GPGPUs use the Single-Instruction-Multiple-Thread (SIMT) execution model where a group
of threads—wavefront or warp—execute instructions in lockstep. When threads in a group …

The US Department of Energy's fastest supercomputers and forthcoming exascale systems
employ Graphics Processing Units (GPUs) to increase the computational performance of …

Raytracing applications have naturally high thread divergence, low warp occupancy and are
limited by memory latency. In this paper, we present an architectural enhancement called …

While there are mature performance monitoring, profiling and instrumentation tools to help
understanding the dynamic behaviour of general-purpose GPU applications, the abstract …

Contemporary data center servers process thousands of similar, independent requests per
minute. In the interest of programmer productivity and ease of scaling, workloads in data …

In GPUs, the control flow management mechanism determines which threads in a warp are
active at any point in time. This mechanism monitors the control flow of scalar threads within …

The computing landscape is undergoing rapid evolution to meet the demand in
dataintensive applications and grand challenging scientific problems. Figure 1.1 illustrates …

Οι GPU, που αρχικά προτάθηκαν αποκλειστικά ως επιταχυντές επεξεργασίας γραφικών,
βρίσκουν πλέον εφαρμογή σε ένα συνεχώς αυξανόμενο εύρος τομέων. Η ανάλυση μιας …

GPGPUs use the Single-Instruction-Multiple-Thread (SIMT) execution model where a group
of threads-wavefront or warp-execute instructions in lockstep. When threads in a group …

Irregular control-flow structures like deeply nested conditional branches are common in real-
world software applications. Improving the performance and efficiency of such programs is …