Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384339318> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4384339318 abstract "The emergence of data-intensive applications, such as Deep Neural Networks (DNN), exacerbates the well-known memory bottleneck in computer systems and demands early attention in the design flow. Electronic System-Level (ESL) design using SystemC Transaction Level Modeling (TLM) enables effective performance estimation, design space exploration, and gradual refinement. However, memory contention is often only detectable after detailed TLM-2.0 approximately-timed or cycle-accurate RTL models are developed. A memory bottleneck detected at such a late stage can severely limit the available design choices or even require costly redesign. In this work, we propose a novel TLM-2.0 loosely-timed contention-aware (LT-CA) modeling style that offers high-speed simulation close to traditional loosely-timed (LT) models, yet shows the same accuracy for memory contention as low-level approximately-timed (AT) models. Thus, our proposed LT-CA modeling breaks the speed/accuracy tradeoff between regular LT and AT models and offers fast and accurate observation and visualization of memory contention. Our extensible SystemC model generator automatically produces desired TLM-1 and TLM-2.0 models from a DNN architecture description for design space exploration focusing on memory contention. We demonstrate our approach with a real-world industry-strength DNN application, GoogLeNet. The experimental results show that the proposed LT-CA modeling is 46x faster in simulation than equivalent AT models with an average error of less than 1% in simulated time. Early detection of memory contentions also suggests that local memories close to computing cores can eliminate memory contention in such applications." @default.
- W4384339318 created "2023-07-15" @default.
- W4384339318 creator A5025324445 @default.
- W4384339318 creator A5038891657 @default.
- W4384339318 date "2023-07-14" @default.
- W4384339318 modified "2023-09-27" @default.
- W4384339318 title "Fast Loosely-Timed Deep Neural Network Models with Accurate Memory Contention" @default.
- W4384339318 cites W2097117768 @default.
- W4384339318 cites W2123345627 @default.
- W4384339318 cites W2143638583 @default.
- W4384339318 cites W2172307690 @default.
- W4384339318 cites W2604319603 @default.
- W4384339318 cites W2907909057 @default.
- W4384339318 cites W2965653519 @default.
- W4384339318 cites W4241061932 @default.
- W4384339318 doi "https://doi.org/10.1145/3607548" @default.
- W4384339318 hasPublicationYear "2023" @default.
- W4384339318 type Work @default.
- W4384339318 citedByCount "0" @default.
- W4384339318 crossrefType "journal-article" @default.
- W4384339318 hasAuthorship W4384339318A5025324445 @default.
- W4384339318 hasAuthorship W4384339318A5038891657 @default.
- W4384339318 hasBestOaLocation W43843393181 @default.
- W4384339318 hasConcept C118524514 @default.
- W4384339318 hasConcept C12186640 @default.
- W4384339318 hasConcept C133875982 @default.
- W4384339318 hasConcept C149635348 @default.
- W4384339318 hasConcept C173608175 @default.
- W4384339318 hasConcept C2776221188 @default.
- W4384339318 hasConcept C2776928060 @default.
- W4384339318 hasConcept C2779602883 @default.
- W4384339318 hasConcept C2780513914 @default.
- W4384339318 hasConcept C37135326 @default.
- W4384339318 hasConcept C41008148 @default.
- W4384339318 hasConceptScore W4384339318C118524514 @default.
- W4384339318 hasConceptScore W4384339318C12186640 @default.
- W4384339318 hasConceptScore W4384339318C133875982 @default.
- W4384339318 hasConceptScore W4384339318C149635348 @default.
- W4384339318 hasConceptScore W4384339318C173608175 @default.
- W4384339318 hasConceptScore W4384339318C2776221188 @default.
- W4384339318 hasConceptScore W4384339318C2776928060 @default.
- W4384339318 hasConceptScore W4384339318C2779602883 @default.
- W4384339318 hasConceptScore W4384339318C2780513914 @default.
- W4384339318 hasConceptScore W4384339318C37135326 @default.
- W4384339318 hasConceptScore W4384339318C41008148 @default.
- W4384339318 hasLocation W43843393181 @default.
- W4384339318 hasOpenAccess W4384339318 @default.
- W4384339318 hasPrimaryLocation W43843393181 @default.
- W4384339318 hasRelatedWork W1567432572 @default.
- W4384339318 hasRelatedWork W1885396597 @default.
- W4384339318 hasRelatedWork W2026454041 @default.
- W4384339318 hasRelatedWork W2028583644 @default.
- W4384339318 hasRelatedWork W2119501389 @default.
- W4384339318 hasRelatedWork W2146527276 @default.
- W4384339318 hasRelatedWork W2533063779 @default.
- W4384339318 hasRelatedWork W2975035977 @default.
- W4384339318 hasRelatedWork W4297990507 @default.
- W4384339318 hasRelatedWork W4384339318 @default.
- W4384339318 isParatext "false" @default.
- W4384339318 isRetracted "false" @default.
- W4384339318 workType "article" @default.