Electrical Resistance Tomographic Image Enhancement Using MRNSD and LSQR

Jaffri, Nasif Raza; Shi, Liwei; Abrar, Usama; Ahmad, Aftab; Yang, Jian

doi:10.1145/3404716.3404722

Cited by 5 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This research activity has important repercussions in the developement, toward a (pre-)Exascale calculation, of other LSQR-based applications involving the solutions of systems with a high sparsity degree, similarly to the Gaia AVU-GSR solver. The parallelization techniques employed in this code could be adapted and exploited in different contexts that adopt the LSQR, such as the reconstruction of images in radioastronomy (Naghibzadeh & van der Veen 2017), geophysics (Joulidehsar et al 2018;Liang et al 2019aLiang et al , 2019b, geodesy (Baur & Austen 2005), medicine (Bin et al 2020;Guo et al 2021), and industry (Jaffri et al 2020) (see Section 1). In conclusion, the continue developement of efficient parallelization techiques is essential to face the increasingly faster production of data in contexts of different nature, going toward the Big Data era.…”

Section: Discussionmentioning

confidence: 99%

“…Concerning the former approach, one of the exploited computational techniques is the LSQR iterative algorithm, to solve large, ill-posed, overdetermined, and possibly sparse systems of equations (Paige & Saunders 1982a, 1982b. This algorithm is employed in several contexts, such as medicine (Bin et al 2020;Guo et al 2021), geophysics (Joulidehsar et al 2018;Liang et al 2019aLiang et al , 2019b, geodesy (Baur & Austen 2005), industry (Jaffri et al 2020), and astronomy (Borriello et al 1986; Van der Marel 1988;Becciani et al 2014;Naghibzadeh & van der Veen 2017;Cesare et al 2021Cesare et al , 2022aCesare et al , 2022bCesare et al , 2022c. For a more in-depth discussion about the LSQR algorithm and other LSQR-based applications and libraries, see Section 2 of Cesare et al (2022c).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The MPI + CUDA Gaia AVU–GSR Parallel Solver Toward Next-generation Exascale Infrastructures

Cesare

Vecchiato

Lattanzi

et al. 2023

PASP

View full text Add to dashboard Cite

We ported to the GPU with CUDA the Astrometric Verification Unit–Global Sphere Reconstruction (AVU–GSR) Parallel Solver developed for the ESA Gaia mission, by optimizing a previous OpenACC porting of this application. The code aims to find, with a [10, 100] μarcsec precision, the astrometric parameters of ∼108 stars, the attitude and instrumental settings of the Gaia satellite, and the global parameter γ of the parametrized Post-Newtonian formalism, by solving a system of linear equations, A × x = b , with the LSQR iterative algorithm. The coefficient matrix A of the final Gaia data set is large, with ∼1011 × 108 elements, and sparse, reaching a size of ∼10–100 TB, typical for the Big Data analysis, which requires an efficient parallelization to obtain scientific results in reasonable timescales. The speedup of the CUDA code over the original AVU–GSR solver, parallelized on the CPU with MPI + OpenMP, increases with the system size and the number of resources, reaching a maximum of ∼14×, >9× over the OpenACC application. This result is obtained by comparing the two codes on the CINECA cluster Marconi100, with 4 V100 GPUs per node. After verifying the agreement between the solutions of a set of systems with different sizes computed with the CUDA and the OpenMP codes and that the solutions showed the required precision, the CUDA code was put in production on Marconi100, essential for an optimal AVU–GSR pipeline and the successive Gaia Data Releases. This analysis represents a first step to understand the (pre-)Exascale behavior of a class of applications that follow the same structure of this code. In the next months, we plan to run this code on the pre-Exascale platform Leonardo of CINECA, with 4 next-generation A200 GPUs per node, toward a porting on this infrastructure, where we expect to obtain even higher performances.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The MPI + CUDA Gaia AVU–GSR Parallel Solver Toward Next-generation Exascale Infrastructures

Cesare

Vecchiato

Lattanzi

et al. 2023

PASP

View full text Add to dashboard Cite

show abstract

“…This research activity has important repercussions in the developement, toward a (pre-)Exascale calculation, of other LSQR-based applications involving the solutions of systems with a high sparsity degree, similarly to the Gaia AVU-GSR solver. The parallelization techniques employed in this code could be adapted and exploited in different contexts that adopt the LSQR, such as the reconstruction of images in radioastronomy (Naghibzadeh and van der Veen, 2017), geophysics (Joulidehsar et al, 2018;Liang et al, 2019a,b), geodesy (Baur and Austen, 2005), medicine (Bin et al, 2020;Guo et al, 2021), and industry (Jaffri et al, 2020) (see Section 1). In conclusion, the continue developement of efficient parallelization techiques is essential to face the increasingly faster production of data in contexts of different nature, going toward the Big Data era.…”

Section: Memory Sectionmentioning

confidence: 99%

“…Concerning the former approach, one of the exploited computational techniques is the LSQR iterative algorithm, to solve large, ill-posed, overdetermined, and possibly sparse systems of equations (Paige and Saunders, 1982a,b). This algorithm is employed in several contexts, such as medicine (Bin et al, 2020;Guo et al, 2021), geophysics (Joulidehsar et al, 2018;Liang et al, 2019a,b), geodesy (Baur and Austen, 2005), industry (Jaffri et al, 2020), and astronomy (Borriello et al, 1986;Van der Marel, 1988;Naghibzadeh and van der Veen, 2017;Becciani et al, 2014;Cesare et al, 2021Cesare et al, , 2022c. For a more in-depth discussion about the LSQR algorithm and other LSQR-based applications and libraries, see Section 2 of Cesare et al (2022b).…”

Section: Introductionmentioning

confidence: 99%

The Mpi + Cuda Gaia Avu–Gsr Parallel Solver Towards Next-Generation Exascale Infrastructures

Cesare¹,

Vecchiato²,

Lattanzi³

et al. 2023

Preprint

View full text Add to dashboard Cite

Toward HPC application portability via C++ PSTL: the Gaia AVU-GSR code assessment

Malenza,

Cesare,

Aldinucci

et al. 2024

J Supercomput

View full text Add to dashboard Cite

The computing capacity needed to process the data generated in modern scientific experiments is approaching ExaFLOPs. Currently, achieving such performances is only feasible through GPU-accelerated supercomputers. Different languages were developed to program GPUs at different levels of abstraction. Typically, the more abstract the languages, the more portable they are across different GPUs. However, the less abstract and co-designed with the hardware, the more room for code optimization and, eventually, the more performance. In the HPC context, portability and performance are a fairly traditional dichotomy. The current C++ Parallel Standard Template Library (PSTL) has the potential to go beyond this dichotomy. In this work, we analyze the main performance benefits and limitations of PSTL using as a use-case the Gaia Astrometric Verification Unit-Global Sphere Reconstruction parallel solver developed by the European Space Agency Gaia mission. The code aims to find the astrometric parameters of $$\sim10^8$$ ∼ 10 8 stars in the Milky Way by iteratively solving a linear system of equations with the LSQR algorithm, originally GPU-ported with the CUDA language. We show that the performance obtained with the PSTL version, which is intrinsically more portable than CUDA, is comparable to the CUDA one on NVIDIA GPU architecture.

show abstract

Electrical Resistance Tomographic Image Enhancement Using MRNSD and LSQR

Cited by 5 publications

References 17 publications

The MPI + CUDA Gaia AVU–GSR Parallel Solver Toward Next-generation Exascale Infrastructures

The MPI + CUDA Gaia AVU–GSR Parallel Solver Toward Next-generation Exascale Infrastructures

The Mpi + Cuda Gaia Avu–Gsr Parallel Solver Towards Next-Generation Exascale Infrastructures

Toward HPC application portability via C++ PSTL: the Gaia AVU-GSR code assessment

Contact Info

Product

Resources

About