the GPU
      Removing the GPU
    3. Install the two GPU screw handles diagonally. Align the screw handles to the cold plate screw slots; then fasten the screw handles by hand.
      Figure 11. Installing the GPU screw handles
      Installing the GPU screw handles
    4. Hold the GPU screw handles to remove the GPU from the GPU baseboard.
      Figure 12. Removing the GPU
      Removing the GPU
    5. Carefully lay the GPU on a flat, static protective surface. Remove the two screw handles by loosening them by hand.
      Figure 13. Removing the GPU screw handles
      Removing the GPU screw handles
    6. Repeat to remove all the GPUs.

After you finish

  1. Install a replacement unit. See Install the B200 GPU baseboard.
  2. If you are instructed to return the component or optional device, follow all packaging instructions, and use any packaging materials for shipping that are supplied to you.