Commit 1ebb152f authored by Neil McGlohon's avatar Neil McGlohon

fixup: compute_time_speedup event timestamp bug

The feature addition of the compute_time_speedup factor did affect
the compute time correctly. It, however, didn't affect the scheduling
of the new event after the compute time. This resulted in the delay
savings from the compute time speedup being applied to the comm. time
instead. This has now been resolved.
parent dd8f83bc
...@@ -1447,7 +1447,7 @@ static void codes_exec_comp_delay( ...@@ -1447,7 +1447,7 @@ static void codes_exec_comp_delay(
m->rc.saved_delay_sample = s->ross_sample.compute_time; m->rc.saved_delay_sample = s->ross_sample.compute_time;
s->compute_time += (mpi_op->u.delay.nsecs/compute_time_speedup); s->compute_time += (mpi_op->u.delay.nsecs/compute_time_speedup);
s->ross_sample.compute_time += (mpi_op->u.delay.nsecs/compute_time_speedup); s->ross_sample.compute_time += (mpi_op->u.delay.nsecs/compute_time_speedup);
ts = mpi_op->u.delay.nsecs; ts = (mpi_op->u.delay.nsecs/compute_time_speedup);
if(ts <= g_tw_lookahead) if(ts <= g_tw_lookahead)
{ {
bf->c28 = 1; bf->c28 = 1;
......
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