Pinpointing and scheduling access conflicts to improve internal resource utilization in solid-state drives

Modern solid-state drives (SSDs)are integrating more internal resources to achieve higher capacity.Parallelizing accesses across internal resources can potentially enhance the performance of SSDs.However,exploiting parallelism inside SSDs is challenging owing to real-time access conflicts.In this paper,we propose a highly parallelizable I/O scheduler (PIOS)to improve internal resource utilization in SSDs from the perspective of I/O scheduling.Specifically, we first pinpoint the conflicting flash requests with precision during the address translation in the Flash Translation Layer (FTL).Then,we introduce conflict eliminated requests (CERs)to reorganize the I/O requests in the device-level queue by dispatching conflicting flash requests to different CERs.Owing to the significant performance discrepancy between flash read and write operations,PIOS employs differentiated scheduling schemes for read and write CER queues to always allocate internal resources to the conflicting CERs that are more valuable.The small dominant size prioritized scheduling policy for the write queue significantly decreases the average write latency.The high parallelism density prioritized scheduling policy for the read queue better utilizes resources by exploiting internal parallelism aggressively.Our evaluation results show that the paralle/izable I/O scheduler (PIOS)can accomplish better SSD performance than existing I/O schedulers implemented in both SSD devices and operating systems.

Graphic Processor Unit Acceleration of Multi-exposure Image Fusion with Median Filter

A fast Graphic Processor Unit(GPU)accelerate algorithm of multiexposure image fusion with median filter is presented in this paper.The proposed algorithm fuses images in YUV space instead of RGB space compared to traditional image fusion method.Furthermore,in YUV space the brightness components and the chromatism components were weighted fused separately with median filter.At last the filtered images were transferred to RGB and merged to the final fusion image.In the GPU acceleration part,three parallel methods were proposed,including sequence images concurrent execution,adjacent kernels merge,and parallel median filter techniques,to expand the concurrency of the algorithm on the GPU platform.In the experimental results,a 16–21 times speedup was obtained compared to the CPU implementation and up to 60 fps performance was achieved in a 1000*1000*6 multi-exposure sequence image fusion case.The results in the experiment demonstrate the high efficiency and high availability of our proposed method.