Louis Duval
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Louis Duval has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Alain Tchana
Univ. Grenoble Alpes, CNRS, Inria, Grenoble INP, LIG, 38000 Grenoble, Grenoble, France
3 shared publications - Daniel Hagimont
IRIT, Université de Toulouse, CNRS, Toulouse INP, UT3 Toulouse, Toulouse, France
3 shared publications - Pascal Felber
University of Neuchâtel
3 shared publications - Renaud Lachaize
Univ. Grenoble Alpes, CNRS, Inria, Grenoble INP, LIG, 38000 Grenoble, Grenoble, France
3 shared publications - Yves Kone
IRIT, Université de Toulouse, CNRS, Toulouse INP, UT3 Toulouse, Toulouse, France
3 shared publications
Latest Publications
- Open Access
- 16 June 2025
- Published by Association for Computing Machinery (ACM) in ACM SIGMETRICS Performance Evaluation Review
- Vol. 53 (1) , 127-129
Understanding Intel User Interrupts
User interrupts (UINTR) is a new hardware feature available in recent Intel Xeon processors. It enables a CPU to send, receive, and handle hardware inter-processor interrupts directly in user mode, %(ring 3), meaning without the intervention of the OS kernel. In this paper, we shed light on the inner working of this facility and investigate, with detailed performance and overhead measurements considering deployments on physical machines and virtual machines with Linux and KVM, how it can be leveraged for more efficient inter-process communications, as an alternative to OS (Unix) signals. With UINTR, preemptive user-level thread schedulers can achieve quantum lengths in the microsecond scale.
- 16 June 2025
- Published by Association for Computing Machinery (ACM) in ACM SIGMETRICS Performance Evaluation Review
- Vol. 53 (1) , 127-129
Open AccessUnderstanding Intel User Interrupts
User interrupts (UINTR) is a new hardware feature available in recent Intel Xeon processors. It enables a CPU to send, receive, and handle hardware inter-processor interrupts directly in user mode, %(ring 3), meaning without the intervention of the OS kernel. In this paper, we shed light on the inner working of this facility and investigate, with detailed performance and overhead measurements considering deployments on physical machines and virtual machines with Linux and KVM, how it can be leveraged for more efficient inter-process communications, as an alternative to OS (Unix) signals. With UINTR, preemptive user-level thread schedulers can achieve quantum lengths in the microsecond scale.
- Open Access
- 9 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 127-129
Understanding Intel User Interrupts
- 9 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 127-129
Open AccessUnderstanding Intel User Interrupts
- Open Access
- 27 May 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Measurement and Analysis of Computing Systems
- Vol. 9 (2) , 1-32
Understanding Intel User Interrupts
User interrupts (UINTR) is a new hardware feature available in recent Intel Xeon processors. It enables a CPU to send, receive, and handle hardware inter-processor interrupts directly in user mode, meaning without the intervention of the OS kernel. In this paper, we shed light on the inner working of this facility and investigate, with detailed performance and overhead measurements considering deployments on physical machines and virtual machines with Linux and KVM, how it can be leveraged for more efficient inter-process communications, as an alternative to OS (Unix) signals. With UINTR, preemptive user-level thread schedulers can achieve quantum lengths in the microsecond scale.
- 27 May 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Measurement and Analysis of Computing Systems
- Vol. 9 (2) , 1-32
Open AccessUnderstanding Intel User Interrupts
User interrupts (UINTR) is a new hardware feature available in recent Intel Xeon processors. It enables a CPU to send, receive, and handle hardware inter-processor interrupts directly in user mode, meaning without the intervention of the OS kernel. In this paper, we shed light on the inner working of this facility and investigate, with detailed performance and overhead measurements considering deployments on physical machines and virtual machines with Linux and KVM, how it can be leveraged for more efficient inter-process communications, as an alternative to OS (Unix) signals. With UINTR, preemptive user-level thread schedulers can achieve quantum lengths in the microsecond scale.