Lines Matching refs:compute

221 * Long-running compute command buffers, while still using traditional end of
223   fences which get reattached when the compute job is rescheduled.
270   userspace is allowed to use userspace fencing or long running compute
293 faults on GPUs are limited to pure compute workloads.
296 compute side, like compute units or command submission engines. If both a 3D
297 job with a DMA fence and a compute workload using recoverable page faults are
300 - The 3D workload might need to wait for the compute job to finish and release
303 - The compute workload might be stuck in a page fault, because the memory
314   achieved through e.g. through dedicated engines and minimal compute unit
325   fences must complete before a compute job with page fault handling can be
327   made visible anywhere in the system, all compute workloads must be preempted
344 Fences` discussions: Infinite fences from compute workloads are allowed to