Affiliation:
1. Lakehead University, Thunder Bay, Ontario, Canada
2. Iowa State University, Ames, Iowa
Abstract
General-purpose computing using graphics processing units (GPGPUs) is an attractive option for acceleration of applications with massively data-parallel tasks. While performance of modern GPGPUs is increasing rapidly, the power consumption of these devices is becoming a major concern. In particular, execution units and register file are among the top three most power-hungry components in GPGPUs. In this work, we exploit trivial instructions to reduce power consumption in GPGPUs.
Trivial instructions are those instructions that do not need computations, i.e., multiplication by one. We found that, during the course of a program's execution, a GPGPU executes many trivial instructions. Execution of these instructions wastes power unnecessarily. In this work, we propose trivial bypassing which skips execution of trivial instructions and avoids unnecessary allocation of resources for trivial instructions. By power gating execution units and skipping trivial computing, trivial bypassing reduces both static and dynamic power. Also, trivial bypassing reduces dynamic energy of register file by avoiding access to register file for source and/or destination operands of trivial instructions. While trivial bypassing reduces energy of GPGPUs, it has detrimental impact on performance as a power-gated execution unit requires several cycles to resume its normal operation. Conventional warp schedulers are oblivious to the status of execution units. We propose a new warp scheduler that prioritizes warps based on availability of execution units. We also propose a set of new power management techniques to reduce performance penalty of power gating, further. To increase energy saving of trivial bypassing, we also propose approximating operands of instructions. We offer a set of new techniques to approximate both integer and floating-point instructions and increase the pool of trivial instructions. Our evaluations using a diverse set of benchmarks reveal that our proposed techniques are able to reduce energy of execution units by 11.2% and dynamic energy of register file by 12.2% with minimal performance and quality degradation.
Publisher
Association for Computing Machinery (ACM)
Subject
Hardware and Architecture,Software
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. TrivialSpy: Identifying Software Triviality via Fine-grained and Dataflow-based Value Profiling;Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis;2023-11-11
2. Selective High-Latency Arithmetic Instruction Reuse in Multicore Processors;2023 27th International Conference on System Theory, Control and Computing (ICSTCC);2023-10-11
3. PTTS: Power-aware tensor cores using two-sided sparsity;Journal of Parallel and Distributed Computing;2023-03
4. AxBy-ViT: Reconfigurable Approximate Computation Bypass for Vision Transformers;2022 23rd International Symposium on Quality Electronic Design (ISQED);2022-04-06
5. G-SEPM;Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis;2021-11-13