Flexible on-stack replacement in LLVM

D’Elia, Daniele Cono; Demetrescu, Camil

doi:10.1145/2854038.2854061

Cited by 16 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To support compilers in applying OSR for unstructured languages we proposed reconstructing and extracting loops. D'Elia and Demetrescu [3] conducted a case study on how to implement function-level on-stack replacement for LLVM at arbitrary points, by using glue code to facilitate a smooth transition between the two versions of a function. In their recent work they focused on a more abstract view on OSR in the context of code transformation [4].…”

Section: Related Workmentioning

confidence: 99%

Supporting on-stack replacement in unstructured languages by loop reconstruction and extraction

Mosaner¹,

Leopoldseder²,

Rigger

et al. 2019

Proceedings of the 16th ACM SIGPLAN International Conference on Managed Programming Languages and Runtimes

View full text Add to dashboard Cite

On-stack replacement (OSR) is a common technique employed by dynamic compilers to reduce program warm-up time. OSR allows switching from interpreted to compiled code during the execution of this code. The main targets are long running loops, which need to be represented explicitly, with dedicated information about condition and body, to be optimized at run time. Bytecode interpreters, however, represent control flow implicitly via unstructured jumps and thus do not exhibit the required high-level loop representation. To enable OSR also for jump-based-often called unstructuredlanguages, we propose the partial reconstruction of loops in order to explicitly represent them in a bytecode interpreter. Besides an outline of the general idea, we implemented our approach in Sulong, a bytecode interpreter for LLVM bitcode, which allows the execution of C/C++. We conducted an evaluation with a set of C benchmarks, which showed speed-ups in warm-up of up to 9x for certain benchmarks. This facilitates execution of programs with long-running loops in rarely called functions, which would yield significant slowdown without OSR. While shown with a prototype implementation, the overall idea of our approach is generalizable for all bytecode interpreters.

show abstract

Section: Related Workmentioning

confidence: 99%

Supporting on-stack replacement in unstructured languages by loop reconstruction and extraction

Mosaner¹,

Leopoldseder²,

Rigger

et al. 2019

Proceedings of the 16th ACM SIGPLAN International Conference on Managed Programming Languages and Runtimes

View full text Add to dashboard Cite

show abstract

“…Another usage of OSR is for obfuscation [13]. Some work are made to introduce frameworks with well defined APIs for OSR [7,2].…”

Section: Related Workmentioning

confidence: 99%

Towards automatic binary runtime loop de-parallelization using on-stack replacement

Yusuf

El-Mahdy

Rohou

2019

Information Processing Letters

View full text Add to dashboard Cite

Runtime compilation has opportunities to parallelize code which are generally not available using static parallelization approaches. However, the parallelized code can possibly slowdown the performance due to unforeseen parallel overheads such as synchronization and speculation support pertaining to the chosen parallelization strategy and the underlying parallel platform. Moreover, with the wide usage of heterogeneous architectures, such choice options become more pronounced. In this paper, we consider an adaptive form of the parallelization operation, for the first time. We propose a method for performing on-stack de-parallelization for a parallelized binary loop at runtime, thereby allowing for rapid loop replacement with a more optimized one. For this paper, we consider a loop parallelization strategy and propose a corresponding de-parallelization method. The method relies on stopping the execution at safe points, gathering threads' states, producing a corresponding serial code, and continuing execution serially. The decision to deparallelize or not is taken based on the anticipated speedup. To assess the extent of our approach, we have conducted an initial study on a small set of programs with various parallelization overheads. Results show up to 4× performance improvement for a synchronization intense program on a 4-core Intel processor.

show abstract

“…Consider V8. During de-optimization, V8 first generates the contents of new stack frames in temporary buffers in the 4 Following the convention of Dolan et al [5], we use Swapstack (Small Caps) to denote the abstract operation, and use SWAPSTACK (ALL CAPS) for the concrete instruction in the Mu instruction set. 5 Therefore, in our terminology, the Boost.Context library [14], the (deprecated) swapcontext POSIX function, as well as the LLVM primitive created by Dolan et al [5], are all implementations of Swapstack, although the work of Dolan et al [5] usually out-performs others because it only saves as many registers as necessary.…”

Section: Osr Without Swapstackmentioning

confidence: 99%

“…However, in the typical runtime re-compilation scenario, the new frame must resume at the program counter equivalent to where the old frame stopped. Fink and Qian [7] solved this problem by inserting assignments and a jump instruction at the beginning of the new function, as follows: [4] call these instructions 'compensation code'. The assignments set local variables of the new frame to their values in the old frame, and the jump instruction jumps to the equivalent PC.…”

Section: Creating New Frames Using Return-orientedmentioning

confidence: 99%

See 1 more Smart Citation

Hop, Skip, & Jump

WangKunshan¹,

Blackburn²,

Hosking³

et al. 2018

SIGPLAN Not.

View full text Add to dashboard Cite

On-stack replacement (OSR) is a performance-critical technology for many languages, especially dynamic languages. Conventional wisdom, apparent in JavaScript engines such as V8 and SpiderMonkey, is that OSR must be implemented in a low-level (i.e., in assembly) and language-specific way. This paper presents an OSR abstraction based on Swapstack, materialized as the API for a low-level virtual machine, and shows how the abstraction of resumption protocols facilitates an elegant implementation of this API on real hardware. Using an experimental JavaScript implementation, we demonstrate that this API enables the language implementation to perform OSR without the need to deal with machine-level details. We also show that the API itself is implementable on concrete hardware. This work helps crystallize OSR abstractions and, by providing a reusable implementation, brings OSR within reach for more language implementers.

show abstract

Flexible on-stack replacement in LLVM

Cited by 16 publications

References 13 publications

Supporting on-stack replacement in unstructured languages by loop reconstruction and extraction

Supporting on-stack replacement in unstructured languages by loop reconstruction and extraction

Towards automatic binary runtime loop de-parallelization using on-stack replacement

Hop, Skip, & Jump

Contact Info

Product

Resources

About