{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:23:56Z","timestamp":1750220636798,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,9,28]],"date-time":"2020-09-28T00:00:00Z","timestamp":1601251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,9,28]]},"DOI":"10.1145\/3422575.3422784","type":"proceedings-article","created":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T01:43:40Z","timestamp":1616377420000},"page":"97-104","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["DELTA: Validate GPU Memory Profiling with Microbenchmarks"],"prefix":"10.1145","author":[{"given":"Xianwei","family":"Zhang","sequence":"first","affiliation":[{"name":"AMD Inc, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evgeny","family":"Shcherbakov","sequence":"additional","affiliation":[{"name":"AMD Inc, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,3,21]]},"reference":[{"volume-title":"Optimizing GPU Cache Policies for MI Workloads. In IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS). 243\u2013248","author":"Alsop J.","key":"e_1_3_2_1_1_1"},{"key":"e_1_3_2_1_2_1","unstructured":"AMD. 2007. Instruction-Based Sampling: A New Performance Analysis Technique for AMD Family 10h Processors. https:\/\/developer.amd.com\/wordpress\/media\/2012\/10\/AMD_IBS_paper_EN.pdf(accessed: 2020-08).  AMD. 2007. Instruction-Based Sampling: A New Performance Analysis Technique for AMD Family 10h Processors. https:\/\/developer.amd.com\/wordpress\/media\/2012\/10\/AMD_IBS_paper_EN.pdf(accessed: 2020-08)."},{"key":"e_1_3_2_1_3_1","unstructured":"AMD. 2017. AMD Radeon RX Vega Graphics. https:\/\/www.amd.com\/en\/products\/graphics\/radeon-rx-vega-64(accessed: 2020-05).  AMD. 2017. AMD Radeon RX Vega Graphics. https:\/\/www.amd.com\/en\/products\/graphics\/radeon-rx-vega-64(accessed: 2020-05)."},{"key":"e_1_3_2_1_4_1","unstructured":"AMD. 2017. \u201dVega\u201d Instruction Set Architecture Reference Guide. https:\/\/developer.amd.com\/wp-content\/resources\/Vega_Shader_ISA_28July2017.pdf(accessed: 2020-05).  AMD. 2017. \u201dVega\u201d Instruction Set Architecture Reference Guide. https:\/\/developer.amd.com\/wp-content\/resources\/Vega_Shader_ISA_28July2017.pdf(accessed: 2020-05)."},{"key":"e_1_3_2_1_5_1","unstructured":"AMD. 2019. AMD Radeon VII Graphics Card. https:\/\/www.amd.com\/en\/products\/graphics\/amd-radeon-vii(accessed: 2020-05).  AMD. 2019. AMD Radeon VII Graphics Card. https:\/\/www.amd.com\/en\/products\/graphics\/amd-radeon-vii(accessed: 2020-05)."},{"key":"e_1_3_2_1_6_1","unstructured":"AMD. 2019. RDNA Architecture. https:\/\/www.amd.com\/system\/files\/documents\/rdna-whitepaper.pdf(accessed: 2020-05).  AMD. 2019. RDNA Architecture. https:\/\/www.amd.com\/system\/files\/documents\/rdna-whitepaper.pdf(accessed: 2020-05)."},{"key":"e_1_3_2_1_7_1","unstructured":"AMD. 2019. ROCProfile Metrics. https:\/\/github.com\/ROCm-Developer-Tools\/rocprofiler\/blob\/amd-master\/test\/tool\/metrics.xml(accessed: 2020-05).  AMD. 2019. ROCProfile Metrics. https:\/\/github.com\/ROCm-Developer-Tools\/rocprofiler\/blob\/amd-master\/test\/tool\/metrics.xml(accessed: 2020-05)."},{"key":"e_1_3_2_1_8_1","unstructured":"AMD. 2020. AMD ROCm Release. https:\/\/github.com\/RadeonOpenCompute\/ROCm(accessed: 2020-06).  AMD. 2020. AMD ROCm Release. https:\/\/github.com\/RadeonOpenCompute\/ROCm(accessed: 2020-06)."},{"key":"e_1_3_2_1_9_1","unstructured":"AMD. 2020. HIP Programming Guide. https:\/\/rocmdocs.amd.com\/en\/latest\/Programming_Guides\/HIP-GUIDE.html(accessed: 2020-05).  AMD. 2020. HIP Programming Guide. https:\/\/rocmdocs.amd.com\/en\/latest\/Programming_Guides\/HIP-GUIDE.html(accessed: 2020-05)."},{"key":"e_1_3_2_1_10_1","unstructured":"AMD. 2020. ROCm Open Ecosystem. https:\/\/www.amd.com\/en\/graphics\/servers-solutions-rocm(accessed: 2020-05).  AMD. 2020. ROCm Open Ecosystem. https:\/\/www.amd.com\/en\/graphics\/servers-solutions-rocm(accessed: 2020-05)."},{"key":"e_1_3_2_1_11_1","unstructured":"AMD. 2020. ROCm Profiler. https:\/\/github.com\/ROCm-Developer-Tools\/rocprofiler\/blob\/amd-master\/doc\/rocprof.md(accessed: 2020-05).  AMD. 2020. ROCm Profiler. https:\/\/github.com\/ROCm-Developer-Tools\/rocprofiler\/blob\/amd-master\/doc\/rocprof.md(accessed: 2020-05)."},{"key":"e_1_3_2_1_12_1","unstructured":"AMD. 2020. rocminfo. https:\/\/github.com\/RadeonOpenCompute\/rocminfo(accessed: 2020-05).  AMD. 2020. rocminfo. https:\/\/github.com\/RadeonOpenCompute\/rocminfo(accessed: 2020-05)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370036.2145820"},{"volume-title":"RAJA: Portable Performance for Large-Scale Scientific Applications. In IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC). 71\u201381","author":"Beckingsale A.","key":"e_1_3_2_1_14_1"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/LLVM-HPC.2014.10"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2398857.2384625"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.11"},{"volume-title":"Poise: Balancing Thread-Level Parallelism and Memory System Performance in GPUs Using Machine Learning. In IEEE International Symposium on High Performance Computer Architecture (HPCA). 492\u2013505","author":"Dublish S.","key":"e_1_3_2_1_18_1"},{"volume-title":"et\u00a0al","year":"2019","author":"Ferrell B.","key":"e_1_3_2_1_19_1"},{"key":"e_1_3_2_1_20_1","unstructured":"GNU. 2008. Debugging with GDB: The GNU Source-Level Debugger. http:\/\/docs.adacore.com\/live\/wave\/gdb-9\/pdf\/gdb\/gdb.pdf(accessed: 2020-08).  GNU. 2008. Debugging with GDB: The GNU Source-Level Debugger. http:\/\/docs.adacore.com\/live\/wave\/gdb-9\/pdf\/gdb\/gdb.pdf(accessed: 2020-08)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2019.2896628"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1065010.1065034"},{"volume-title":"The Symposium on High Performance Chips (HotChips). 1\u201344","author":"Mantor M.","key":"e_1_3_2_1_24_1"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2549523"},{"key":"e_1_3_2_1_26_1","unstructured":"Nvidia. 2020. CUDA Profiler. https:\/\/docs.nvidia.com\/cuda\/profiler-users-guide\/index.html(accessed: 2020-05).  Nvidia. 2020. CUDA Profiler. https:\/\/docs.nvidia.com\/cuda\/profiler-users-guide\/index.html(accessed: 2020-05)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124545"},{"key":"e_1_3_2_1_28_1","unstructured":"ORNL. 2019. Frontier Supercomputer. https:\/\/www.olcf.ornl.gov\/frontier\/(accessed: 2020-05).  ORNL. 2019. Frontier Supercomputer. https:\/\/www.olcf.ornl.gov\/frontier\/(accessed: 2020-05)."},{"key":"e_1_3_2_1_29_1","unstructured":"ORNL. 2019. Summit Supercomputer. https:\/\/www.olcf.ornl.gov\/summit\/(accessed: 2020-05).  ORNL. 2019. Summit Supercomputer. https:\/\/www.olcf.ornl.gov\/summit\/(accessed: 2020-05)."},{"volume-title":"Quality Assessment of GPU Power Profiling Mechanisms. In IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). 702\u2013711","author":"Sen D.","key":"e_1_3_2_1_30_1"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358307"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240771"}],"event":{"name":"MEMSYS 2020: The International Symposium on Memory Systems","acronym":"MEMSYS 2020","location":"Washington DC USA"},"container-title":["The International Symposium on Memory Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3422575.3422784","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3422575.3422784","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:55Z","timestamp":1750197715000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3422575.3422784"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,28]]},"references-count":32,"alternative-id":["10.1145\/3422575.3422784","10.1145\/3422575"],"URL":"https:\/\/doi.org\/10.1145\/3422575.3422784","relation":{},"subject":[],"published":{"date-parts":[[2020,9,28]]},"assertion":[{"value":"2021-03-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}