Tango: A Deep Neural Network Benchmark Suite for Various Accelerators
This provides a more accessible evaluation environment for researchers and developers working with DNNs on resource-limited platforms, though it is incremental as it builds on existing benchmark efforts.
The authors tackled the lack of scalable DNN benchmark suites by proposing Tango, a new suite that runs on any platform supporting CUDA and OpenCL, and they provided architectural statistics from running it on various accelerators including simulators, GPUs, and FPGAs.
Deep neural networks (DNNs) have been proving the effectiveness in various computing fields. To provide more efficient computing platforms for DNN applications, it is essential to have evaluation environments that include assorted benchmark workloads. Though a few DNN benchmark suites have been recently released, most of them require to install proprietary DNN libraries or resource-intensive DNN frameworks, which are hard to run on resource-limited mobile platforms or architecture simulators. To provide a more scalable evaluation environment, we propose a new DNN benchmark suite that can run on any platform that supports CUDA and OpenCL. The proposed benchmark suite includes the most widely used five convolution neural networks and two recurrent neural networks. We provide in-depth architectural statistics of these networks while running them on an architecture simulator, a server- and a mobile-GPU, and a mobile FPGA.