Kraken and Jaguar Shine in Supercomputing Challenge

The Kraken and Jaguar supercomputers housed at the University of Tennessee’s National Institute for Computational Sciences and the Oak Ridge National Laboratory’s Leadership Computing Facility continued to demonstrate their balanced architectures this week, taking half the top spots in this year’s High-Performance Computing (HPC) Challenge.

Kraken supercomputer

The challenge gives the world’s most powerful systems an opportunity to demonstrate the range of hardware and software capabilities necessary for a useful supercomputer.

The Department of Energy-sponsored Jaguar system took first place in two of the competition’s four benchmarks, known as HPL and STREAM. HPL, or High-Performance Linpack, measures the speed of a supercomputer by solving a dense linear system of equations, while STREAM measures the memory bandwidth and corresponding computational rate for a simple vector kernel.

In addition, Jaguar took second place in a benchmark known as Global FFT and third place in another called RandomAccess. Global FFT, or Fast Fourier Transform, evaluates a system’s ability to transform one function into another, while RandomAccess evaluates a memory system’s performance with small, randomly placed transactions.

The University of Tennessee Kraken system, which is sponsored by the National Science Foundation, also demonstrated that it is an elite system. Kraken took second place in the HPL benchmark and third in the Global FFT.

According to Oak Ridge Leadership Computing Facility Project Director Buddy Bland, the HPC Challenge results highlight the value of Jaguar and Kraken and of the Cray XT5 architecture on which they are built.

“These awards demonstrate that these machines continue to be the best in the world for accomplishing the science missions of the Department of Energy and the National Science Foundation,” Bland said.

The HPC Challenge awards are given each November at SC, the international conference for high-performance computing, networking, storage and analysis. This year’s conference, SC10, is being held in New Orleans.

Source: Oak Ridge National Laboratory

The Kraken and Jaguar supercomputers housed at the University of Tennessees National Institute for Computational Sciences and the Oak Ridge National Laboratorys Leadership Computing Facility continued to demonstrate their balanced architectures this week, taking half the top spots in this year’s High-Performance Computing (HPC) Challenge.

The challenge gives the world’s most powerful systems an opportunity to demonstrate the range of hardware and software capabilities necessary for a useful supercomputer.

The Department of Energy-sponsored Jaguar system took first place in two of the competition’s four benchmarks, known as HPL and STREAM. HPL, or High-Performance Linpack, measures the speed of a supercomputer by solving a dense linear system of equations, while STREAM measures the memory bandwidth and corresponding computational rate for a simple vector kernel.

In addition, Jaguar took second place in a benchmark known as Global FFT and third place in another called RandomAccess. Global FFT, or Fast Fourier Transform, evaluates a system’s ability to transform one function into another, while RandomAccess evaluates a memory system’s performance with small, randomly placed transactions.

The University of Tennessee Kraken system, which is sponsored by the National Science Foundation, also demonstrated that it is an elite system.

The Kraken and Jaguar supercomputers housed at the University of Tennessee’s National Institute for Computational Sciences and the Oak Ridge National Laboratory’s Leadership Computing Facility continued to demonstrate their balanced architectures this week, taking half the top spots in this year’s High-Performance Computing (HPC) Challenge.

The challenge gives the world’s most powerful systems an opportunity to demonstrate the range of hardware and software capabilities necessary for a useful supercomputer.

The Department of Energy-sponsored Jaguar system took first place in two of the competition’s four benchmarks, known as HPL and STREAM. HPL, or High-Performance Linpack, measures the speed of a supercomputer by solving a dense linear system of equations, while STREAM measures the memory bandwidth and corresponding computational rate for a simple vector kernel.

In addition, Jaguar took second place in a benchmark known as Global FFT and third place in another called RandomAccess. Global FFT, or Fast Fourier Transform, evaluates a system’s ability to transform one function into another, while RandomAccess evaluates a memory system’s performance with small, randomly placed transactions.

The University of Tennessee Kraken system, which is sponsored by the National Science Foundation, also demonstrated that it is an elite system. Kraken took second place in the HPL benchmark and third in the Global FFT.

According to Oak Ridge Leadership Computing Facility Project Director Buddy Bland, the HPC Challenge results highlight the value of Jaguar and Kraken and of the Cray XT5 architecture on which they are built.

“These awards demonstrate that these machines continue to be the best in the world for accomplishing the science missions of the Department of Energy and the National Science Foundation,” Bland said.

The HPC Challenge awards are given each November at SC, the international conference for high-performance computing, networking, storage and analysis. This year’s conference, SC10, is being held in New Orleans.

Kraken took second place in the HPL benchmark and third in the Global FFT.

According to Oak Ridge Leadership Computing Facility Project Director Buddy Bland, the HPC Challenge results highlight the value of Jaguar and Kraken and of the Cray XT5 architecture on which they are built.

“These awards demonstrate that these machines continue to be the best in the world for accomplishing the science missions of the Department of Energy and the National Science Foundation,” Bland said.

The HPC Challenge awards are given each November at SC, the international conference for high-performance computing, networking, storage and analysis. This year’s conference, SC10, is being held in New Orleans.

Be Sociable, Share!