Search

Reflecting on oneself and others in relationships is an ability that is central to our social existence. Specifically, considering formative autobiographical experiences in relationships may contribute to more flexibility in perceiving, as well as in shaping present relationships. Reflecting on such experiences mobilizes different social cognitive and affective processes. We aim to explore the neural basis of these processes. With a newly developed functional magnetic imaging (fMRI) task, we investigated brain activation in 35 healthy individuals during recall of relationship episodes involving themselves or others. We found that recalling formative episodes involving themselves modulated brain activity in the right parahippocampus, left precuneus, bilateral fusiform gyrus, bilateral insula, and left presupplementary motor area. These areas are involved in memory processes, self-generated thought, and affective experience. The recall of relationship episodes involving others led to similar activation patterns. Our results underscore the close link between self-reflection, understanding others, and memory processes and emphasize the role of affective dimensions for self-relevant experiences. They contribute to a growing body of research on neural mechanisms involved in complex social cognitive processes decisive for our capacity to navigate our social environment.

Heterogenous memory systems that consist of multiple memory technologies are becoming common in high-performance computing environments. Modern processors and accelerators, such as the Intel Knights Landing (KNL) CPU and NVIDIA Volta GPU, feature small-size high-bandwidth memory near the compute cores and large-size normal-bandwidth memory that is connected off-chip. Theoretically, HBM can provide about four times higher bandwidth than conventional DRAM. However, many factors impact the actual performance improvement that an application can achieve on such system. In this paper, we focus on the Intel KNL system and identify the most important factors on the application performance, including the application memory access pattern, the problem size, the threading level and the actual memory configuration. We use a set of representative applications from both scientific and data-analytics domains. Our results show that applications with regular memory access benefit from MCDRAM, achieving up to three times performance when compared to the performance obtained using only DRAM. On the contrary, applications with irregular memory access pattern are latency-bound and may suffer from performance degradation when using only MCDRAM. Also, we provide memory-centric analysis of four applications, identify their major data objects, correlate their characteristics to the performance improvement on the testbed., QC 20180601

The NVIDIA Volta GPU microarchitecture introduces a specialized unit, called Tensor Core that performs one matrix-multiply-and-accumulate on 4x4 matrices per clock cycle. The NVIDIA Tesla V100 accelerator, featuring the Volta microarchitecture, provides 640 Tensor Cores with a theoretical peak performance of 125 Tflops/s in mixed precision. In this paper, we investigate current approaches to program NVIDIA Tensor Cores, their performances and the precision loss due to computation in mixed precision. Currently, NVIDIA provides three different ways of programming matrix-multiply-and-accumulate on Tensor Cores: the CUDA Warp Matrix Multiply Accumulate (WMMA) API, CUTLASS, a templated library based on WMMA, and cuBLAS GEMM. After experimenting with different approaches, we found that NVIDIA Tensor Cores can deliver up to 83 Tflops/s in mixed precision on a Tesla V100 GPU, seven and three times the performance in single and half precision respectively. A WMMA implementation of batched GEMM reaches a performance of 4 Tflops/s. While precision loss due to matrix multiplication with half precision input might be critical in many HPC applications, it can be considerably reduced at the cost of increased computation. Our results indicate that HPC applications using matrix multiplications can strongly benefit from using of NVIDIA Tensor Cores., QC 20180904

Modern graphics processing units (GPUs) are using increasingly larger register file (RF) which occupies a large fraction of GPU core area and is very frequently access ed. This makes RF vulnerable to soft-errors (SE). In this paper, we present two techniques for improving SE resilience of GPU RF . First, we propose compressing the RF values for reducing the number of vulnerable bits. We leverage value similarity and the presence of narrow-width values to perform compression at warp or thread-level, respectively. Second, we propose sel ective hardening to design a portion of register entry with SE immun e circuits. By collectively using these techniques, higher r esilience can be provided with lower overhead. Without hardening, our warp and thread-level compression techniques bring 47.0% and 40.8% reduction in SE vulnerability, respectively.