Compiler-Enhanced Incremental Checkpointing

Bronevetsky, Greg; Marques, Daniel; Pingali, Keshav; Rugina, Radu

doi:10.1007/978-3-540-85261-2_1

Cited by 10 publications

(14 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This process restores the memory changes captured in the checkpointing buffer. Upon completion of the checkpointing recovery, the program resumes its normal Prior research has investigated hardware-based checkpointing [5,31,46] and software-only checkpointing [11,12,35,39,50,62]. Hardware-based schemes rely on hardware support to buffer checkpointing states and facilitate recovery.…”

Section: Checkpointing Basicsmentioning

confidence: 99%

“…However, existing software-only checkpointing schemes suffer from prohibitive overhead by copying a large amount of memory at runtime. These schemes often employ heavy-weight checkpointing processes that operate at the application level [11,12], operating system level [34,39,50] or virtual-machine level [62]. They focus on providing software checkpointing service to enhance system robustness and reliability, thus performance of checkpoint-enabled applications is not the primary concern.…”

Section: Checkpointing Basicsmentioning

confidence: 99%

“…A solution needs to protect such long-running programs from hardware failures and minimize service interruptions. Bronevetsky et al [11,12] proposed using compiler techniques to implement an application-level, non-blocking, coordinated global checkpointing solution for MPI-based programs on distributed-memory parallel computing clusters. The source program is preprocessed by a compiler where manually annotated checkpoint macros are converted into checkpoint library calls.…”

Section: Software-only Checkpointingmentioning

confidence: 99%

See 2 more Smart Citations

Compiler Support for Fine-Grain Software-Only Checkpointing

Zhao

Steffan

Amza

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We explore three application areas for our fine-grain checkpointing support. First, we utilize our efficient software-only checkpointing to support overlapping execution with delinquent loads through ii the prototyping and evaluation of both control-speculation and data-speculation transformations. We further propose a theoretical timing model and confirm its effectiveness with a real-machine workload.Second, we investigate its application to debugging, in particular by providing the ability for a debugger to rewind to an arbitrarily-placed point within the execution of a buggy program. A study using BugBench applications shows that our compiler-based fine-grain checkpointing has more than a factor of 100 less overhead than full-process, unoptimized checkpointing. Finally, we demonstrate that compilerbased checkpointing support can be leveraged to free the programmer from manually implementing and maintaining detailed software rollback mechanisms when coding a backtracking algorithm for a realistic CAD application, with runtime overhead of only 15% compared to the manual implementation.iii

show abstract

Section: Checkpointing Basicsmentioning

confidence: 99%

Section: Checkpointing Basicsmentioning

confidence: 99%

Section: Software-only Checkpointingmentioning

confidence: 99%

See 1 more Smart Citation

Compiler Support for Fine-Grain Software-Only Checkpointing

Zhao

Steffan

Amza

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…With MemCheckPoint stores are not commit points and memory can be corrupted with wrong values. Thus, a mechanism for memory checkpointing either in software [4] or in hardware, such as ReVive [24] …”

Section: Knobsmentioning

confidence: 99%

ESoftCheck: Removal of Non-vital Checks for Fault Tolerance

Garzarán

Snir

2009

2009 International Symposium on Code Generation and Optimization

View full text Add to dashboard Cite

Abstract-As semiconductor technology scales into the deep submicron regime the occurrence of transient or soft errors will increase. This will require new approaches to error detection. Software checking approaches are attractive because they require little hardware modification and can be easily adjusted to fit different reliability and performance requirements. Unfortunately, software checking adds a significant performance overhead.In this paper we present ESoftCheck, a set of compiler optimization techniques to determine which are the vital checks, that is, the minimum number of checks that are necessary to detect an error and roll back to a correct program state. ESoftCheck identifies the vital checks on platforms where registers are hardware-protected with parity or ECC, when there are redundant checks and when checks appear in loops. ESoftCheck also provides knobs to trade reliability for performance based on the support for recovery and the degree of trustiness of the operations. Our experimental results on a Pentium 4 show that ESoftCheck can obtain 27.1% performance improvement without losing fault coverage.

show abstract

“…Another effort to tackle the non-FIFO is Message Tagging [4,18]. The idea behind Message Tagging is that the system wraps some additional information onto the outgoing messages, which is called header.…”

Section: Chandy-lamport Algorithmmentioning

confidence: 99%

Event Logging: Portable and Efficient Checkpointing in Heterogeneous Environments with Non-FIFO Communication Platforms

Lastovetsky

19th IEEE International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

show abstract

Compiler-Enhanced Incremental Checkpointing

Cited by 10 publications

References 4 publications

Compiler Support for Fine-Grain Software-Only Checkpointing

Compiler Support for Fine-Grain Software-Only Checkpointing

ESoftCheck: Removal of Non-vital Checks for Fault Tolerance

Event Logging: Portable and Efficient Checkpointing in Heterogeneous Environments with Non-FIFO Communication Platforms

Contact Info

Product

Resources

About