Computer Science and Engineering

Although understanding of shape features in the context of shape matching and retrieval has made considerable progress in recent years, the case for partial and incomplete models in presence of pose variations still begs a robust and efficient solution. A signature that encodes features at multi-scales in a pose invariant manner is more appropriate for this case. The Heat Kernel Signature function from spectral theory exhibits this multi-scale property. We show how this concept can be merged with the persistent homology to design a novel efficient pose-oblivious matching algorithm for all models, be they partial, incomplete, or complete. We make the algorithm scalable so that it can handle large data sets. Several test results show the robustness of our approach.

Recent advances in mesh deformations have been dominated by two techniques: one uses an intermediate structure like a cage which transfers the user intended moves to the mesh, the other lets the user to impart the moves to the mesh directly. The former one lets the user deform the model in real-time and also preserve the shape with sophisticated techniques like Green Coordinates. The direct techniques on the other hand free the user from the burden of creating an appropriate cage though they take more computing time to solve larger non-linear optimizations. It would be ideal to develop a cage-free technique that provides real-time deformation while respecting the local geometry. Using a simple eigen-framework, we devise such a technique. Our framework creates an implicit skeleton automatically. The user only specifies the motion in a simple and intuitive manner, and our algorithm computes a deformation whose quality is similar to that of the cage-based scheme with Green Coordinates.

Data collection management is disclosed. A data collection configuration is obtained. The data collection configuration is translated into executable code in a language usable to collect data. Data is collected using the executable code. The collected data values are provided as output. Metrics management is also disclosed. A configuration of a metric is obtained. The metric configuration includes a definition of how computation of the metric is to be performed and a mapping between a computation input and collected data. Collected data values are obtained based at least in part on the mapping. Metric values are computed according to the definition. One or more results associated with the computed metric values are stored.

Map-reduce framework has received a significant attention and is being used for programming both large-scale clusters and multi-core systems. While the high productivity aspect of map-reduce has been well accepted, it is not clear if the API results in efficient implementations for different subclasses of data-intensive applications. In this paper, we present a system MATE (Map-reduce with an Alternate API), that provides a high-level, but distinct API. Particularly, our API includes a programmer-managed reduction object, which ...

Graphics Processing Units (GPUs) are increasingly becoming part of HPC clusters. Nevertheless, cloud computing services and resource management frameworks targeting heterogeneous clusters including GPUs are still in their infancy. Further, GPU software stacks (e.g., CUDA driver and runtime) currently provide very limited support to concurrency. In this paper, we propose a runtime system that provides abstraction and sharing of GPUs, while allowing isolation of concurrent applications. A central component of our runtime is a memory manager that provides a virtual memory abstraction to the applications. Our runtime is flexible in terms of scheduling policies, and allows dynamic (as opposed to programmer-defined) binding of applications to GPUs. In addition, our framework supports dynamic load balancing, dynamic upgrade and downgrade of GPUs, and is resilient to their failures. Our runtime can be deployed in combination with VM-based cloud computing services to allow virtualization of heterogeneous clusters, or in combination with HPC cluster resource managers to form an integrated resource management infrastructure for heterogeneous clusters. Experiments conducted on a three-node cluster show that our GPU sharing scheme allows up to a 28% and a 50% performance improvement over serialized execution on short-and long-running jobs, respectively. Further, dynamic inter-node load balancing leads to an additional 18-20% performance benefit.

A trend that has materialized, and has given rise to much attention, is of the increasingly heterogeneous computing platforms. Presently, it has become very common for a desktop or a notebook computer to come equipped with both a multi-core CPU and a graphics processing unit (GPU). Capitalizing on the maximum computational power of such architectures (i.e., by simultaneously exploiting both the multi-core CPU and the GPU), starting from a high-level API, is a critical challenge. We believe that it would be highly desirable to support a simple way for programmers to realize the full potential of today's heterogeneous machines. This paper describes a compiler and runtime framework that can map a class of applications, namely those characterized by generalized reductions, to a system with a multi-core CPU and GPU. Starting with simple C functions with added annotations, we automatically generate the middleware API code for the multi-core, as well as CUDA code to exploit the GPU simultaneously. The runtime system provides efficient schemes for dynamically partitioning the work between CPU cores and the GPU. Our experimental results from two applications, for example, k-means clustering and principal component analysis, show that, through effectively harnessing the heterogeneous architecture, we can achieve significantly higher performance compared with using only the GPU or the multi-core CPU. In k-means clustering, the heterogeneous version with eight CPU cores and a GPU achieved a speedup of about 32.09x relative to one-thread CPU. When compared with the faster of CPU-only and GPU-only executions, we were able to achieve a performance gain of about 60%. In principal component analysis, the heterogeneous version attained a speedup of 10.4x relative to the one-thread CPU version. When compared with the faster of CPU-only and GPU-only versions, the heterogeneous version achieved a performance gain of about 63.8%.

In data-intensive computing, an important problem that has received relatively little attention is of transparent processing of data stored in remote data repositories. Interesting load balancing considerations arise for these scenarios. Particularly, based on where data is generated and how it is shared, a dataset of interest can be divided across multiple data repositories, which may be geographically distributed and the data may be partitioned in a number of ways. This paper focuses on enabling such distributed processing of data from distributed resources. We have developed a load balancing algorithm, which minimizes the total time spent on processing the data. We consider weighted sum of two factors, a load balancing factor and a term that captures the amount of time spent by processing nodes waiting for the data. Our solutions have been implemented and evaluated in the context of FREERIDE-G (FRamework for Rapid Implementation of Datamining Engines in Grid). We have extensively evaluated our techniques using two data-intensive applications.

This paper examines energy management in a heterogeneous processor consisting of an integrated CPU-GPU for highperformance computing (HPC) applications. Energy management for HPC applications is challenged by their uncompromising performance requirements and complicated by the need for coordinating energy management across distinct core types-a new and less understood problem. We examine the intra-node CPU-GPU frequency sensitivity of HPC applications on tightly coupled CPU-GPU architectures as the first step in understanding power and performance optimization for a heterogeneous multi-node HPC system. The insights from this analysis form the basis of a coordinated energy management scheme, called DynaCo, for integrated CPU-GPU architectures. We implement DynaCo on a modern heterogeneous processor and compare its performance to a state-of-the-art power-and performance-management algorithm. DynaCo improves measured average energy-delay squared (ED^2) product by up to 30% with less than 2% average performance loss across several exascale and other HPC workloads.

Map-reduce has been a topic of much interest in the last 2-3 years. While it is well accepted that the map-reduce APIs enable significantly easier programming, the performance aspects of the use of map-reduce are less well understood. This paper focuses on comparing the map-reduce paradigm with a system that was developed earlier at Ohio State, FREERIDE (FRamework for Rapid Implementation of Datamining Engines). The API and the functionality offered by FREERIDE has many similarities with the map-reduce API. However, there are some differences in the API. Moreover, while FREERIDE was motivated by data mining computations, map-reduce was motivated by searching, sorting, and related applications in a data-center. We compare the programming APIs and performance of the Hadoop implementation of mapreduce with FREERIDE. For our study, we have taken three data mining algorithms, which are k-means clustering, apriori association mining, and k-nearest neighbor search. We have also included a simple data scanning application, word-count. The main observations from our results are as follows. For the three data mining applications we have considered, FREERIDE outperformed Hadoop by a factor of 5 or more. For word-count, Hadoop is better by a factor of up to 2. With increasing dataset sizes, the relative performance of Hadoop becomes better. Overall, it seems that Hadoop has significant overheads related to initialization, I/O, and sorting of (key, value) pairs. Thus, despite an easy to program API, Hadoop's map-reduce does not appear very suitable for data mining computations on modest-sized datasets.

A trend that has materialized, and has given rise to much attention, is of the increasingly heterogeneous computing platforms. Presently, it has become very common for a desktop or a notebook computer to come equipped with both a multi-core CPU and a GPU. Capitalizing on the maximum computational power of such architectures (i.e., by simultaneously exploiting both the multi-core CPU and the GPU) starting from a high-level API is a critical challenge. We believe that it would be highly desirable to support a simple way for programmers to realize the full potential of today's heterogeneous machines. This paper describes a compiler and runtime framework that can map a class of applications, namely those characterized by generalized reductions, to a system with a multi-core CPU and GPU. Starting with simple C functions with added annotations, we automatically generate the middleware API code for the multi-core, as well as CUDA code to exploit the GPU simultaneously. The runtime system provides efficient schemes for dynamically partitioning the work between CPU cores and the GPU. Our experimental results from two applications, e.g., k-means clustering and Principal Component Analysis (PCA), show that, through effectively harnessing the heterogeneous architecture, we can achieve significantly higher performance compared to using only the GPU or the multi-core CPU. In k-means, the heterogeneous version with 8 CPU cores and a GPU achieved a speedup of about 32.09x relative to 1-thread CPU. When compared to the faster of CPU-only and GPU-only executions, we were able to achieve a performance gain of about 60%. In PCA, the heterogeneous version attained a speedup of 10.4x relative to the 1-thread CPU version. When compared to the faster of CPU-only and GPU-only versions, we achieved a performance gain of about 63.8%.

The deluge of available data for analysis demands the need to scale the performance of data mining implementations. With the current architectural trends, one of the major challenges today is achieving programmability and performance for data mining applications on multi-core machines and cluster of multi-core machines. To address this problem, we have been developing a runtime framework, FREERIDE, that enables parallel execution of data mining and data analysis tasks. The contributions of this paper are twofold: 1) This paper describes and evaluates various shared-memory parallelization techniques developed in our run-time system on a cluster of multi-cores, and 2) We report on a detailed performance study to understand why certain parallelization techniques outperform other techniques for a particular application.

Heterogeneous computing nodes are becoming commonplace today, and recent trends strongly indicate that clusters, supercomputers, and cloud environments will increasingly host more heterogeneous resources, with some being massively parallel (e.g., GPU). With such heterogeneous environments becoming common, it is important to revisit scheduling problems for clusters and cloud environments. In this paper, we formulate and address the problem of value-driven scheduling of independent jobs on heterogeneous clusters, which captures both the urgency and relative priority of jobs. Our overall scheduling goal is to maximize the aggregate value or yield of all jobs. Exploiting the portability available from the underlying programming model, we propose four novel scheduling schemes that can automatically and dynamically map jobs onto heterogeneous resources. Additionally, to improve the utilization of massively parallel resources, we also propose heuristics to automatically decide when and which jobs can share a single resource.

Driven by the cost-effectiveness and the powerefficiency, GPUs are being increasingly used to accelerate computations in many domains. However, developing highly efficient GPU implementations requires a lot of expertise and effort. Thus, tool support for tuning GPU programs is urgently needed, and more specifically, low-overhead mechanisms for collecting finegrained runtime information are critically required. Unfortunately, profiling tools and mechanisms available today either collect very coarse-grained information, or have prohibitive overheads. This paper presents a low-overhead and fine-grained profiling technique developed specifically for GPUs, which we refer to as GMProf. GMProf uses two ideas to help reduce the overheads of collecting fine-grained information. The first idea involves exploiting a number of GPU architectural features to collect reasonably accurate information very efficiently, and the second idea is to use simple static analysis methods to reduce the overhead of runtime profiling. The specific implementation of GMProf we report in this paper focuses on shared memory usage. Particularly, we help programmers understand (1) which locations in shared memory are infrequently accessed? and (2) which data elements in device memory are frequently accessed? We have evaluated GMProf using six popular GPU kernels with different characteristics. Our experimental results show that GMProf, with all optimizations, incurs a moderate overhead, e.g., 1.36 times on average for shared memory profiling. Furthermore, for three of the six evaluated kernels, GMProf verified that shared memory is effectively used, and for the remaining three kernels, it not only helped accurately identify the inefficient use of shared memory, but also helped tune the implementations. The resulting tuned implementations had a speedup of 15.18 times on average.

As power becomes an increasingly important design factor in high-end supercomputers, future systems will likely operate with power limitations significantly below their peak power specifications. These limitations will be enforced through a combination of software and hardware power policies, which will filter down from the system level to individual nodes. Hardware is already moving in this direction by providing power-capping interfaces to the user. The power/performance trade-off at the node level is critical in maximizing the performance of powerconstrained cluster systems, but is also complex because of the many interacting architectural features and accelerators that comprise the hardware configuration of a node. The key to solving this challenge is an accurate power/performance model that will aid in selecting the right configuration from a large set of available configurations. In this paper, we present a novel approach to generate such a model offline using kernel clustering and multivariate linear regression. Our model requires only two iterations to select a configuration, which provides a significant advantage over exhaustive search-based strategies. We apply our model to predict power and performance for different applications using arbitrary configurations, and show that our model, when used with hardware frequency-limiting, selects configurations with significantly higher performance at a given power limit than those chosen by frequency-limiting alone. When applied to a set of 36 computational kernels from a range of applications, our model accurately predicts power and performance; it maintains 91% of optimal performance while meeting power constraints 88% of the time. When the model violates a power constraint, it exceeds the constraint by only 6% in the average case, while simultaneously achieving 54% more performance than an oracle.