{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:31:45Z","timestamp":1750221105553,"version":"3.41.0"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2018,11,16]],"date-time":"2018-11-16T00:00:00Z","timestamp":1542326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100011002","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572062,61502019"],"award-info":[{"award-number":["61572062,61502019"]}],"id":[{"id":"10.13039\/501100011002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2016YFB1000503"],"award-info":[{"award-number":["2016YFB1000503"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Archit. Code Optim."],"published-print":{"date-parts":[[2018,12,31]]},"abstract":"<jats:p>\n            Modern Graphic Processing Units (GPUs) have become pervasive computing devices in datacenters due to their high performance with massive thread level parallelism (TLP). GPUs are equipped with large register files (RF) to support fast context switch between massive threads and scratchpad memory (SPM) to support inter-thread communication within the cooperative thread array (CTA). However, the TLP of GPUs is usually limited by the inefficient resource management of register file and scratchpad memory. This inefficiency also leads to register file and scratchpad memory underutilization. To overcome the above inefficiency, we propose a new resource management approach\n            <jats:italic>EXPARS<\/jats:italic>\n            for GPUs.\n            <jats:italic>EXPARS<\/jats:italic>\n            provides a larger register file logically by expanding the register file to scratchpad memory. When the available register file becomes limited, our approach leverages the underutilized scratchpad memory to support additional register allocation. Therefore, more CTAs can be dispatched to SMs, which improves the GPU utilization. Our experiments on representative benchmark suites show that the number of CTAs dispatched to each SM increases by 1.28\u00d7 on average. In addition, our approach improves the GPU resource utilization significantly, with the register file utilization improved by 11.64% and the scratchpad memory utilization improved by 48.20% on average. With better TLP, our approach achieves 20.01% performance improvement on average with negligible energy overhead.\n          <\/jats:p>","DOI":"10.1145\/3280849","type":"journal-article","created":{"date-parts":[[2018,11,16]],"date-time":"2018-11-16T13:08:54Z","timestamp":1542373734000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Improving Thread-level Parallelism in GPUs Through Expanding Register File to Scratchpad Memory"],"prefix":"10.1145","volume":"15","author":[{"given":"Chao","family":"Yu","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuebin","family":"Bai","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingxiao","family":"Sun","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,11,16]]},"reference":[{"volume-title":"Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS\u201909)","author":"Bakhoda Ali","key":"e_1_2_1_1_1","unstructured":"Ali Bakhoda , George L. Yuan , Wilson W. L. Fung , Henry Wong , and Tor M. Aamodt . 2009. Analyzing CUDA workloads using a detailed GPU simulator . In Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS\u201909) . IEEE, 163--174. Ali Bakhoda, George L. Yuan, Wilson W. L. Fung, Henry Wong, and Tor M. Aamodt. 2009. Analyzing CUDA workloads using a detailed GPU simulator. In Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS\u201909). IEEE, 163--174."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037700"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872362.2872368"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2024723.2000093"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155675"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.18"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2597652.2597685"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2907294.2907298"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830784"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508148.2485952"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195655"},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques (PACT\u201913)","author":"Kay\u0131ran Onur","year":"2013","unstructured":"Onur Kay\u0131ran , Adwait Jog , Mahmut Taylan Kandemir , and Chita Ranjan Das . 2013 . Neither more nor less: Optimizing thread-level parallelism for GPGPUs . In Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques (PACT\u201913) . IEEE, 157--166. Onur Kay\u0131ran, Adwait Jog, Mahmut Taylan Kandemir, and Chita Ranjan Das. 2013. Neither more nor less: Optimizing thread-level parallelism for GPGPUs. In Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques (PACT\u201913). IEEE, 157--166."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967941"},{"key":"e_1_2_1_15_1","unstructured":"Nvidia Kepler. 2012. NVIDIA\u2019s Next Generation CUDATM Compute Architecture: Kepler TM GK110. Retrieved from https:\/\/www.nvidia.com\/content\/PDF\/kepler\/NVIDIA-kepler-GK110-architecture-whitepaper.pdf.  Nvidia Kepler. 2012. NVIDIA\u2019s Next Generation CUDATM Compute Architecture: Kepler TM GK110. Retrieved from https:\/\/www.nvidia.com\/content\/PDF\/kepler\/NVIDIA-kepler-GK110-architecture-whitepaper.pdf."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00073"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123974"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168947"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835937"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628107"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508148.2485964"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3177964"},{"key":"e_1_2_1_23_1","volume-title":"Gupta","author":"Namaki-Shoushtari Majid","year":"2013","unstructured":"Majid Namaki-Shoushtari , Abbas Rahimi , Nikil Dutt , Puneet Gupta , and Rajesh K . Gupta . 2013 . ARGO : Aging-aware GPGPU register file allocation. In Proceedings of the 9th IEEE\/ACM\/IFIP International Conference on Hardware\/Software Codesign and System Synthesis. IEEE Press , 30. Majid Namaki-Shoushtari, Abbas Rahimi, Nikil Dutt, Puneet Gupta, and Rajesh K. Gupta. 2013. ARGO: Aging-aware GPGPU register file allocation. In Proceedings of the 9th IEEE\/ACM\/IFIP International Conference on Hardware\/Software Codesign and System Synthesis. IEEE Press, 30."},{"key":"e_1_2_1_24_1","unstructured":"Nvidia. 2009. Nvidia\u2019s next generation cuda compute architecture: Fermi. Retrieved from https:\/\/www.nvidia.com\/content\/PDF\/fermi_white_papers\/NVIDIA_Fermi_Compute_Architecture_Whitepaper.pdf.  Nvidia. 2009. Nvidia\u2019s next generation cuda compute architecture: Fermi. Retrieved from https:\/\/www.nvidia.com\/content\/PDF\/fermi_white_papers\/NVIDIA_Fermi_Compute_Architecture_Whitepaper.pdf."},{"key":"e_1_2_1_25_1","unstructured":"Nvidia. 2011. CUDA C\/C++ SDK code samples. Retrieved from https:\/\/developer.nvidia.com\/cuda-toolkit-40.  Nvidia. 2011. CUDA C\/C++ SDK code samples. Retrieved from https:\/\/developer.nvidia.com\/cuda-toolkit-40."},{"key":"e_1_2_1_26_1","unstructured":"Nvidia. 2014. Nvidia GeForce GTX 980 whitepaper. Retrieved from https:\/\/international.download.nvidia.com\/geforce-com\/international\/pdfs\/GeForce_GTX_980_Whitepaper_FINAL.PDF.  Nvidia. 2014. Nvidia GeForce GTX 980 whitepaper. Retrieved from https:\/\/international.download.nvidia.com\/geforce-com\/international\/pdfs\/GeForce_GTX_980_Whitepaper_FINAL.PDF."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485953"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522352"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173211"},{"key":"e_1_2_1_30_1","volume-title":"Geng Daniel Liu, and Wen-Mei W. Hwu","author":"Stratton John A.","year":"2012","unstructured":"John A. Stratton , Christopher Rodrigues , I- Jui Sung , Nady Obeid , Li-Wen Chang , Nasser Anssari , Geng Daniel Liu, and Wen-Mei W. Hwu . 2012 . Parboil : A revised benchmark suite for scientific and commercial throughput computing. Center Reliable High-perform . Comput. 127 (2012). John A. Stratton, Christopher Rodrigues, I-Jui Sung, Nady Obeid, Li-Wen Chang, Nasser Anssari, Geng Daniel Liu, and Wen-Mei W. Hwu. 2012. Parboil: A revised benchmark suite for scientific and commercial throughput computing. Center Reliable High-perform. Comput. 127 (2012)."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.106"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.57"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/2755753.2755837"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967951"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195656"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.57"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/4.509850"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835939"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830813"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370858"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.59"},{"key":"e_1_2_1_42_1","volume-title":"SMGuard: A flexible and fine-grained resource management framework for GPUs","author":"Yu Chao","year":"2018","unstructured":"Chao Yu , Yuebin Bai , Hailong Yang , Kun Cheng , Yuhao Gu , Zhongzhi Luan , and Depei Qian . 2018. SMGuard: A flexible and fine-grained resource management framework for GPUs . IEEE Trans. Parallel Distrib. Syst . ( 2018 ). Chao Yu, Yuebin Bai, Hailong Yang, Kun Cheng, Yuhao Gu, Zhongzhi Luan, and Depei Qian. 2018. SMGuard: A flexible and fine-grained resource management framework for GPUs. IEEE Trans. Parallel Distrib. Syst. (2018)."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751234"}],"container-title":["ACM Transactions on Architecture and Code Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3280849","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3280849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:01:51Z","timestamp":1750208511000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3280849"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,16]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,12,31]]}},"alternative-id":["10.1145\/3280849"],"URL":"https:\/\/doi.org\/10.1145\/3280849","relation":{},"ISSN":["1544-3566","1544-3973"],"issn-type":[{"type":"print","value":"1544-3566"},{"type":"electronic","value":"1544-3973"}],"subject":[],"published":{"date-parts":[[2018,11,16]]},"assertion":[{"value":"2018-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-11-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}