Multi-Tenant Virtual GPUs for Optimising Performance of a Financial Risk Application

Graphics Processing Units (GPUs) are becoming popular accelerators in modern High-Performance Computing (HPC) clusters. Installing GPUs on each node of the cluster is not efficient resulting in high costs and power consumption as well as underutilisation of the accelerator. The research reported in this paper is motivated towards the use of few physical GPUs by providing cluster nodes access to remote GPUs on-demand for a financial risk application. We hypothesise that sharing GPUs between several nodes, referred to as multi-tenancy, reduces the execution time and energy consumed by an application. Two data transfer modes between the CPU and the GPUs, namely concurrent and sequential, are explored. The key result from the experiments is that multi-tenancy with few physical GPUs using sequential data transfers lowers the execution time and the energy consumed, thereby improving the overall performance of the application.

Maintaining legacy data: saving Belfast Harbour (UK) tide-gauge data (1902-2010)

Tide gauge data are identified as legacy data given the radical transition between observation method and required output format associated with tide gauges over the 20th-century. Observed water level variation through tide-gauge records is regarded as the only significant basis for determining recent historical variation (decade to century) in mean sea-level and storm surge. There are limited tide gauge records that cover the 20th century, such that the Belfast (UK) Harbour tide gauge would be a strategic long-term (110 years) record, if the full paper-based records (marigrams) were digitally restructured to allow for consistent data analysis. This paper presents the methodology of extracting a consistent time series of observed water levels from the 5 different Belfast Harbour tide gauges’ positions/machine types, starting late 1901. Tide-gauge data was digitally retrieved from the original analogue (daily) records by scanning the marigrams and then extracting the sequential tidal elevations with graph-line seeking software (Ungraph™). This automation of signal extraction allowed the full Belfast series to be retrieved quickly, relative to any manual x–y digitisation of the signal. Restructuring variably lengthed tidal data sets to a consistent daily, monthly and annual file format was undertaken by project-developed software: Merge&Convert and MergeHYD allow consistent water level sampling both at 60 min (past standard) and 10 min intervals, the latter enhancing surge measurement. Belfast tide-gauge data have been rectified, validated and quality controlled (IOC 2006 standards). The result is a consistent annual-based legacy data series for Belfast Harbour that includes over 2 million tidal-level data observations.

No discrimination shock avoidance with sequential presentation of stimuli but shore crabs still reduce shock exposure

Insights into the potential for pain may be obtained from examination of behavioural responses to noxious stimuli. In particular, prolonged responses coupled with long-term motivational change and avoidance learning cannot be explained by nociceptive reflex but are consistent with the idea of pain. Here, we placed shore crabs alternately in two halves of a test area divided by an opaque partition. Each area had a dark shelter and in one repeated small electric shocks were delivered in an experimental but not in a control group. Crabs showed no specific avoidance of the shock shelter either during these trials or in a subsequent test in which both were offered simultaneously; however they often emerged from the shock shelter during a trial and thus avoided further shock. More crabs emerged in later trials and took less time to emerge than in early trials. Thus, despite the lack of discrimination learning between the two shelters they used other tactics to markedly reduce the amount of shock received. We note that a previous experiment using simultaneous presentation of two shelters demonstrated rapid discrimination and avoidance learning but the paradigm of sequential presentation appears to prevent this. Nevertheless, the data show clearly that the shock is aversive and tactics, other than discrimination learning, are used to avoid it. Thus, the behaviour is only partially consistent with the idea of pain.