Related papers: Fast Parallel I/O on Cluster Computers
Modern parallel filesystems such as Lustre are designed to provide high, scalable I/O bandwidth in response to growing I/O requirements; however, the bursty I/O characteristics of many data-intensive scientific applications make it…
The unprecedented growth in data demand from emerging applications has turned virtual memory (VM) into a major performance bottleneck. Researchers explore new hardware/OS co-designs to optimize VM across diverse applications and systems. To…
In paravirtualization, the page table management components of the guest operating systems are properly patched for the security guarantees of the hypervisor. However, none of them pay enough attentions to the performance improvements,…
The steeply growing performance demands for highly power- and energy-constrained processing systems such as end-nodes of the internet-of-things (IoT) have led to parallel near-threshold computing (NTC), joining the energy-efficiency…
Many scientific computations need multi-node parallelism for matching up both space (memory) and time (speed) ever-increasing requirements. The use of GPUs as accelerators introduces yet another level of complexity for the programmer and…
Parallel applications can spend a significant amount of time performing I/O on large-scale supercomputers. Fast near-compute storage accelerators called burst buffers can reduce the time a processor spends performing I/O and mitigate I/O…
Virtual clusters are widely used computing platforms than can be deployed in multiple cloud platforms. The ability to dynamically grow and shrink the number of nodes has paved the way for customised elastic computing both for High…
Network Function Virtualization (NFV) carries the potential for on-demand deployment of network algorithms in virtual machines (VMs). In large clouds, however, VM resource allocation incurs delays that hinder the dynamic scaling of such NFV…
Systolic arrays and shared-L1-memory manycore clusters are commonly used architectural paradigms that offer different trade-offs to accelerate parallel workloads. While the first excel with regular dataflow at the cost of rigid…
The Lustre parallel file system has been widely adopted by high-performance computing (HPC) centers as an effective system for managing large-scale storage resources. Lustre achieves unprecedented aggregate performance by parallelizing I/O…
Recent applications in the domain of near-sensor computing require the adoption of floating-point arithmetic to reconcile high precision results with a wide dynamic range. In this paper, we propose a multi-core computing cluster that…
In this paper, the utilization of mobile devices (MDs) as decode-and-forward relays in a device-to-device assisted virtual MIMO (VMIMO) system is studied. Single antenna MDs are randomly distributed on a 2D plane according to a Poisson…
GRVI is an FPGA-efficient RISC-V RV32I soft processor. Phalanx is a parallel processor and accelerator array framework. Groups of processors and accelerators form shared memory clusters. Clusters are interconnected with each other and with…
The ALICE experiment has undergone a major upgrade for LHC Run 3 and will collect data at an interaction rate 50 times larger than before. The new computing scheme for Run 3 replaces the traditionally separate online and offline frameworks…
The NEMO High Performance Computing Cluster at the University of Freiburg has been made available to researchers of the ATLAS and CMS experiments. Users access the cluster from external machines connected to the World-wide LHC Computing…
A PC-based parallel computer for medium/large scale lattice QCD simulations is suggested. The Eotvos Univ., Inst. Theor. Phys. cluster consists of 137 Intel P4-1.7GHz nodes. Gigabit Ethernet cards are used for nearest neighbor communication…
Enabling efficient, high-performance data access in parallel file systems (PFS) is critical for today's high-performance computing systems. PFS client-side I/O heavily impacts the final I/O performance delivered to individual applications…
In the past couple of decades, the computational abilities of supercomput- ers have increased tremendously. Leadership scale supercomputers now are capable of petaflops. Likewise, the problem size targeted by applications running on such…
Large language models (LLMs) require vast amounts of GPU compute to train, but limited availability and high costs of GPUs make homogeneous clusters impractical for many organizations. Instead, assembling heterogeneous clusters by pooling…
Multi-device inference can reduce Transformer latency by parallelizing computation. However, existing methods require high inter-device bandwidth, making them impractical for bandwidth-constrained environments. We present ASTRA, a…