GPUs have become an integral part of modern systems, but their implications for system security are not yet clear. This paper demonstrates both that discrete GPUs cannot be used as secure co-processors and that GPUs provide a stealthy platform for malware. First, we examine a recent proposal to use discrete GPUs as secure co-processors and show that the security guarantees of the proposed system do not hold on the GPUs we investigate. Second, we demonstrate that (under certain circumstances) it is possible to bypass IOMMU protections and create stealthy, long-lived GPU-based malware. We demonstrate a novel attack that compromises the in-kernel GPU driver and one that compromises GPU microcode to gain full access to CPU physical memory. In general, we find that the highly sophisticated, but poorly documented GPU hardware architecture, hidden behind obscure close-source device drivers and vendor-specific APIs, not only make GPUs a poor choice for applications requiring strong security, but also make GPUs into a security threat.

Co-occurrence and mutual exclusivity (COME) of DNA methylation refer to two or more genes that tend to be positively or negatively correlated in DNA methylation among different samples. Although COME of gene mutations in pan-cancer have been well explored, little is known about the COME of DNA methylation in pan-cancer. Here, we systematically explored the COME of DNA methylation profile in diverse human cancer. A total of 5,128,332 COME events were identified in 14 main cancers types in The Cancer Genome Atlas (TCGA). We also identified functional epigenetic modules of the zinc finger gene family in six cancer types by integrating the gene expression and DNA methylation data and the frequently occurred COME network. Interestingly, most of the genes in those functional epigenetic modules are epigenetically repressed. Strikingly, those frequently occurred COME events could be used to classify the patients into several subtypes with significant different clinical outcomes in six cancers as well as pan-cancer (p-value ≤ = 0.05). Moreover, we observed significant associations between different COME subtypes and clinical features (e.g., age, gender, histological type, neoplasm histologic grade, and pathologic stage) in distinct cancers. Taken together, we identified millions of COME events of DNA methylation in pan-cancer and detected functional epigenetic COME events that could separate tumor patients into different subtypes, which may benefit the diagnosis and prognosis of pan-cancer.

Despite the popularity of GPUs in high-performance and scientific computing, and despite increasingly general-purpose hardware capabilities, the use of GPUs in network servers or distributed systems poses significant challenges. GPUnet is a native GPU networking layer that provides a socket abstraction and high-level networking APIs for GPU programs. We use GPUnet to streamline the development of high-performance, distributed applications like in-GPU-memory MapReduce and a new class of low-latency, high-throughput GPU-native network services such as a face verification server.

No abstract

No abstract