Luigi Crisci
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Luigi Crisci has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Biagio Cosenza
University of Salerno, Fisciano (Salerno), Italy
8 shared publications - Davide Gadioli
Politecnico di Milano
7 shared publications - Gianluca Palermo
Politecnico di Milano, Milano, Italy
7 shared publications - Gianmarco Accordi
Politecnico di Milano - DEIB, Milan, Italy
7 shared publications - Andrea Rosario Beccari
EXSCALATE, Dompé farmaceutici S.p.A.
6 shared publications - Emanuele Vitali
Politecnico di Milano - DEIB, Milan, Italy
5 shared publications
Latest Publications
- Open Access
miniLB: A Performance Portability Study of Lattice-Boltzmann Simulations
The Lattice Boltzmann Method (LBM) is a computational technique of Computational Fluid Dynamics (CFD) that has gained popularity due to its high parallelism and ability to handle complex geometries with minimal effort. Although LBM frameworks are increasingly important in various industries and research fields, their complexity makes them difficult to modify and can lead to suboptimal performance. This paper presents miniLB, the first, to the best of our knowledge, SYCL-based LBM mini-app.miniLB addresses the need for a performance-portable LBM proxy app capable of abstracting complex fluid dynamics simulations across heterogeneous computing systems. We analyze SYCL semantics for performance portability and evaluate miniLB on multiple GPU architectures using various SYCL implementations. Our results, compared against a manually-tuned FORTRAN version, demonstrate effectiveness of miniLB in assessing LBM performance across diverse hardware, offering valuable insights for optimizing large-scale LBM frameworks in modern computing environments.
Open AccessminiLB: A Performance Portability Study of Lattice-Boltzmann Simulations
The Lattice Boltzmann Method (LBM) is a computational technique of Computational Fluid Dynamics (CFD) that has gained popularity due to its high parallelism and ability to handle complex geometries with minimal effort. Although LBM frameworks are increasingly important in various industries and research fields, their complexity makes them difficult to modify and can lead to suboptimal performance. This paper presents miniLB, the first, to the best of our knowledge, SYCL-based LBM mini-app.miniLB addresses the need for a performance-portable LBM proxy app capable of abstracting complex fluid dynamics simulations across heterogeneous computing systems. We analyze SYCL semantics for performance portability and evaluate miniLB on multiple GPU architectures using various SYCL implementations. Our results, compared against a manually-tuned FORTRAN version, demonstrate effectiveness of miniLB in assessing LBM performance across diverse hardware, offering valuable insights for optimizing large-scale LBM frameworks in modern computing environments.
- Open Access
- 7 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 107-109
LIGATE - LIgand Generator and portable drug discovery platform AT Exascale
The COVID-19 pandemic demonstrates that a top priority for society, now and in the future, is to be able to respond quickly to diseases with effective treatments. Among the new tools that pharmaceutical industries and researchers have in their hands nowadays, there are the extensive computer simulations capable of evaluating in-silico the interaction between possible drugs and the target proteins. The central goal of the LIGATE project is to create and validate a leading application solution for drug discovery in High-Performance Computing (HPC) systems up to the exascale level. The overall project purpose is the automation of the drug design process, which is currently performed with substantial human effort throughout the different phases of the process: preparation of input parameters, management of data sets with billions of molecules, interaction with HPC queue management systems to handle jobs, and optimization of scoring function parameters and thresholds.
- 7 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 107-109
Open AccessLIGATE - LIgand Generator and portable drug discovery platform AT Exascale
The COVID-19 pandemic demonstrates that a top priority for society, now and in the future, is to be able to respond quickly to diseases with effective treatments. Among the new tools that pharmaceutical industries and researchers have in their hands nowadays, there are the extensive computer simulations capable of evaluating in-silico the interaction between possible drugs and the target proteins. The central goal of the LIGATE project is to create and validate a leading application solution for drug discovery in High-Performance Computing (HPC) systems up to the exascale level. The overall project purpose is the automation of the drug design process, which is currently performed with substantial human effort throughout the different phases of the process: preparation of input parameters, management of data sets with billions of molecules, interaction with HPC queue management systems to handle jobs, and optimization of scoring function parameters and thresholds.
- Open Access
- 16 April 2024
- Published by Elsevier in Future Generation Computer Systems
- Vol. 158, 44-59
Enabling performance portability on the LiGen drug discovery pipeline
- 16 April 2024
- Published by Elsevier in Future Generation Computer Systems
- Vol. 158, 44-59
Open AccessEnabling performance portability on the LiGen drug discovery pipeline
- Open Access
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Unlocking performance portability on LUMI-G supercomputer: A virtual screening case study
High-Performance Computing is the target system for virtual screening applications, which aim to suggest which candidates to test in the drug discovery process. The HPC heterogeneity of modern systems raises the functional and performance portability challenge. LiGen is a well-known virtual screening application that can offload the most demanding computation on GPUs. It has been used to perform extreme-scale virtual screening campaigns on HPC systems equipped with NVIDIA cards using a CUDA implementation. This paper reports the experience of running its SYCL implementation on the LUMI-G HPC system that leverages AMD GPUs. Based on the experimental results, the LiGen SYCL implementation performs well on AMD GPUs, enabling LiGen to run a virtual screening campaign on LUMI-G HPC infrastructure.
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessUnlocking performance portability on LUMI-G supercomputer: A virtual screening case study
High-Performance Computing is the target system for virtual screening applications, which aim to suggest which candidates to test in the drug discovery process. The HPC heterogeneity of modern systems raises the functional and performance portability challenge. LiGen is a well-known virtual screening application that can offload the most demanding computation on GPUs. It has been used to perform extreme-scale virtual screening campaigns on HPC systems equipped with NVIDIA cards using a CUDA implementation. This paper reports the experience of running its SYCL implementation on the LUMI-G HPC system that leverages AMD GPUs. Based on the experimental results, the LiGen SYCL implementation performs well on AMD GPUs, enabling LiGen to run a virtual screening campaign on LUMI-G HPC infrastructure.
- Open Access
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
SYCL-Bench 2020: Benchmarking SYCL 2020 on AMD, Intel, and NVIDIA GPUs
Today, the SYCL standard represents the most advanced programming model for heterogeneous computing, delivering both productivity, portability, and performance in pure C++17. SYCL 2020, in particular, represents a major enhancement that pushes the boundaries of heterogeneous programming by introducing a number of new features. As the new features are implemented by existing compilers, it becomes critical to assess the maturity of the implementation through accurate and specific benchmarking. This paper presents SYCL-Bench 2020, an extended benchmark suite specifically designed to evaluate six key features of SYCL 2020: unified shared memory, reduction kernel, specialization constants, group algorithms, in-order queue, and atomics. We experimentally evaluate SYCL-Bench 2020 on GPUs from the three major vendors, i.e., AMD, Intel, and NVIDIA, and on two different SYCL implementations AdaptiveCPP and oneAPI DPC++.
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessSYCL-Bench 2020: Benchmarking SYCL 2020 on AMD, Intel, and NVIDIA GPUs
Today, the SYCL standard represents the most advanced programming model for heterogeneous computing, delivering both productivity, portability, and performance in pure C++17. SYCL 2020, in particular, represents a major enhancement that pushes the boundaries of heterogeneous programming by introducing a number of new features. As the new features are implemented by existing compilers, it becomes critical to assess the maturity of the implementation through accurate and specific benchmarking. This paper presents SYCL-Bench 2020, an extended benchmark suite specifically designed to evaluate six key features of SYCL 2020: unified shared memory, reduction kernel, specialization constants, group algorithms, in-order queue, and atomics. We experimentally evaluate SYCL-Bench 2020 on GPUs from the three major vendors, i.e., AMD, Intel, and NVIDIA, and on two different SYCL implementations AdaptiveCPP and oneAPI DPC++.
- Open Access
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
SimSYCL: A SYCL Implementation Targeting Development, Debugging, Simulation and Conformance
The open SYCL standard has established itself as a cross-vendor, cross-platform means to develop software which benefits from GPU and accelerator parallelism. Inherent difficulties in portability between and debuggability of programs for these targets remain. However, as we demonstrate, the SYCL specification lends itself to be implemented purely in software in a manner that is accessible to debuggers and which can be employed to simulate the characteristics of different hardware targets. We introduce SimSYCL, a novel library-only SYCL implementation with extensive simulation and verification capabilities. By executing all SYCL commands synchronously on the host CPU, it is able to diagnose various manifestations of undefined behavior within kernels, and grants developers the ability to step into kernels with an ordinary debugger to discover other logic errors. We demonstrate that the reduced complexity of this approach, combined with an implementation focus on fast compilation, considerably speeds up the edit-compile-debug cycle compared to other SYCL implementations while maintaining reasonable runtime performance. Furthermore, we show how SimSYCL’s simulation capabilities allow unit-testing user code for cross-platform portability, and that its comprehensive validation detects and reports several classes of user errors which remain undiagnosed by performance-focused implementations.
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessSimSYCL: A SYCL Implementation Targeting Development, Debugging, Simulation and Conformance
The open SYCL standard has established itself as a cross-vendor, cross-platform means to develop software which benefits from GPU and accelerator parallelism. Inherent difficulties in portability between and debuggability of programs for these targets remain. However, as we demonstrate, the SYCL specification lends itself to be implemented purely in software in a manner that is accessible to debuggers and which can be employed to simulate the characteristics of different hardware targets. We introduce SimSYCL, a novel library-only SYCL implementation with extensive simulation and verification capabilities. By executing all SYCL commands synchronously on the host CPU, it is able to diagnose various manifestations of undefined behavior within kernels, and grants developers the ability to step into kernels with an ordinary debugger to discover other logic errors. We demonstrate that the reduced complexity of this approach, combined with an implementation focus on fast compilation, considerably speeds up the edit-compile-debug cycle compared to other SYCL implementations while maintaining reasonable runtime performance. Furthermore, we show how SimSYCL’s simulation capabilities allow unit-testing user code for cross-platform portability, and that its comprehensive validation detects and reports several classes of user errors which remain undiagnosed by performance-focused implementations.
- Open Access
- 2 February 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 80 (8) , 11798-11815
Out of kernel tuning and optimizations for portable large-scale docking experiments on GPUs
Virtual screening is an early stage in the drug discovery process that selects the most promising candidates. In the urgent computing scenario, finding a solution in the shortest time frame is critical. Any improvement in the performance of a virtual screening application translates into an increase in the number of candidates evaluated, thereby raising the probability of finding a drug. In this paper, we show how we can improve application throughput using Out-of-kernel optimizations. They use input features, kernel requirements, and architectural features to rearrange the kernel inputs, executing them out of order, to improve the computation efficiency. These optimizations’ implementations are designed on an extreme-scale virtual screening application, named LiGen, that can hinge on CUDA and SYCL kernels to carry out the computation on modern supercomputer nodes. Even if they are tailored to a single application, they might also be of interest for applications that share a similar design pattern. The experimental results show how these optimizations can increase kernel performance by 2 $$\times$$ , respectively, up to 2.2 $$\times$$ in CUDA and up to 1.9 $$\times$$ , in SYCL. Moreover, the reported speedup can be achieved with the best-proposed parameterization, as shown by the data we collected and reported in this manuscript.- 2 February 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 80 (8) , 11798-11815
Open AccessOut of kernel tuning and optimizations for portable large-scale docking experiments on GPUs
Virtual screening is an early stage in the drug discovery process that selects the most promising candidates. In the urgent computing scenario, finding a solution in the shortest time frame is critical. Any improvement in the performance of a virtual screening application translates into an increase in the number of candidates evaluated, thereby raising the probability of finding a drug. In this paper, we show how we can improve application throughput using Out-of-kernel optimizations. They use input features, kernel requirements, and architectural features to rearrange the kernel inputs, executing them out of order, to improve the computation efficiency. These optimizations’ implementations are designed on an extreme-scale virtual screening application, named LiGen, that can hinge on CUDA and SYCL kernels to carry out the computation on modern supercomputer nodes. Even if they are tailored to a single application, they might also be of interest for applications that share a similar design pattern. The experimental results show how these optimizations can increase kernel performance by 2 $$\times$$ , respectively, up to 2.2 $$\times$$ in CUDA and up to 1.9 $$\times$$ , in SYCL. Moreover, the reported speedup can be achieved with the best-proposed parameterization, as shown by the data we collected and reported in this manuscript. - Open Access
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1790-1800
Domain-Specific Energy Modeling for Drug Discovery and Magnetohydrodynamics Applications
Over the past few years, the adoption of energy efficiency techniques in modern computer systems is becoming increasingly relevant for sustainable computing. A well-known power management software technique for energy-efficient computing is frequency scaling which modulates the device frequency to explore the energy-performance trade-off. To achieve energy savings, a frequency tuning phase is required because different applications can have different energy and runtime behaviors depending on the frequency setting. Machine learning models can be used to predict energy and runtime, and therefore optimal frequency configurations, based on static or dynamic features extracted from the target application. While general-purpose energy models can be very accurate for a wide range of applications, their accuracy can be limited by the specific input of the target application. We present an energy characterization that spans the fields of drug discovery and magnetohydrodynamics by using two real-world applications as case studies: LiGen and Cronos. Additionally, to overcome the limitations of general-purpose approaches, we define two domain-specific energy models, which enhance the general-purpose energy models by leveraging the target application’s input parameter to increase the final accuracy. Experimental results show that for both applications, domain-specific models achieve a ten times lower error compared to the general-purpose energy models.
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1790-1800
Open AccessDomain-Specific Energy Modeling for Drug Discovery and Magnetohydrodynamics Applications
Over the past few years, the adoption of energy efficiency techniques in modern computer systems is becoming increasingly relevant for sustainable computing. A well-known power management software technique for energy-efficient computing is frequency scaling which modulates the device frequency to explore the energy-performance trade-off. To achieve energy savings, a frequency tuning phase is required because different applications can have different energy and runtime behaviors depending on the frequency setting. Machine learning models can be used to predict energy and runtime, and therefore optimal frequency configurations, based on static or dynamic features extracted from the target application. While general-purpose energy models can be very accurate for a wide range of applications, their accuracy can be limited by the specific input of the target application. We present an energy characterization that spans the fields of drug discovery and magnetohydrodynamics by using two real-world applications as case studies: LiGen and Cronos. Additionally, to overcome the limitations of general-purpose approaches, we define two domain-specific energy models, which enhance the general-purpose energy models by leveraging the target application’s input parameter to increase the final accuracy. Experimental results show that for both applications, domain-specific models achieve a ten times lower error compared to the general-purpose energy models.
- Open Access
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 272-278
Tunable and Portable Extreme-Scale Drug Discovery Platform at Exascale
Today digital revolution is having a dramatic impact on the pharmaceutical industry and the entire healthcare system. The implementation of machine learning, extreme-scale computer simulations, and big data analytics in the drug design and development process offers an excellent opportunity to lower the risk of investment and reduce the time to the patient. Within the LIGATE project 1, we aim to integrate, extend, and co-design best-in-class European components to design Computer-Aided Drug Design (CADD) solutions exploiting today's high-end supercomputers and tomorrow's Exascale resources, fostering European competitiveness in the field. The proposed LIGATE solution is a fully integrated workflow that enables to deliver the result of a virtual screening campaign for drug discovery with the highest speed along with the highest accuracy. The full automation of the solution and the possibility to run it on multiple supercomputing centers at once permit to run an extreme scale in silico drug discovery campaign in few days to respond promptly for example to a worldwide pandemic crisis.
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 272-278
Open AccessTunable and Portable Extreme-Scale Drug Discovery Platform at Exascale
Today digital revolution is having a dramatic impact on the pharmaceutical industry and the entire healthcare system. The implementation of machine learning, extreme-scale computer simulations, and big data analytics in the drug design and development process offers an excellent opportunity to lower the risk of investment and reduce the time to the patient. Within the LIGATE project 1, we aim to integrate, extend, and co-design best-in-class European components to design Computer-Aided Drug Design (CADD) solutions exploiting today's high-end supercomputers and tomorrow's Exascale resources, fostering European competitiveness in the field. The proposed LIGATE solution is a fully integrated workflow that enables to deliver the result of a virtual screening campaign for drug discovery with the highest speed along with the highest accuracy. The full automation of the solution and the possibility to run it on multiple supercomputing centers at once permit to run an extreme scale in silico drug discovery campaign in few days to respond promptly for example to a worldwide pandemic crisis.
- Open Access
Improving computation efficiency using input and architecture features for a virtual screening application
Virtual screening is an early stage of the drug discovery process that selects the most promising candidates. In the urgent computing scenario it is critical to find a solution in a short time frame. In this paper, we focus on a real-world virtual screening application to evaluate out-of-kernel optimizations, that consider input and architecture features to improve the computation efficiency on GPU. Experiment results on a modern supercomputer node show that we can almost double the performance. Moreover, we implemented the optimization using SYCL and it provides a consistent benefit with the CUDA optimization. A virtual screening campaign can use this gain in performance to increase the number of evaluated candidates, improving the probability of finding a drug.
Open AccessImproving computation efficiency using input and architecture features for a virtual screening application
Virtual screening is an early stage of the drug discovery process that selects the most promising candidates. In the urgent computing scenario it is critical to find a solution in a short time frame. In this paper, we focus on a real-world virtual screening application to evaluate out-of-kernel optimizations, that consider input and architecture features to improve the computation efficiency on GPU. Experiment results on a modern supercomputer node show that we can almost double the performance. Moreover, we implemented the optimization using SYCL and it provides a consistent benefit with the CUDA optimization. A virtual screening campaign can use this gain in performance to increase the number of evaluated candidates, improving the probability of finding a drug.