FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100537219> ?p ?o ?g. }

• W3100537219 abstract "CPU simulators are useful tools for modeling CPU execution behavior. However, they suffer from inaccuracies due to the cost and complexity of setting their fine-grained parameters, such as the latencies of individual instructions. This complexity arises from the expertise required to design benchmarks and measurement frameworks that can precisely measure the values of parameters at such fine granularity. In some cases, these parameters do not necessarily have a physical realization and are therefore fundamentally approximate, or even unmeasurable. In this paper we present DiffTune, a system for learning the parameters of x86 basic block CPU simulators from coarse-grained end-to-end measurements. Given a simulator, DiffTune learns its parameters by first replacing the original simulator with a differentiable surrogate, another function that approximates the original function; by making the surrogate differentiable, DiffTune is then able to apply gradient-based optimization techniques even when the original function is non-differentiable, such as is the case with CPU simulators. With this differentiable surrogate, DiffTune then applies gradient-based optimization to produce values of the simulator's parameters that minimize the simulator's error on a dataset of ground truth end-to-end performance measurements. Finally, the learned parameters are plugged back into the original simulator. DiffTune is able to automatically learn the entire set of microarchitecture-specific parameters within the Intel x86 simulation model of llvm-mca, a basic block CPU simulator based on LLVM's instruction scheduling model. DiffTune's learned parameters lead llvm-mca to an average error that not only matches but lowers that of its original, expert-provided parameter values." @default.
• W3100537219 created "2020-11-23" @default.
• W3100537219 creator A5034476447 @default.
• W3100537219 creator A5043695340 @default.
• W3100537219 creator A5053008951 @default.
• W3100537219 creator A5091194125 @default.
• W3100537219 date "2020-10-01" @default.
• W3100537219 modified "2023-09-30" @default.
• W3100537219 title "DiffTune: Optimizing CPU Simulator Parameters with Learned Differentiable Surrogates" @default.
• W3100537219 cites W1984753492 @default.
• W3100537219 cites W1994616650 @default.
• W3100537219 cites W2063884320 @default.
• W3100537219 cites W2064675550 @default.
• W3100537219 cites W2100218206 @default.
• W3100537219 cites W2113167168 @default.
• W3100537219 cites W2119717200 @default.
• W3100537219 cites W2138146350 @default.
• W3100537219 cites W2147657366 @default.
• W3100537219 cites W2157070686 @default.
• W3100537219 cites W2170467352 @default.
• W3100537219 cites W2295283246 @default.
• W3100537219 cites W2794800068 @default.
• W3100537219 cites W2897675008 @default.
• W3100537219 cites W2963674831 @default.
• W3100537219 cites W3011000655 @default.
• W3100537219 cites W3015480182 @default.
• W3100537219 cites W3024161604 @default.
• W3100537219 cites W3033227568 @default.
• W3100537219 cites W3033482053 @default.
• W3100537219 cites W3103041597 @default.
• W3100537219 cites W3125750521 @default.
• W3100537219 cites W4245923077 @default.
• W3100537219 cites W4246166885 @default.
• W3100537219 doi "https://doi.org/10.1109/micro50266.2020.00045" @default.
• W3100537219 hasPublicationYear "2020" @default.
• W3100537219 type Work @default.
• W3100537219 sameAs 3100537219 @default.
• W3100537219 citedByCount "12" @default.
• W3100537219 countsByYear W31005372192020 @default.
• W3100537219 countsByYear W31005372192021 @default.
• W3100537219 countsByYear W31005372192022 @default.
• W3100537219 countsByYear W31005372192023 @default.
• W3100537219 crossrefType "proceedings-article" @default.
• W3100537219 hasAuthorship W3100537219A5034476447 @default.
• W3100537219 hasAuthorship W3100537219A5043695340 @default.
• W3100537219 hasAuthorship W3100537219A5053008951 @default.
• W3100537219 hasAuthorship W3100537219A5091194125 @default.
• W3100537219 hasBestOaLocation W31005372192 @default.
• W3100537219 hasConcept C111919701 @default.
• W3100537219 hasConcept C134306372 @default.
• W3100537219 hasConcept C14036430 @default.
• W3100537219 hasConcept C170723468 @default.
• W3100537219 hasConcept C173608175 @default.
• W3100537219 hasConcept C177774035 @default.
• W3100537219 hasConcept C201203610 @default.
• W3100537219 hasConcept C202615002 @default.
• W3100537219 hasConcept C2524010 @default.
• W3100537219 hasConcept C2777210771 @default.
• W3100537219 hasConcept C2777904410 @default.
• W3100537219 hasConcept C33923547 @default.
• W3100537219 hasConcept C41008148 @default.
• W3100537219 hasConcept C44154836 @default.
• W3100537219 hasConcept C49154492 @default.
• W3100537219 hasConcept C78458016 @default.
• W3100537219 hasConcept C86803240 @default.
• W3100537219 hasConcept C9390403 @default.
• W3100537219 hasConceptScore W3100537219C111919701 @default.
• W3100537219 hasConceptScore W3100537219C134306372 @default.
• W3100537219 hasConceptScore W3100537219C14036430 @default.
• W3100537219 hasConceptScore W3100537219C170723468 @default.
• W3100537219 hasConceptScore W3100537219C173608175 @default.
• W3100537219 hasConceptScore W3100537219C177774035 @default.
• W3100537219 hasConceptScore W3100537219C201203610 @default.
• W3100537219 hasConceptScore W3100537219C202615002 @default.
• W3100537219 hasConceptScore W3100537219C2524010 @default.
• W3100537219 hasConceptScore W3100537219C2777210771 @default.
• W3100537219 hasConceptScore W3100537219C2777904410 @default.
• W3100537219 hasConceptScore W3100537219C33923547 @default.
• W3100537219 hasConceptScore W3100537219C41008148 @default.
• W3100537219 hasConceptScore W3100537219C44154836 @default.
• W3100537219 hasConceptScore W3100537219C49154492 @default.
• W3100537219 hasConceptScore W3100537219C78458016 @default.
• W3100537219 hasConceptScore W3100537219C86803240 @default.
• W3100537219 hasConceptScore W3100537219C9390403 @default.
• W3100537219 hasFunder F4320306076 @default.
• W3100537219 hasFunder F4320332815 @default.
• W3100537219 hasLocation W31005372191 @default.
• W3100537219 hasLocation W31005372192 @default.
• W3100537219 hasLocation W31005372193 @default.
• W3100537219 hasOpenAccess W3100537219 @default.
• W3100537219 hasPrimaryLocation W31005372191 @default.
• W3100537219 hasRelatedWork W1756061458 @default.
• W3100537219 hasRelatedWork W2092389159 @default.
• W3100537219 hasRelatedWork W2359802300 @default.
• W3100537219 hasRelatedWork W2362309373 @default.
• W3100537219 hasRelatedWork W2554083593 @default.
• W3100537219 hasRelatedWork W2946327134 @default.
• W3100537219 hasRelatedWork W3092461782 @default.
• W3100537219 hasRelatedWork W3100537219 @default.
• W3100537219 hasRelatedWork W4238301398 @default.

• next