000198208 001__ 198208
000198208 005__ 20190316235907.0
000198208 037__ $$aREP_WORK
000198208 245__ $$aMulti-Lane FlowPools: A Detailed Look
000198208 269__ $$a2012
000198208 260__ $$c2012
000198208 300__ $$a13
000198208 336__ $$aReports
000198208 520__ $$aFlowPools, proposed by are a powerful way to express dataflow logic in highly parallelized applications. The original paper proposes two ways of implementing a FlowPool: Single-Lane FlowPools (SLFP) and Multi-Lane FlowPools (MLFP). While SLFPs showed decent performance overall, insertion operations do not scale. MLFPs solve this limitation as benchmarks discussed in have shown. This report goes into the details of the implementation of MLFPs and lies out the benchmarking results to show that MLFPs may reduce insertion time by 49 - 54% on a 4-core i7 machine with respect to comparable concurrent queue data structures in the Java standard library.
000198208 6531_ $$adataflow
000198208 6531_ $$aconcurrent queues
000198208 6531_ $$alock-free
000198208 700__ $$0247866$$aSchlatter, Tobias$$g184229
000198208 700__ $$0244134$$aProkopec, Aleksandar$$g191413
000198208 700__ $$0242185$$aMiller, Heather$$g191683
000198208 700__ $$0240993$$aHaller, Philipp$$g172057
000198208 700__ $$0241835$$aOdersky, Martin$$g126003
000198208 8564_ $$s1169836$$uhttps://infoscience.epfl.ch/record/198208/files/tobias-schlatter-multilane-flowpools.pdf$$yn/a$$zn/a
000198208 909C0 $$0252187$$pLAMP$$xU10409
000198208 909CO $$ooai:infoscience.tind.io:198208$$pIC$$preport$$qGLOBAL_SET
000198208 917Z8 $$x191413
000198208 937__ $$aEPFL-REPORT-198208
000198208 973__ $$aEPFL
000198208 980__ $$aREPORT