World's Fastest GPUs

GPU Test Drive

Verify the benefits of GPU-acceleration for your workloads

GPU-Accelerated Applications Available for Testing


Available Libraries

  • NVIDIA CUDA versions 5.0, 5.5, 6.0, 6.5, 7.0, 7.5
  • NVIDIA cuDNN v2, v3, v4
  • FFTW3 (single and double precision builds)
  • HDF5
  • OpenBLAS
  • OpenCV
  • Python 2.7.9 with H5py, NumPy, pandas, PyCUDA, pydot, scikit-image, scikit-learn, SciPy, SymPy, Theano and more
  • MATLAB toolboxes: Computer Vision System, Control System, Econometrics, Financial, Image Processing, Neural Network, Optimization, Parallel Computing Toolbox (PCT), Signal Processing, Statistics

MPI & Compiler Software

  • MVAPICH2 versions 1.9, 2.0, 2.1
  • OpenMPI versions 1.7.x, 1.8.x
  • GNU GCC Compiler Collection (multiple versions, as needed)
    Provides C, C++ and Fortran compilers.
  • Intel Parallel Studio XE Cluster Edition (multiple versions, as needed)
    Provides C, C++ and Fortran Compilers; Integrated Performance Primitives (IPP), Math Kernel Library (MKL), Clik Plus, Threading Building Blocks (TBB), MPI Library, MPI Benchmarks, Trace Analyzer & Collector, VTune Amplifier XE, Inspector XE, Advisor XE
  • PGI Accelerator Fortran/C/C++ Server (multiple versions, as needed)
    Provides Portland Group C, C++ and Fortran compilers. GPU-acceleration is supported via CUDA Fortran and OpenACC.

Systems Available for Testing

Photograph of Microway HPC clusters of various sizes and configurations
Microway offers a Linux and Windows benchmark cluster for customers to test GPU-enabled applications. The cluster includes:

  • Microway NumberSmasher GPU Nodes
  • Two NVIDIA Tesla K80, K40 or M40 GPUs per node
  • Professional Graphics – NVIDIA Quadro M4000
  • Two 14-core Intel Xeon E5-2690v4 series “Broadwell” CPUs in each node
  • Intel Direct I/O with PCI-E 3.0 support
  • FDR InfiniBand HCAs and switching
  • Over 16 TFLOPS Single and 5 TFLOPS Double Precision GPU performance per node
  • CentOS Linux or Windows 8.1*
  • Pre-configured GPU-enabled software packages
  • Alternate test configurations available upon request.

*Windows 8.1 users must provide their own applications.


Your Information

Name (required)


E-mail (required)



How Did You Hear About Us


Benchmark Details


Operating System

Timeframe for Testing

Additional Requirements/Comments

Why GPUs?

Unlike traditional CPUs, which focus on general-purpose software applications, Tesla GPUs are designed specifically to provide the highest compute performance possible. For many applications, a GPU-accelerated system will be 5X to 25X times faster than a CPU-only system:

Chart of NVIDIA Tesla K80 performance compared to other architectures

The Tesla K80 and M40 GPUs are the latest and fastest accelerators. Tesla K80 is the fastest general-purpose computational GPU. Based on the Kepler architecture, it features:

Dual GPU Accelerators

Two GPUs deliver aggregate memory bandwidth of 480 GB/s – data-intensive applications will experience the best memory throughput on Tesla K80.

Improved GPU Boost

With more boost levels and dynamic GPU Boost, Tesla K80 delivers up to 50% higher application performance. Tesla K80 delivers peak performance by intelligently scaling clocks to the maximum setting available for the power and thermal envelope.

24GB (2x 12GB) of GPU Memory in the same footprint

With double the density of earlier GPUs (2x 12GB GPUs on a single PCB), Tesla K80 allows you to accelerate your most data-intensive applications in smaller system footprints.

Twice the Registers and 2X the L1 cache per SMX

Tesla K80 has double the registers, speeding applications up to 30% faster without any change to the code by enabling more threads to run concurrently.

Try today on advanced, fully integrated hardware

Whether you use community-built code or have in-house GPU-accelerated applications, we are offering remote benchmarking time on our latest hardware. This includes NVIDIA Tesla K80 and M40 GPUs with over 3X the performance of previous Tesla GPUs.

See how fast your code can run

To log in and test your code, register above. After registration, you will receive an email with instructions. For any questions, please email

Tesla GPU Accelerated Applications

NVIDIA Tesla GPU compute processors accelerate many common scientific codes – AMBER, NAMD and LAMMPS are just a few of the applications enjoying significant speed-ups. You can run your own code or one of the preloaded applications.

Read Our Blog on GPU Benchmarking

Comments are closed.