Resolving A Graphics Processing Unit Problem - IBM Power System 8335-GCA Manual

Table 3. Network adapter problems and service actions (continued).
Problem
Adapter stops working suddenly
Link indicator light on the adapter is off
Link light on the adapter is on, but there is no
communication from the adapter
Other problems

Resolving a graphics processing unit problem

Learn about the possible problems and service actions that you can perform to resolve a graphics
processing unit (GPU) problem.
Note: To determine the location of the GPU, see "Identifying the location of the GPU" on page 22.
16
Problem analysis, system parts, and locations for the 8335-GCA, 8335-GTA, 8335-GTB, and 8348-21C
Service action
1. If the system was recently installed, moved, serviced,
or upgraded, verify that the adapter is seated
properly and all associated cables are correctly
connected.
2. Inspect the PCIe socket and verify that there is no
dirt or debris in the socket.
3. Inspect the card and verify that it is not physically
damaged.
4. Verify that all cables are properly seated and are not
physically damaged. If you recently added one or
more new adapters, remove them and then test to
determine whether the failing adapter is functioning
properly again. If the network adapter is functioning
again, review the IBM support tips to confirm that
there are no PCI address, driver, or firmware
conflicts. Then, reinstall the new adapters again one
at a time until all adapters function properly.
5. Replace the adapter.
6. Replace the system backplane.
7. Replace the CPU.
1. Verify that the cable functions properly by testing it
with a known working connection.
2. Verify that the port or ports on the switch are
enabled and functional.
3. Verify that the switch and adapter are compatible.
4. Replace the adapter.
1. Verify that the most recent driver is installed, or
install the most recent driver if it is not already
installed.
2. Verify that the adapter and its link have compatible
settings, such as speed and duplex configuration.
For information about adapter diagnostics, see
Supporting diagnostics. For information about adapter
user information, see "User guides for GPUs and PCIe
adapters" on page 25.