Adaptive Cache and Concurrency Allocation on GPGPUs


Memory bandwidth is critical to GPGPU performance. Exploiting locality in caches can better utilize memory bandwidth. But, memory requests issued by excessive threads cause cache thrashing and saturate memory bandwidth, degrading performance. In this paper, we tend to propose adaptive cache and concurrency allocation (CCA) to stop cache thrashing and improve the use of bandwidth and computational resources, hence improving performance. In step with locality and reuse distance of access patterns in GPGPU program, warps on a stream multiprocessor are dynamically divided into three teams: cached, bypassed, and waiting. The information cache accommodates the footprint of cached warps. Bypassed warps cannot allocate cache lines in the information cache to forestall cache thrashing, but are in a position to take advantage of obtainable memory bandwidth and computational resource. Waiting warps are de-scheduled. Experimental results show that adaptive CCA can important improve benchmark performance, with 80 percent harmonic mean IPC improvement over the baseline.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Adaptive Pulse Wave Imaging Automated Spatial Vessel Wall Inhomogeneity Detection in Phantoms and in-Vivo ABSTRACT: Imaging the mechanical characteristics of the artery wall may aid in the diagnosis of vascular
PROJECT TITLE : An Adaptive and Robust Edge Detection Method Based on Edge Proportion Statistics ABSTRACT: One of the most important preprocessing steps for high-level tasks in the field of image analysis and computer vision is
PROJECT TITLE : Learned Image Downscaling for Upscaling Using Content Adaptive Resampler ABSTRACT: SR models based on deep convolutional neural networks have shown greater performance in recovering the underlying high-resolution
PROJECT TITLE : Multipatch Unbiased Distance Non-Local Adaptive Means With Wavelet Shrinkage ABSTRACT: Many existing non-local means (NLM) approaches either utilise Euclidean distance to quantify the similarity between patches,
PROJECT TITLE : Depth Restoration From RGB-D Data via Joint Adaptive Regularization and Thresholding on Manifolds ABSTRACT: By integrating the properties of local and non-local manifolds that offer low-dimensional parameterizations

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry