University of Southern California, Los Angeles, California
Ling Zhuo, V. K. Prasanna Kumar
2005 ACM/SIGDA 13th international symposium on Field-programmable gate arrays, 2005 – FPGA
Floating-point Sparse Matrix-Vector Multiplication (SpMXV) is a key computational kernel in scientific and engineering applications. The poor data locality of sparse matrices significantly reduces the performance of SpMXV on general-purpose ...
Ling Zhuo, V. K. Prasanna Kumar
18th International Parallel and Distributed Processing Symposium (IPDPS 2004), 2004 – IPDPS
The abundant hardware resources on current FPGAs provide new opportunities to improve the performance of hardware implementations of scientific computations. In this paper, we propose two FPGA-based algorithms for floating-point matrix ...
Ling Zhuo, V. K. Prasanna Kumar
IEEE Transactions on Computers, vol. 57,no. 8,2008 – TC
Numerical linear algebra operations are key primitives in scientific computing. Performance optimizations of such operations have been extensively investigated. With the rapid advances in technology, hardware acceleration of linear algebra ...
Ling Zhuo, V. K. Prasanna Kumar
IEEE Transactions on Parallel and Distributed Systems, vol. 18,no. 4,2007 – TPDS
Abstractâ€”The abundant hardware resources on current reconfigurable computing systems provide new opportunities for high-performance parallel implementations of scientific computations. In this paper, we study designs for floating-point matrix ...
Ling Zhuo, Gerald R. Morris, V. K. Prasanna Kumar
IEEE Transactions on Parallel and Distributed Systems, vol. 18,no. 10,2007 – TPDS
Field programmable gate arrays (FPGAs) have become an attractive option for accelerating scientific applications. Many scientific operations such as matrix-vector multiplication and dot product involve the reduction of a sequentially produced stream ...
Gokul Govindu, Ling Zhuo, Seonil Choi, V. K. Prasanna Kumar
18th International Parallel and Distributed Processing Symposium (IPDPS 2004), 2004 – IPDPS
FPGAs are increasingly being used in the high performance and scientific computing community to implement floating-point based hardware accelerators. In this paper we analyze the floating-point multiplier and adder/subtractor units by considering the ...
Ling Zhuo, V. K. Prasanna Kumar
34th International Conference on Parallel Processing (ICPP 2005), 2005 – ICPP
Numerical linear algebra operations are key primitives in scientific computing. Performance optimizations of such operations have been extensively investigated and some basic operations have been implemented as software libraries. With the rapid ...
Ling Zhuo, V. K. Prasanna Kumar
12th International Conference on Parallel and Distributed Systems, 2006 – ICPADS
Recently, reconfigurable computing systems have been built which employ Field-Programmable Gate Arrays (FPGAs) as hardware accelerators for general-purpose processors. These systems provide new opportunities for highperformance computing. In this ...
Ling Zhuo, V. K. Prasanna Kumar
17th Symposium on Computer Architecture and High Performance Computing (SBAC-PAD 2005), 2005 – SBAC-PAD
Field-Programmable Gate Arrays (FPGAs) have become an attractive option for scientific applications. However, due to the pipelining in the FPGA-based floating-point units, data hazards may occur during reduction of series of values. A typical example ...