A. Sudarsanam - Academia.edu (original) (raw)
Papers by A. Sudarsanam
1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, 1997
We investigate the problem of code generation for DSP systems on a chip. Such systems devote a li... more We investigate the problem of code generation for DSP systems on a chip. Such systems devote a limited quantity of silicon to program ROM, so application software must be maximally dense. Additionally, the software must be written so as to meet various high-performance constraints, which may include hard real-time constraints. Unfortunately, current compiler technology is unable to generate dense, high-performance code for DSPs, whose architectures are highly irregular. Consequently, designers often resort to programming application software in assembly-a Time-consuming, error-prone, and non-portable task. Thus, DSP compiler technology must be improved substantially. We describe some optimizations that significantly improve the quality of compiler-generated code. Our optimizations are applied globally and even across procedure calls. Additionally, they are applied to the machine-dependent assembly representation of the source program. Our target architecture is the Texas Instruments' TMS320C25 DSP
Proceedings of 9th International Symposium on Systems Synthesis, 1996
... Department of Electrical Engineering Princeton University, Princeton, New Jersey 08544, USA {... more ... Department of Electrical Engineering Princeton University, Princeton, New Jersey 08544, USA { guido,ashok,sharad}@ee.princeton.edu Abstract In this paper we investigate the problem of code gen-eration for address computation for DSP processors. ...
British Journal of Hospital Medicine, 2005
RefDoc Bienvenue - Welcome. Refdoc est un service / is powered by. ...
Motorola's AltivecTM technology provides a new, SIMD vector extension to the PowerPCTM ar-ch... more Motorola's AltivecTM technology provides a new, SIMD vector extension to the PowerPCTM ar-chitecture. Altivec technology provides embedded and computing system designers with a new one part-one code base approach to product design. Intel's Streaming SIMD ...
Hardware/Software Co-Design, 1996
The advent of 0.5 processing that allows for the integration of 5 million transistors on a single... more The advent of 0.5 processing that allows for the integration of 5 million transistors on a single integrated circuit has brought forth new challenges and opportunities in embedded-system design. This high level of integration makes it possible and desirable to integrate a ...
Code Generation for Embedded Processors, 2002
The emergence of integrated circuits in which both the program-ROM and the processor are integrat... more The emergence of integrated circuits in which both the program-ROM and the processor are integrated on a single die initiates a new era of problems for programming language compilers. In such a micro-architecture, code performance, and particularly code density, ...
Radiology, 1977
Five of 7 cases of exophthalmos showed improvement within three months with 2,000 rads of 6 MeV r... more Five of 7 cases of exophthalmos showed improvement within three months with 2,000 rads of 6 MeV radiation. A new technique of X-ray beam localization employing a direct measurement 12 mm posterior to the anterior extent of the cornea was used and found more accurate than using a fixed point (external canthus). All cases should be treated bilaterally. Retreatment after radiation failure is not recommended. There were no complications. Improvement is usually rapid as orbital irradiation, not including the pituitary, causes rapid destruction of the massive collection of lymphocytes and a reduction in the bulky mass and edema of the orbit.
IET Computers & Digital Techniques, 2010
IET Computers & Digital Techniques, 2009
ABSTRACT
... Sudarsanam1 Sharad Malik1 Steven Tjiang2 Stan Liao2 1Department of Electrical Engineering, Pr... more ... Sudarsanam1 Sharad Malik1 Steven Tjiang2 Stan Liao2 1Department of Electrical Engineering, Princeton University, Princeton, New Jersey, USA 2Advanced Technology Group, Synopsys Inc., Mountain View, California, USA ABSTRACT We investigate the problem of code ...
This paper addresses the problem of solving computationally intensive algorithms such as multimed... more This paper addresses the problem of solving computationally intensive algorithms such as multimedia and graphics applications. A novel methodology to design embedded compute-intensive processing elements (ECIPEs) is proposed. In order to identify common data flow patterns among core data flow graphs (DFGs), a low-complexity and parallelism-aware common subgraph extraction algorithm is proposed. In addition, a reconfiguration-aware static scheduling technique to
We address the problem of code generation for embedded DSP systems. In such systems, it is typica... more We address the problem of code generation for embedded DSP systems. In such systems, it is typical for one or more digital signal processors (DSPs), program memory, and custom circuitry to be integrated onto a single IC. Consequently, the amount of silicon area that is ...
1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, 1997
We investigate the problem of code generation for DSP systems on a chip. Such systems devote a li... more We investigate the problem of code generation for DSP systems on a chip. Such systems devote a limited quantity of silicon to program ROM, so application software must be maximally dense. Additionally, the software must be written so as to meet various high-performance constraints, which may include hard real-time constraints. Unfortunately, current compiler technology is unable to generate dense, high-performance code for DSPs, whose architectures are highly irregular. Consequently, designers often resort to programming application software in assembly-a Time-consuming, error-prone, and non-portable task. Thus, DSP compiler technology must be improved substantially. We describe some optimizations that significantly improve the quality of compiler-generated code. Our optimizations are applied globally and even across procedure calls. Additionally, they are applied to the machine-dependent assembly representation of the source program. Our target architecture is the Texas Instruments' TMS320C25 DSP
Proceedings of 9th International Symposium on Systems Synthesis, 1996
... Department of Electrical Engineering Princeton University, Princeton, New Jersey 08544, USA {... more ... Department of Electrical Engineering Princeton University, Princeton, New Jersey 08544, USA { guido,ashok,sharad}@ee.princeton.edu Abstract In this paper we investigate the problem of code gen-eration for address computation for DSP processors. ...
British Journal of Hospital Medicine, 2005
RefDoc Bienvenue - Welcome. Refdoc est un service / is powered by. ...
Motorola's AltivecTM technology provides a new, SIMD vector extension to the PowerPCTM ar-ch... more Motorola's AltivecTM technology provides a new, SIMD vector extension to the PowerPCTM ar-chitecture. Altivec technology provides embedded and computing system designers with a new one part-one code base approach to product design. Intel's Streaming SIMD ...
Hardware/Software Co-Design, 1996
The advent of 0.5 processing that allows for the integration of 5 million transistors on a single... more The advent of 0.5 processing that allows for the integration of 5 million transistors on a single integrated circuit has brought forth new challenges and opportunities in embedded-system design. This high level of integration makes it possible and desirable to integrate a ...
Code Generation for Embedded Processors, 2002
The emergence of integrated circuits in which both the program-ROM and the processor are integrat... more The emergence of integrated circuits in which both the program-ROM and the processor are integrated on a single die initiates a new era of problems for programming language compilers. In such a micro-architecture, code performance, and particularly code density, ...
Radiology, 1977
Five of 7 cases of exophthalmos showed improvement within three months with 2,000 rads of 6 MeV r... more Five of 7 cases of exophthalmos showed improvement within three months with 2,000 rads of 6 MeV radiation. A new technique of X-ray beam localization employing a direct measurement 12 mm posterior to the anterior extent of the cornea was used and found more accurate than using a fixed point (external canthus). All cases should be treated bilaterally. Retreatment after radiation failure is not recommended. There were no complications. Improvement is usually rapid as orbital irradiation, not including the pituitary, causes rapid destruction of the massive collection of lymphocytes and a reduction in the bulky mass and edema of the orbit.
IET Computers & Digital Techniques, 2010
IET Computers & Digital Techniques, 2009
ABSTRACT
... Sudarsanam1 Sharad Malik1 Steven Tjiang2 Stan Liao2 1Department of Electrical Engineering, Pr... more ... Sudarsanam1 Sharad Malik1 Steven Tjiang2 Stan Liao2 1Department of Electrical Engineering, Princeton University, Princeton, New Jersey, USA 2Advanced Technology Group, Synopsys Inc., Mountain View, California, USA ABSTRACT We investigate the problem of code ...
This paper addresses the problem of solving computationally intensive algorithms such as multimed... more This paper addresses the problem of solving computationally intensive algorithms such as multimedia and graphics applications. A novel methodology to design embedded compute-intensive processing elements (ECIPEs) is proposed. In order to identify common data flow patterns among core data flow graphs (DFGs), a low-complexity and parallelism-aware common subgraph extraction algorithm is proposed. In addition, a reconfiguration-aware static scheduling technique to
We address the problem of code generation for embedded DSP systems. In such systems, it is typica... more We address the problem of code generation for embedded DSP systems. In such systems, it is typical for one or more digital signal processors (DSPs), program memory, and custom circuitry to be integrated onto a single IC. Consequently, the amount of silicon area that is ...