1,184 papers · page 15 of 60
Uncertain or probabilistic graphs have been ubiquitously used in many emerging applications. Previously CPU based techniques were proposed to use sampling but suffer from (1) low computation efficiency and large memory overhead, (2) low degree of parallelism, and (3) nonexistent …
Convolution is the most time-consuming part in the computation of convolutional neural networks (CNNs), which have achieved great successes in numerous practical applications. Due to the complex data dependency and the increase in the amount of model samples, the convolution suff…
We present optimizations to improve communication performance by reducing on-node data movement for a class of distributed memory applications. The primary concept is to eliminate the data movement associated with packing and unpacking subsets of the data during communication. Wi…
We present Reflector, to support both high-level and low-level I/O monitoring through user-defined interfaces such as HDF5 and NetCDF in addition to POSIX- and MPI-IO. We evaluate Reflector on both an on-premises 500-core HPC cluster and a leadership-class supercomputer at the La…
Graph coloring is an assignment of colors to the vertices of a graph such that no two adjacent vertices get the same color. It is a key building block in many applications. Finding a coloring with a minimal number of colors is often only part of the problem. In addition, the solu…
Combinatorial search is central to many applications, yet the huge irregular search trees and the need to respect search heuristics make it hard to parallelise. We aim to improve the reuse of intricate parallel search implementations by providing the first general purpose scalabl…
Transactional data structure libraries (TDSL) combine the ease-of-programming of transactions with the high performance and scalability of custom-tailored concurrent data structures. They can be very efficient thanks to their ability to exploit data structure semantics in order t…
While developed largely for higher density and lower power, byte-addressable nonvolatile memory can also allow data to persist across program runs and system crashes without the need to flush to disk or flash. If data is to be recovered after a crash, however, care must be taken …
This paper proposes to enhance current task-based programming models by breaking their current master-slave approach between the main processor and its hardware accelerators. As a proof-of-concept, it presents an extension of the OmpSs@FPGA toolchain that allows the tasks offload…
Balanced search trees typically use key comparisons to guide their operations, and achieve logarithmic running time. By relying on numerical properties of the keys, interpolation search achieves lower search complexity and better performance. Although interpolation-based data str…
The proliferation of fast, dense, byte-addressable nonvolatile memory suggests the possibility of keeping data in pointer-rich "in-memory" format across program runs and even crashes. For full generality, such data requires dynamic memory allocation. Toward this end, we introduce…
Concurrency has been a subject of study for more than 50 years. Still, many developers struggle to adapt their sequential code to be accessed concurrently. This need has pushed for generic solutions and specific concurrent data structures. Wait-free universal constructions are a…
We present an approach to automatically detect and reproduce error code propagation bugs in MPI implementations. Specifically, we combine static analysis and program repair for bug detection, and apply fault injection to reproduce error propagation bugs found in MPI libraries wri…
Molecular dynamics (MD) simulations are playing an increasingly important role in many research areas. Pair-wise potentials are widely used in MD simulations of bio-molecules, polymers, and nano-scale materials. Due to a low compute-to-memory-access ratio, their calculation is of…
Key-Value Stores (KVSs) came into prominence as highly-available, eventually consistent (EC), "NoSQL" Databases, but have quickly transformed into general-purpose, programmable storage systems. Thus, EC, while relevant, is no longer sufficient. Complying with the emerging require…
Current state-of-the-art in GPU networking utilizes a host-centric, kernel-boundary communication model that reduces performance and increases code complexity. To address these concerns, recent works have explored performing network operations from within a GPU kernel itself. How…
We introduce a structure-aware parallel technique for context-bounded analysis of concurrent programs. The key intuition consists in decomposing the set of concurrent traces into symbolic subsets that are separately explored by multiple instances of the same decision procedure ru…
The byte-addressable persistent memory (PMEM) devices have opened new opportunities for building high-performance storage systems. With both DRAM and PMEM in the system, it is important to choose the correct storage data structures on each of them to achieve the best overall perf…
SpMM (multiplication of a sparse matrix and a dense matrix) and SDDMM (sampled dense-dense matrix multiplication) are at the core of many scientific, machine learning, and data mining applications. Because of the irregular memory accesses, the two kernels have poor data locality,…
Scaling a parallel program to modern supercomputers is challenging due to inter-process communication, code serialization, and resource contention. Performance analysis tools for finding such scaling bottlenecks either base on profiling or tracing. Profiling incurs lower overhead…