Shared memory architectures have recently experienced a large increase in thread-level
parallelism, leading to complex memory hierarchies with multiple cache memory levels and …

To harness a heterogeneous memory hierarchy, it is advantageous to integrate application
knowledge in guiding frequent memory move, ie, replicating or migrating virtual memory …

Both NUMA thread/data placement and hardware prefetcher configuration have significant
impacts on HPC performance. Optimizing both together leads to a large and complex design …

Non-Uniform Memory Access (NUMA) architectures are widely used in mainstream multi-
socket computer systems to scale memory bandwidth. Without a NUMA-aware design …

Non Uniform Memory Access (NUMA) architectures are nowadays common for running High-
Performance Computing (HPC) applications. In such architectures, several distinct physical …

In the age of the cloud-native, container technology, referred as OS-level virtualization, is
increasingly adopted to deploy cloud applications. Compared with virtual machines …

Nowadays, NUMA architectures are common in compute-intensive systems. Achieving high
performance for multi-threaded application requires both a careful placement of threads on …

Shared memory systems are becoming increasingly complex as they typically integrate
several storage devices. That brings different access latencies or bandwidth rates …

Evolving requirements may necessitate API migration-re-engineering an application to
replace its dependence on one API with the dependence on another API for the same …

In parallel architectures that have a Non-Uniform Memory Access (NUMA) behavior, the
map** of memory pages to NUMA nodes influences the performance of parallel …