% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Bhattacharya:1038334,
      author       = {Bhattacharya, Tinish and Hutchinson, George H. and
                      Pedretti, Giacomo and Sheng, Xia and Ignowski, Jim and
                      Vaerenbergh, Thomas Van and Beausoleil, Ray and Strachan,
                      John Paul and Strukov, Dmitri B.},
      title        = {{C}omputing high-degree polynomial gradients in memory},
      journal      = {Nature Communications},
      volume       = {15},
      number       = {1},
      issn         = {2041-1723},
      address      = {[London]},
      publisher    = {Springer Nature},
      reportid     = {FZJ-2025-01332},
      pages        = {8211 (2024)},
      year         = {2024},
      abstract     = {Specialized function gradient computing hardware could
                      greatly improve the performance of state-of-the-art
                      optimization algorithms. Prior work on such hardware,
                      performed in the context of Ising Machines and related
                      concepts, is limited to quadratic polynomials and not
                      scalable to commonly used higher-order functions. Here, we
                      propose an approach for massively parallel gradient
                      calculations of high-degree polynomials, which is conducive
                      to efficient mixed-signal in-memory computing circuit
                      implementations and whose area scales proportionally with
                      the product of the number of variables and terms in the
                      function and, most importantly, independent of its degree.
                      Two flavors of such an approach are proposed. The first is
                      limited to binary-variable polynomials typical in
                      combinatorial optimization problems, while the second type
                      is broader at the cost of a more complex periphery. To
                      validate the former approach, we experimentally demonstrated
                      solving a small-scale third-order Boolean satisfiability
                      problem based on integrated metal-oxide memristor crossbar
                      circuits, with competitive heuristics algorithm. Simulation
                      results for larger-scale, more practical problems show
                      orders of magnitude improvements in area, speed and energy
                      efficiency compared to the state-of-the-art. We discuss how
                      our work could enable even higher-performance systems after
                      co-designing algorithms to exploit massively parallel
                      gradient computation.},
      cin          = {PGI-14},
      ddc          = {500},
      cid          = {I:(DE-Juel1)PGI-14-20210412},
      pnm          = {5234 - Emerging NC Architectures (POF4-523) / 5232 -
                      Computational Principles (POF4-523)},
      pid          = {G:(DE-HGF)POF4-5234 / G:(DE-HGF)POF4-5232},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {39294142},
      UT           = {WOS:001315990000007},
      doi          = {10.1038/S41467-024-52488-Y},
      url          = {https://juser.fz-juelich.de/record/1038334},
}