deekey777
2009-11-19, 13:57:04
http://www.accelereyes.com/gbench
Introduction
Jacket GBENCH allows users to gauge the GPU performance of their computer relative to equivalent benchmarks obtained from a variety of other computers, including the CPU of the same computer. Benchmarks include six different tasks, common to the technical computing community:
1. LU: LU decomposition of 1024 x 1024 matrix
2. FFT: Fast Fourier Transform of a 2^20 x 1 vector
3. BLAS: Matrix multiplication of two 1024x1024 matrices
4. 3D Conv: Convolution of 64x64x64 array with 3x3x3 kernel
5. FOR/GFOR: Matrix-vector multiplication of 1024x1024x32 array
6. Equations: Solution of a system of 1024 equations
Note: GBENCH v1.0 was built using Jacket v1.2.1 and MATLAB R2009b. GBENCH requires CUDA 2.3 (driver and toolkit).
...
"The introduction of "Jacket GBENCH" brings a much needed GPU benchmark to the industry", said Jeff Fettig, Director of Sales for James River Technical, Inc.,an AccelerEyes reseller and HPC Solution provider specializing in GPU Accelerated Computing Solutions. "Much like LINPACK, GBENCH establishes an industry standard for measuring the incredible computational horsepower of GPU accelerated solutions like our 8 GPU Velocity Micro VSC455 V8."
Leider wohl nur für CUDA-fähige Grafikkarten.
Introduction
Jacket GBENCH allows users to gauge the GPU performance of their computer relative to equivalent benchmarks obtained from a variety of other computers, including the CPU of the same computer. Benchmarks include six different tasks, common to the technical computing community:
1. LU: LU decomposition of 1024 x 1024 matrix
2. FFT: Fast Fourier Transform of a 2^20 x 1 vector
3. BLAS: Matrix multiplication of two 1024x1024 matrices
4. 3D Conv: Convolution of 64x64x64 array with 3x3x3 kernel
5. FOR/GFOR: Matrix-vector multiplication of 1024x1024x32 array
6. Equations: Solution of a system of 1024 equations
Note: GBENCH v1.0 was built using Jacket v1.2.1 and MATLAB R2009b. GBENCH requires CUDA 2.3 (driver and toolkit).
...
"The introduction of "Jacket GBENCH" brings a much needed GPU benchmark to the industry", said Jeff Fettig, Director of Sales for James River Technical, Inc.,an AccelerEyes reseller and HPC Solution provider specializing in GPU Accelerated Computing Solutions. "Much like LINPACK, GBENCH establishes an industry standard for measuring the incredible computational horsepower of GPU accelerated solutions like our 8 GPU Velocity Micro VSC455 V8."
Leider wohl nur für CUDA-fähige Grafikkarten.