cuda.bindings.nvml.PerfPolicyType#

class cuda.bindings.nvml.PerfPolicyType(value: int)#

Represents type of perf policy for which violation times can be queried

See nvmlPerfPolicyType_t.

POWER: 0: How long did power violations cause the GPU to be below application clocks.
THERMAL: 1: How long did thermal violations cause the GPU to be below application clocks.
SYNC_BOOST: 2: How long did sync boost cause the GPU to be below application clocks.
BOARD_LIMIT: 3: How long did the board limit cause the GPU to be below application clocks.
LOW_UTILIZATION: 4: How long did low utilization cause the GPU to be below application clocks.
RELIABILITY: 5: How long did the board reliability limit cause the GPU to be below application clocks.
TOTAL_APP_CLOCKS: 10: Total time the GPU was held below application clocks by any limiter (0 - 5 above).
TOTAL_BASE_CLOCKS: 11: Total time the GPU was held below base clocks.

COUNT: 12