Commit 21f8204e authored by Chris Wilson's avatar Chris Wilson 🤔

i915/gem_exec_schedule: Trim repetitions for preempt-queue

Double the queue length each time, instead of a plain increment, so we
reduce the number of iterations we require by 4.
Signed-off-by: Chris Wilson's avatarChris Wilson <chris@chris-wilson.co.uk>
Acked-by: default avatarMika Kuoppala <mika.kuoppala@linux.intel.com>
parent d97a7c4f
Pipeline #176003 passed with stages
in 9 minutes and 27 seconds
......@@ -1479,7 +1479,7 @@ static void preempt_queue(int fd, unsigned ring, unsigned int flags)
const struct intel_execution_engine2 *e;
__for_each_physical_engine(fd, e) {
for (unsigned depth = 0; depth <= MAX_ELSP_QLEN; depth++)
for (unsigned depth = 1; depth <= MAX_ELSP_QLEN; depth *= 2)
__preempt_queue(fd, ring, e->flags, depth, flags);
}
}
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment