Install the B200 GPU baseboard

Follow instructions in this section to install 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.
• Touch the static-protective package that contains the component to any unpainted metal surface on the server; then, remove it from the package and place it on a static-protective surface.
• Make sure to inspect the connectors and sockets on the GPU and the GPU baseboard. Do not use the GPU or the GPU baseboard if its connectors are damaged or missing, or if there are debris in the sockets. Replace the GPU or the GPU baseboard with a new one before continuing the installation procedure.

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

Firmware and driver download: You might need to update the firmware or driver after replacing a component.

• Go to Drivers and Software download website for ThinkSystem SR780a V3 to see the latest firmware and driver updates for your server.

• Go to Update the firmware for more information on firmware updating tools.

The following illustration shows the B200 GPU numbering and corresponding slot numbering in XCC.

Figure 1. B200 GPU numbering

Physical GPU socket	Slot numbering in XCC	Logical 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. (Optional) Remove the new GPU baseboard from the package box.
   1. Hold the two handles, and remove the GPU baseboard out from the package box.
   Figure 2. Removing the GPU baseboard from the package box
   
   
2. Install the GPUs onto the GPU baseboard. Use the GPU screw handles to install the GPUs onto the baseboard, then simultaneously fasten the two diagonal Torx T15 screws with the screwdriver set to the proper torque.
   1. Carefully lay the GPU baseboard on a flat, static protective surface.
   2. Install the two GPU screw handles diagonally. Align the screw handles to the cold plate screw holes; then fasten the screw handles by hand.
      Figure 3. Installing the GPU screw handles
      
      
   3. Hold the GPU screw handles to carefully place the GPU onto the GPU baseboard.
      Figure 4. Installing the GPU
      
      
   4. Remove the two screw handles by loosening them by hand.
      Figure 5. Removing the GPU screw handles
      
      
   5. First set the torque screwdriver to 0.11±0.011 newton-meters, 0.97±0.097 inch-pounds to simultaneously fasten the two diagonal screws; then, simultaneously fasten the two diagonal screws.
   6. Then set the torque screwdriver to 0.6±0.024 newton-meters, 5.3±0.212 inch-pounds to simultaneously fasten the two diagonal screws; then, simultaneously fasten the two diagonal screws.
      Figure 6. Installing the GPU
      
      
   7. Repeat to install all the GPUs.
3. Install the GPU complex.
   1. Hold the handles (1) on both sides of the GPU baseboard in the correct orientation as illustrated; then, align the GPU complex with the seventeen standoffs on the GPU complex adapter plate, and carefully place it onto the adapter plate.
      Figure 7. GPU complex installation
      
      
   2. Remove the handles. Attach the Torx T25 extension bit to the screwdriver and unfasten the four M4 screws that secure the handles to the GPU complex; then, remove the handles from the GPU complex.
      Figure 8. Removing handles
      
      
   3. Follow the sequence shown in the illustration below to fasten the eighteen Torx T15 captive screws to secure the GPU complex.
      Important

      Do not overtighten the screws to avoid damage.

      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 9. Screw installation
      
      
4. Align the hose guide with the screw hole on the chassis; then, fasten the three M3 screws (PH2, 3 x M3, 0.5 newton-meters, 4.3 inch-pounds) to secure the hose guide. Repeat to install the hose guide on the other side.
   Figure 10. Installing the hose guides
   
   
5. Align the CX-7 adapter card protective bracket with the corresponding screw holes; then, fasten the two M3 screws (PH2, 2 x M3, 0.5 newton-meters, 4.3 inch-pounds) to secure the bracket to the chassis.
   Figure 11. Installing CX-7 adapter card protective bracket
   
   
6. Align the GPU connector protective bracket with the corresponding screw holes; then, fasten the two M3 screws (PH2, 2 x M3, 0.5 newton-meters, 4.3 inch-pounds) to secure the GPU connector protective bracket to the chassis.
   Figure 12. Installing GPU connector protective bracket
   
   
7. Install the PCIe switch shuttle.
   1. Press the two blue release latches.
   2. Press the two lock latches on both sides of the PCIe switch shuttle.
   3. Push the PCIe switch shuttle into the chassis until it stops.
   4. Rotate the two release levers until they lock into place.
      Figure 13. PCIe switch shuttle installation