The Sunway TaihuLight supercomputer has enabled significant advances across diverse scientific and engineering domains, particularly through large-scale numerical and data-driven applications. However, on its SW26010 processor, the absence of an efficient data-sharing mechanism among computing cores often limits the performance of these applications. This paper presents swAllies, a high-efficiency data-sharing library designed to enhance application performance on the SW26010 processor. swAllies builds upon the SW26010’s register-level communication capabilities and integrates two strategies: a bandwidth-oriented strategy and a redundancy-oriented strategy. Both strategies enhance memory access efficiency by reducing redundant data movement and improving bandwidth utilization. Additional optimizations are incorporated to improve the library’s performance and flexibility, while manual and genetic-algorithm-based parameter tuning further improves adaptability across workloads. On the 2D FD4 benchmark, swAllies, together with standard optimization techniques, achieves a 13.54× speedup, reaching 85% of the theoretical upper bound. Across eight representative workloads, swAllies delivers up to 2.71× speedup, demonstrating its effectiveness for real-world scientific applications on the Sunway TaihuLight.
AnselJKamilSVeeramachaneniK, et al. (2014) Opentuner: an extensible framework for program autotuning. In: Proceedings of the 23rd international conference on Parallel architectures and compilation,Edmonton, AB, Canada, August 24–27, 2014, pp. 303–316.
7.
BergstraJBengioY (2012) Random search for hyper-parameter optimization. Journal of Machine Learning Research13: 281–305.
8.
BertoniCApplencourtTGaoL, et al. (2025) Millions of matrix-multiplications: gemm variations on Aurora. In: 2025 IEEE international parallel and distributed processing symposium workshops (IPDPSW),Milan, Italy, June 3–7, 2025, pp. 850–856. DOI: 10.1109/IPDPSW66978.2025.00135.
9.
CahenyPAlvarezLDerradjiS, et al. (2018) Reducing cache coherence traffic with a numa-aware runtime approach. IEEE Transactions on Parallel and Distributed SystemsPP(99): 1. https://doi.org/10.1109/tpds.2017.2787123
10.
Cantu-PazE (2000) Efficient and Accurate Parallel Genetic Algorithms. Genetic Algorithms & Evolutionary Computation, Vol. 1.
11.
ChenBFuHWeiY, et al. (2018) Simulating the wenchuan earthquake with accurate surface topography on sunway taihulight. In: Proceedings of the international conference for high performance computing, networking, storage, and analysis, SC 2018, Dallas, TX, USA, November 11-16, 2018, pp. 40:1–40:12. https://dl.acm.org/citation.cfm?id=3291710
12.
ChenYLiuYShiX, et al. (2023) Lifetime-based optimization for simulating quantum circuits on a new sunway supercomputer. In: Proceedings of the 28th ACM SIGPLAN annual symposium on principles and practice of parallel programming, Montreal, QC, Canada, February 25–March 1, 2023, pp. 148–159.
13.
ChetlurSWoolleyCVandermerschP, et al. (2014) Cudnn: Efficient Primitives for Deep Learning. arXiv preprint arXiv:1410.0759. https://doi.org/10.48550/arXiv.1410.0759
14.
Coello CoelloCA (2002) Theoretical and numerical constraint-handling techniques used with evolutionary algorithms: a survey of the state of the art. Computer Methods in Applied Mechanics and Engineering191(11-12): 1245–1287. https://doi.org/10.1016/s0045-7825(01)00323-1
15.
CosenzaBDurilloJJErmonS, et al. (2017) Autotuning stencil computations with structural ordinal regression learning. In: Parallel & distributed processing symposium,Orlando, FL, USA, May 29–June 2, 2017.
16.
DattaKMurphyMVolkovV, et al. (2008) Stencil computation optimization and auto-tuning on state-of-the-art multicore architectures. In: Proceedings of the 2008 ACM/IEEE conference on supercomputing,Austin, TX, USA, November 15–21, 2008. IEEE Press, p. 4.
17.
DuanXGaoPZhangT, et al. (2018) Redesigning lammps for peta-scale and hundred-billion-atom simulation on sunway taihulight. In: SC18: international conference for high performance computing, networking, storage and analysis, Dallas, TX, USA, November 11–16, 2018. IEEE Press, pp. 148–159.
18.
DuanXShaoQWengJ, et al. (2023) Bio-esmd: a data centric implementation for large-scale biological system simulation on sunway taihulight supercomputer. IEEE Transactions on Parallel and Distributed Systems34(3): 881–893. https://doi.org/10.1109/TPDS.2022.3220559
19.
FuHLiaoJYangJ, et al. (2016) The sunway taihulight supercomputer: system and applications. Science China Information Sciences59(7): 072001. https://doi.org/10.1007/s11432-016-5588-7
20.
FuHYinWYangG, et al. (2017) 18.9-pflops nonlinear earthquake simulation on sunway taihulight: enabling depiction of 18-hz and 8-meter scenarios. In: The international conference for high performance computing, networking, storage and analysis, Denver, CO, USA, November12–17, 2017.
21.
GanLFuHXueW, et al. (2014) Scaling and analyzing the stencil performance on multi-core and many-core architectures. In: Parallel and distributed systems (ICPADS), 2014 20th IEEE international conference on, Hsinchu, Taiwan, December 16–19, 2014.IEEE press, pp. 103–110.
22.
HeyT (2011) The fourth paradigm: data-intensive scientific discovery. Proceedings of the IEEE99(8): 1334–1337.
23.
HuMYuHGuK, et al. (2018) A particle-filter framework for robust cryo-em 3d reconstruction. Nature Methods15(12): 1083–1089. https://doi.org/10.1038/s41592-018-0223-8
24.
IyerRDeVIllikkalR, et al. (2021) Advances in microprocessor cache architectures over the last 25 years. IEEE Micro41(6): 78–88. https://doi.org/10.1109/mm.2021.3114903
LiYDuanXGanL, et al. (2021) Enabling large-scale simulation of cam on the sunway taihulight supercomputer. IEEE Transactions on Computers71(4): 824–837. https://doi.org/10.1109/tc.2021.3063422
27.
LiuZChuXLvX, et al. (2019) Sunwaylb: enabling extreme-scale lattice boltzmann method based computing fluid dynamics simulations on sunway taihulight. In: 2019 IEEE international parallel and distributed processing symposium, IPDPS 2019, Rio de Janeiro, Brazil, May 20–24, 2019, pp. 557–566. https://doi.org/10.1109/IPDPS.2019.00065
28.
LiuYLiuXLiF, et al. (2021) Closing the “quantum supremacy” gap: achieving real-time simulation of a random quantum circuit using a new sunway supercomputer. In: International conference for High performance computing, networking, storage and analysis, St. Louis, MO, USA, November14–19, 2021, pp. 1–12.
29.
ManKFTangKSKwongS (2001) Genetic Algorithms: Concepts and Designs. Springer Science & Business Media.
30.
MicikeviciusP (2009) 3d finite difference computation on gpus using cuda. In: The workshop on general Purpose processing on graphics processing units, Washington, DC, USA, March8, 2009, pp. 79–84.
31.
National Supercomputing Center in Wuxi (2016) Sunway taihulight user guide. Wuxi, China: National Supercomputing Centerin Wuxi. https://www.nsccwx.cn/shangji/82.html#downloadbox(accessed October 2025).
32.
Nguyen-CongKWillmanJTMooreSG, et al. (2021) Billion atom molecular dynamics simulations of carbon at extreme conditions and experimental time and length scales. In: International conference for high performance computing, networking, storage and analysis, St. Louis, MO, USA, November14–19, 2021, pp. 01–12. ACM.
PolychroniouORaghavanARossKA (2015) Rethinking simd vectorization for in-memory databases. In: Proceedings of the 2015 ACM SIGMOD international conference on management of data, Melbourne, VIC, Australia, May 31–June 4, 2015, pp. 1493–1508. ACM.
39.
RaschASchulzeRSteuwerM, et al. (2021) Efficient auto-tuning of parallel programs with interdependent tuning parameters via auto-tuning framework (ATF). ACM Transactions on Architecture and Code Optimization18(1): 1–26. https://doi.org/10.1145/3427093
40.
ShinguSTakaharaHFuchigamiH, et al. (2002) A 26.58 tflops global atmospheric simulation with the spectral transform method on the earth simulator. In: Supercomputing, ACM/IEEE 2002 conference,Baltimore, MD, USA, November 16–22, 2002, pp. 52.
41.
SimonyanKZissermanA (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. https://doi.org/10.48550/arXiv.1409.1556
42.
StrzodkaRShaheenMPajakD, et al. (2011) Impact of system and cache bandwidth on stencil computations across multiple processor generations. In: Proc. workshop on applications for multi-and many-core processors (A4MMC) at ISCA 2011,San Jose, CA, USA, June 4–8, 2011.
VeltenMSchöneRIlscheT, et al. (2022) Memory performance of amd epyc rome and intel cascade lake sp server processors. In: Proceedings of the 2022 ACM/SPEC on International Conference on Performance Engineering,Beijing, China, April 9–13, 2022, pp. 165–175.
45.
WangRTobarRDolenskyM, et al. (2020) Processing full-scale square kilometre array data on the summit supercomputer. In: International conference for high performance computing, networking, storage and analysis, Atlanta, GA, USA, November 9–19, 2020, pp. 1–12. IEEE.
46.
WienkeSSpringerPTerbovenC, et al. (2012) Openacc-first experiences with real-world applications. In: European Conference on Parallel Processing, Rhodes Island, Greece, August 27–31,2012. Springer, pp. 859–870.
47.
WilliamsSWatermanAPattersonD (2009) Roofline: an insightful visual performance model for multicore architectures. Communications of the ACM52(4): 65–76. https://doi.org/10.1145/1498765.1498785
48.
XuJFuHGanL, et al. (2016) Evaluating the power8 architecture through optimizing stencil-based algorithmsTrustcom/BigDataSE/ISPA, 2016 IEEE. IEEE, pp. 1374–1381.
49.
XuZLinJMatsuokaS (2017) Benchmarking sw26010 many-core processor. In: Parallel and distributed processing symposium workshops, Orlando, FL, USA, May 29–June 2, 2017, pp. 743–752.
50.
XuJFuHShiW, et al. (2018a) Performance tuning and analysis for stencil-based applications on power8 processor. ACM Transactions on Architecture and Code Optimization15(4): 41. https://doi.org/10.1145/3264422
51.
XuSXuYXueW, et al. (2018b) Taming the “monster”: overcoming program optimization challenges on sw26010 through precise performance modeling. In: 2018 IEEE international parallel and distributed processing symposium, IPDPS 2018, Vancouver, BC, Canada, May 21-25, 2018, pp. 763–773.
52.
XuJFuJGanL, et al. (2025) Leveraging the hardware resources to accelerate cryo-em reconstruction of relion on the new sunway supercomputer. ACM Transactions on Architecture and Code Optimization22(1): 1–25. https://doi.org/10.1145/3701990. https://doi.org/10.1145/3701990
53.
YangCXueWFuH, et al. (2016) 10m-core scalable fully-implicit solver for nonhydrostatic atmospheric dynamics. In: International conference for high performance computing, networking, storage and analysis, Salt Lake City, UT, USA, November13–18, 2016, p. 6.
54.
YavitsLMoradAGinosarR (2014) The effect of communication and synchronization on amdahl law in multicore systems. Parallel Computing40(1): 1–16. https://doi.org/10.1016/j.parco.2013.11.001
55.
ZhangBYangXYangF, et al. (2010) The cublas and cula based gpu acceleration of adaptive finite element framework for bioluminescence tomography. Optics Express18(19): 20201–20214. https://doi.org/10.1364/OE.18.020201
56.
ZhaoWFuHFangJ, et al. (2018) Optimizing convolutional neural networks on the sunway taihulight supercomputer. ACM Transactions on Architecture and Code Optimization15(1): 13–26. https://doi.org/10.1145/3177885
