2 Hits in 3.0 sec

Swizzle Inventor

Phitchaya Mangpo Phothilimthana, Rastislav Bodik, Archibald Samuel Elliott, An Wang, Abhinav Jangda, Bastian Hagedorn, Henrik Barthels, Samuel J. Kaufman, Vinod Grover, Emina Torlak
2019 Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS '19  
Our synthesis algorithm scales to real-world programs, allowing us to invent new GPU kernels for stencil computations, matrix transposition, and a finite field multiplication algorithm (used in cryptographic  ...  We develop Swizzle Inventor to help programmers implement swizzle programs, by writing program sketches that omit swizzles and delegating their creation to an automatic synthesizer.  ...  [3] for helping us to reproduce their results, and Uday Bondhugula and Albert Cohen for a discussion of polyhedral compilation.  ... 
doi:10.1145/3297858.3304059 dblp:conf/asplos/PhothilimthanaE19 fatcat:32utummparetfj33zz6hbnotsm

Porcupine: A Synthesizing Compiler for Vectorized Homomorphic Encryption [article]

Meghan Cowan, Deeksha Dangwal, Armin Alaghi, Caroline Trippel, Vincent T. Lee, Brandon Reagen
2021 arXiv   pre-print
Homomorphic encryption (HE) is a privacy-preserving technique that enables computation directly on encrypted data.  ...  We evaluate Procupine using a set of kernels and show speedups of up to 51% (11% geometric mean) compared to heuristic-driven hand-optimized kernels.  ...  Swizzle Inventor [32] synthesized optimized data movement for GPU kernels from a sketch that specified that computation strategy and left data movement unspecified.  ... 
arXiv:2101.07841v1 fatcat:lpi5byepkreqnfag4u2aod3y6e