26 research outputs found
An algorithmic pipeline for analyzing multi-parametric flow cytometry data
No full textFlow cytometry (FC) is a single-cell profiling platform for measuring the phenotypes (protein expressions) of individual cells from millions of cells in biological samples. In the last several years, FC has begun to employ high-throughput technologies, and to generate high-dimensional data, and hence algorithms for analyzing the data represent a bottleneck. This dissertation addresses several computational challenges arising in modern cytometry while mining information from high-dimensional and high-content biological data. A collection of combinatorial and statistical algorithms for locating, matching, prototyping, and classifying cellular populations from multi-parametric flow cytometry data is developed. The algorithms developed in this dissertation are assembled into a data analysis pipeline called flowMatch. This pipeline consists of five well-defined algorithmic modules for (1) transforming data to stabilize within-population variance, (2) identifying phenotypic cell populations by robust clustering algorithms, (3) registering cell populations across samples, (4) encapsulating a class of samples with templates, and (5) classifying samples based on their similarity with the templates. Each module of flowMatch is designed to perform a specific task independent of other modules of the pipeline. However, they can also be employed sequentially in the order described above to perform the complete data analysis. The flowMatch pipeline is made available as an open-source R package in Bioconductor (http://www.bioconductor.org/). I have employed flowMatch for classifying leukemia samples, evaluating the phosphorylation effects on T cells, classifying healthy immune profiles, comparing the impact of two treatments for Multiple Sclerosis, and classifying the vaccination status of HIV patients. In these analyses, the pipeline is able to reach biologically meaningful conclusions quickly and efficiently with the automated algorithms. The algorithms included in flowMatch can also be applied to problems outside of flow cytometry such as in microarray data analysis and image recognition. Therefore, this dissertation contributes to the solution of fundamental problems in computational cytometry and related domains
Performance optimization, modeling and analysis of sparse matrix-matrix products on multi-core and many-core processors
No full textRecommended from our members
Communication-Avoiding and Memory-Constrained Sparse Matrix-Matrix Multiplication at Extreme Scale
No full textSparse matrix-matrix multiplication (SpGEMM) is a widely used kernel in
various graph, scientific computing and machine learning algorithms. In this
paper, we consider SpGEMMs performed on hundreds of thousands of processors
generating trillions of nonzeros in the output matrix. Distributed SpGEMM at
this extreme scale faces two key challenges: (1) high communication cost and
(2) inadequate memory to generate the output. We address these challenges with
an integrated communication-avoiding and memory-constrained SpGEMM algorithm
that scales to 262,144 cores (more than 1 million hardware threads) and can
multiply sparse matrices of any size as long as inputs and a fraction of output
fit in the aggregated memory. As we go from 16,384 cores to 262,144 cores on a
Cray XC40 supercomputer, the new SpGEMM algorithm runs 10x faster when
multiplying large-scale protein-similarity matrices
Communication-Avoiding and Memory-Constrained Sparse Matrix-Matrix Multiplication at Extreme Scale
No full textiSpLib: A Library for Accelerating Graph Neural Networks using Auto-tuned Sparse Operations
No full textPerformance optimization, modeling and analysis of sparse matrix-matrix products on multi-core and many-core processors
No full textThis record is for a(n) postprint of an article published in Parallel Computing in 2019; the version of record is available at https://doi.org/10.1016/j.parco.2019.102545.postprin
Optimizing High Performance Markov Clustering for Pre-Exascale Architectures
No full textHipMCL is a high-performance distributed memory implementation of the popular Markov Cluster Algorithm (MCL) and can cluster large-scale networks within hours using a few thousand CPU-equipped nodes. It relies on sparse matrix computations and heavily makes use of the sparse matrix-sparse matrix multiplication kernel (SpGEMM). The existing parallel algorithms in HipMCL are not scalable to Exascale architectures, both due to their communication costs dominating the runtime at large concurrencies and also due to their inability to take advantage of accelerators that are increasingly popular. In this work, we systematically remove scalability and performance bottlenecks of HipMCL. We enable GPUs by performing the expensive expansion phase of the MCL algorithm on GPU. We propose a CPU-GPU joint distributed SpGEMM algorithm called pipelined Sparse SUMMA and integrate a probabilistic memory requirement estimator that is fast and accurate. We develop a new merging algorithm for the incremental processing of partial results produced by the GPUs, which improves the overlap efficiency and the peak memory usage. We also integrate a recent and faster algorithm for performing SpGEMM on CPUs. We validate our new algorithms and optimizations with extensive evaluations. With the enabling of the GPUs and integration of new algorithms, HipMCL is up to 12.4x faster, being able to cluster a network with 70 million proteins and 68 billion connections just under 15 minutes using 1024 nodes of ORNL’s Summit supercomputer
