In-Memory Data Parallel Processor
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Recent developments in Non-Volatile Memories (NVMs) have opened up a new horizon for in-memory computing. Despite the significant performance gain offered by computational NVMs, previous works have relied on manual mapping of specialized kernels to the memory arrays, making it infeasible to execute more general workloads. We combat this problem by proposing a programmable in-memory processor architecture and data-parallel programming framework. The efficiency of the proposed in-memory processor comes from two sources: massive parallelism and reduction in data movement. A compact instruction set provides generalized computation capabilities for the memory array. The proposed programming framework seeks to leverage the underlying parallelism in the hardware by merging the concepts of data-flow and vector processing. To facilitate in-memory programming, we develop a compilation framework that takes a TensorFlow input and generates code for our in-memory processor. Our results demonstrate 7.5x speedup over a multi-core CPU server for a set of applications from Parsec and 763x speedup over a server-class GPU for a set of Rodinia benchmarks.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The obvious approach i) is to design the DAC circuits with the capability of providing both positive and negative voltages161. This means doubling the number of DAC output levels, and thereby increasing the DAC resolution in 1 bit (with the associated increase in the Silicon area cost as explained in Section Input driving circuits (Block 4)).”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [161]
Citations
Cites
A scalable processing-in-memory accelerator for parallel graph processing
Ahn, J., Hong, S., Yoo, S., Mutlu, O., & Choi, K. (2015) · Proceedings of the 42nd Annual International Symposium on Computer Architecture · doi:10.1145/2749469.2750386 · Cited by 767 · cited 3×
“Near-Memory Computing Past processing-in-memory (PIM) solutions move compute near the memory [4, 5, 10, 17, 18, 24, 31, 33, 35, 38, 46, 47].”
BackgroundTOP-PIM: throughput-oriented programmable processing in memory
Zhang, D., Jayasena, N., Lyashevsky, A., Greathouse, J. L., Xu, L., & Ignatowski, M. (2014) · Proceedings of the 23rd international symposium on High-performance parallel and distributed computing · doi:10.1145/2600212.2600213 · Cited by 320
A 3D-stacked logic-in-memory accelerator for application-specific data intensive computing
Zhu, Q., Akin, B., Sumbul, H. E., Sadi, F., Hoe, J. C., Pileggi, L., & Franchetti, F. (2013) · IEEE International D Systems Integration Conference · doi:10.1109/3dic.2013.6702348 · Cited by 120 · cited 1×
“Near-Memory Computing Past processing-in-memory (PIM) solutions move compute near the memory [4, 5, 10, 17, 18, 24, 31, 33, 35, 38, 46, 47].”
BackgroundScaling towards kilo-core processors with asymmetric high-radix topologies
Abeyratne, N., Das, R., Li, Q., Sewell, K., Giridhar, B., Dreslinski, R., Blaauw, D. T., & Mudge, T. (2013) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca.2013.6522344 · Cited by 59
Self-citationProgramming the FlexRAM parallel intelligent memory system
Fraguela, B. B., Renau, J., Feautrier, P., Padua, D., & Torrellas, J. (2003) · ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming · doi:10.1145/781498.781505 · Cited by 27 · cited 1×
“Near-Memory Computing Past processing-in-memory (PIM) solutions move compute near the memory [4, 5, 10, 17, 18, 24, 31, 33, 35, 38, 46, 47].”
Background
Research works printed but not linked: 2
- Shaizeen Aga , Supreet Jeloka , Arun Subramaniyan , Satish Narayanasamy , David Blaauw , and Reetuparna Das . 2017 . Compute Caches 2017 IEEE International Symposium on High Performance Computer Architecture, HPCA 2017 , Austin, TX, USA, February 4--8 , 2017. IEEE. Shaizeen Aga, Supreet Jeloka, Arun Subramaniyan, Satish Narayanasamy, David Blaauw, and Reetuparna Das. 2017. Compute Caches 2017 IEEE International Symposium on High Performance Computer Architecture, HPCA 2017, Austin, TX, USA, February 4--8, 2017. IEEE.
- Chris Yakopcic and Tarek M Taha . 2013 . Energy efficient perceptron pattern recognition using segmented memristor crossbar arrays. In Neural Networks (IJCNN) , The 2013 International Joint Conference on. IEEE, 1--8. Chris Yakopcic and Tarek M Taha. 2013. Energy efficient perceptron pattern recognition using segmented memristor crossbar arrays. In Neural Networks (IJCNN), The 2013 International Joint Conference on. IEEE, 1--8.
Cited by
Hardware implementation of memristor-based artificial neural networks
Aguirre, F., Sebastian, A., Le Gallo, M., Song, W., Wang, T., Yang, J. J., Lu, W., Chang, M.-F., Ielmini, D., Yang, Y., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-45670-9 · Cited by 564
“The obvious approach i) is to design the DAC circuits with the capability of providing both positive and negative voltages 161 .”
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
“[40] propose an ISA-programmable memristorbased accelerator.”
SIMDRAM: a framework for bit-serial SIMD processing using DRAM
Hajinazar, N., Oliveira, G. F., Gregorio, S., Ferreira, J. D., Ghiasi, N. M., Patel, M., Alser, M., Ghose, S., Gómez-Luna, J., & Mutlu, O. (2021) · Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems · doi:10.1145/3445814.3446749 · Cited by 181
Processing-in-Memory for Energy-Efficient Neural Network Training: A Heterogeneous Approach
Liu, J., Zhao, H., Ogleari, M., Li, D., & Zhao, J. (2018) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro.2018.00059 · Cited by 157
“Whereas previous PIM-based accelerator designs [5, 9, 10, 41–45] investigated Fig.”
BackgroundMethodDuality cache for data parallel acceleration
Fujiki, D., Mahlke, S. A., & Das, R. (2019) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1145/3307650.3322257 · Cited by 117
Self-citation
Metadata
- Authors
- Fujiki, D., Mahlke, S., & Das, R.
- Affiliations
- University of Michigan (US)
- Venue
- Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems
- Publisher
- ACM
- Published
- 2018-03-19
- Pages
- 1-14
- OpenAlex
- W2794243109
- Cited by
- 109
- References
- 5
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 3 · 2023: 9 · 2022: 16 · 2021: 27 · 2020: 24 · 2019: 19 · 2018: 6
- FWCI
- 16.34
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) (publishedVersion)
- Funders
- NSF (1652294)
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Keywords
- in-memory computing, non-volatile memory, data-parallel programming, dataflow programming, vector processing, TensorFlow, data movement reduction, parallelism
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: In-Memory Data Parallel Processor. https://app.cochat.ai/papers/10.1145/3173162.3173171
- The paper
- Fujiki, D., Mahlke, S., & Das, R. (2018). In-Memory Data Parallel Processor. Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems. https://doi.org/10.1145/3173162.3173171
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.