CPU versus GPU: which can perform matrix computation faster—performance comparison for basic linear algebra subprograms
The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
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 computing time can be accelerated by using graphics processing units (GPUs) to implement the ANNs (see Fig. 1a), as these can perform multiple operations in parallel10–12.”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [12]
Citations
Cites
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077 · cited 1×
“GPU-accelerated BLAS, which is a powerful tool for designing and deploying GPU-accelerated deep learning, is adopted by TensorFlow [16], Torch, Caffe [17], Theano and Deeplearning4j.”
MethodTensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408
The NumPy Array: A Structure for Efficient Numerical Computation
van der Walt, S., Colbert, S. C., & Varoquaux, G. (2011) · Computing in Science & Engineering · doi:10.1109/mcse.2011.37 · Cited by 9,381 · cited 2×
“Many numerical software applications use BLAS-compatible libraries to perform linear algebra computations, including Armadillo, LAPACK [11], LINPACK, GNU Octave, Mathematica, MATLAB [12], NumPy [13], and R.”
MethodAnderson, E., Bai, Z., Bischof, C., Blackford, L. S., Demmel, J., Dongarra, J., Du Croz, J., Greenbaum, A., Hammarling, S., McKenney, A., et al. (1999) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9780898719604 · Cited by 4,435
DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
Guo, H., TANG, R., Ye, Y., Li, Z., & He, X. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/239 · Cited by 2,538 · cited 1×
“On the top of these platforms, many deep learning approaches have been for task of text [18], image [19], video [20] and recommender system [21].”
BackgroundSelf-citationA Survey of General‐Purpose Computation on Graphics Hardware
Owens, J. D., Luebke, D., Govindaraju, N., Harris, M., Krüger, J., Lefohn, A. E., & Purcell, T. J. (2007) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2007.01012.x · Cited by 2,101 · cited 1×
“The first one is the general-purpose central processing unit (CPU) [4] and the second one is the graphics processing unit (GPU) [5, 6].”
BackgroundA set of level 3 basic linear algebra subprograms
Dongarra, J. J., Du Croz, J., Hammarling, S., & Duff, I. S. (1990) · ACM Transactions on Mathematical Software · doi:10.1145/77626.79170 · Cited by 1,821 · cited 2×
“1 ; k is obtained, where we can achieve the parallelism of TRSM [23].”
BackgroundBasic Linear Algebra Subprograms for Fortran Usage
Lawson, C. L., Hanson, R. J., Kincaid, D. R., & Krogh, F. T. (1979) · ACM Transactions on Mathematical Software · doi:10.1145/355841.355847 · Cited by 1,634 · cited 2×
“In 1979, Lawson et al. [7] described the advantages of adopting a set of basic routines for problems in numerical linear algebra.”
BackgroundAn extended set of FORTRAN basic linear algebra subprograms
Dongarra, J. J., Du Croz, J., Hammarling, S., & Hanson, R. J. (1988) · ACM Transactions on Mathematical Software · doi:10.1145/42288.42291 · Cited by 887 · cited 1×
“Thus, an additional set of BLAS, called the Level 2 BLAS [22], was designed for a small set of matrix–vector operations that occur frequently in the implementation of many common algorithms on linear algebra.”
BackgroundDebunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU
Lee, V. W., Kim, C., Chhugani, J., Deisher, M., Kim, D., Nguyen, A. D., Satish, N., Smelyanskiy, M., Chennupaty, S., Hammarlund, P., et al. (2010) · Proceedings of the 37th annual international symposium on Computer architecture · doi:10.1145/1815961.1816021 · Cited by 640 · cited 1×
“The first one is the general-purpose central processing unit (CPU) [4] and the second one is the graphics processing unit (GPU) [5, 6].”
Background
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
“1a), as these can perform multiple operations in parallel 10 – 12 .”
The growing memristor industry
Lanza, M., Pazos, S., Aguirre, F., Sebastian, A., Le Gallo, M., Alam, S. M., Ikegawa, S., Yang, J. J., Vianello, E., Chang, M.-F., et al. (2025) · Nature · doi:10.1038/s41586-025-08733-5 · Cited by 177
“Graphics processing units (GPUs) are specialized electronic circuits that excel in parallel processing tasks 10,11 ; some of them are able to carry out (on average) 100–1,000 trillion operations per second—namely, TOPS, or TFLOPS if the data are codified in floating-point format 12 .”
Deep learning in electron microscopy
Ede, J. M. (2021) · Machine Learning Science and Technology · doi:10.1088/2632-2153/abd614 · Cited by 144
A survey on deep learning fundamentals
Tian, C., Cheng, T., Peng, Z., Zuo, W., Tian, Y., Zhang, Q., Wang, F., & Zhang, D. D. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11368-7 · Cited by 53
Boost Vision Transformer with GPU-Friendly Sparsity and Quantization
Yu, C., Chen, T., Gan, Z., & Fan, J. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02170 · Cited by 65
“End-users need to program the FPGA hardware [22] and develop specific bit-width libraries like Basic Linear Algebra Subprograms (BLAS) [19], which is a heavy burden for actual deployment.”
Background
Metadata
- Authors
- Li, F., Ye, Y., Tian, Z., & Zhang, X.
- Affiliations
- Harbin Institute of Technology (CN)
- City University of Hong Kong (HK)
- Corresponding author
- Li, Feng
- Zhang, Xiaofeng
- Venue
- Neural Computing and Applications
- Published
- 2018-01-25
- Volume
- 31
- Issue
- 8
- Pages
- 4353-4365
- ISSN
- 0941-0643 (ISSN-L)
- 1433-3058
- OpenAlex
- W2785187918
- Cited by
- 29
- References
- 26
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 9 · 2023: 2 · 2022: 2 · 2021: 4 · 2020: 4 · 2018: 1
- FWCI
- 2.48
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Neural Computing and Applications (publishedVersion)
- Funders
- NSFC (61572158, 61602132)
- Shenzhen Science and Technology Program (JSGG20150512145714247, JCYJ20160330163900579, JCYJ20170413105929681)
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Matrix Theory and Algorithms
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Numerical Methods and Algorithms
- Keywords
- BLAS, numerical linear algebra, heterogeneous computing, processor selection, performance comparison, GPU architecture, processor architecture
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: CPU versus GPU: which can perform matrix computation faster—performance comparison for basic linear algebra subprograms. https://app.cochat.ai/papers/10.1007/s00521-018-3354-z
- The paper
- Li, F., Ye, Y., Tian, Z., & Zhang, X. (2019). CPU versus GPU: which can perform matrix computation faster—performance comparison for basic linear algebra subprograms. Neural Computing and Applications. https://doi.org/10.1007/s00521-018-3354-z
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.