A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is
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. ...  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
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  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