9 September 2023 in ACM Transactions on Embedded Computing Systems
Healthcare is a pivotal research field, and medical imaging is crucial in many applications. Therefore finding new architectural and algorithmic solutions would benefit highly repetitive image processing procedures. One of the most complex tasks in this sense is image registration, which finds the optimal geometric alignment among 3D image stacks and is widely employed in healthcare and robotics. Given the high computational demand of such a procedure, hardware accelerators are promising real-time and energy-efficient solutions, but they are complex to design and integrate within software pipelines. Therefore, this work presents an automation framework called Hephaestus that generates efficient 3D image registration pipelines combined with reconfigurable accelerators. Moreover, to alleviate the burden from the software, we codesign software-programmable accelerators that can adapt at run-time to the image volume dimensions. Hephaestus features a cross-platform abstraction layer that enables transparently high-performance and embedded systems deployment. However, given the computational complexity of 3D image registration, the embedded devices become a relevant and complex setting being constrained in memory; thus, they require further attention and tailoring of the accelerators and registration application to reach satisfactory results. Therefore, with Hephaestus , we also propose an approximation mechanism that enables such devices to perform the 3D image registration and even achieve, in some cases, the accuracy of the high-performance ones. Overall, Hephaestus demonstrates 1.85× of maximum speedup, 2.35× of efficiency improvement with respect to the State of the Art, a maximum speedup of 2.51× and 2.76× efficiency improvements against our software, while attaining state-of-the-art accuracy on 3D registrations.
18 August 2025 in ACM Transactions on Reconfigurable Technology and Systems
Quantum computing is a new paradigm of computation that exploits principles from quantum mechanics to achieve an exponential speedup compared to classical logic. However, noise strongly limits current quantum hardware, reducing achievable performance and limiting the scaling of the applications. For this reason, current noisy intermediate-scale quantum devices require Quantum Error Correction (QEC) mechanisms to identify errors occurring in the computation and correct them in real time. Nevertheless, the high computational complexity of QEC algorithms is incompatible with the tight time constraints of quantum devices. Thus, hardware acceleration is paramount to achieving real-time QEC. This work presents QASBA, an FPGA-based hardware accelerator for the Sparse Blossom Algorithm (SBA), a state-of-the-art decoding algorithm. After profiling the state-of-the-art software counterpart, we developed a design methodology for hardware development based on the SBA. We also devised an automation process to help users without expertise in hardware design in deploying architectures based on QASBA. We implement QASBA on different FPGA architectures and experimentally evaluate resource usage, execution time, and energy efficiency of our solution. Our solution attains up to \(25.05\times\) speedup and \(304.16\times\) improvement in energy efficiency compared to the software baseline.
4 August 2025 in IEEE Transactions on Quantum Engineering
The Boolean matching problem via NP-equivalence requires determining whether two Boolean functions are equivalent or not up to a permutation and negation of the input binary variables. Its solution is a fundamental step in the electronic design automation (EDA) tool chains commonly used for digital circuit design. In fact, the library-mapping step of an EDA workflow requires matching parts of the gate-level design (netlist) with the components available in a technology library, considering them as Boolean functions, while taking into account that permutations and negations of input variables can be efficiently implemented through rewiring and the use of inverters. For $n$-to-$n$ vector Boolean functions, where $n$ is the number of input and output variables, the search space of possible negations and permutations is super-exponential in size, while the $\mathcal {O}(n!n2^{2n})$ time complexity of classical approaches allows solving only small instances of the NP-problem, often limited to $n$-to-1 Boolean functions (executing $\mathcal {O}(n!2^{2n})$ bit operations). This work presents a quantum algorithm for matching $n$-to-$n$ vector Boolean functions by effectively combining the Grover-meets-Simon approach with an original and novel use of the Simon solver without the constraints imposed by its usual premises. We provide a fully detailed quantum circuit implementing our proposal, calculate its cost by evaluating key performance indicators for circuit synthesis, and show an exponential speedup over classical solutions. Finally, we validate our approach on the Boolean functions included in the ISCAS benchmark suite, which are of practical interest in EDA.