International audienceSeveral different metrics have been proposed for quantifying the throughput of multicore processors. There is no clear consensus about which metric should be used. Some studies even use several throughput metrics. We show that there exists a relation between single-thread average performance metrics and throughput metrics, and that throughput metrics inherit the meaning or lack of meaning of the corresponding single-thread metric. We show that two popular throughput metrics, the weighted speedup and the harmonic mean of speedups, are inconsistent: they do not give equal importance to all benchmarks. Moreover we demonstrate that the weighted speedup favors unfairness. We show that the harmonic mean of IPCs, a seldom use...
Designers of chip multiprocessors will increasingly be called upon to optimize for a combination of ...
Since many years, we observe a shift from classical multiprocessor systems tomulticores, which tight...
International audienceIn the area of code performance optimisation and tuning, we are faced on the d...
International audienceSeveral different metrics have been proposed for quantifying the throughput of...
Measuring throughput is not as straightforward as measuring execution time. This has led to an ongoi...
International audienceRunning multiple programs on a processor aims at increasing the throughput of ...
Running multiple programs on a processor aims at increasing the throughput of that processor. Howeve...
Multicore processors can improve performance by decreasing the execution latency of parallel program...
Weighted speedup is nowadays the most commonly used multiprogram workload performance metric. Weight...
Abstract—Weighted speedup is nowadays the most commonly used multiprogram workload performance metri...
Multi-threaded processors execute multiple threads concurrently in order to increase overall through...
International audienceMulti-threaded processors execute multiple threads concurrently in order to in...
Throughput (TP) has been a fundamental metric in quantifying input system performance. TP is a conce...
Advanced many-core CPU chips already have few hundreds of processing cores (e.g. 160 cores in an IBM...
Understanding why the performance of a multithreaded program does not improve linearly with the numb...
Designers of chip multiprocessors will increasingly be called upon to optimize for a combination of ...
Since many years, we observe a shift from classical multiprocessor systems tomulticores, which tight...
International audienceIn the area of code performance optimisation and tuning, we are faced on the d...
International audienceSeveral different metrics have been proposed for quantifying the throughput of...
Measuring throughput is not as straightforward as measuring execution time. This has led to an ongoi...
International audienceRunning multiple programs on a processor aims at increasing the throughput of ...
Running multiple programs on a processor aims at increasing the throughput of that processor. Howeve...
Multicore processors can improve performance by decreasing the execution latency of parallel program...
Weighted speedup is nowadays the most commonly used multiprogram workload performance metric. Weight...
Abstract—Weighted speedup is nowadays the most commonly used multiprogram workload performance metri...
Multi-threaded processors execute multiple threads concurrently in order to increase overall through...
International audienceMulti-threaded processors execute multiple threads concurrently in order to in...
Throughput (TP) has been a fundamental metric in quantifying input system performance. TP is a conce...
Advanced many-core CPU chips already have few hundreds of processing cores (e.g. 160 cores in an IBM...
Understanding why the performance of a multithreaded program does not improve linearly with the numb...
Designers of chip multiprocessors will increasingly be called upon to optimize for a combination of ...
Since many years, we observe a shift from classical multiprocessor systems tomulticores, which tight...
International audienceIn the area of code performance optimisation and tuning, we are faced on the d...