Auto-vectorization of interleaved data for SIMD

D Nuzman, I Rosen, A Zaks - ACM SIGPLAN Notices, 2006 - dl.acm.org
Most implementations of the Single Instruction Multiple Data (SIMD) model available today
require that data elements be packed in vector registers. Operations on disjoint vector …

An empirical study of smart contract decompilers

X Liu, B Hua, Y Wang, Z Pan - 2023 IEEE international …, 2023 - ieeexplore.ieee.org
Smart contract decompilers, converting smart contract bytecode into smart contract source
code, have been used extensively in many scenarios such as binary code analysis, reverse …

Induction variable analysis with delayed abstractions

S Pop, A Cohen, GA Silber - International Conference on High …, 2005 - Springer
This paper presents the design of an induction variable analyzer suitable for the analysis of
typed, low-level, three address representations in SSA form. At the heart of our analyzer is a …

Frozen glass phase in the multi-index matching problem

OC Martin, M Mézard, O Rivoire - Physical review letters, 2004 - APS
The multi-index matching is an NP-hard combinatorial optimization problem; for two indices
it reduces to the well understood bipartite matching problem that belongs to the polynomial …

The SSA representation framework: semantics, analyses and GCC implementation

S Pop - 2006 - pastel.hal.science
The Static Single Assignment (SSA) language is one of the intermediate representations
commonly used in industrial compilers. However, there was little interest from the static …

Improving loop parallelization by a combination of static and dynamic analyses in HLS

F Dewald, J Rohde, C Hochberger… - ACM Transactions on …, 2022 - dl.acm.org
High-level synthesis (HLS) can be used to create hardware accelerators for compute-
intense software parts such as loop structures. Usually, this process requires significant …

Complete inlining of recursive calls: Beyond tail-recursion elimination

P Tang - Proceedings of the 44th annual ACM Southeast …, 2006 - dl.acm.org
A compiler optimizing transformation called complete inlining to inline and eliminate
recursive calls is presented. The complete inlining can eliminate the recursive calls that …

Using GCC analysis techniques to enable parallel memory accesses in HLS

J Rohde, C Hochberger - FSP 2017; Fourth International …, 2017 - ieeexplore.ieee.org
High-Level synthesis typically tries to generate efficient hardware structures starting from
procedural, imperative programming languages like C. Unfortunately, statements in these …

Erbium: Reconciling languages, runtimes, compilation and optimizations for streaming applications

C Miranda - 2013 - theses.hal.science
As transistors size and power limitations stroke computer industry, hardware parallelism
arose as the solution, bringing old forgotten problems back into equation to solve the …

System and method for configuration of an ensemble solver

J Ezick, J Springer, NT Vasilache - US Patent 11,797,894, 2023 - Google Patents
In a system for enabling configuration of an ensemble of several solvers, such that the
ensemble can efficiently solve a constraint problem, for each one of several candidate …