Matches in SemOpenAlex for { <https://semopenalex.org/work/W2492496105> ?p ?o ?g. }
Showing items 1 to 42 of
42
with 100 items per page.
- W2492496105 endingPage "116" @default.
- W2492496105 startingPage "109" @default.
- W2492496105 abstract "Publisher Summary The inverse error function erfinv is a standard component of mathematical libraries, and particularly useful in statistical applications for converting uniform random numbers into Normal random numbers. This chapter presents a new approximation of the erfinv function, which is significantly more efficient for graphics processing units (GPU) execution due to the greatly reduced warp divergence. It also illustrates the cost of warp divergence, and the way in which it can sometimes be avoided by redesigning algorithms and approximations which were originally developed for conventional CPUs. Further, it discusses the dilemma which can face library developers. Whether the new double precision approximations are viewed as better than the existing ones depends on how they are likely to be used. For random inputs they are up to three times faster, but they can also be slower when the inputs within each warp are all identical, or vary very little." @default.
- W2492496105 created "2016-08-23" @default.
- W2492496105 creator A5056186758 @default.
- W2492496105 date "2012-01-01" @default.
- W2492496105 modified "2023-09-27" @default.
- W2492496105 title "Approximating the erfinv Function" @default.
- W2492496105 cites W1970767055 @default.
- W2492496105 cites W779002 @default.
- W2492496105 doi "https://doi.org/10.1016/b978-0-12-385963-1.00010-1" @default.
- W2492496105 hasPublicationYear "2012" @default.
- W2492496105 type Work @default.
- W2492496105 sameAs 2492496105 @default.
- W2492496105 citedByCount "8" @default.
- W2492496105 countsByYear W24924961052017 @default.
- W2492496105 countsByYear W24924961052018 @default.
- W2492496105 countsByYear W24924961052020 @default.
- W2492496105 countsByYear W24924961052023 @default.
- W2492496105 crossrefType "book-chapter" @default.
- W2492496105 hasAuthorship W2492496105A5056186758 @default.
- W2492496105 hasBestOaLocation W24924961052 @default.
- W2492496105 hasConcept C41008148 @default.
- W2492496105 hasConceptScore W2492496105C41008148 @default.
- W2492496105 hasLocation W24924961051 @default.
- W2492496105 hasLocation W24924961052 @default.
- W2492496105 hasOpenAccess W2492496105 @default.
- W2492496105 hasPrimaryLocation W24924961051 @default.
- W2492496105 hasRelatedWork W2093578348 @default.
- W2492496105 hasRelatedWork W2350741829 @default.
- W2492496105 hasRelatedWork W2358668433 @default.
- W2492496105 hasRelatedWork W2376932109 @default.
- W2492496105 hasRelatedWork W2382290278 @default.
- W2492496105 hasRelatedWork W2390279801 @default.
- W2492496105 hasRelatedWork W2748952813 @default.
- W2492496105 hasRelatedWork W2766271392 @default.
- W2492496105 hasRelatedWork W2899084033 @default.
- W2492496105 hasRelatedWork W3004735627 @default.
- W2492496105 isParatext "false" @default.
- W2492496105 isRetracted "false" @default.
- W2492496105 magId "2492496105" @default.
- W2492496105 workType "book-chapter" @default.