Hardware/software partitioning
Deciding which system functions should execute in hardware and which should remain in software while respecting cost, execution-time, and architectural constraints.
Team · Hardware / software co-design
Adil Iguider
Researcher · Hardware/Software Co-design & Optimization
Adil's research focuses on embedded-system co-design and the hardware/software partitioning problem: how to place computational functions across software and dedicated hardware while optimizing performance, cost, and other system constraints.
At Algorizk
This expertise complements Algorizk's cryptography and formal-methods work by connecting algorithm structure to hardware architecture, FPGA resource trade-offs, and hardware/software boundaries.
Research focus
Optimization methods for systems that cross the software/hardware boundary.
Multi-objective co-design
Optimization methods for balancing competing embedded-system objectives such as hardware area, execution time, and implementation constraints.
Graph and optimization methods
Research using Lagrangian relaxation, shortest-path formulations, minimax methods, knapsack refinement, and heuristic search.
Algorithmic hardware acceleration
Applying co-design reasoning to computational kernels where the boundary between software and FPGA hardware materially affects performance and resource use.
Selected research
Published work on embedded-system HW/SW partitioning.
2021
Shortest Path Method for Hardware/Software Partitioning Problems
International Journal of Information Systems and Social Change
2020
Heuristic algorithms for multi-criteria hardware/software partitioning in embedded systems codesign
Computers & Electrical Engineering 84, 106610
2019
GO Game Inspired Algorithm for Hardware Software Partitioning in Multiprocessor Embedded Systems
Computer and Information Science 12(4), 111–122
2019
Embedded systems hardware software partitioning using minimax algorithm
Smart City Applications
2018
HW/SW Partitioning Algorithms for Multi-objective Optimization in Embedded Systems
International Journal of Information Science and Technology
2017
Embedded Systems HW/SW Partitioning Based on Lagrangian Relaxation Method
Innovations in Smart Cities and Applications
Research → engineering
Hardware/software co-design is directly relevant to cryptographic acceleration.
Modern prover and finite-field workloads are rarely accelerated by moving everything into hardware. The engineering problem is to identify the kernels that justify dedicated hardware, choose data boundaries carefully, and optimize latency, throughput, memory, and FPGA resources as one system.
See Algorizk's workStart a conversation
Have a difficult research problem?
Tell us what you are trying to prove, optimize, or implement. We can begin with a focused technical assessment of the problem, risks, and possible research directions.
Screened inquiries
Submit a concise, non-confidential description through the dedicated project inquiry form.
Direct contact information and a secure communication channel can be provided after the initial inquiry has been reviewed.
Submit a project inquiry