IBOM: An Integrated and Balanced On-Chip Memory for High Performance GPGPUs
- 14 November 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 29 (3) , 586-599
Abstract
GPGPU accelerated computing has revolutionized a broad range of applications. To serve between the ever-growing computing capability and external memory, the on-chip memory is becoming increasingly important to GPGPU performance for general-purpose computing. Inherited from the traditional CPUs, however, the contemporary GPGPU on-chip memory design is suboptimal to the SIMT (single instruction, multiple threads) execution. In particular, the on-chip first-level data (L1D) cache thrashing, resulting from insufficient capacity and imbalanced usage, leads to a low hit rate and limits the overall performance. In this study, we reform the contemporary on-chip memory design and propose an integrated and balanced on-chip memory (IBOM) architecture for high-performance GPGPUs. It first virtually enlarges the L1D cache size by an integrated architecture that exploits the under-utilized register file (RF) with lightweight ISA, compiler and microarchitecture supports. Then with sufficient capacity, it is able to improve the cache usage by a set balancing technique that exploits the under-utilized set resources. In our proposed IBOM design, the register and cache accesses are amenable to normal pipeline operations with simple changes. It adequately exploits the size inversion in GPGPU on-chip memory, and enables optimized utilization of the precious resources for higher performance and energy efficiency with even smaller on-chip memory size. The experiment results demonstrate that the proposed IBOM design can offer an average of 29.6% increase in L1D hit rate and in turn 3X performance improvement for the cache-sensitive applications.Keywords
Funding Information
- National Natural Science Foundation of China (61772331, 61402285, 61602300, 61202026, 61332001)
- Program of China National 1000 Young Talent Plan
This publication has 32 references indexed in Scilit:
- Bank Stealing for a Compact and Efficient Register File Architecture in GPGPUIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2016
- Warped-compression2015
- Energy-Efficient eDRAM-Based On-Chip Storage Architecture for GPGPUsIEEE Transactions on Computers, 2015
- Skewed Compressed Caches2014
- Adaptive Cache Management for Energy-Efficient GPU Computing2014
- Power Modeling for GPU Architectures Using McPATACM Transactions on Design Automation of Electronic Systems, 2014
- Cache-Conscious Wavefront Scheduling2012
- Unifying Primary Cache, Scratch, and Register File Memories in a Throughput Processor2012
- Counter-Based Cache Replacement and Bypassing AlgorithmsIEEE Transactions on Computers, 2008
- Dynamic Warp Formation and Scheduling for Efficient GPU Control Flow2007