The Bitlet model: a parameterized analytical model to compare PIM and CPU systems
Currently, data-intensive applications are gaining popularity. Together with this trend, processing-in-memory (PIM)-based systems are being given more attention and have become more relevant. This article describes an analytical modeling tool called Bitlet that can be used in a parameterized fashion...
| Main Authors: | , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/162977 |
| _version_ | 1811695042777055232 |
|---|---|
| author | Ronen, Ronny Eliahu, Adi Leitersdorf, Orian Peled, Natan Korgaonkar, Kunal Chattopadhyay, Anupam Perach, Ben Kvatinsky, Shahar |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Ronen, Ronny Eliahu, Adi Leitersdorf, Orian Peled, Natan Korgaonkar, Kunal Chattopadhyay, Anupam Perach, Ben Kvatinsky, Shahar |
| author_sort | Ronen, Ronny |
| collection | NTU |
| description | Currently, data-intensive applications are gaining popularity. Together with this trend, processing-in-memory (PIM)-based systems are being given more attention and have become more relevant. This article describes an analytical modeling tool called Bitlet that can be used in a parameterized fashion to estimate the performance and power/energy of a PIM-based system and, thereby, assess the affinity of workloads for PIM as opposed to traditional computing. The tool uncovers interesting trade-offs between, mainly, the PIM computation complexity (cycles required to perform a computation through PIM), the amount of memory used for PIM, the system memory bandwidth, and the data transfer size. Despite its simplicity, the model reveals new insights when applied to real-life examples. The model is demonstrated for several synthetic examples and then applied to explore the influence of different parameters on two systems - IMAGING and FloatPIM. Based on the demonstrations, insights about PIM and its combination with a CPU are provided. |
| first_indexed | 2024-10-01T07:17:11Z |
| format | Journal Article |
| id | ntu-10356/162977 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:17:11Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1629772022-11-14T06:05:44Z The Bitlet model: a parameterized analytical model to compare PIM and CPU systems Ronen, Ronny Eliahu, Adi Leitersdorf, Orian Peled, Natan Korgaonkar, Kunal Chattopadhyay, Anupam Perach, Ben Kvatinsky, Shahar School of Computer Science and Engineering Engineering::Computer science and engineering CPU Systems Data-Intensive Application Currently, data-intensive applications are gaining popularity. Together with this trend, processing-in-memory (PIM)-based systems are being given more attention and have become more relevant. This article describes an analytical modeling tool called Bitlet that can be used in a parameterized fashion to estimate the performance and power/energy of a PIM-based system and, thereby, assess the affinity of workloads for PIM as opposed to traditional computing. The tool uncovers interesting trade-offs between, mainly, the PIM computation complexity (cycles required to perform a computation through PIM), the amount of memory used for PIM, the system memory bandwidth, and the data transfer size. Despite its simplicity, the model reveals new insights when applied to real-life examples. The model is demonstrated for several synthetic examples and then applied to explore the influence of different parameters on two systems - IMAGING and FloatPIM. Based on the demonstrations, insights about PIM and its combination with a CPU are provided. This work was supported by the European Research Council through the European Union’s Horizon 2020 Research and Innovation Programme under Grant No. 757259 and by the Israel Science Foundation under Grant No. 1514/17. 2022-11-14T06:05:44Z 2022-11-14T06:05:44Z 2022 Journal Article Ronen, R., Eliahu, A., Leitersdorf, O., Peled, N., Korgaonkar, K., Chattopadhyay, A., Perach, B. & Kvatinsky, S. (2022). The Bitlet model: a parameterized analytical model to compare PIM and CPU systems. ACM Journal On Emerging Technologies in Computing Systems, 18(2), 1-29. https://dx.doi.org/10.1145/3465371 1550-4832 https://hdl.handle.net/10356/162977 10.1145/3465371 2-s2.0-85129742863 2 18 1 29 en ACM Journal on Emerging Technologies in Computing Systems © 2022 Association for Computing Machinery. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering CPU Systems Data-Intensive Application Ronen, Ronny Eliahu, Adi Leitersdorf, Orian Peled, Natan Korgaonkar, Kunal Chattopadhyay, Anupam Perach, Ben Kvatinsky, Shahar The Bitlet model: a parameterized analytical model to compare PIM and CPU systems |
| title | The Bitlet model: a parameterized analytical model to compare PIM and CPU systems |
| title_full | The Bitlet model: a parameterized analytical model to compare PIM and CPU systems |
| title_fullStr | The Bitlet model: a parameterized analytical model to compare PIM and CPU systems |
| title_full_unstemmed | The Bitlet model: a parameterized analytical model to compare PIM and CPU systems |
| title_short | The Bitlet model: a parameterized analytical model to compare PIM and CPU systems |
| title_sort | bitlet model a parameterized analytical model to compare pim and cpu systems |
| topic | Engineering::Computer science and engineering CPU Systems Data-Intensive Application |
| url | https://hdl.handle.net/10356/162977 |
| work_keys_str_mv | AT ronenronny thebitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT eliahuadi thebitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT leitersdorforian thebitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT pelednatan thebitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT korgaonkarkunal thebitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT chattopadhyayanupam thebitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT perachben thebitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT kvatinskyshahar thebitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT ronenronny bitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT eliahuadi bitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT leitersdorforian bitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT pelednatan bitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT korgaonkarkunal bitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT chattopadhyayanupam bitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT perachben bitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems AT kvatinskyshahar bitletmodelaparameterizedanalyticalmodeltocomparepimandcpusystems |