Low-Overhead Trace Collection and Profiling on GPU Compute Kernels.

Sébastien Darche Michel R. Dagenais

Published in: ACM Trans. Parallel Comput. (2024)

Keyphrases

low overhead
high reliability
load balancing
real time
shared memory
energy efficient
support vector
communication cost
kernel function
wireless sensor networks
multi agent systems
higher order
high precision
message passing
parallel computing
distributed breakout