Michael Welcome, Charles Rendleman, Leonid Oliker, Rupak Biswas
Adaptive mesh refinement (AMR) is a powerful technique that reduces the resources necessary to solve otherwise intractable problems in computational science. The AMR strategy solves the problem on a...
PERI- Auto-tuning Memory Intensive Kernels for Multicore (2009)
Samuel Williams, Kaushik Datta, Jonathan Carter, Leonid Oliker, John Shalf, Katherine Yelick, ...
We present an auto-tuning approach to optimize application performance on emerging multicore architectures. The methodology extends the idea of search-based performance optimizations, popular in...
Stencil Computation Optimization and Auto-tuning on State-of-the-Art Multicore Architectures (2009)
Kaushik Datta, Mark Murphy, Vasily Volkov, Samuel Williams, Jonathan Carter, Leonid Oliker, ...
Understanding the most efficient design and utilization of emerging multicore systems is one of the most challenging questions faced by the mainstream and scientific computing industries in several...
Scientific application performance on leading scalar and vector supercomputing platforms (2009)
Leonid Oliker, Andrew Canning, Jonathan Carter, John Shalf, Stéphane Ethier
The last decade has witnessed a rapid proliferation of superscalar cache-based microprocessors to build high-end computing (HEC) platforms, primarily because of their generality, scalability, and...
Julian Borrill, Leonid Oliker, John Shalf, Hongzhang Shan
With the exponential growth of high-fidelity sensor and simulated data, the scientific community is increasingly reliant on ultrascale HPC resources to handle their data analysis requirements....
for 3D Unstructured Grids on the SP2 (2009)
Leonid Oliker, Rupak Biswas, Roger C. Strawn, Leonid Oliker, Rupak Biswas, Roger C. Strawn
Dynamic mesh adaption on unstructured grids is a powerful tool for computing unsteady flows that require local grid modifications to efficiently resolve solution features. For this work, we consider...
Julian Borrill, Leonid Oliker, John Shalf, Hongzhang Shan
With the exponential growth of high-fidelity sensor and simulated data, the scientific community is increasingly reliant on ultrascale HPC resources to handle their data analysis requirements....
Contents 1 Performance Characteristics of Potential Petascale Scientific Applications 3 (2008)
Leonid Oliker, John Shalf, Jonathan Carter, Andrew Canning, Shoaib Kamil, Michael Lijewski, ...
Horst D. Simon, Leonid Oliker, Andrew Canning, Jonathan Carter, Michael Wehner, Stephane Ethier, ...
Applications scientists have observed a frustrating trend of stagnating application performance despite dramatic increases in claimed peak performance of high-performance computing (HPC) systems....
ABSTRACT Reconfigurable Hybrid Interconnection for Static and Dynamic Scientific Applications (2008)
Shoaib Kamil, Ali Pinar, Daniel Gunter, Michael Lijewski, Leonid Oliker, John Shalf
As we enter the era of peta-scale computing, system architects must plan for machines composed of tens or even hundreds of thousands of processors. Although fully connected networks such as fat-tree...
Michael Welcome, Charles Rendleman, Leonid Oliker, Rupak Biswas
Adaptive mesh refinement (AMR) is a powerful technique that reduces the resources necessary to solve otherwise intractable problems in computational science. The AMR strategy solves the problem on a...
Adrian Wong, Leonid Oliker, William Kramer, Teresa Kaltz, David Bailey
Obtaining maximum utilization of parallel systems continues to be an active area of research and development. This article outlines a new benchmark, called the Effective System Performance (ESP)...
Jonathan Carter, Yoshinori Tsuda, Min Soe, George Vahala, Angus Macnab, Leonid Oliker, ...
Highly optimized large-scale lattice Boltzmann simulations of 3D magnetohydrodynamic turbulence are performed on the Earth Simulator. We discuss code optimization schemes for both single processor...
Performance evaluation of scientific applications on modern parallel vector systems (2008)
Jonathan Carter, Leonid Oliker, John Shalf
Abstract. Despite their dominance of high-end computing (HEC) through the 1980’s, vector systems have been gradually replaced by microprocessorbased systems. However, while peak performance of...
Dense and Sparse Matrix Operations on (2008)
Samuel W. Williams, John Shalf, Leonid Oliker, Parry Husbands, Katherine Yelick, The Cell Processor
Copyright c○2005 by the authors.
ABSTRACT The Potential of the Cell Processor for Scientific Computing (2008)
Samuel Williams, John Shalf, Leonid Oliker, Shoaib Kamil, Parry Husb, Katherine Yelick
The slowing pace of commodity microprocessor performance improvements combined with ever-increasing chip power demands has become of utmost concern to computational scientists. As a result, the high...
OPTIMIZATION AND PERFORMANCE MODELING OF STENCIL COMPUTATIONS ON MODERN MICROPROCESSORS ‡ (2008)
Kaushik Datta, Shoaib Kamil, Samuel Williams, Leonid Oliker, John Shalf, Katherine Yelick
Abstract. Stencil-based kernels constitute the core of many important scientific applications on block-structured grids. Unfortunately, these codes achieve a low fraction of peak performance, due...
Leonid Oliker, Andrew Canning, Jonathan Carter, John Shalf, Stéphane Ethier, Leonid Oliker, ...
The last decade has witnessed a rapid proliferation of superscalar cache-based microprocessors to build highend computing (HEC) platforms, primarily because of their generality, scalability, and cost...
ABSTRACT The Potential of the Cell Processor for Scientific Computing (2008)
Samuel Williams, John Shalf, Leonid Oliker, Shoaib Kamil, Parry Husb, Katherine Yelick
The slowing pace of commodity microprocessor performance improvements combined with ever-increasing chip power demands has become of utmost concern to computational scientists. As a result, the high...
Michael Wehner, Leonid Oliker, John Shalf
We present a speculative extrapolation of the performance aspects of an atmospheric general circulation model to ultra-high resolution and describe alternative technological paths to realize...
ABSTRACT Leading Computational Methods on Scalar and Vector HEC Platforms (2008)
Leonid Oliker, Jonathan Carter, Michael Wehner, Andrew Canning, Stephane Ethier, Art Mirin, ...
The last decade has witnessed a rapid proliferation of superscalar cache-based microprocessors to build high-end computing (HEC) platforms, primarily because of their generality, scalability, and...
Communication Requirements and Interconnect Optimization for High-End Scientific Applications (2008)
Kamil, Shoaib, Oliker, Leonid, Pinar, Ali, Shalf, John
The path towards realizing peta-scale computing is increasingly dependent on building supercomputers with unprecedented numbers of processors. To prevent the interconnect from dominating the overall...
Scientific Application Performance on Candidate PetaScale Platforms (2008)
Oliker, Leonid, Canning, Andrew, Carter, Jonathan, Iancu, Costin, Lijewski, Michael, Kamil, Shoaib, ...
Scientific Computing Kernels on the Cell Processor (2008)
Williams, Samuel W., Shalf, John, Oliker, Leonid, Kamil, Shoaib, Husbands, Parry, Yelick, Katherine
Leonid Oliker, Gas Dynamics Hyperbolic, High-order Godunov, Grid Amr
Table 1. Overview of scientific applications examined in our study. Eight applications from diverse areas in scientific computing were chosen to compare the performance on our suite of leading...
Adrian Wong, Leonid Oliker, William Kramer, Teresa Kaltz, David Bailey
Obtaining maximum utilization of parallel systems continues to be an active area of research and development. This article outlines a new benchmark, called the Effective System Performance (ESP)...
Scientific Application Performance on Candidate PetaScale Platforms (2008)
Leonid Oliker, Andrew Canning, Jonathan Carter, Costin Iancu, Michael Lijewski, Shoaib Kamil, ...
After a decade where HEC (high-end computing) capability was dominated by the rapid pace of improvements to CPU clock frequency, the performance of next-generation supercomputers is increasingly...
Performance Evaluation and Modeling of Ultra-Scale Systems (2008)
Leonid Oliker, Rupak Biswas, David Bailey, Allan Snavely
The growing gap between sustained and peak performance for full-scale complex scientific applications on conventional supercomputers is a major concern in high performance computing (HPC). The...
The success of parallel computing in solving real-life computationally-intensive problems relies on their efficient mapping and execution on large-scale multiprocessor architectures. Many important...
Transitive Closure on the Imagine Stream Processor (2008)
The increasing gap between processor and memory speeds is a well-known problem in modern computer architecture. The Imagine system is designed to address the processormemory gap through streaming...
Adrian Wong, Leonid Oliker, William Kramer, Teresa Kaltz, David Bailey
Obtaining maximum utilization of parallel systems continues to be an active area of research and development. This article outlines a new benchmark, called the Effective System Performance (ESP)...
Evaluation of Architectural Paradigms for Addressing the Processor-Memory Gap (2008)
Leonid Oliker, Parry Husb, Gorden Griem, Jacqueline Chame
Abstract- Many high performance applications run well below the peak arithmetic performance of the underlying machine, with inefficiencies often attributed to poor memory system behavior. In the...
Performance evaluation of scientific applications on modern parallel vector systems (2008)
Jonathan Carter, Leonid Oliker, John Shalf
Abstract. Despite their dominance of high-end computing (HEC) through the 1980’s, vector systems have been gradually replaced by microprocessor-based systems. However, while peak performance of...
ABSTRACT The Potential of the Cell Processor for Scientific Computing (2008)
Samuel Williams, John Shalf, Leonid Oliker, Shoaib Kamil, Parry Husb, Katherine Yelick
The slowing pace of commodity microprocessor performance improvements combined with ever-increasing chip power demands has become of utmost concern to computational scientists. As a result, the high...
Lattice Boltzmann simulation optimization on leading multicore platforms (2008)
Samuel Williams, Jonathan Carter, Leonid Oliker, John Shalf, Katherine Yelick
We present an auto-tuning approach to optimize application performance on emerging multicore architectures. The methodology extends the idea of searchbased performance optimizations, popular in...
Siddhartha Chatterjee, John R. Gilbert, Leonid Oliker, Robert Schreiber, Thomas J. Sheffler, Prof Siddhartha Chatterjee
'95 conferences. y
Rupak Biswas, Sajal K. Das, Daniel Harvey, Leonid Oliker
The ability to dynamically adapt an unstructured grid (or mesh) is a powerful tool for solving computational problems with evolving physical features; however, an efficient parallel implementation is...
E cient Parallelization of a Dynamic Unstructured Application on the Tera MTA 1 (2007)
The success of parallel computing in solving real-life computationally-intensive problems relies on their e cient mapping and execution on large-scale multiprocessor architectures. Many important...
Abstract Parallel Tetrahedral Mesh Adaptation with Dynamic Load Balancing 1 (2007)
Leonid Oliker, Rupak Biswas, Harold N. Gabow
The ability to dynamically adapt an unstructured grid is a powerful tool for efciently solving computational problems with evolving physical features. In this paper, we report on our experience...
Adrian Wong, Leonid Oliker, William Kramer, Teresa Kaltz, David Bailey
Obtaining maximum utilization of parallel systems continues to be an active area of research and development. This article outlines a new benchmark, called the Effective System Performance (ESP)...
Abstract. The Conjugate Gradient (CG) algorithm is perhaps the best-known iterative technique to solve sparse linear systems that are symmetric and positive definite. For systems that are...
Ordering Schemes for Sparse Matrices using Modern Programming Paradigms (2007)
Leonid Oliker, Xiaoye Li, Parry Husbands, Rupak Biswas
The Conjugate Gradient (CG) algorithm is perhaps the best-known iterative technique to solve sparse linear systems that are symmetric and positive definite. In previous work, we investigated the...
Scientific Application Performance on Leading Scalar and Vector Supercomputing Platforms (2007)
Oliker, Leonid, Canning, Andrew, Carter, Jonathan, Shalf, John, Ethier, Stephane
Reconfigurable Hybrid Interconnection for Static and Dynamic Scientific Applications (2007)
Shoaib Kamil, Ali Pinar, Daniel Gunter, Michael Lijewski, Leonid Oliker, John Shalf
As we enter the era of petascale computing, system architects must plan for machines composed of tens or even hundreds of thousands of processors. Although fully connected networks such as fattree...
Scientific computing kernels on the cell processor (2007)
Samuel Williams, John Shalf, Leonid Oliker, Shoaib Kamil, Parry Husb, Katherine Yelick
The slowing pace of commodity microprocessor performance improvements combined with ever-increasing chip power demands has become of utmost concern to computational scientists. As a result, the high...
Optimization of Sparse Matrix-vector Multiplication on Emerging Multicore Platforms (2007)
Samuel Williams, Leonid Oliker, Richard Vuduc, John Shalf, Katherine Yelick, James Demmel
We are witnessing a dramatic change in computer architecture due to the multicore paradigm shift, as every electronic device from cell phones to supercomputers confronts parallelism of unprecedented...
Optimization of Sparse Matrix-vector Multiplication on Emerging Multicore Platforms (2007)
Samuel Williams, Leonid Oliker, Richard Vuduc, John Shalf, Katherine Yelick, James Demmel
We are witnessing a dramatic change in computer architecture due to the multicore paradigm shift, as every electronic device from cell phones to supercomputers confronts parallelism of unprecedented...
Reconfigurable Hybrid Interconnection for Static and Dynamic Scientific Applications (2006)
Kamil, Shoaib, Pinar, Ali, Gunter, Daniel, Lijewski, Michael, Oliker, Leonid, Shalf, John, ...
As we enter the era of petascale computing, system architects must plan for machines composed of tens of thousands or even hundreds of thousands of processors. Although fully connected networks such...
Welcome, Michael, Rendleman, Charles, Oliker, Leonid, Biswas, Rupak
Adaptive mesh refinement (AMR) is a powerful technique that reduces the resources necessary to solve otherwise in-tractable problems in computational science. The AMR strategy solves the problem on a...
Carter, Jonathan, Oliker, Leonid
The last decade has witnessed a rapid proliferation of superscalarcache-based microprocessors to build high-end computing (HEC) platforms, primarily because of their generality, scalability, and cost...
Implicit and explicit optimizations for stencil computations (2006)
Shoaib Kamil, Kaushik Datta, Samuel Williams, Leonid Oliker, John Shalf, Katherine Yelick
Stencil-based kernels constitute the core of many scientific applications on block-structured grids. Unfortunately, these codes achieve a low fraction of peak performance, due primarily to the...
Jonathan Carter, Leonid Oliker
Abstract. The last decade has witnessed a rapid proliferation of superscalar cache-based microprocessors to build high-end computing (HEC) platforms, primarily because of their generality,...
Implicit and explicit optimizations for stencil computations (2006)
Shoaib Kamil, Kaushik Datta, Samuel Williams, Leonid Oliker, John Shalf, Katherine Yelick
Stencil-based kernels constitute the core of many scientific applications on block-structured grids. Unfortunately, these codes achieve a low fraction of peak performance, due primarily to the...
Carter, Jonathan, Oliker, Leonid, Shalf, John
The last decade has witnessed a rapid proliferation of superscalar cache-based microprocessors to build high-endcomputing (HEC) platforms, primarily because of their generality,scalability, and cost...
The Potential of the Cell Processor for Scientific Computing (2005)
Williams, Samuel, Shalf, John, Oliker, Leonid, Husbands, Parry, Kamil, Shoaib, Yelick, Katherine
The slowing pace of commodity microprocessor performance improvements combined with ever-increasing chip power demands has become of utmost concern to computational scientists. As a result, the high...
Dense and Sparse Matrix Operations on the Cell Processor (2005)
Williams, Samuel W., Shalf, John, Oliker, Leonid, Husbands, Parry, Yelick, Katherine
The slowing pace of commodity microprocessor performance improvements combined with ever-increasing chip power demands has become of utmost concern to computational scientists. Therefore, the high...
Integrated Performance Monitoring of a Cosmology Application on Leading HEC Platforms (2005)
Borrill, Julian, Carter, Jonathan, Oliker, Leonid, Skinner, David, Biswas, Rupak
The Cosmic Microwave Background (CMB) is an exquisitely sensitive probe of the fundamental parameters of cosmology. Extracting this information is computationally intensive, requiring massively...
Performance of Ultra-Scale Applications on Leading Vector and Scalar HPC Platforms (2005)
Oliker, Leonid, Canning, Andrew, Carter, Jonathan Carter, Shalf, John, Simon, Horst, Ethier, Stephane, ...
John Shalf, Shoaib Kamil, Leonid Oliker, David Skinner
The path towards realizing peta-scale computing is increasingly dependent on scaling up to unprecedented numbers of processors. To prevent the interconnect architecture between processors from...
Impact of modern memory subsystems on cache optimizations for stencil computations (2005)
Shoaib Kamil, Parry Husb, Leonid Oliker, John Shalf, Katherine Yelick
In this work we investigate the impact of evolving memory system features, such as large on-chip caches, automatic prefetch, and the growing distance to main memory on 3D stencil computations. These...
Performance of Ultra-Scale Applications on Leading Vector and Scalar HPC Platforms (2005)
Leonid Oliker, Andrew Canning, Jonathan Carter, John Shalf, Horst Simon, Stephane Ethier, ...
Abstract The last decade has witnessed a rapid proliferation of superscalar cache-based microprocessors to build high-end capability and capacity computers primarily because of their generality,...
Science-driven system architecture: A new process for leadership class computing (2005)
Horst Simon, William Kramer, William Saphir, John Shalf, David Bailey, Leonid Oliker, ...
Abstract Over the past several years, computational scientists have observed a frustrating trend of stagnating application performance despite dramatic increases in peak performance of high...
Understanding Ultra-Scale Application Communication Requirements (2005)
Shoaib Kamil, John Shalf, Leonid Oliker, David Skinner
As thermal constraints reduce the pace of CPU performance improvements, the cost and scalability of future HPC architectures will be increasingly dominated by the interconnect. In this work we...
Science-driven system architecture: A new process for leadership class computing (2005)
Horst Simon, William Kramer, William Saphir, John Shalf, David Bailey, Leonid Oliker, ...
Abstract Over the past several years, computational scientists have observed a frustrating trend of stagnating application performance despite dramatic increases in peak performance of high...
Leonid Oliker, Andrew Canning, Jonathan Carter, John Shalf, David Skinner, Stéphane Ethier, ...
The growing gap between sustained and peak performance for scientific applications is a well-known problem in high performance computing. The recent development of parallel vector systems offers the...
John Shalf, Shoaib Kamil, Leonid Oliker, David Skinner
The path towards realizing peta-scale computing is increasingly dependent on scaling up to unprecedented numbers of processors. To prevent the interconnect architecture between processors from...
Performance Evaluation of the SX6 Vector Architecture for Scientific Computations (2005)
Leonid Oliker, Andrew Canning, Jonathan Carter, John Shalf, David Skinner, Stephane Ethier, ...
The growing gap between sustained and peak performance for scientific applications has become a well-known problem in high performance computing. The recent development of parallel vector systems...
Science-driven system architecture: A new process for leadership class computing (2004)
Simon, Horst, Kramer, William, Saphir, William, Shalf, John, Bailey, David, Oliker, Leonid, ...
Over the past several years, computational scientists have observed a frustrating trend of stagnating application performance despite dramatic increases in peak performance of high performance...
Optimizing performance of superscalar codes for a single Cray X1 MSP processor (2004)
Shan, Hongzhang, Strohmaier, Erich, Oliker, Leonid
The growing gap between sustained and peak performance for full-scale complex scientific applications on conventional supercomputers is a major concern in high performance computing. The...
A performance evaluation of the Cray X1 for scientific applications (2004)
Oliker, Leonid, Biswas, Rupak, Borrill, Julian, Canning, Andrew, Carter, Jonathan, Djomehri, Jahed, ...
The last decade has witnessed a rapid proliferation of superscalar cache-based microprocessors to build high-end capability and capacity computers primarily because of their generality, scalability,...
Evaluation of leading scalar and vector architectures for scientific computations (2004)
Simon, Horst D., Oliker, Leonid, Canning, Andrew, Carter, Jonathan, Ethier, Stephane, Shalf, John
Simon, Horst, Kramer, William, Saphir, William, Shalf, John, Bailey, David, Oliker, Leonid, ...
Lawrence Berkeley National Laboratory (Berkeley Lab) proposes to create a National Facility for Advanced Computational Science (NFACS) and to establish a new partnership between the American computer...
Job scheduling in a heterogenous grid environment (2004)
Oliker, Leonid, Biswas, Rupak, Shan, Hongzhang, Smith, Warren
Computational grids have the potential for solving large-scale scientific problems using heterogeneous and geographically distributed resources. However, a number of major technical hurdles must be...
Identifying performance bottlenecks on modern microarchitectures using an adaptable probe (2004)
Griem, Gorden, Oliker, Leonid, Shalf, John, Yelick, Katherine
The gap between peak and delivered performance for scientific applications running on microprocessor-based systems has grown considerably in recent years. The inability to achieve the desired...
Scheduling in Heterogeneous Grid Environments: The Effects of Data Migration (2004)
Oliker, Leonid, Biswas, Rupak, Shan, Hongzhang, Smith, Warren
Scientific computations on modern parallel vector systems (2004)
Leonid Oliker, Andrew Canning, Jonathan Carter, John Shalf, Stephane Ethier
Computational scientists have seen a frustrating trend of stagnating application performance despite dramatic increases in the claimed peak capability of high performance computing systems. This...
A Performance Evaluation of the Cray X1 for Scientific Applications (2004)
Leonid Oliker, Rupak Biswas, Julian Borrill, Andrew Canning, M. Jahed Djomehri, Hongzhang Shan, ...
Abstract. The last decade has witnessed a rapid proliferation of superscalar cache-based microprocessors to build high-end capability and capacity computers primarily because of their generality,...
Leonid Oliker, Andrew Canning, Jonathan Carter, John Shalf, David Skinner, Stéphane Ethier, ...
The growing gap between sustained and peak performance for scientific applications is a well-known problem in high end computing. The recent development of parallel vector systems offers the...
Scientific computations on modern parallel vector systems (2004)
Leonid Oliker, Andrew Canning, Jonathan Carter, John Shalf, Stephane Ethier
Computational scientists have seen a frustrating trend of stagnating application performance despite dramatic increases in the claimed peak capability of HPC systems. This trend has been widely...
Identifying performance bottlenecks on modern microarchitectures using an adaptable probe (2004)
Gorden Griem, Leonid Oliker, John Shalf, Katherine Yelick
The gap between peak and delivered performance for scientific applications running on microprocessor-based systems has grown considerably in recent years. The inability to achieve the desired...
Scientific computations on modern parallel vector systems (2004)
Leonid Oliker, Andrew Canning, Jonathan Carter, John Shalf, Stephane Ethier
Computational scientists have seen a frustrating trend of stagnating application performance despite dramatic increases in the claimed peak capability of high performance computing systems. This...
Scheduling in Heterogeneous Grid Environments: The Effects of Data Migration (2004)
Abstract — Computational grids have the potential for solving large-scale scientific problems using heterogeneous and geographically distributed resources. However, a number of major technical...
Leonid Oliker, Andrew Canning, Jonathan Carter, John Shalf, David Skinner, Stéphane Ethier, ...
The growing gap between sustained and peak performance for scientific applications is a well-known problem in high end computing. The recent development of parallel vector systems offers the...
Performance characteristics of a cosmology package on leading HPC architectures (2004)
Jonathan Carter, Julian Borrill, Leonid Oliker
Abstract. The Cosmic Microwave Background (CMB) is a snapshot of the Universe some 400,000 years after the Big Bang. The pattern of anisotropies in the CMB carries a wealth of information about the...
Horst Simon, William Kramer, William Saphir, John Shalf, David Bailey, Leonid Oliker, ...
This proposal includes data that shall not be disclosed, duplicated, or used in whole or in part, for any purpose other than to evaluate this proposal. Disclosures of information contained in this...
Evaluation of architectural paradigms for addressing the processor-memory gap (2003)
Oliker, Leonid, Gorden, Grime, Husbands, Parry, Chame, Jacqualine
Many high performance applications run well below the peak arithmetic performance of the underlying machine, with inefficiencies often attributed to poor memory system behavior. In the context of...
Oliker, Leonid, Canning, Andrew, Carter, Jonathan, Shalf, John, Skinner, David, Ethier, Stephane, ...
The growing gap between sustained and peak performance for scientific applications is a well-known problem in high end computing. The recent development of parallel vector systems offers the...
Performance evaluation of two emerging media processors: VIRAM and imagine (2003)
Oliker, Leonid, Duell, Jason, Narayanan, Manikandan, Chatterji, Sourav
This work presents two emerging media microprocessors, VIRAM and Imagine, and comparesthe implementation strategies and performance results of these unique architectures. VIRAM is a complete system...
Job superscheduler architecture and performance in computational grid environments (2003)
Hongzhang Shan, Leonid Oliker, Rupak Biswas
Computational grids hold great promise in utilizing geographically separated heterogeneous resources to solve large-scale complex scientific problems. However, a number of major technical hurdles,...
Performance evaluation of two emerging media processors: Viram and imagine (2003)
Sourav Chatterji, An Narayanan, Jason Duell, Leonid Oliker
This work presents ' two emerging media microprocessors, VIRAM and Imagine, and compares the implementation strategies and performance results ' of these unique architectures. VIRAM is a...
Evaluation of Leading Scalar and Vector Architectures for Scientific Computations (2003)
Horst D Simon, Leonid Oliker, Andrew Canning, Jonathan Carter, Stephane Ethier, John Shalf
evelopment of parallel vector systems offers the potential to reduce this gap for many computational science codes and deliver a substantial increase in computing capabilities. This project examines...
Leonid Oliker, Jonathan Carter, John Shalf, David Skinner, Stephane Ethier, Rupak Biswas, ...
The growing gap between sustained and peak performance for scientific applications has become a well-known problem in high performance computing. The recent development of parallel vector systems...
Message passing and shared address space parallelism on an SMP cluster (2003)
Hongzhang Shan, Jaswinder P. Singh, Leonid Oliker, Rupak Biswas
Currently, message passing (MP) andsh*#q address space (SAS) are th two leading parallel programming paradigms. MP h* been standardizedwith MPI, and is th more common and matureapproach hproach code...
Scientific kernels on VIRAM and imagine media processors (2002)
Narayanan, Manikamdan, Oliker, Leonid, Janin, Adam, Husbands, Parry, Li, Xiaoye S.
Many high performance applications run well below the peak arithmetic performance of the underlying machine, with inefficiencies often attributed to a lack of memory bandwidth. In this work we...
Memory-Intensive Benchmarks: IRAM vs. Cache-Based Machines (2002)
Brian R. Gaeke, Parry Husb, Xiaoye S. Li, Leonid Oliker, Katherine A. Yelick, Rupak Biswas
The increasing gap between processor and memory performance has led to new architectural models for memory-intensive applications. In this paper, we use a set of memory-intensive benchmarks to...
Memory-Intensive Benchmarks: IRAM vs. Cache-Based Machines (2002)
Brian R. Gaeke, Parry Husb, Xiaoye S. Li, Leonid Oliker, Katherine A. Yelick, Rupak Biswas
The increasing gap between processor and memory performance has led to new architectural models for memory-intensive applications. In this paper, we use a set of memory-intensive benchmarks to...
Society For Industrial, Leonid Oliker, Xiaoye Li, Parry Husbands, Rupak Biswas
Theconjuga#8 gra#uga t (CG)a#G).K--1; is perha#8 the best-knownitera#55 e technique for solvingspa#in linea# systemstha# a#a symmetrica#m positive definite.For systemstha# a#a ill conditioned, it is...
Memory-intensive benchmarks: IRAM vs. cache-based machines (2001)
Gaeke, Brian G., Husbands, Parry, Kim, Hyun Jin, Li, Xiaoye S., Moon, Hyun Jin, Oliker, Leonid, ...
The increasing gap between processor and memory performance has led to new architectural models for memory-intensive applications. In this paper, we explore the performance of a set of...
A comparison of three programming models for adaptive applications on the Origin2000 (2001)
Shan, Hongzhang, Singh, Jaswinder Pal, Oliker, Leonid, Biswas, Rupak
Message passing vs. shared address space on a cluster of SMPs (2001)
Shan, Hongzhang, Singh, Jaswinder Pal, Oliker, Leonid, Biswas, Rupak
Ordering schemes for sparse matrices using modern programming paradigms (2000)
Oliker, Leonid, Li, Xiaoye, Husbands, Parry, Biswas, Rupak
The Conjugate Gradient (CG) algorithm is perhaps the best-known iterative technique to solve sparse linear systems that are symmetric and positive definite. In previous work, we investigated the...
Design strategies for irregularly adapting parallel applications (2000)
Oliker, Leonid, Biswas, Rupak, Shan, Hongzhang, Sing, Jaswinder Pal
ESP: A system utilization benchmark (2000)
Wong, Adrian T., Oliker, Leonid, Kramer, William T.C., Kaltz, Teresa L., Bailey, David H.
A comparison of three programming models for adaptive applications on the Origin2000 (2000)
Shan, Hongzhang, Singh, Jaswinder Pal, Oliker, Leonid, Biswas, Rupak
ESP: A system utilization benchmark (2000)
Adrian T. Wong, Leonid Oliker, Teresa L. Kaltz, David H. Bailey
This article describes a new benchmark, called the Effective System Performance (ESP) test, which is designed to measure system-level performance, including such factors as job scheduling efficiency,...
ESP: A system utilization benchmark (2000)
Adrian T. Wong, Leonid Oliker, Teresa L. Kaltz, David H. Bailey
This article describes a new benchmark, called the Effective System Performance (ESP) test, which is designed to measure system-level performance, including such factors as job scheduling efficiency,...
A Comparison of Three Programming Models for Adaptive Applications on the Origin2000 (2000)
Hongzhang Shan, Jaswinder Pal Singh, Leonid Oliker
Adaptive applications have computational workloads and communication patterns which change unpredictably at runtime, requiring dynamic load balancing to achieve scalable performance on parallel...
ESP: A system utilization benchmark (2000)
Adrian T. Wong, Leonid Oliker, Teresa L. Kaltz, David H. Bailey
This article describes a new benchmark, called the Effective System Performance (ESP) test, which is designed to measure system-level performance, including such factors as job scheduling efficiency,...
System utilization benchmark on the Cray T3E and IBM SP2 (2000)
Adrian Wong, Leonid Oliker, William Kramer, Teresa Kaltz, David Bailey
Abstract. Obtaining maximum utilization of parallel systems continues to be an active area of research and development. This article outlines a new benchmark, called the Eective System Performance...
Leonid Oliker And, Leonid Oliker, Xiaoye Li, Gerd Heber, Rupak Biswas
The Conjugate Gradient (CG) algorithm is perhaps the best-known iterative technique to solve sparse linear systems that are symmetric and positive definite. A sparse matrix-vector multiply (SPMV)...
Ordering Unstructured Meshes for Sparse Matrix Computations on Leading Parallel Systems (2000)
Leonid Oliker Xiaoye, Leonid Oliker, Xiaoye Li, Gerd Heber, Rupak Biswas
this paper, we focus on the efficiency of SPMV using various ordering/partitioning algorithms. We examine different implementations using three leading programming paradigms and architectures....
Ordering Unstructured Meshes for Sparse Matrix Computations on Leading Parallel Systems (2000)
Leonid Oliker, Xiaoye Li, Gerd Heber, Rupak Biswas
. Computer simulations of realistic applications usually require solving a set of non-linear partial differential equations (PDEs) over a finite region. The process of obtaining numerical solutions...
Ordering unstructured meshes for sparse matrix computations on leading parallel systems (2000)
Leonid Oliker, Xiaoye Li, Gerd Heber, Rupak Biswas
Abstract. Computer simulations of realistic applications usually require solving a set of non-linear partial di erential equations (PDEs) over a nite region. The process of obtaining numerical...
A Comparison of Three Programming Models for Adaptive Applications on the Origin2000 (2000)
Hongzhang Shan, Jaswinder Pal Singh, Leonid Oliker
Adaptive applications have computational workloads and communication patterns which change unpredictably at runtime, requiring dynamic load balancing to achieve scalable performance on parallel...
Abstract Evaluating System Effectiveness in High Performance Computing Systems (1999)
Adrian T. Wong, Leonid Oliker, Teresa L. Kaltz, David H. Bailey
High performance scientific computer systems traditionally have been compared using individual job performance metrics. However, such metrics tend to ignore high-level system issues, such as how...
Abstract Evaluating System Effectiveness in High Performance Computing Systems (1999)
Adrian T. Wong, Leonid Oliker, Teresa L. Kaltz, David H. Bailey
High performance scientific computer systems traditionally have been compared using individual job performance metrics. However, such metrics tend to ignore high-level system issues, such as how...
Parallelization of a Dynamic Unstructured Application using Three Leading Paradigms (1999)
The success of parallel computing in solving real-life computationally-intensive problems relies on their efficient mapping and execution on large-scale multiprocessor architectures. Many important...
Parallel Tetrahedral Mesh Adaptation with Dynamic Load Balancing (1999)
Leonid Oliker, Rupak Biswas, Harold N. Gabow
The ability to dynamically adapt an unstructured grid is a powerful tool for efficiently solving computational problems with evolving physical features. In this paper, we report on our experience...
Parallelization of a Dynamic Unstructured Application using Three Leading Paradigms (1999)
Leonid Oliker National, Leonid Oliker
The success of parallel computing in solving real-life computationally-intensive problems relies on their efficient mapping and execution on large-scale multiprocessor architectures. Many important...
PLUM : parallel load balancing for unstructured adaptive meshes / (1998)
Thesis (Ph. D.)--University of Colorado, 1998.
Leonid Oliker, Leonid Oliker, Olivera Mcbryan, Plum Parallelloadbalancingfor Unstructuredadaptivemeshes, A. Mcbryan
Dynamicmeshadaptionon unstructured grids is a powerful tool for com-puting large-scale problems that require grid modifications to efficiently resolve so-lution features. Unfortunately, an efficient...
Leonid Oliker, Leonid Oliker, Oliver A. Mcbryan
Thesis directed by Professor Oliver A. Mcbryan Dynamic mesh adaption on unstructured grids is a powerful tool for com-puting large-scale problems that require grid modifications to efficiently...
PLUM: Parallel Load Balancing for Adaptive Unstructured Meshes (1998)
Mesh adaption is a powerful tool for efficient unstructured-grid computations but causes load imbalance among processors on a parallel machine. We present a novel method called PLUM to dynamically...
PLUM: Parallel Load Balancing for Unstructured Adaptive Meshes (1998)
Leonid Oliker, Leonid Oliker, Charbel Farhat, Oliver A. Mcbryan, Oliver A. Mcbryan
this paper, this process required no more than three iterations, and all shared vertices were processed as a function of the number of shared edges plus a small communication overhead.
Efficient Load Balancing and Data Remapping for Adaptive Grid Calculations (1997)
Leonid Oliker, Rupak Biswas, Leonid Oliker, Rupak Biswas, Leonid Oliker, Rupak Biswas
Mesh adaption is a powerful tool for efficient unstructuredgrid computations but causes load imbalance among processors on a parallel machine. We present a novel method to dynamically balance the...
BALANCING ADAPTIVE MESHES (1997)
Rupak Biswas, Leonid Oliker, Rupak Biswas, Leonid Oliker
Abstract. Mesh adaption is a powerful tool for efilcient unstructured-grid computa-tions but causes load imbalance on multiprocessor systems. To address this problem, we have developed PLU M, an...
Load Balancing Sequences of Unstructured Adaptive Grids (1997)
Rupak Biswas Leonid, Leonid Oliker
Mesh adaption is a powerful tool for efficient unstructured grid computations but causes load imbalance on multiprocessor systems. To address this problem, we have developed PLUM, an automatic...
Experiments with Repartitioning and Load Balancing Adaptive Meshes (1997)
. Mesh adaption is a powerful tool for efficient unstructured-grid computations but causes load imbalance on multiprocessor systems. To address this problem, we have developed PLUM, an automatic...
Load Balancing Unstructured Adaptive Grids for CFD Problems (1997)
Rupak Biswas Leonid, Leonid Oliker
Mesh adaption is a powerful tool for efficient unstructured-grid computations but causes load imbalance among processors on a parallel machine. A dynamic load balancing method is presented that...
Efficient Load Balancing and Data Remapping for Adaptive Grid Calculations (1997)
Mesh adaption is a powerful tool for efficient unstructuredgrid computations but causes load imbalance among processors on a parallel machine. We present a novel method to dynamically balance the...
Load Balancing Unstructured Adaptive Grids for CFD Problems (1997)
Mesh adaption is a powerful tool for efficient unstructured-grid computations but causes load imbalance among processors on a parallel machine. A dynamic load balancing method is presented that...
Load Balancing Sequences of Unstructured Adaptive Grids (1997)
Mesh adaption is a powerful tool for efficient unstructured grid computations but causes load imbalance on multiprocessor systems. To address this problem, we have developed PLUM, an automatic...
Direct all correspondence to: (1996)
Siddhartha Chatterjee, John R. Gilbert, Leonid Oliker, Robert Schreiber, Thomas J. Sheffler, Siddhartha Chatterjee, ...
*This work was performed while Chatterjee and Sheffier were postdoctoral scientists at RIACS, and Schreiber was a senior scientist at R1ACS. This work was supported by the NAS Systems Division via...
Parallel Implementation of an Adaptive Scheme for 3D (1996)
Leonid Oliker, Leonid Oliker, Leonid Oliker T, Rupak Biswas, Rupak Biswas, Rupak Biswas, ...
Abstract. Dynamic mesh adaption on unstructured grids is a powerful tool for computing unsteady flows that require local grid modifications to efficiently resolve solution features. For this work, we...
Global Load balancing with Parallel Mesh Adaption on Distributed-Memory Systems (1996)
Rupak Biswas, Leonid Oliker, Andrew Sohn, Rupak Biswas, Leonid Oliker, Andrew Sohn
Dynamic mesh adaption on unstructured grids is a powerful tool for efficiently computing unsteady problems to resolve solution features of interest. Unfortu-nately, this causes load imbalance among...
Global Load Balancing with Parallel Mesh Adaption on Distributed-Memory Systems (1996)
Http Www Supercomp, Rupak Biswas, Leonid Oliker, Andrew Sohn
: Dynamic mesh adaption on unstructured grids is a powerful tool for efficiently computing unsteady problems to resolve solution features of interest. Unfortunately, this causes load imbalance among...
New Computational Methods For The Prediction And Analysis Of Helicopter Noise (1996)
Roger C. Strawn, Leonid Oliker, Rupak Biswas
This paper describes several new methods to predict and analyze rotorcraft noise. These methods are: 1) a combined computational fluid dynamics and Kirchhoff scheme for far-field noise predictions,...
Global Load Balancing with Parallel Mesh Adaption on Distributed-Memory Systems (1996)
Rupak Biswas Research, Rupak Biswas, Leonid Oliker, Andrew Sohn
: Dynamic mesh adaption on unstructured grids is a powerful tool for efficiently computing unsteady problems to resolve solution features of interest. Unfortunately, this causes load imbalance among...
Parallel Implementation of an Adaptive Scheme for 3D Unstructured Grids on the SP2 (1996)
Leonid Oliker, Rupak Biswas, Roger C. Strawn
. Dynamic mesh adaption on unstructured grids is a powerful tool for computing unsteady flows that require local grid modifications to efficiently resolve solution features. For this work, we...
Global Load Balancing with Parallel Mesh Adaption on Distributed-Memory Systems (1996)
Rupak Biswas Leonid, Leonid Oliker, Andrew Sohn
Dynamic mesh adaption on unstructured grids is a powerful tool for efficiently computing unsteady problems to resolve solution features of interest. Unfortunately, this causes load imbalance among...
Parallel Implementation of an Adaptive Scheme for 3D Unstructured Grids on the SP2 (1996)
Leonid Oliker, Rupak Biswas, Roger C. Strawn
. Dynamic mesh adaption on unstructured grids is a powerful tool for computing unsteady flows that require local grid modifications to efficiently resolve solution features. For this work, we...
Global Load Balancing with Parallel Mesh Adaption on Distributed-Memory Systems (1996)
Rupak Biswas, Leonid Oliker, Andrew Sohn
: Dynamic mesh adaption on unstructured grids is a powerful tool for efficiently computing unsteady problems to resolve solution features of interest. Unfortunately, this causes load imbalance among...
Algorithms for Automatic Alignment of Arrays (1996)
Siddhartha Chatterjee, John R. Gilbert, Leonid Oliker, Robert Schreiber, Thomas J. Sheffler, Prof Siddhartha Chatterjee
Aggregate data objects (such as arrays) are distributed across the processor memories when compiling a data-parallel language for a distributed-memory machine. The mapping determines the amount of...
System Utilization Benchmark on the Cray T3E and IBM SP (1911)
Adrian Wong Leonid, Adrian Wong, Leonid Oliker, William Kramer, Teresa Kaltz, David Bailey
This article outlines a new benchmark, called the Effective System Performance (ESP) test, designed to provide a utilization metric that is transferable between systems and illuminate the effects of...
System Utilization Benchmark on the Cray T3E and IBM SP (1911)
Adrian Wong, Leonid Oliker, William Kramer, Teresa Kaltz, David Bailey
This article outlines a new benchmark, called the Effective System Performance (ESP) test, designed to provide a utilization metric that is transferable between systems and illuminate the effects of...