Exploiting data locality in GPUs is critical to making more efficient use of the existing caches
and the NUMA-based memory hierarchy expected in future GPUs. While modern GPU …

Long latency of memory operation is a prominent performance bottleneck in graphics
processing units (GPUs). The small data cache that must be shared across dozens of warps …

The massive parallelism present in GPUs comes at the cost of reduced L1 and L2 cache
sizes per thread, leading to serious cache contention problems such as thrashing. Hence …

Graphics Processing Units (GPUs) are the accelerator of choice in a variety of application
domains, because they can accelerate massively parallel workloads and can be easily …

Bandwidth achieved from local/shared caches and memory is a major performance
determinant in Graphics Processing Units (GPUs). These existing sources of bandwidth are …

Graphics Processing Units (GPUs) concurrently execute thousands of threads, which makes
them effective for achieving high throughput for a wide range of applications. However, the …

Cache coherence has been studied extensively in the context of chip multiprocessors
(CMP). It is well known that conventional directory-based and snooping coherence protocols …

Albeit GPUs are supposed to be tolerant to long latency of data fetch operation, we observe
that L1 cache misses occur in a bursty manner for many memory-intensive applications. This …

Modern GPUs suffer from cache contention due to the limited cache size that is shared
across tens of concurrently running warps. To increase the per-warp cache size prior …

Graph convolutional neural networks (GCNs) are emerging neural networks for graph
structures that include large features associated with each vertex. The operations of GCN …