FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3016562408> ?p ?o ?g. }

• W3016562408 abstract "GPUs are a key enabler of the revolution in machine learning and high performance computing, functioning as de facto co-processors to accelerate large-scale computation. As the programming stack and tool support have matured, GPUs have also become accessible to programmers, who may lack detailed knowledge of the underlying architecture and fail to fully leverage the GPU's computation power. GEVO (Gpu optimization using EVOlutionary computation) is a tool for automatically discovering optimization opportunities and tuning the performance of GPU kernels in the LLVM representation. GEVO uses population-based search to find edits to GPU code compiled to LLVM-IR and improves performance on desired criteria while retaining required functionality. We demonstrate that GEVO improves the execution time of the GPU programs in the Rodinia benchmark suite and the machine learning models, SVM and ResNet18, on NVIDIA Tesla P100. For the Rodinia benchmarks, GEVO improves GPU kernel runtime performance by an average of 49.48% and by as much as 412% over the fully compiler-optimized baseline. If kernel output accuracy is relaxed to tolerate up to 1% error, GEVO can find kernel variants that outperform the baseline version by an average of 51.08%. For the machine learning workloads, GEVO achieves kernel performance improvement for SVM on the MNIST handwriting recognition (3.24X) and the a9a income prediction (2.93X) datasets with no loss of model accuracy. GEVO achieves 1.79X kernel performance improvement on image classification using ResNet18/CIFAR-10, with less than 1% model accuracy reduction." @default.
• W3016562408 created "2020-04-24" @default.
• W3016562408 creator A5028220093 @default.
• W3016562408 creator A5040205022 @default.
• W3016562408 creator A5045603380 @default.
• W3016562408 creator A5068526197 @default.
• W3016562408 date "2020-04-17" @default.
• W3016562408 modified "2023-09-25" @default.
• W3016562408 title "GEVO: GPU Code Optimization using Evolutionary Computation" @default.
• W3016562408 cites W1480909796 @default.
• W3016562408 cites W1524336136 @default.
• W3016562408 cites W1568229137 @default.
• W3016562408 cites W157468466 @default.
• W3016562408 cites W1758861635 @default.
• W3016562408 cites W1815597787 @default.
• W3016562408 cites W1966533006 @default.
• W3016562408 cites W1979660747 @default.
• W3016562408 cites W1980199047 @default.
• W3016562408 cites W1992208469 @default.
• W3016562408 cites W1992851788 @default.
• W3016562408 cites W1994197834 @default.
• W3016562408 cites W2001936191 @default.
• W3016562408 cites W201139614 @default.
• W3016562408 cites W2019313821 @default.
• W3016562408 cites W2020572638 @default.
• W3016562408 cites W2034102265 @default.
• W3016562408 cites W2057156093 @default.
• W3016562408 cites W2061719199 @default.
• W3016562408 cites W2062452378 @default.
• W3016562408 cites W2062918259 @default.
• W3016562408 cites W2069265488 @default.
• W3016562408 cites W2078391824 @default.
• W3016562408 cites W2079664326 @default.
• W3016562408 cites W2084178119 @default.
• W3016562408 cites W2097998348 @default.
• W3016562408 cites W2102539288 @default.
• W3016562408 cites W2104560855 @default.
• W3016562408 cites W2106683494 @default.
• W3016562408 cites W2107262494 @default.
• W3016562408 cites W2111935653 @default.
• W3016562408 cites W2112617148 @default.
• W3016562408 cites W2112796928 @default.
• W3016562408 cites W2114012357 @default.
• W3016562408 cites W2116672403 @default.
• W3016562408 cites W2117689653 @default.
• W3016562408 cites W2119814172 @default.
• W3016562408 cites W2121344286 @default.
• W3016562408 cites W2122233197 @default.
• W3016562408 cites W2122433740 @default.
• W3016562408 cites W2122947685 @default.
• W3016562408 cites W2126071695 @default.
• W3016562408 cites W2126105956 @default.
• W3016562408 cites W2132473764 @default.
• W3016562408 cites W2133297674 @default.
• W3016562408 cites W2135026800 @default.
• W3016562408 cites W2142883190 @default.
• W3016562408 cites W2143161696 @default.
• W3016562408 cites W2145124323 @default.
• W3016562408 cites W2145373440 @default.
• W3016562408 cites W2151497118 @default.
• W3016562408 cites W2153635508 @default.
• W3016562408 cites W2160145830 @default.
• W3016562408 cites W2162036626 @default.
• W3016562408 cites W2162960800 @default.
• W3016562408 cites W2163605009 @default.
• W3016562408 cites W2163671349 @default.
• W3016562408 cites W2164918225 @default.
• W3016562408 cites W2171476591 @default.
• W3016562408 cites W2186615578 @default.
• W3016562408 cites W2292282166 @default.
• W3016562408 cites W2294628582 @default.
• W3016562408 cites W2402144811 @default.
• W3016562408 cites W2527855935 @default.
• W3016562408 cites W2551286567 @default.
• W3016562408 cites W2553303224 @default.
• W3016562408 cites W2554131156 @default.
• W3016562408 cites W2557728737 @default.
• W3016562408 cites W2594529350 @default.
• W3016562408 cites W2604766223 @default.
• W3016562408 cites W2620219518 @default.
• W3016562408 cites W2625200202 @default.
• W3016562408 cites W2735592989 @default.
• W3016562408 cites W2735771726 @default.
• W3016562408 cites W2767002384 @default.
• W3016562408 cites W2768116780 @default.
• W3016562408 cites W2782213427 @default.
• W3016562408 cites W2782417188 @default.
• W3016562408 cites W2785366763 @default.
• W3016562408 cites W2794670651 @default.
• W3016562408 cites W2798341898 @default.
• W3016562408 cites W2799953961 @default.
• W3016562408 cites W2804032941 @default.
• W3016562408 cites W2884166449 @default.
• W3016562408 cites W2885820039 @default.
• W3016562408 cites W2899771611 @default.
• W3016562408 cites W2951104886 @default.
• W3016562408 cites W2951781666 @default.
• W3016562408 cites W2952332632 @default.
• W3016562408 cites W2954767663 @default.
• W3016562408 cites W2962750597 @default.

• next