Benchmarking a New Paradigm: Experimental Analysis and Characterization of a Real Processing-in-Memory System
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Many modern workloads, such as neural networks, databases, and graph processing, are fundamentally memory-bound. For such workloads, the data movement between main memory and CPU cores imposes a significant overhead in terms of both latency and energy. A major reason is that this communication happens through a narrow bus with high latency and limited bandwidth, and the low data reuse in memory-bound workloads is insufficient to amortize the cost of main memory access. Fundamentally addressing this data movement bottleneck requires a paradigm where the memory system assumes an active role in computing by integrating processing capabilities. This paradigm is known as processing-in-memory (PIM). Recent research explores different forms of PIM architectures, motivated by the emergence of new 3D-stacked memory technologies that integrate memory with a logic layer where processing elements can be easily placed. Past works evaluate these architectures in simulation or, at best, with simplified hardware prototypes. In contrast, the UPMEM company has designed and manufactured the first publicly-available real-world PIM architecture. The UPMEM PIM architecture combines traditional DRAM memory arrays with general-purpose in-order cores, called DRAM Processing Units (DPUs), integrated in the same chip. This paper provides the first comprehensive analysis of the first publicly-available real-world PIM architecture. We make two key contributions. First, we conduct an experimental characterization of the UPMEM-based PIM system using microbenchmarks to assess various architecture limits such as compute throughput and memory bandwidth, yielding new insights. Second, we present PrIM (Processing-In-Memory benchmarks), a benchmark suite of 16 workloads from different application domains (e.g., dense/sparse linear algebra, databases, data analytics, graph processing, neural networks, bioinformatics, image processing), which we identify as memory-bound. We evaluate the performance and scaling characteristics of PrIM benchmarks on the UPMEM PIM architecture, and compare their performance and energy consumption to their modern CPU and GPU counterparts. Our extensive evaluation conducted on two real UPMEM-based PIM systems with 640 and 2,556 DPUs provides new insights about suitability of different workloads to the PIM system, programming recommendations for software designers, and suggestions and hints for hardware and architecture designers of future PIM systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Strukov, D. B., Snider, G. S., Stewart, D. R., & Williams, R. S. (2008) · Nature · doi:10.1038/nature06932 · Cited by 11,828
Needleman, S. B., & Wunsch, C. D. (1970) · Journal of Molecular Biology · doi:10.1016/0022-2836(70)90057-4 · Cited by 11,288 · cited 1×
“Needleman-Wunsch (NW) [259] is a bioinformatics algo-rithm that performs global sequence alignment, i.e., it compares two biological sequences over their entire length to find out the optimal alignment of these sequences.”
Validity of the single processor approach to achieving large scale computing capabilities
Amdahl, G. M. (1967) · Proceedings of the April 18-20, 1967, spring joint computer conference on - AFIPS '67 (Spring) · doi:10.1145/1465482.1465560 · Cited by 4,339
Williams, S., Waterman, A., & Patterson, D. A. (2009) · Communications of the ACM · doi:10.1145/1498765.1498785 · Cited by 2,798 · cited 3×
“We employ the roofline model [215], as described in Section III-C, to quantify the memory boundedness of the CPU versions of the workloads.”
BackgroundMethodInfluentialIndependent component filters of natural images compared with simple cells in primary visual cortex
van Hateren, J. H., & van der Schaaf, A. (1998) · Proceedings of the Royal Society of London. Series B: Biological Sciences · doi:10.1098/rspb.1998.0303 · Cited by 1,106
PUMA: A Programmable Ultra-efficient Memristor-based Accelerator for Machine Learning Inference
Ankit, A., Hajj, I. E., Chalamalasetti, S. R., Ndu, G., Foltin, M., Williams, R. S., Faraboschi, P., Hwu, W.-M. W., Strachan, J. P., Roy, K., et al. (2019) · Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems · doi:10.1145/3297858.3304049 · Cited by 424
Self-citationBuddy-RAM: Improving the Performance and Efficiency of Bulk Bitwise Operations Using DRAM
Seshadri, V., Lee, D., Mullins, T., Hassan, H., Boroumand, A., Kim, J., Kozuch, M. A., Mutlu, O., Gibbons, P. B., & Mowry, T. C. (2016) · arXiv · doi:10.48550/arxiv.1611.09988 · Cited by 54 · cited 2×
“A recent work, called SIMDRAM [37], designs a framework for implementing and executing arbitrary operations in a bit-serial SIMD fashion inside DRAM arrays, building on the Ambit substrate [25, 26].”
MethodSelf-citation
Metadata
- Authors
- Gomez-Luna, J., Hajj, I. E., Fernandez, I., Giannoula, C., Oliveira, G. F., & Mutlu, O.
- Venue
- IEEE Access
- Published
- 2022
- Volume
- 10
- Pages
- 52565-52608
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4285121610
- Cited by
- 175
- References
- 7
- FWCI
- 25.77
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Benchmarking a New Paradigm: Experimental Analysis and Characterization of a Real Processing-in-Memory System. https://app.cochat.ai/papers/10.1109/access.2022.3174101
- The paper
- Gomez-Luna, J., Hajj, I. E., Fernandez, I., Giannoula, C., Oliveira, G. F., & Mutlu, O. (2022). Benchmarking a New Paradigm: Experimental Analysis and Characterization of a Real Processing-in-Memory System. IEEE Access. https://doi.org/10.1109/access.2022.3174101
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.