Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376131445> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4376131445 abstract "Computing-in-memory (CIM) has been an ongoing prominent research area for easing the energy efficiency of machine learning tasks in edge devices. Recently, embedded non-volatile memory (eNVM) CIM architectures have been popular as an edge device, where it can turn off their supply during standby for low power consumption. However, most eNVMs (e.g., MRAMs and RRAMs) require the use of specialized technologies and are mostly used as single-level cell (SLC) data storage [2], [3]. In the technologies that do not provide eNVMs, logic-compatible single-poly non-volatile embedded flash (eflash) memory [1] can be considered an alternative. Although the cell area of the single-poly non-volatile eflash is significant, we can considerably compensate for the cell area penalty by using multi-level cells (MLCS). Further, in eNVM CIMs, the analog computations must be quantized with an ADC, where the SAR ADCs are a popular conversion topology. However, SAR ADC designs result in significant power consumption and area overhead due to its capacitor DAC driving and high accuracy comparators [5]. In this work, we propose to overcome such challenges by proposing 1) a logic-compatible single-poly nonvolatile eflash memory macro using MLC and an SLC at the same time to increase computation density while maintaining a reasonable signal margin, 2) a resolution configurable differential SAR TDC used for both memory programming and computing with replacing analog voltage comparators to inverters in order to reduce power consumption and area, and 3) an energy-efficient 2’s complement dual-slope computation with MLC and SLC sharing a single differential TDC for multi-bit weight computation. We fabricated the proposed eFlash CIM macro in a $65 mathrm{~nm}$ CMOS process. Our measurements show that the proposed CIM macro achieves up to 333 TOPSM energy efficiency and 186.2 GOPS throughput." @default.
- W4376131445 created "2023-05-12" @default.
- W4376131445 creator A5028702107 @default.
- W4376131445 creator A5034621834 @default.
- W4376131445 creator A5035123235 @default.
- W4376131445 creator A5045028723 @default.
- W4376131445 creator A5055738906 @default.
- W4376131445 creator A5060747608 @default.
- W4376131445 creator A5065408994 @default.
- W4376131445 creator A5077005883 @default.
- W4376131445 date "2023-04-01" @default.
- W4376131445 modified "2023-10-14" @default.
- W4376131445 title "A 333TOPS/W Logic-Compatible Multi-Level Embedded Flash Compute-In-Memory Macro with Dual-Slope Computation" @default.
- W4376131445 doi "https://doi.org/10.1109/cicc57935.2023.10121209" @default.
- W4376131445 hasPublicationYear "2023" @default.
- W4376131445 type Work @default.
- W4376131445 citedByCount "0" @default.
- W4376131445 crossrefType "proceedings-article" @default.
- W4376131445 hasAuthorship W4376131445A5028702107 @default.
- W4376131445 hasAuthorship W4376131445A5034621834 @default.
- W4376131445 hasAuthorship W4376131445A5035123235 @default.
- W4376131445 hasAuthorship W4376131445A5045028723 @default.
- W4376131445 hasAuthorship W4376131445A5055738906 @default.
- W4376131445 hasAuthorship W4376131445A5060747608 @default.
- W4376131445 hasAuthorship W4376131445A5065408994 @default.
- W4376131445 hasAuthorship W4376131445A5077005883 @default.
- W4376131445 hasConcept C111919701 @default.
- W4376131445 hasConcept C11413529 @default.
- W4376131445 hasConcept C119599485 @default.
- W4376131445 hasConcept C127413603 @default.
- W4376131445 hasConcept C149635348 @default.
- W4376131445 hasConcept C155745195 @default.
- W4376131445 hasConcept C165801399 @default.
- W4376131445 hasConcept C177950962 @default.
- W4376131445 hasConcept C24326235 @default.
- W4376131445 hasConcept C2742236 @default.
- W4376131445 hasConcept C2779960059 @default.
- W4376131445 hasConcept C2780165032 @default.
- W4376131445 hasConcept C41008148 @default.
- W4376131445 hasConcept C45374587 @default.
- W4376131445 hasConcept C9390403 @default.
- W4376131445 hasConceptScore W4376131445C111919701 @default.
- W4376131445 hasConceptScore W4376131445C11413529 @default.
- W4376131445 hasConceptScore W4376131445C119599485 @default.
- W4376131445 hasConceptScore W4376131445C127413603 @default.
- W4376131445 hasConceptScore W4376131445C149635348 @default.
- W4376131445 hasConceptScore W4376131445C155745195 @default.
- W4376131445 hasConceptScore W4376131445C165801399 @default.
- W4376131445 hasConceptScore W4376131445C177950962 @default.
- W4376131445 hasConceptScore W4376131445C24326235 @default.
- W4376131445 hasConceptScore W4376131445C2742236 @default.
- W4376131445 hasConceptScore W4376131445C2779960059 @default.
- W4376131445 hasConceptScore W4376131445C2780165032 @default.
- W4376131445 hasConceptScore W4376131445C41008148 @default.
- W4376131445 hasConceptScore W4376131445C45374587 @default.
- W4376131445 hasConceptScore W4376131445C9390403 @default.
- W4376131445 hasLocation W43761314451 @default.
- W4376131445 hasOpenAccess W4376131445 @default.
- W4376131445 hasPrimaryLocation W43761314451 @default.
- W4376131445 hasRelatedWork W1481681735 @default.
- W4376131445 hasRelatedWork W2021714649 @default.
- W4376131445 hasRelatedWork W2056658160 @default.
- W4376131445 hasRelatedWork W2100799217 @default.
- W4376131445 hasRelatedWork W2117170259 @default.
- W4376131445 hasRelatedWork W2156387609 @default.
- W4376131445 hasRelatedWork W2168856828 @default.
- W4376131445 hasRelatedWork W2415152353 @default.
- W4376131445 hasRelatedWork W3134760666 @default.
- W4376131445 hasRelatedWork W3150851598 @default.
- W4376131445 isParatext "false" @default.
- W4376131445 isRetracted "false" @default.
- W4376131445 workType "article" @default.