Matches in SemOpenAlex for { <https://semopenalex.org/work/W3007797378> ?p ?o ?g. }
- W3007797378 endingPage "991" @default.
- W3007797378 startingPage "980" @default.
- W3007797378 abstract "Memory subsystems are a major energy bottleneck in computing platforms due to frequent transfers between processors and off-chip memory. We propose approximate memory compression, a technique that leverages the intrinsic resilience of emerging workloads such as machine learning and data analytics to reduce off-chip memory traffic, thereby improving energy and performance. We realize approximate memory compression by enhancing the memory controller to be aware of approximate memory regions-regions in memory that contain approximation-resilient data-and to transparently compress (decompress) the data written to (read from) these regions. To provide control over approximations, each approximate memory region is associated with an error constraint such as the maximum error that may be introduced in each data element. The quality-aware memory controller subjects memory transactions to a compression scheme that introduces approximations, thereby reducing memory traffic, while adhering to the specified error constraint for each approximate memory region. A software interface is provided to allow programmers to identify data structures (DSs) that are resilient to approximations. A runtime quality control framework automatically determines the error constraints for the identified DSs such that a given target application-level quality is maintained. We evaluate our proposal by applying it to three different main memory technologies in the context of a general-purpose computing system-DDR3 DRAM, LPDDR3 DRAM, and spin-transfer torque magnetic RAM (STT-MRAM). To demonstrate the feasibility of the proposed concepts, we also implement a hardware prototype using the Intel UniPHY-DDR3 memory controller and Nios-II processor, a Hynix DDR3 DRAM module, and a Stratix-IV field-programmable gate array (FPGA) development board. Across a wide range of machine learning benchmarks, approximate memory compression obtains significant benefits in main memory energy (1.18× for DDR3 DRAM, 1.52× for LPDDR3 DRAM, and 2.0× for STT-MRAM) and a simultaneous improvement in execution time (5.2% for DDR3 DRAM, 5.4% for LPDDR3 DRAM, and 9.3% for STT-MRAM) with nearly identical application output quality." @default.
- W3007797378 created "2020-03-06" @default.
- W3007797378 creator A5047643363 @default.
- W3007797378 creator A5065766721 @default.
- W3007797378 creator A5066464351 @default.
- W3007797378 creator A5089217343 @default.
- W3007797378 date "2020-04-01" @default.
- W3007797378 modified "2023-09-29" @default.
- W3007797378 title "Approximate Memory Compression" @default.
- W3007797378 cites W1851732076 @default.
- W3007797378 cites W1985148487 @default.
- W3007797378 cites W2003777196 @default.
- W3007797378 cites W2006198238 @default.
- W3007797378 cites W2020517863 @default.
- W3007797378 cites W2025632321 @default.
- W3007797378 cites W2026005150 @default.
- W3007797378 cites W2030922317 @default.
- W3007797378 cites W2041420601 @default.
- W3007797378 cites W2046531456 @default.
- W3007797378 cites W2052201685 @default.
- W3007797378 cites W2053709612 @default.
- W3007797378 cites W2091434413 @default.
- W3007797378 cites W2097243222 @default.
- W3007797378 cites W2122636510 @default.
- W3007797378 cites W2131017271 @default.
- W3007797378 cites W2131413854 @default.
- W3007797378 cites W2147657366 @default.
- W3007797378 cites W2147926533 @default.
- W3007797378 cites W2171894735 @default.
- W3007797378 cites W2231875869 @default.
- W3007797378 cites W2237415205 @default.
- W3007797378 cites W2244005500 @default.
- W3007797378 cites W2293281321 @default.
- W3007797378 cites W2474451066 @default.
- W3007797378 cites W2565435739 @default.
- W3007797378 cites W2593172471 @default.
- W3007797378 cites W2742847738 @default.
- W3007797378 cites W2743069335 @default.
- W3007797378 cites W4236372686 @default.
- W3007797378 cites W4248591063 @default.
- W3007797378 cites W4249176607 @default.
- W3007797378 cites W4313016175 @default.
- W3007797378 doi "https://doi.org/10.1109/tvlsi.2020.2970041" @default.
- W3007797378 hasPublicationYear "2020" @default.
- W3007797378 type Work @default.
- W3007797378 sameAs 3007797378 @default.
- W3007797378 citedByCount "7" @default.
- W3007797378 countsByYear W30077973782020 @default.
- W3007797378 countsByYear W30077973782021 @default.
- W3007797378 countsByYear W30077973782022 @default.
- W3007797378 countsByYear W30077973782023 @default.
- W3007797378 crossrefType "journal-article" @default.
- W3007797378 hasAuthorship W3007797378A5047643363 @default.
- W3007797378 hasAuthorship W3007797378A5065766721 @default.
- W3007797378 hasAuthorship W3007797378A5066464351 @default.
- W3007797378 hasAuthorship W3007797378A5089217343 @default.
- W3007797378 hasBestOaLocation W30077973781 @default.
- W3007797378 hasConcept C100800780 @default.
- W3007797378 hasConcept C149635348 @default.
- W3007797378 hasConcept C152890283 @default.
- W3007797378 hasConcept C171675096 @default.
- W3007797378 hasConcept C173608175 @default.
- W3007797378 hasConcept C176649486 @default.
- W3007797378 hasConcept C203479927 @default.
- W3007797378 hasConcept C41008148 @default.
- W3007797378 hasConcept C51290061 @default.
- W3007797378 hasConcept C57863822 @default.
- W3007797378 hasConcept C63511323 @default.
- W3007797378 hasConcept C6557445 @default.
- W3007797378 hasConcept C74426580 @default.
- W3007797378 hasConcept C86803240 @default.
- W3007797378 hasConcept C93446704 @default.
- W3007797378 hasConcept C9390403 @default.
- W3007797378 hasConcept C98986596 @default.
- W3007797378 hasConceptScore W3007797378C100800780 @default.
- W3007797378 hasConceptScore W3007797378C149635348 @default.
- W3007797378 hasConceptScore W3007797378C152890283 @default.
- W3007797378 hasConceptScore W3007797378C171675096 @default.
- W3007797378 hasConceptScore W3007797378C173608175 @default.
- W3007797378 hasConceptScore W3007797378C176649486 @default.
- W3007797378 hasConceptScore W3007797378C203479927 @default.
- W3007797378 hasConceptScore W3007797378C41008148 @default.
- W3007797378 hasConceptScore W3007797378C51290061 @default.
- W3007797378 hasConceptScore W3007797378C57863822 @default.
- W3007797378 hasConceptScore W3007797378C63511323 @default.
- W3007797378 hasConceptScore W3007797378C6557445 @default.
- W3007797378 hasConceptScore W3007797378C74426580 @default.
- W3007797378 hasConceptScore W3007797378C86803240 @default.
- W3007797378 hasConceptScore W3007797378C93446704 @default.
- W3007797378 hasConceptScore W3007797378C9390403 @default.
- W3007797378 hasConceptScore W3007797378C98986596 @default.
- W3007797378 hasFunder F4320332180 @default.
- W3007797378 hasFunder F4320335353 @default.
- W3007797378 hasIssue "4" @default.
- W3007797378 hasLocation W30077973781 @default.
- W3007797378 hasOpenAccess W3007797378 @default.
- W3007797378 hasPrimaryLocation W30077973781 @default.
- W3007797378 hasRelatedWork W2155373950 @default.