With the growing complexity in architecture and the size of large-scale computing systems, monitoring and analyzing system behavior and events has become daunting. Monitoring data amounting to terabytes per day are co...
详细信息
Cloud storage systems have become a common data storage scheme. The most immediate problem is that the cloud service provider is not trusted, so certain measures must be taken to ensure the reliability of the data. In...
详细信息
The storage subsystem of the Aurora platform at Argonne National Laboratory offers the potential for unprecedented application I/O performance. Its hardware stack combines NVMe drives, persistent memory devices, a lar...
详细信息
This study proposes a high-performance and reliable eigensolver via mixed-precision arithmetic between ordinary and highly-accurate precisions. Eigenvalue decomposition is ubiquitous in simulations. Various eigensolve...
详细信息
To effectively enhance the mobility without other degradations, such as much negative threshold voltage, this work fabricated the a-IGZO/a-IZO heterojunction-channel TFTs with dual-gate structure. The fabricated a-IZO...
详细信息
It is of great concern for highperformance microprocessors to optimize logic delay and improve performance in the semi-custom design flow based on commercial standard cell library. To solve this issue, the paper prop...
详细信息
The MPI correctness benchmarks MPI-Corrbench and the MPI Bugs Initiative contain standardized test cases of correct and erroneous use of MPI, allowing MPI correctness tool developers to assess their tools' perform...
详细信息
We introduce dSalmon, a highly efficient framework for outlier detection on streaming data. dSalmon can be used with both Python and C++, meeting the requirements of modern data science research. It provides an intuit...
详细信息
ISBN:
(纸本)9783031488849;9783031488856
We introduce dSalmon, a highly efficient framework for outlier detection on streaming data. dSalmon can be used with both Python and C++, meeting the requirements of modern data science research. It provides an intuitive interface and has almost no package dependencies. dSalmon implements main stream outlier detection approaches from literature. By using pure C++ in its core and making the most of available parallelism, data is analyzed with superior processing speed. We describe design decisions and outline the software architecture of dSalmon. Additionally, we perform thorough evaluations on benchmarking datasets to measure execution time, memory requirements and energy consumption when performing outlier detection. Experiments show that dSalmon requires substantially less resources and in most cases is able to process datasets between one and three orders of magnitude faster than established Python implementations.
As the performance gap between hardware and software widens, performance analysis tools are essential for understanding the behavior of large-scale high-performance Computing (HPC) programs. These tools provide insigh...
Students' difficulties to learn concurrent programming are well known amongst computer Science instructors. While in the International Computing Education community it is still up to debate the extent to which suc...
详细信息
ISBN:
(纸本)9783031448997;9783031449000
Students' difficulties to learn concurrent programming are well known amongst computer Science instructors. While in the International Computing Education community it is still up to debate the extent to which such topic should be included in pre-university curricula, based on our country's Ministerial guidelines for technical high schools with a specialization in computer Science, students are expected to acquire key concurrent programming skills. With the aim of getting insights about the nature of students' difficulties, as well as to identify possible pedagogical approaches to be adopted by teachers, we have undertaken an investigation on students' perception, proficiency and self-confidence when dealing with concurrency and synchronization tasks. We then present the results of a preliminary study carried out by submitting a survey in a couple of representative high schools of our area. The survey includes subjective perception questions as well as small program comprehension tasks addressing students' understanding of thread synchronization. Moreover, we also analyze students' self-confidence in connection with their actual performance in such tasks. A total of 68 high school students were engaged in the survey. Our findings indicate that students' perception of self-confidence tends to weakly correlate to their actual performance, although more in general they express a low self-confidence level in relation to the topic. In particular, the results clearly show that the concept of thread synchronization is especially difficult to master for a large majority of them.
暂无评论