Unserializable interleaving detection using hardware counters
Material type:
ArticleDescription: 1 archivo (190,0 kB)Subject(s): Online resources: Summary: Concurrent programs are needed to take advantage of multicore computers. Debugging such concurrent programs is very difficult due to their nondeterminism. So, error detection tools need to be used in production environments. One very popular detection technique is interleaving analysis, which detects atomicity violations in shared memory programs. Unfortunately, the algorithms that implement this technique can be very costly at runtime, restricting its use to the software testing stage. This paper shows how to use the hardware counters present in today's processors to detect the occurrence of unserializable interleavings. This optimization will reduce the overhead introduced by concurrency bug detection tools.
| Item type | Home library | Collection | Call number | URL | Status | Date due | Barcode | |
|---|---|---|---|---|---|---|---|---|
Capítulo de libro
|
Biblioteca de la Facultad de Informática | Biblioteca digital | A0321 (Browse shelf(Opens below)) | Link to resource | No corresponde |
Formato de archivo: PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca)
Concurrent programs are needed to take advantage of multicore computers. Debugging such concurrent programs is very difficult due to their nondeterminism. So, error detection tools need to be used in production environments. One very popular detection technique is interleaving analysis, which detects atomicity violations in shared memory programs. Unfortunately, the algorithms that implement this technique can be very costly at runtime, restricting its use to the software testing stage. This paper shows how to use the hardware counters present in today's processors to detect the occurrence of unserializable interleavings. This optimization will reduce the overhead introduced by concurrency bug detection tools.
IASTED International Conference on Parallel and Distributed Computing and Systems (24ª : 2012 : Las Vegas) PDCS 2012