In high-performance computing (HPC), parallelization is essential for improving computational efficiency as data and computation scales exceed single-node capacity. Existing methods, such as the polyhedral model used in Pluto -Distmem, focus on loop and array optimizations within shared memory but struggle with high communication overheads and inflexibility in distributed environments. These methods often fail to effectively partition computation and manage data across nodes, leading to suboptimal performance. This paper presents Arachne , an innovative system designed to address these shortcomings by generating distributed parallel code with minimized communication overhead. The system introduces a dynamic programming algorithm to optimally distribute computational tasks across multiple processes, ensuring minimal communication costs. It also incorporates user-friendly compiler directives, allowing programmers to influence code generation easily and accommodate a broader range of parallelization scenarios without needing in-depth knowledge of parallel architectures. Arachne significantly reduces the learning curve and need for extensive code modifications, making parallel programming more accessible and efficient. Evaluation of various HPC benchmarks demonstrates that Arachne outperforms existing methods by reducing communication overhead, lowering memory requirements, and supporting more complex parallel logic, thus enhancing the overall scalability and efficiency of HPC applications.

Cloud vendors are now providing cloud gaming services with GPUs. GPUs in cloud gaming experience periods of idle because not every frame in a game always keeps the GPU busy for rendering. Previous works temporally co-locate games with best-effort applications to harvest these idle cycles. However, these works ignore the spatial sharing of GPUs, leading to not maximized throughput improvement. The newly introduced RT (ray tracing) Cores inside GPU SMs for ray tracing exacerbate the situation.

Although the prognosis of lower-grade glioma (LGG) patients is better than others, outcomes are highly heterogeneous. Isocitrate dehydrogenase (IDH) mutation and 1p/19q codeletion status can identify patient subsets with different prognosis. However, in the era of precision medicine, there is still a lack of biomarkers that can accurately predict the individual prognosis of each patient. In this study, we found that most DNA damage response (DDR) genes were aberrantly expressed in LGG patients and were associated with their prognosis. Consequently, we developed an artificial neural network (ANN) model based on DDR genes to predict outcomes of LGG glioma patients. Then, we validated the predictive ability in an independent external dataset and found that the concordance indexes and area under time-dependent receiver operating characteristic curves of the predict index (PI) calculated based on the model were superior to those of the mutation markers. Subgroup analyses demonstrated that the model could accurately identify patients with the same mutation status but different prognosis. Moreover, the model can also identify patients with favorable prognostic mutation status but poor prognosis or vice versa. Finally, we also found that the PI was associated with the mutation status and with the altered immune microenvironment. These results demonstrated that the ANN model can accurately predict outcomes of LGG patients and will contribute to individualized therapies. In addition, a web-based application program for the model was developed.