FR3113326B1 - Procédé de calcul convolutif intra-mémoire et circuit intégré correspondant - Google Patents

Procédé de calcul convolutif intra-mémoire et circuit intégré correspondant Download PDF

Info

Publication number
FR3113326B1
FR3113326B1 FR2008327A FR2008327A FR3113326B1 FR 3113326 B1 FR3113326 B1 FR 3113326B1 FR 2008327 A FR2008327 A FR 2008327A FR 2008327 A FR2008327 A FR 2008327A FR 3113326 B1 FR3113326 B1 FR 3113326B1
Authority
FR
France
Prior art keywords
voltage signals
integrated circuit
convolutional calculation
pcmij
iwl
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
FR2008327A
Other languages
English (en)
Other versions
FR3113326A1 (fr
Inventor
Antonino Conte
Rosa Francesco La
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
STMicroelectronics Rousset SAS
STMicroelectronics SRL
Original Assignee
STMicroelectronics Rousset SAS
STMicroelectronics SRL
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by STMicroelectronics Rousset SAS, STMicroelectronics SRL filed Critical STMicroelectronics Rousset SAS
Priority to FR2008327A priority Critical patent/FR3113326B1/fr
Priority to EP21189279.9A priority patent/EP3955171A1/fr
Priority to US17/393,075 priority patent/US20220044099A1/en
Priority to CN202110899221.7A priority patent/CN114067884A/zh
Publication of FR3113326A1 publication Critical patent/FR3113326A1/fr
Application granted granted Critical
Publication of FR3113326B1 publication Critical patent/FR3113326B1/fr
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C13/00—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00
    • G11C13/0002—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00 using resistive RAM [RRAM] elements
    • G11C13/0004—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00 using resistive RAM [RRAM] elements comprising amorphous/crystalline phase transition cells
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C11/00—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
    • G11C11/54—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using elements simulating biological cells, e.g. neuron
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations
    • G06F17/153—Multidimensional correlation or convolution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G06N3/065—Analogue means
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C13/00—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00
    • G11C13/0002—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00 using resistive RAM [RRAM] elements
    • G11C13/0021—Auxiliary circuits
    • G11C13/0038—Power supply circuits
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C13/00—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00
    • G11C13/0002—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00 using resistive RAM [RRAM] elements
    • G11C13/0021—Auxiliary circuits
    • G11C13/004—Reading or sensing circuits or methods
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C13/00—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00
    • G11C13/0002—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00 using resistive RAM [RRAM] elements
    • G11C13/0021—Auxiliary circuits
    • G11C13/0069—Writing or programming circuits or methods
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C5/00—Details of stores covered by group G11C11/00
    • G11C5/14—Power supply arrangements, e.g. power down, chip selection or deselection, layout of wirings or power grids, or multiple supply levels
    • G11C5/147—Voltage reference generators, voltage or current regulators; Internally lowered supply levels; Compensation for voltage drops
    • H—ELECTRICITY
    • H10—SEMICONDUCTOR DEVICES; ELECTRIC SOLID-STATE DEVICES NOT OTHERWISE PROVIDED FOR
    • H10B—ELECTRONIC MEMORY DEVICES
    • H10B63/00—Resistance change memory devices, e.g. resistive RAM [ReRAM] devices
    • H10B63/30—Resistance change memory devices, e.g. resistive RAM [ReRAM] devices comprising selection components having three or more electrodes, e.g. transistors
    • H10B63/32—Resistance change memory devices, e.g. resistive RAM [ReRAM] devices comprising selection components having three or more electrodes, e.g. transistors of the bipolar type
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C13/00—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00
    • G11C13/0002—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00 using resistive RAM [RRAM] elements
    • G11C13/0021—Auxiliary circuits
    • G11C13/004—Reading or sensing circuits or methods
    • G11C2013/0045—Read using current through the cell
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C13/00—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00
    • G11C13/0002—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00 using resistive RAM [RRAM] elements
    • G11C13/0021—Auxiliary circuits
    • G11C13/0069—Writing or programming circuits or methods
    • G11C2013/0078—Write using current through the cell

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Neurology (AREA)
  • Power Engineering (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Semiconductor Memories (AREA)
  • Techniques For Improving Reliability Of Storages (AREA)

Abstract

Le circuit intégré pour le calcul convolutif (CNVL) comprend une matrice (ARR) de points mémoires non volatils (MPTij) comprenant chacun une cellule mémoire résistive à changement de phase (PCMij) couplée à une ligne de bit (BLj), et un transistor bipolaire de sélection (BJTij) couplé en série à la cellule et ayant une borne de base reliée à une ligne de mot (WLi), un circuit convertisseur d’entrée (INCVRT) configuré pour recevoir et convertir des valeurs d’entrée (A1-A4) en signaux de tension (V1-V4) et pour appliquer successivement les signaux de tension (V1-V4) sur des lignes de bit sélectionnées (BL1-BL4) sur des intervalles de temps respectifs (t1-t4), et un circuit convertisseur de sortie (OUTCVRT) configuré pour intégrer sur les intervalles de temps successifs (t1-t4) les courants de lecture (IWL) résultant des signaux de tension (V1-V4) qui polarisent les cellules mémoires résistives à changement de phase respectives (PCMij) et circulant dans des lignes de mots sélectionnées, et pour convertir les courants de lecture intégrés (IWL) en valeurs de sortie (Bi). Figure de l’abrégé : Fig 4
FR2008327A 2020-08-06 2020-08-06 Procédé de calcul convolutif intra-mémoire et circuit intégré correspondant Active FR3113326B1 (fr)

Priority Applications (4)

Application Number Priority Date Filing Date Title
FR2008327A FR3113326B1 (fr) 2020-08-06 2020-08-06 Procédé de calcul convolutif intra-mémoire et circuit intégré correspondant
EP21189279.9A EP3955171A1 (fr) 2020-08-06 2021-08-03 Procédé de calcul de convolution en mémoire et circuit intégré correspondant
US17/393,075 US20220044099A1 (en) 2020-08-06 2021-08-03 Method for in-memory convolutional computation and corresponding integrated circuit
CN202110899221.7A CN114067884A (zh) 2020-08-06 2021-08-05 用于存储器中卷积计算的方法和对应的集成电路

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR2008327A FR3113326B1 (fr) 2020-08-06 2020-08-06 Procédé de calcul convolutif intra-mémoire et circuit intégré correspondant
FR2008327 2020-08-06

Publications (2)

Publication Number Publication Date
FR3113326A1 FR3113326A1 (fr) 2022-02-11
FR3113326B1 true FR3113326B1 (fr) 2023-01-06

Family

ID=73013725

Family Applications (1)

Application Number Title Priority Date Filing Date
FR2008327A Active FR3113326B1 (fr) 2020-08-06 2020-08-06 Procédé de calcul convolutif intra-mémoire et circuit intégré correspondant

Country Status (4)

Country Link
US (1) US20220044099A1 (fr)
EP (1) EP3955171A1 (fr)
CN (1) CN114067884A (fr)
FR (1) FR3113326B1 (fr)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11942144B2 (en) 2022-01-24 2024-03-26 Stmicroelectronics S.R.L. In-memory computation system with drift compensation circuit
US11894052B2 (en) * 2022-04-12 2024-02-06 Stmicroelectronics S.R.L. Compensated analog computation for an in-memory computation system
CN118098310B (zh) * 2024-04-25 2024-08-20 南京大学 基于超前补偿型跨阻放大器的光电存算阵列读出电路

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110807519B (zh) * 2019-11-07 2023-01-17 清华大学 基于忆阻器的神经网络的并行加速方法及处理器、装置

Also Published As

Publication number Publication date
US20220044099A1 (en) 2022-02-10
CN114067884A (zh) 2022-02-18
FR3113326A1 (fr) 2022-02-11
EP3955171A1 (fr) 2022-02-16

Similar Documents

Publication Publication Date Title
FR3113326B1 (fr) Procédé de calcul convolutif intra-mémoire et circuit intégré correspondant
CN110825345B (zh) 使用非易失性存储器单元的乘法
JP6858870B2 (ja) 不揮発性半導体記憶素子を用いたニューラルネットワーク演算回路
US11004510B2 (en) Cross-point memory compensation
US9595325B2 (en) Apparatus and methods for sensing hard bit and soft bits
Le et al. Resistive RAM with multiple bits per cell: Array-level demonstration of 3 bits per cell
US8400816B2 (en) Resistance change memory device
US20210019609A1 (en) Mixed signal neuromorphic computing with nonvolatile memory devices
US8773887B1 (en) Resistive memory devices and related methods
US7292471B2 (en) Semiconductor memory device having a voltage-controlled-oscillator-based readout circuit
TWI581370B (zh) 具有高能源效率讀取架構之記憶體陣列
US8625329B2 (en) Semiconductor storage device including variable resistive elements
WO2016087763A1 (fr) Circuit de lecture pour mémoire résistive
JP2003151282A (ja) 混成抵抗性交点メモリセルアレイおよびその製造方法
JP2004005950A5 (fr)
KR20090096294A (ko) 저항체를 이용한 멀티 레벨 비휘발성 메모리 장치
TW202205113A (zh) 用於記憶體運算交叉式網路中的類比混合信號之時域比例式讀出介面
US20210020228A1 (en) Analog-to-digital converter for non-volatile memory arrays used for in-memory computation with floating bitlines
US20220114431A1 (en) Memory-integrated neural network
KR100218082B1 (ko) 더미데이타선을 갖는 반도체 메모리
CN114400031B (zh) 一种补码映射的rram存算一体芯片及电子设备
EP2689422A1 (fr) Architecture de memoire logique, notamment pour mram ou pcram ou rram
JP2020155168A (ja) 半導体記憶装置
CN101609710B (zh) 感测放大器电路及其数据感测方法
CN115019852A (zh) 基于忆阻器的存算一体时序同步计算单元及方法

Legal Events

Date Code Title Description
PLFP Fee payment

Year of fee payment: 2

PLSC Publication of the preliminary search report

Effective date: 20220211

PLFP Fee payment

Year of fee payment: 3

PLFP Fee payment

Year of fee payment: 4

PLFP Fee payment

Year of fee payment: 5