The proceedings contain 36 papers. The topics discussed include: computing everywhere, all at once: harnessing the computing continuum for science;redundancy-free high-performance dynamic GNN training with hierarchica...
ISBN:
(纸本)9798400701559
The proceedings contain 36 papers. The topics discussed include: computing everywhere, all at once: harnessing the computing continuum for science;redundancy-free high-performance dynamic GNN training with hierarchical pipeline parallelism;Auto-HPCnet: an automatic framework to build neural network-based surrogate for high-performance computing applications;performance optimization using multimodal modeling and heterogeneous GNN;GPU-enabled asynchronous multi-level checkpoint caching and prefetching;RAPIDS: reconciling availability, accuracy, and performance in managing geo-distributed scientific data;FZ-GPU: a fast and high-ratio lossy compressor for scientific computing applications on GPUs;closing the performance gap between leveling and tiering compaction via bundle compaction;and let it go: relieving garbage collection pain for latency critical applications in Golang.
We provide new deterministic algorithms for the edge coloring problem, which is one of the classic and highly studied distributed local symmetry breaking problems. As our main result, we show that a (2Δ- 1)-edge colo...
详细信息
With the increased demand for Computer Science degrees in the work force, Computer Science is becoming more prominent in high schools. AP Computer Science principles (AP CSP) is a course that serves as a bridge into C...
详细信息
Quantum computing is generating significant excitement within the interdisciplinary academic community, government, and industry. Despite rapid growth in the area, formal education in non-classical computing is limite...
详细信息
ISBN:
(纸本)9798400705328
Quantum computing is generating significant excitement within the interdisciplinary academic community, government, and industry. Despite rapid growth in the area, formal education in non-classical computing is limited or absent in many computer science programs. Among the contributing factors is the cutting-edge nature of the field and, until somewhat recently, lack of available platforms for development. Consequently, many computer science graduates will enter the field with little or no background, or even conversational fluency in basic quantum principles. In the near term this will hinder broader adoption of quantum technologies, and will leave interested students underprepared for possible careers in the area or continued studies in graduate school. This experience report details the creation of a new course in Quantum Programming at a mid-sized, regional comprehensive university from initial conception to deployment. This work differs from previous treatments, as the professor came into the project without any background in quantum computing or physics. The course was written from a software-development perspective and is intended for a post-secondary audience from interdisciplinary, technical backgrounds. The course was successfully deployed in the fall semester of 2022 with positive reactions by both students and the professor. The author hopes that this project will add to the growing body of literature in this area, and serve as a template for other educators.
The proceedings contain 19 papers. The topics discussed include: a simple view of multiparty session types;on the preciseness of subtyping in session types: 10 years later;higher-order unification for free!: reusing t...
ISBN:
(纸本)9798400709692
The proceedings contain 19 papers. The topics discussed include: a simple view of multiparty session types;on the preciseness of subtyping in session types: 10 years later;higher-order unification for free!: reusing the meta-language unification for the object language;declarative macro-programming of collective systems with aggregate computing: an experience report;hierarchical higher-order port-graphs: a rewriting-based modelling language;on the almost-sure termination of binary sessions;formal verification of executable matrix inversion via adjoint matrix and gaussian elimination;grammar-based pattern matching and type checking for difference data structures;evidence tampering and chain of custody in layered attestations;and towards effective ASP-based stream reasoning: facilitate the reasoning over patterns of events.
We describe a simple deterministic O(epsilon(-1) log Delta) round distributed algorithm for (2 alpha+ 1) (1 + epsilon) approximation of minimum weighted dominating set on graphs with arboricity at most alpha. Here Del...
详细信息
ISBN:
(纸本)9781450392624
We describe a simple deterministic O(epsilon(-1) log Delta) round distributed algorithm for (2 alpha+ 1) (1 + epsilon) approximation of minimum weighted dominating set on graphs with arboricity at most alpha. Here Delta denotes the maximum degree. We also show a lower bound proving that this round complexity is nearly optimal even for the unweighted case, via a reduction from the celebrated KMW lower bound on distributed vertex cover approximation [Kuhn, Moscibroda, and Wattenhofer Jacm'16]. Our algorithm improves on all the previous results (that work only for unweighted graphs) including a randomized O(alpha(2)) approximation in O(log n) rounds [Lenzen and Wattenhofer DISC'10], a deterministic O(alpha log Delta) approximation in O(log Delta) rounds [Lenzen and Wattenhofer DISC'10], a deterministic O(alpha) approximation in O(log(2) Delta) rounds [implicit in Bansal and Umboh IPL'17 and Kuhn, Moscibroda, and Wattenhofer SODA'06], and a randomized O(alpha) approximation in O(alpha log n) rounds [Morgan, Solomon and Wein DISC'21]. We also provide a randomized O(alpha log Delta) round distributed algorithm that sharpens the approximation factor to alpha (1 + o(1)). If each node is restricted to do polynomial-time computations, our approximation factor is tight in the first order as it is NP-hard to achieve alpha - 1 - epsilon approximation [Bansal and Umboh IPL'17].
The proceedings contain 59 papers. The topics discussed include: rethinking design paradigm of graph processing system with a CXL-like memory semantic fabric;a case study of data management challenges presented in lar...
ISBN:
(纸本)9798350301199
The proceedings contain 59 papers. The topics discussed include: rethinking design paradigm of graph processing system with a CXL-like memory semantic fabric;a case study of data management challenges presented in large-scale machine learning workflows;an asynchronous dataflow-driven execution model for distributed accelerator computing;an empirical study of container image configurations and their impact on start times;how workflow engines should talk to resource managers: a proposal for a common workflow scheduling interface;Layercake: efficient inference serving with cloud and mobile resources;optimal sizing of a globally distributed low carbon cloud federation;predicting the performance-cost trade-off of applications across multiple systems;a deep learning pipeline parallel optimization method;HDFL: a heterogeneity and client dropout-aware federated learning framework;heterogeneous federated learning using dynamic model pruning and adaptive gradient;and measuring the impact of gradient accumulation on cloud-based distributed training.
Terrain parameters such as slope, aspect, and hillshading are essential in various applications, including agriculture, forestry, and hydrology. However, generating high-resolution terrain parameters is computationall...
详细信息
ISBN:
(纸本)9798400701559
Terrain parameters such as slope, aspect, and hillshading are essential in various applications, including agriculture, forestry, and hydrology. However, generating high-resolution terrain parameters is computationally intensive, making it challenging to provide these value-added products to communities in need. We present a scalable workflow called GEOtiled that leverages data partitioning to accelerate the computation of terrain parameters from digital elevation models, while preserving accuracy. We assess our workflow in terms of its accuracy and wall time by comparing it to SAGA, which is highly accurate but slow to generate results, and to GDAL, which supports memory optimizations but not data parallelism. We obtain a coefficient of determination (R-2) between GEOtiled and SAGA of 0.794, ensuring accuracy in our terrain parameters. We achieve an X6 speedup compared to GDAL when generating the terrain parameters at a high-resolution (10 m) for the Contiguous United States (CONUS).
We obtain improved distributed algorithms in the CONGEST message-passing setting for problems on power graphs of an input graph G. This includes Coloring, Maximal Independent Set, and related problems. For R = f(∆k, n...
详细信息
We present round complexity results in the CONGEST model for Replacement Paths (RPaths), Minimum Weight Cycle (MWC), and All Nodes Shortest Cycles (ANSC). We study these fundamental problems in both directed and undir...
详细信息
ISBN:
(纸本)9781450392624
We present round complexity results in the CONGEST model for Replacement Paths (RPaths), Minimum Weight Cycle (MWC), and All Nodes Shortest Cycles (ANSC). We study these fundamental problems in both directed and undirected graphs, weighted and unweighted. Many of our results are optimal to within a polylog factor: For an.. -node graph.. we establish near linear lower and upper bounds for RPaths if.. is directed andweighted, and forMWC and ANSC if.. is weighted, directed or undirected;near root n lower and upper bounds for undirected weighted RPaths;and Theta(D) bound for undirected unweighted RPaths. We also present lower and upper bounds for approximation: a (2 - ( 1/g))-approximation algorithm for undirected unweighted MWC that runs in O-similar to (root n +D) rounds, improving on the previous best bound of O-similar to (root ng +D) rounds, where.. is the MWC length, and a ( 1 +epsilon)-approximation algorithm for directed weighted RPaths and (2 +epsilon)-approximation for weighted undirected MWC, for any constant epsilon > 0, that beat the round complexity lower bound for an exact solution.
暂无评论