WO2023100490A1 - 演算装置および固体撮像装置 - Google Patents
演算装置および固体撮像装置 Download PDFInfo
- Publication number
- WO2023100490A1 WO2023100490A1 PCT/JP2022/038204 JP2022038204W WO2023100490A1 WO 2023100490 A1 WO2023100490 A1 WO 2023100490A1 JP 2022038204 W JP2022038204 W JP 2022038204W WO 2023100490 A1 WO2023100490 A1 WO 2023100490A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- signal
- transistor
- memory cell
- input
- output
- 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.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06G—ANALOGUE COMPUTERS
- G06G7/00—Devices in which the computing operation is performed by varying electric or magnetic quantities
- G06G7/48—Analogue computers for specific processes, systems or devices, e.g. simulators
- G06G7/60—Analogue computers for specific processes, systems or devices, e.g. simulators for living beings, e.g. their nervous systems ; for problems in the medical field
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- 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
- G11C11/21—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements
- G11C11/34—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices
- G11C11/40—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices using transistors
- G11C11/41—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices using transistors forming static cells with positive feedback, i.e. cells not needing refreshing or charge regeneration, e.g. bistable multivibrator or Schmitt trigger
- G11C11/412—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices using transistors forming static cells with positive feedback, i.e. cells not needing refreshing or charge regeneration, e.g. bistable multivibrator or Schmitt trigger using field-effect transistors only
-
- 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
Definitions
- the present disclosure relates to arithmetic devices and solid-state imaging devices.
- Patent Document 1 A flip-flop type memory cell that writes information by injecting hot electrons has been proposed (Patent Document 1). Further, there is a demand for an arithmetic device capable of executing a sum-of-products operation on a memory cell array using SRAM (Static Random Access Memory) technology.
- SRAM Static Random Access Memory
- Arithmetic devices are required to suppress increases in memory cell area.
- An arithmetic device includes a first inverter having a first input and a first output, and a second input connected to the first output and a first inverter connected to the first input.
- a memory cell each having a second inverter having a second output for outputting a signal, a first transistor receiving a first signal from the second output, and a resistor connected in series with the first transistor.
- a memory cell array including a plurality of memory cells is provided.
- a solid-state imaging device includes: a first inverter having a first input section and a first output section; a second input section connected to the first output section; A memory cell each having a second inverter having a second output for outputting a 1 signal, a first transistor receiving the first signal from the second output, and a resistor connected in series with the first transistor.
- a memory cell array including a plurality of
- FIG. 1 is a block diagram showing an example of the overall configuration of an imaging device according to an embodiment of the present disclosure
- FIG. 2 is a diagram illustrating a configuration example of pixels of an imaging device according to an embodiment of the present disclosure
- FIG. FIG. 4 is a diagram showing another configuration example of pixels of the imaging device according to the embodiment of the present disclosure
- FIG. 4 is a diagram showing another configuration example of pixels of the imaging device according to the embodiment of the present disclosure
- 1 is a diagram showing a configuration example of a memory cell array of an imaging device according to an embodiment of the present disclosure
- FIG. 1 is a diagram showing a configuration example of a memory cell of an imaging device according to an embodiment of the present disclosure
- FIG. 3 is a diagram showing a layout example of memory cells of the imaging device according to the embodiment of the present disclosure
- 4 is a diagram showing a configuration example of resistors of the imaging device according to the embodiment of the present disclosure
- FIG. FIG. 5 is a diagram showing another configuration example of resistors of the imaging device according to the embodiment of the present disclosure
- FIG. 4 is a diagram for explaining an example of sum-of-products operation processing by the imaging device according to the embodiment of the present disclosure
- FIG. 5 is a diagram showing another configuration example of the memory cell of the imaging device according to the embodiment of the present disclosure
- FIG. 5 is a diagram showing a configuration example of a memory cell array of an imaging device according to Modification 1 of the present disclosure
- FIG. 5 is a diagram showing a configuration example of a memory cell of an imaging device according to Modification 1 of the present disclosure
- FIG. 10 is a diagram illustrating a configuration example of a memory cell of an imaging device according to modification 2 of the present disclosure
- FIG. 11 is a diagram illustrating another configuration example of a memory cell of an imaging device according to modification 2 of the present disclosure
- FIG. 11 is a diagram illustrating another configuration example of a memory cell of an imaging device according to modification 2 of the present disclosure
- FIG. 10 is a diagram illustrating a configuration example of a memory cell of an imaging device according to modification 3 of the present disclosure
- FIG. 11 is a diagram illustrating another configuration example of a memory cell of an imaging device according to modification 3 of the present disclosure
- FIG. 11 is a diagram illustrating another configuration example of a memory cell of an imaging device according to modification 3 of the present disclosure
- 1 is a block diagram showing a configuration example of an electronic device having an imaging device
- FIG. 1 is a block diagram showing an example of a schematic configuration of a vehicle control system
- FIG. 4 is an explanatory diagram showing an example of installation positions of an outside information detection unit and an imaging unit
- 1 is a diagram showing an example of a schematic configuration of an endoscopic surgery system
- FIG. 3 is a block diagram showing an example of functional configurations of a camera head and a CCU;
- FIG. 1 is a block diagram showing an example of the overall configuration of an imaging device 1, which is an example of an arithmetic device according to an embodiment of the present disclosure.
- the imaging device 1 is a solid-state imaging device that photoelectrically converts incident light to capture an image of a subject.
- the imaging device 1 has a memory cell array capable of executing a sum-of-products operation, and realizes CIM (Computing in memory) that performs operations on the memory cell array, which is a non-Von Neumann type arithmetic unit.
- CIM Computer in memory
- the imaging device 1, which is a solid-state imaging device is, for example, a CMOS (Complementary Metal Oxide Semiconductor) image sensor.
- the imaging device 1 a plurality of pixels each having a photoelectric conversion unit are provided two-dimensionally.
- the imaging device 1 captures incident light (image light) from a subject via an optical lens system (not shown).
- the imaging device 1 converts the amount of incident light that forms an image on the imaging surface into an electric signal on a pixel-by-pixel basis, and outputs the electric signal as a pixel signal.
- the imaging device 1 can be used in electronic devices such as digital still cameras and video cameras.
- the imaging device 1 has a pixel section 100 in which a plurality of pixels P are two-dimensionally arranged as an imaging area.
- the pixel unit 100 can also be said to be a pixel array in which the pixels P are arranged in a matrix.
- the imaging device 1 also has a memory cell array 200 in which a plurality of memory cells 20 are arranged in rows and columns.
- the imaging device 1 includes a first substrate 101 and a second substrate 201.
- the first substrate 101 and the second substrate 201 are each composed of a semiconductor substrate (for example, a silicon substrate), and are stacked one on top of the other.
- a pixel portion 100 is provided on the first substrate 101 .
- a memory cell array 200 is provided on the second substrate 201 .
- the aspect of the memory cell array 200 may be rectangular (longitudinally or horizontally) or square.
- the memory cell array 200 may be arranged at any position (right edge, center, top edge, etc.) of the second substrate 201 .
- the pixel section 100 and the memory cell array 200 may be provided on the same substrate.
- the substrate provided with the memory cell array 200 may be a substrate of an oxide semiconductor, a compound semiconductor, or the like.
- the imaging device 1 has, for example, a vertical drive circuit 111, a column signal processing circuit 112, a horizontal drive circuit 113, a control circuit 115, etc. in the peripheral region of the pixel section 100.
- the imaging device 1 has, for example, a memory control circuit 211, a memory signal processing circuit 212, a storage section 214, an input/output section 215, etc. in the peripheral area of the memory cell array 200.
- a pixel P has a photoelectric conversion unit and a plurality of pixel transistors.
- the photoelectric conversion unit is, for example, a photodiode.
- the multiple pixel transistors include, for example, a transfer transistor, an amplification transistor, a selection transistor, a reset transistor, and the like.
- the pixel P has, for example, a photoelectric conversion unit 12, which is a photodiode, a transfer transistor 13, an amplification transistor 14, a selection transistor 15, and a reset transistor 16, as in the example shown in FIG.
- the pixel P generates a pixel signal based on charges photoelectrically converted by the photoelectric conversion unit.
- the plurality of pixels P of the pixel unit 100 include pixels (R pixels) having filters that transmit light in the red wavelength range, pixels (G pixels) having filters that transmit light in the green wavelength range, and blue pixels. and a pixel (B pixel) having a filter that transmits light in the wavelength range of .
- the R pixels, G pixels, and B pixels are arranged, for example, according to the so-called Bayer array.
- the R pixel, G pixel, and B pixel generate an R component pixel signal, a G component pixel signal, and a B component pixel signal, respectively. Therefore, the imaging device 1 can obtain RGB pixel signals.
- the filters provided in the pixels P are not limited to primary color (RGB) color filters, and may be complementary color filters such as Cy (cyan), Mg (magenta), and Ye (yellow). .
- Pixel P may have a memory transistor and a capacitor capable of holding electric charge.
- the memory transistor 17a and the capacitor 18a hold charges photoelectrically converted by the photoelectric conversion unit 12a
- the memory transistor 17b and the capacitor 18b hold charges photoelectrically converted by the photoelectric conversion unit 12b.
- the amplification transistor 14, the selection transistor 15, the reset transistor 16, and the like may be arranged for a plurality of photoelectric conversion units, and may be shared by a plurality of pixels P. .
- the amplification transistor 14 and the selection transistor 15 can output a pixel signal based on the charge photoelectrically converted by the photoelectric conversion unit 12a and a pixel signal based on the charge photoelectrically converted by the photoelectric conversion unit 12b.
- the photoelectric conversion units 12a to 12c each have a photoelectric conversion film 121, an upper electrode 122 and a lower electrode 123.
- the photoelectric conversion film 121 is made of an organic material or an inorganic material, and converts incident light into charges.
- the amplification transistor 14 and the selection transistor 15 are connected to the transfer transistor 13a and can output a pixel signal based on the charges photoelectrically converted by the photoelectric conversion unit 12a. Further, the amplification transistor 14 and the selection transistor 15 are connected to the transfer transistors 13b and 13c, and transfer pixel signals based on the charges generated by the photoelectric conversion unit 12b and pixel signals based on the charges generated by the photoelectric conversion unit 12c, respectively. can output.
- the pixel P may be a pixel capable of outputting a pixel signal by a pulse width modulation (PWM) method.
- the pixel P may be a DVS (Dynamic Vision Sensor) pixel, and may output a pixel signal indicating that the amount of received light has changed beyond a predetermined threshold.
- so-called convolution pixels may be arranged in the pixel unit 100, and pixel signals obtained by adding pixel signals of respective pixels may be output.
- a plurality of pixel rows composed of a plurality of pixels P arranged in the horizontal direction and a plurality of pixel columns composed of a plurality of pixels P arranged in the vertical direction are provided.
- a pixel drive line Lread (row selection line, reset control line, etc.) is wired for each pixel row
- a vertical signal line Lsig is wired for each pixel column.
- the pixel drive line Lread transmits drive signals for reading signals from pixels.
- One end of the pixel drive line Lread is connected to an output terminal corresponding to each pixel row of the vertical drive circuit 111 .
- the vertical drive circuit 111 is composed of a shift register, an address decoder, and the like.
- the vertical drive circuit 111 sequentially selects and scans each pixel of the pixel section 100 to output a pixel signal of each pixel.
- the vertical drive circuit 111 is a pixel drive section that drives each pixel P of the pixel section 100, for example, in units of rows.
- the vertical drive circuit 111 can also be said to be a pixel control circuit that controls the pixels P.
- FIG. A signal output from each pixel P in a pixel row selectively scanned by the vertical drive circuit 111 is supplied to the column signal processing circuit 112 through the vertical signal line Lsig.
- the column signal processing circuit 112 is composed of amplifiers, horizontal selection switches, etc. provided for each vertical signal line Lsig.
- the column signal processing circuit 112 performs signal processing such as CDS (Correlated Double Sampling) processing and AD (Analog to Digital) conversion processing on the pixel signal of each pixel.
- the column signal processing circuit 112 can also be said to be a pixel signal processing circuit that processes signals output from the pixels P. FIG.
- the horizontal drive circuit 113 is composed of a shift register, an address decoder, etc., and sequentially drives the horizontal selection switches of the column signal processing circuit 112 while scanning them. By selective scanning by the horizontal drive circuit 113 , the pixel signals of each pixel processed by the column signal processing circuit 112 are sequentially transmitted to the memory control circuit 211 .
- the control circuit 115 receives a clock input from the outside, data instructing an operation mode, and the like, and controls each part of the imaging device 1 .
- the control circuit 115 has a timing generator that generates various timing signals, and controls peripheral circuits such as the vertical driving circuit 111, the column signal processing circuit 112, and the horizontal driving circuit 113 based on the various timing signals generated by the timing generator. drive control.
- the memory control circuit 211 is composed of a shift register, an address decoder, and the like.
- the memory control circuit 211 and the memory cell array 200 are provided side by side in the vertical direction as shown in FIG.
- the memory control circuit 211 supplies signals for controlling the memory cells 20 to each memory cell 20 of the memory cell array 200 to control the operation of each memory cell 20 .
- the memory control circuit 211 causes each memory cell 20 of the memory cell array 200 to perform a sum-of-products operation, and outputs a signal (sum-of-products signal) obtained by the sum-of-products operation to the memory signal processing circuit 212 .
- the memory control circuit 211 outputs, for example, a control signal associated with the pixel signal of each pixel input from the column signal processing circuit 112 to each memory cell 20 of the memory cell array 200 .
- the memory control circuit 211 generates a control signal (for example, a signal Act, which will be described later) according to the input pixel signal, and outputs it to each memory cell 20 of the memory cell array 200 .
- a sum-of-products operation is performed using a control signal input to each memory cell 20 according to a pixel signal and the data held in each memory cell 20, and the generated sum-of-products signal is sent to the memory signal processing circuit 212. transmitted.
- the memory control circuit 211 can output the pixel signal of each pixel input from the column signal processing circuit 112 to the outside via the input/output unit 215 .
- the memory signal processing circuit 212 has an ADC (Analog to Digital Converter) or the like, and performs various signal processing on the sum-of-products signal read from the memory cell array 200 .
- the memory signal processing circuit 212 and the memory cell array 200 are arranged side by side in the horizontal direction as shown in FIG.
- the memory signal processing circuit 212 performs, for example, an AD conversion process on the sum-of-products signal, which is an analog signal output from the memory cell array 200 .
- the memory signal processing circuit 212 outputs the product-sum signal converted into a digital signal to the input/output unit 215 .
- the memory signal processing circuit 212 may perform processing using an activation function, pooling processing, and the like, and output the processed sum-of-products signal to the input/output unit 215 .
- the ADC of the memory signal processing circuit 212 is, for example, a single slope ADC.
- the ADC may be a double integration type, successive approximation type (SAR), delta sigma type, or other AD conversion circuit.
- An ADC that detects a difference as in a DVS (Dynamic Vision Sensor) may be used.
- the ADC resolution ie, the number of bits for AD conversion, may be 1 bit or 2 bits or more (for example, 10 bits or 12 bits).
- the memory signal processing circuit 212 causes the storage unit 214 to store signals, parameters, and the like input from an external device (for example, an image processing device) via the input/output unit 215, and executes them based on instructions from the external device. change signal processing.
- the storage unit 214 has a memory and stores data such as signals and parameters used for signal processing performed by the memory signal processing circuit 212 .
- the input/output unit 215 outputs signals sequentially input from the memory signal processing circuit 212 to an external device such as an image processing device such as an ISP (Image Signal Processor).
- the input/output unit 215 also outputs signals and parameters input from an external device to the memory signal processing circuit 212 and the control circuit 115 .
- the input/output unit 215 can write data to the memory cells 20 of the memory cell array 200 .
- the input/output unit 215 writes, for example, a data value indicating a learning result input from an external device into each memory cell 20 of the memory cell array 200 . It is also possible to reflect the result calculated by the memory signal processing circuit 212 in the data of the memory cell 20 to update the learning result.
- the memory control circuit 211 or the memory signal processing circuit 212 may write data to the memory cells 20 of the memory cell array 200 .
- the memory control circuit 211 or the memory signal processing circuit 212 may change the data held in each memory cell 20 according to the data acquired by the input/output unit 215 .
- FIG. 5 is a diagram showing a configuration example of the memory cell array 200 of the imaging device 1 according to the embodiment of the present disclosure.
- the plurality of memory cells 20 are arranged in a horizontal direction (row direction) that is a first direction and a vertical direction (a second direction that is orthogonal to the first direction). columns). It can also be said that the plurality of memory cells 20 are arranged in the horizontal direction (horizontal direction on the paper surface) and the vertical direction (vertical direction on the paper surface).
- a word line WL and a signal line L1 for transmitting a signal Act are provided for each of the plurality of memory cells 20 arranged in the horizontal direction. It can also be said that the word line WL and the signal line L1 are provided for a memory cell row composed of a plurality of memory cells 20 arranged in the horizontal direction.
- Each of the word lines WL and the signal lines L1 is, for example, wiring extending in the horizontal direction.
- a first bit line BL, a second bit line BLB, and a signal line L2 through which a sum-of-products signal is transmitted are provided for each of the plurality of memory cells 20 arranged in the vertical direction.
- a first bit line BL, a second bit line BLB, and a signal line L2 are provided for a memory cell column composed of a plurality of memory cells 20 arranged in the vertical direction.
- the first bit line BL, the second bit line BLB, and the signal line L2 are, for example, lines extending in the vertical direction.
- the signal line L2 and the memory control circuit 211 are arranged horizontally.
- the signal line L2 and the memory signal processing circuit 212 are provided side by side in the vertical direction.
- word lines WL and signal lines L1 are arranged for each memory cell row, and first bit lines BL, second bit lines BLB and signal lines L2 are arranged for each memory cell column. Wired. It can also be said that the memory cell 20 is arranged at the intersection of the corresponding word line WL and the pair of the first bit line BL and the second bit line BLB.
- the word line WL and the signal line L1 are connected to the memory control circuit 211 described above.
- the memory control circuit 211 supplies a signal to the word line WL and a signal Act to the signal line L1.
- the first bit line BL and the second bit line BLB are connected to the input/output unit 215 or the memory control circuit 211, for example.
- a signal is supplied to the first bit line BL and the second bit line BLB by the input/output unit 215 or the memory control circuit 211 and input to each memory cell 20 .
- Signal line L2 is connected to memory signal processing circuit 212 .
- the sum-of-products signal is input to the memory signal processing circuit 212 via the signal line L2.
- FIG. 6 is a diagram showing a configuration example of the memory cell 20 of the imaging device 1 according to the embodiment of the present disclosure.
- FIG. 7 is a diagram showing a layout example of the memory cell 20.
- the memory cell 20 has a first inverter INV1, a second inverter INV2, a transistor M5, a transistor M6, a transistor M7, and a resistor R.
- the memory cell 20 is a storage element capable of storing 1-bit information.
- the memory cell 20 has a flip-flop circuit 30 including a first inverter INV1 and a second inverter INV2, and can be called a flip-flop type memory cell.
- the first inverter INV1 has a transistor M1 and a transistor M3 connected in series.
- the first inverter INV1 has an input section 21a and an output section 21b, and can output an inverted signal of an input signal.
- the second inverter INV2 has a transistor M2 and a transistor M4 connected in series.
- the second inverter INV2 has an input section 22a and an output section 22b, and can output an inverted signal of the input signal.
- the input portion 21a of the first inverter INV1 is electrically connected to the output portion 22b of the second inverter INV2, and the output portion 21b of the first inverter INV1 is electrically connected to the input portion 22a of the second inverter INV2. .
- the transistors M1 to M7 are MOS transistors (MOSFETs) having gate, source, and drain terminals, respectively.
- Transistor M1 and transistor M2 are each NMOS transistors, and transistor M3 and transistor M4 are each PMOS transistors.
- Transistors M5, M6 and M7 are, for example, NMOS transistors.
- Each transistor of the memory cell 20 may be a MISFET.
- the gates of the transistor M1 and the transistor M3 are electrically connected to each other to form an input section 21a.
- Gates of the transistor M2 and the transistor M4 are electrically connected to each other to form an input section 22a.
- Each source of the transistor M1 and the transistor M2 is connected to a ground line (ground line).
- Each source of the transistor M3 and the transistor M4 is connected to a power supply line.
- a first holding node 31 and a second holding node 32 shown in FIG. 6 are nodes capable of holding a signal.
- the first holding node 31 is a node that connects the output portion 21b of the first inverter INV1 and the input portion 22a of the second inverter INV2.
- the second holding node 32 is a node that connects the output portion 22b of the second inverter INV2 and the input portion 21a of the first inverter INV1.
- the memory cell 20 stores a digital signal depending on whether the potential of the first retention node 31 and the potential of the second retention node 32 are high or low.
- the first retention node 31 and the second retention node 32 can also be said to be storage nodes.
- the gates of the transistors M5 and M6 are electrically connected to the word line WL. Each of the transistors M5 and M6 is controlled to be on (conducting state) or off (non-conducting state) by a signal input via the word line WL.
- One of the source and drain of the transistor M5 is electrically connected to the input section 22a of the second inverter INV2 and the output section 21b of the first inverter INV1.
- the other of the source and drain of the transistor M5 is connected to the first bit line BL.
- the transistor M5 electrically connects or disconnects the output portion 21b of the first inverter INV1 and the first bit line BL.
- One of the source and drain of the transistor M6 is electrically connected to the input section 21a of the first inverter INV1 and the output section 22b of the second inverter INV2.
- the other of the source and drain of the transistor M6 is connected to the second bit line BLB.
- the transistor M6 electrically connects or disconnects the output portion 22b of the second inverter INV2 and the second bit line BLB.
- the gate of the transistor M7 is electrically connected to the second holding node 32 and receives a signal from the output section 22b of the second inverter INV2.
- the transistor M7 is turned on or off depending on the potential of the second holding node 32.
- FIG. One of the source and the drain of the transistor M7 is connected in series with the resistor R and electrically connected to the signal line L1 to which the signal Act is input (transmitted).
- the other of the source and drain of the transistor M7 is electrically connected to the signal line L2.
- a signal line L2 is a summation line.
- the transistor M7 can generate a current according to the potential of the second retention node 32 and the potential of the signal Act applied to its gate, and can supply the generated current to the signal line L2.
- the transistors M1 and M5 are formed in the active region 41.
- Transistor M 3 is formed in active region 42 and transistor M 4 is formed in active region 43 .
- the transistors M2 and M6 are formed in the active region 44.
- FIG. Transistor M7 is formed in active region 45 .
- the gates of the transistors M1, M3 and M7 are integrally formed. Gates of the transistors M2 and M4 are integrally formed.
- the resistor R is configured by laminating a plurality of conductors and a plurality of insulators.
- Resistor R is a resistive element with a tunnel junction.
- the resistor R is, for example, a two-terminal element and is connected in series with the transistor M7.
- the resistor R has a structure in which conductors and insulators are alternately laminated. The thickness of the insulator is thinned so that a tunnel effect occurs. Note that the resistance value of the resistor R is determined by the thickness of the insulator, the material of the insulator, the number of films to be laminated, and the like. By adjusting the film thickness of the insulator, etc., a high resistance element can be realized in a small area.
- the resistor R may be, for example, a high resistance element with a resistance value of 1 M ⁇ or more. In the layout example shown in FIG. 7, the resistor R is formed so as to overlap one of the source and drain of the transistor M7.
- FIG. 8 is a diagram showing a configuration example of resistors of the imaging device 1 according to the embodiment of the present disclosure.
- the resistor R has insulators 51, 52, 53 and conductors 61, 62, 63, 64, as shown in FIG.
- the insulators 51 to 53 are made of silicon oxide (SiOx), for example.
- the insulators 51-53 may be made of silicon nitride (SiNx). Note that the insulators 51 to 53 may be formed to contain at least one oxide of hafnium (Hf), zirconium (Zr), titanium (Ti), aluminum (Al), magnesium (Mg), or the like. good.
- the insulators 51 to 53 may be made of a semiconductor material, or may be made of another material.
- the conductors 61-64 are made of titanium nitride (TiN), for example.
- the conductors 61-64 may be formed to contain at least one of oxides or nitrides of tantalum (Ta), tungsten (W), copper (Cu) elements, or the like.
- the conductors 61 to 64 may be made of a semiconductor material, or may be made of another material. That is, for example, the conductors 61 to 64 may be made of Ti, Ta, W, Cu, Ru, Pt, Ir, In, Sn, Zn, Ga or C, or compounds, oxides or nitrides thereof. good.
- the conductors 61-64 may be configured using the same material, or may be configured using different materials.
- Examples of the structure of the resistor R include TiN/ SiO2 /TiN, TiN/ ZrO2 /TiN, ITO/ ZrO2 /ITO, TiN/ HfO2 /ITO, TiN/ Al2O3 /TiN, CoFeB/MgO . /CoFeB and the like.
- the structure and material of the tunnel resistance element are not limited to the examples described above, and any structure and material can be selected as long as a tunnel barrier is formed and a desired resistance value is obtained.
- resistor R may be configured using a ferroelectric material, or may be configured using a magnetic material.
- Resistor R may be a ferroelectric tunnel junction (FTJ), a magnetic tunnel junction (MTJ), or other high resistance element.
- the resistor R may be, for example, an MTJ element configured by sandwiching an insulator 55 between two magnetic bodies 65 and 66, as in the example shown in FIG.
- the resistor R may be an element capable of storing information by remnant polarization or the like.
- the memory control circuit 211 sets the potential of the word line WL shown in FIGS. 5 and 6 to a high potential. That is, the signal level of the signal supplied to the word line WL is set to high level. When the potential of the word line WL becomes high level, the transistors M5 and M6 are turned on.
- the potential of one of the first bit line BL and the second bit line BLB is set to a high potential, and the potential of the other bit line is set to a low potential. That is, the signal level of the signal supplied to one bit line is set to high level, and the signal level of the signal supplied to the other bit line is set to low level.
- the potential of the first bit line BL is applied to the input portion 22a of the second inverter via the transistor M5.
- the potential of the second bit line BLB is applied to the input portion 21a of the first inverter through the transistor M6.
- the first bit line BL and the second bit line BLB are precharged in advance. For example, by precharging, the first bit line BL and the second bit line BLB are set to the same potential. After the potentials of the first bit line BL and the second bit line BLB are precharged, the potential of the word line WL is set to high level. When the potential of the word line WL becomes high level, the transistors M5 and M6 are turned on.
- the output section 21b of the first inverter is electrically connected to the first bit line BL.
- the output section 22b of the second inverter is electrically connected to the second bit line BLB by turning on the transistor M6.
- the potential of the first bit line BL changes according to the potential of the output portion 21 b of the first inverter, that is, the potential of the first holding node 31 .
- the potential of the second bit line BLB changes according to the potential of the output section 22b of the second inverter, that is, the potential of the second holding node 32.
- FIG. the data stored in the memory cell 20, ie the signal held by the first holding node 31 and the second holding node 32 can be read out to the first bit line BL and the second bit line BLB.
- the signal lines L1 and L2 are precharged in advance. For example, precharging sets the signal line L1 and the signal line L2 to the same potential. In this case, no current flows through the transistor M7 and the resistor R because the drain and source of the transistor M7 are at the same potential.
- the signal Act input to each signal line L1 is kept at a low level for a predetermined period of time.
- the signal Act becomes low level, a potential difference is generated between the drain and source of the transistor M7. This enables the transistor M7 to output a current corresponding to the potential of the second holding node 32 given to the gate, the potential of the signal Act, and the resistor R.
- the potential of the signal line L2 is lowered according to the amount of charge generated by the transistor M7 of each memory cell 20.
- the charges generated by each transistor M7 are added on the signal line L2 to generate a sum-of-products signal resulting from the addition.
- a sum-of-products signal corresponding to the sum of the multiplied values is calculated on the signal line L2.
- the sum-of-products signal which is the result of the sum-of-products operation, can be read out to the memory signal processing circuit 212 via the signal line L2.
- the memory signal processing circuit 212 performs AD conversion on the sum-of-products signal, which is an input analog signal.
- the memory signal processing circuit 212 can improve the accuracy of AD conversion by increasing the resolution of ADC, that is, the number of bits for AD conversion. Therefore, it is possible to improve the calculation accuracy of the sum-of-products calculation.
- the imaging apparatus 1 can perform pulse width modulation (PWM) control in the case of sum-of-products calculation.
- the memory control circuit 211 of the imaging device 1 outputs a signal Act, which is a pulse signal, to each memory cell 20 via the signal line L1.
- the memory control circuit 211 controls, for example, the pulse width of the signal Act to be different for each signal line L1 or for each of the plurality of signal lines L1.
- the signal Act input to each signal line L1 is set to low level for different times for each signal line L1 or for each of the plurality of signal lines L1, for example.
- the transistor M7 of each memory cell 20 outputs current according to the pulse width of the signal Act input to that memory cell 20.
- FIG. Charges corresponding to the period during which the signal Act is at low level are transferred from each memory cell 20 to the signal line L2 and added.
- the output signals of the memory cells 20 corresponding to the pulse width of the signal Act are added to form a sum-of-products signal.
- the potential of the sum-of-products signal changes according to the pulse width of each signal Act input to the memory cell array 200 .
- FIG. 10 is a diagram for explaining an example of sum-of-products calculation processing by the imaging device 1 according to the embodiment of the present disclosure.
- the voltage of the signal Act and the voltage of the sum-of-products signal are shown on the same time axis.
- a signal Act[0] shown in FIG. 10 is a signal commonly input to the first memory cell row.
- Signal Act[2], signal Act[n-2], and signal Act[n-1] are signals input to the second, n-1, and n-th memory cell rows, respectively. be.
- the PWM drive adjusts the value by which the signal value held in the memory cell 20 is multiplied.
- the gate of the transistor M7 of the memory cell 20 is electrically connected to the second retention node 32, but the gate of the transistor M7 is electrically connected to the first retention node 31 as shown in FIG. may be connected to One of the source and the drain of the transistor M7 is connected in series with the resistor R and electrically connected to the signal line L1 to which the signal Act is input. The other of the source and drain of the transistor M7 is electrically connected to the signal line L2.
- the transistor M7 can generate a current corresponding to the potential of the first holding node 31 and the potential of the signal Act applied to its gate, and can supply the generated current to the signal line L2.
- the imaging apparatus 1 may perform the control of the pulse amplitude modulation method.
- the input signal can be multi-valued, and a highly accurate sum-of-products operation can be realized.
- An arithmetic device (imaging device 1) includes a first inverter (INV1) having a first input section (input section 21a) and a first output section (output section 21b), and a first inverter (INV1) connected to the first output section. a second inverter (INV2) having a second input (input 22a) connected to the first input and a second output (output 22b) connected to the first input for outputting the first signal;
- a memory cell array 200 including a plurality of memory cells 20 each having a first transistor (transistor M7) to which a first signal is input and a resistor (resistor R) connected in series with the first transistor is provided.
- the imaging device 1 has a transistor M7 to which the signal held in the memory cell 20 is input, and a resistor R connected in series with the transistor M7.
- the charges generated by the transistor M7 of each memory cell 20 are added on the signal line L2 to obtain a product-sum signal. Therefore, the sum-of-products operation can be performed with a small memory cell area, and an increase in the memory cell area can be prevented. In addition, it is possible to perform highly accurate sum-of-products calculation with a small cell area.
- FIG. 12 is a diagram showing a configuration example of the memory cell array 200 of the imaging device 1 according to Modification 1 of the present disclosure.
- a signal line L2a to which the first sum-of-products signal is transmitted and a second sum-of-products signal are transmitted for each of the plurality of memory cells 20 arranged in the vertical direction.
- a signal line L2b are provided. It can also be said that the signal line L2a and the signal line L2b are provided for a memory cell column composed of a plurality of memory cells 20 arranged in the vertical direction.
- the signal line L2a and the signal line L2b are connected to the memory signal processing circuit 212 described above.
- the memory signal processing circuit 212 receives the first sum-of-products signal through the signal line L2a and the second sum-of-products signal through the signal line L2b.
- FIG. 13 is a diagram showing a configuration example of the memory cell 20 of the imaging device 1 according to Modification 1 of the present disclosure.
- the memory cell 20 has transistors M7a, M7b and resistors R1, R2.
- the transistor M7a and resistor R1 have the same configurations as the transistor M7 and resistor R in the above-described embodiment.
- a gate of the transistor M7a is electrically connected to the second holding node 32 and receives a signal from the output section 22b of the second inverter INV2.
- One of the source and drain of the transistor M7a is connected to the resistor R1 and electrically connected to the signal line L1 to which the signal Act is input.
- the other of the source and drain of the transistor M7a is electrically connected to the signal line L2a.
- the transistor M7a can generate a current according to the potential of the second holding node 32 and the potential of the signal Act applied to its gate, and can supply the generated current to the signal line L2a. Charges generated by the transistor M7a of each memory cell 20 are added on the signal line L2a to obtain a first sum-of-products signal.
- a gate of the transistor M7b is electrically connected to the first holding node 31 and receives a signal from the output section 21b of the first inverter INV1.
- One of the source and the drain of the transistor M7b is connected to the resistor R2 and electrically connected to the signal line L1 to which the signal Act is input.
- the other of the source and drain of the transistor M7b is electrically connected to the signal line L2b.
- the transistor M7b can generate a current corresponding to the potential of the first retention node 31 and the potential of the signal Act applied to its gate, and can supply the generated current to the signal line L2b.
- the charges generated by transistor M7b of each memory cell 20 are summed on signal line L2b to obtain a second sum-of-products signal.
- FIG. 14 is a diagram illustrating a configuration example of the memory cell 20 of the imaging device 1 according to Modification 2 of the present disclosure.
- One of the source and drain of transistor M7 is electrically connected to first retention node 31 .
- the other of the source and drain of the transistor M7 is connected in series with the resistor R and electrically connected to the signal line L1 to which the signal Act is input.
- the transistor M7 can generate a current corresponding to the input potential of the first holding node 31 and the potential of the signal Act, and supplies the generated current to the first bit line BL. obtain.
- the first bit line BL is also a summation line, and charges from each memory cell 20 can be summed on the first bit line BL to obtain a sum-of-products signal.
- the signal Act which is a pulse signal
- the word line WL may be input to the word line WL.
- a ground potential or a power supply potential may be applied to the signal line L1. Also in the case of this modification, it is possible to obtain the same effects as those of the imaging apparatus of the above-described embodiment.
- one of the source and drain of the transistor M7 may be electrically connected to the second retention node 32 as shown in FIG.
- the other of the source and drain of the transistor M7 is connected to the resistor R and electrically connected to the signal line L1 to which the signal Act is input, as in the case of FIG.
- the transistor M7 can generate a current corresponding to the input potential of the second holding node 32 and the potential of the signal Act, and can supply the generated current to the second bit line BLB.
- the second bit line BLB is also a sum line and the charge from each memory cell 20 can be summed at the second bit line BLB to obtain a sum of products signal.
- FIG. 16 is a diagram showing another configuration example of the memory cell 20 of the imaging device 1 according to Modification 2 of the present disclosure.
- the memory cell 20 has transistors M7a, M7b and resistors R1, R2.
- One of the source and drain of transistor M7a is electrically connected to first retention node 31 .
- one of the source and drain of the transistor M7b is electrically connected to the second retention node 32 .
- the transistor M7a When performing a sum-of-products operation, the transistor M7a can generate a current corresponding to the potential of the first holding node 31 and the potential of the signal Act, and can supply the generated current to the first bit line BL.
- the first bit line BL is also a first summing line and the charge from each memory cell 20 can be summed on the first bit line BL to obtain a first sum-of-products signal.
- the transistor M7b can generate a current corresponding to the potential of the second retention node 32 and the potential of the signal Act, and can supply the generated current to the second bit line BLB.
- the second bit line BLB is also a second summing line and the charge from each memory cell 20 can be summed at the second bit line BLB to obtain a second sum-of-products signal.
- FIG. 17 is a diagram illustrating a configuration example of the memory cell 20 of the imaging device 1 according to Modification 3 of the present disclosure.
- a back gate of each of the transistor M3 and the transistor M4 is electrically connected to the word line WL.
- the source of transistor M3 is connected to the first bit line BL, and the source of transistor M4 is connected to the second bit line BLB.
- the first bit line BL and the second bit line BLB are also power supply lines for the transistor M3 and the transistor M4, respectively.
- the threshold voltages of the transistors M3 and M4 are adjusted by the potential applied to the Bark gates of the transistors M3 and M4 via the word line WL.
- the transistors M3 and M4 can be on/off controlled, and data can be written to the memory cell 20 according to the signals of the first bit line BL and the second bit line BLB.
- the gate of the transistor M7 is electrically connected to the first retention node 31.
- One of the source and drain of the transistor M7 is connected to the resistor R and electrically connected to the signal line L1 to which the signal Act is input.
- the other of the source and drain of the transistor M7 is electrically connected to the signal line L2.
- the transistor M7 can generate a current corresponding to the potential of the first retention node 31 and the potential of the signal Act, and can supply the generated current to the signal line L2.
- the gate of the transistor M7 may be electrically connected to the second retention node 32 as shown in FIG. In the example shown in FIG.
- one of the source and drain of the transistor M7 is connected to the resistor R and electrically connected to the signal line L1 to which the signal Act is input.
- the other of the source and drain of the transistor M7 is electrically connected to the signal line L2.
- the transistor M7 can generate a current corresponding to the potential of the second retention node 32 and the potential of the signal Act, and supply the generated current to the signal line L2. Also in the case of this modification, it is possible to obtain the same effects as those of the imaging apparatus of the above-described embodiment.
- FIG. 19 is a diagram showing another configuration example of the memory cell 20 of the imaging device 1 according to Modification 3 of the present disclosure.
- the memory cell 20 has transistors M7a, M7b and resistors R1, R2.
- the gate of transistor M7a is electrically connected to first retention node 31 .
- the transistor M7a can generate a current corresponding to the potential of the first retention node 31 and the potential of the signal Act, and can supply the generated current to the signal line L2a. Charges generated by the transistor M7a of each memory cell 20 are added on the signal line L2a to obtain a first sum-of-products signal.
- the gate of the transistor M7b is electrically connected to the second holding node 32.
- the transistor M7b can generate a current corresponding to the potential of the second retention node 32 and the potential of the signal Act, and can supply the generated current to the signal line L2b.
- the charges generated by transistor M7b of each memory cell 20 are summed on signal line L2b to obtain a second sum-of-products signal.
- the first sum-of-products signal and the second sum-of-products signal can be read out, and high-precision sum-of-products calculation can be realized.
- FIG. 20 shows a schematic configuration of the electronic device 1000. As shown in FIG.
- the electronic device 1000 includes, for example, a lens group 1001, an imaging device 1, a DSP (Digital Signal Processor) circuit 1002, a frame memory 1003, a display unit 1004, a recording unit 1005, an operation unit 1006, and a power supply unit 1007. and are interconnected via a bus line 1008 .
- a lens group 1001 an imaging device 1
- a DSP (Digital Signal Processor) circuit 1002 a frame memory 1003, a display unit 1004, a recording unit 1005, an operation unit 1006, and a power supply unit 1007. and are interconnected via a bus line 1008 .
- DSP Digital Signal Processor
- a lens group 1001 captures incident light (image light) from a subject and forms an image on the imaging surface of the imaging device 1 .
- the imaging apparatus 1 converts the amount of incident light, which is imaged on the imaging surface by the lens group 1001 , into an electric signal for each pixel and supplies the electric signal to the DSP circuit 1002 as a pixel signal.
- the DSP circuit 1002 is a signal processing circuit that processes signals supplied from the imaging device 1 .
- a DSP circuit 1002 outputs image data obtained by processing a signal from the imaging device 1 .
- a frame memory 1003 temporarily holds image data processed by the DSP circuit 1002 in frame units.
- the display unit 1004 is, for example, a panel type display device such as a liquid crystal panel or an organic EL (Electro Luminescence) panel. to record.
- a panel type display device such as a liquid crystal panel or an organic EL (Electro Luminescence) panel. to record.
- the operation unit 1006 outputs operation signals for various functions of the electronic device 1000 in accordance with user's operations.
- the power supply unit 1007 appropriately supplies various power supplies to the DSP circuit 1002, the frame memory 1003, the display unit 1004, the recording unit 1005, and the operation unit 1006 as operating power supplies.
- the technology (the present technology) according to the present disclosure can be applied to various products.
- the technology according to the present disclosure can be realized as a device mounted on any type of moving body such as automobiles, electric vehicles, hybrid electric vehicles, motorcycles, bicycles, personal mobility, airplanes, drones, ships, and robots. may
- FIG. 21 is a block diagram showing a schematic configuration example of a vehicle control system, which is an example of a mobile control system to which the technology according to the present disclosure can be applied.
- a vehicle control system 12000 includes a plurality of electronic control units connected via a communication network 12001.
- the vehicle control system 12000 includes a drive system control unit 12010, a body system control unit 12020, an outside information detection unit 12030, an inside information detection unit 12040, and an integrated control unit 12050.
- a microcomputer 12051, an audio/image output unit 12052, and an in-vehicle network I/F (interface) 12053 are illustrated.
- the drive system control unit 12010 controls the operation of devices related to the drive system of the vehicle according to various programs.
- the driving system control unit 12010 includes a driving force generator for generating driving force of the vehicle such as an internal combustion engine or a driving motor, a driving force transmission mechanism for transmitting the driving force to the wheels, and a steering angle of the vehicle. It functions as a control device such as a steering mechanism to adjust and a brake device to generate braking force of the vehicle.
- the body system control unit 12020 controls the operation of various devices equipped on the vehicle body according to various programs.
- the body system control unit 12020 functions as a keyless entry system, a smart key system, a power window device, or a control device for various lamps such as headlamps, back lamps, brake lamps, winkers or fog lamps.
- body system control unit 12020 can receive radio waves transmitted from a portable device that substitutes for a key or signals from various switches.
- the body system control unit 12020 receives the input of these radio waves or signals and controls the door lock device, power window device, lamps, etc. of the vehicle.
- the vehicle exterior information detection unit 12030 detects information outside the vehicle in which the vehicle control system 12000 is installed.
- the vehicle exterior information detection unit 12030 is connected with an imaging section 12031 .
- the vehicle exterior information detection unit 12030 causes the imaging unit 12031 to capture an image of the exterior of the vehicle, and receives the captured image.
- the vehicle exterior information detection unit 12030 may perform object detection processing or distance detection processing such as people, vehicles, obstacles, signs, or characters on the road surface based on the received image.
- the imaging unit 12031 is an optical sensor that receives light and outputs an electrical signal according to the amount of received light.
- the imaging unit 12031 can output the electric signal as an image, and can also output it as distance measurement information.
- the light received by the imaging unit 12031 may be visible light or non-visible light such as infrared rays.
- the in-vehicle information detection unit 12040 detects in-vehicle information.
- the in-vehicle information detection unit 12040 is connected to, for example, a driver state detection section 12041 that detects the state of the driver.
- the driver state detection unit 12041 includes, for example, a camera that captures an image of the driver, and the in-vehicle information detection unit 12040 detects the degree of fatigue or concentration of the driver based on the detection information input from the driver state detection unit 12041. It may be calculated, or it may be determined whether the driver is dozing off.
- the microcomputer 12051 calculates control target values for the driving force generator, the steering mechanism, or the braking device based on the information inside and outside the vehicle acquired by the vehicle exterior information detection unit 12030 or the vehicle interior information detection unit 12040, and controls the drive system control unit.
- a control command can be output to 12010 .
- the microcomputer 12051 realizes the functions of ADAS (Advanced Driver Assistance System) including collision avoidance or shock mitigation, follow-up driving based on inter-vehicle distance, vehicle speed maintenance driving, vehicle collision warning, or vehicle lane deviation warning. Cooperative control can be performed for the purpose of ADAS (Advanced Driver Assistance System) including collision avoidance or shock mitigation, follow-up driving based on inter-vehicle distance, vehicle speed maintenance driving, vehicle collision warning, or vehicle lane deviation warning. Cooperative control can be performed for the purpose of ADAS (Advanced Driver Assistance System) including collision avoidance or shock mitigation, follow-up driving based on inter-vehicle distance, vehicle speed maintenance driving, vehicle collision warning, or vehicle
- the microcomputer 12051 controls the driving force generator, the steering mechanism, the braking device, etc. based on the information about the vehicle surroundings acquired by the vehicle exterior information detection unit 12030 or the vehicle interior information detection unit 12040, so that the driver's Cooperative control can be performed for the purpose of autonomous driving, etc., in which vehicles autonomously travel without depending on operation.
- the microcomputer 12051 can output a control command to the body system control unit 12020 based on the information outside the vehicle acquired by the information detection unit 12030 outside the vehicle.
- the microcomputer 12051 controls the headlamps according to the position of the preceding vehicle or the oncoming vehicle detected by the vehicle exterior information detection unit 12030, and performs cooperative control aimed at anti-glare such as switching from high beam to low beam. It can be carried out.
- the audio/image output unit 12052 transmits at least one of audio and/or image output signals to an output device capable of visually or audibly notifying the passengers of the vehicle or the outside of the vehicle.
- an audio speaker 12061, a display unit 12062, and an instrument panel 12063 are illustrated as output devices.
- the display unit 12062 may include at least one of an on-board display and a head-up display, for example.
- FIG. 22 is a diagram showing an example of the installation position of the imaging unit 12031.
- the vehicle 12100 has imaging units 12101, 12102, 12103, 12104, and 12105 as the imaging unit 12031.
- the imaging units 12101, 12102, 12103, 12104, and 12105 are provided at positions such as the front nose of the vehicle 12100, the side mirrors, the rear bumper, the back door, and the upper part of the windshield in the vehicle interior, for example.
- An image pickup unit 12101 provided in the front nose and an image pickup unit 12105 provided above the windshield in the passenger compartment mainly acquire images in front of the vehicle 12100 .
- Imaging units 12102 and 12103 provided in the side mirrors mainly acquire side images of the vehicle 12100 .
- An imaging unit 12104 provided in the rear bumper or back door mainly acquires an image behind the vehicle 12100 .
- Forward images acquired by the imaging units 12101 and 12105 are mainly used for detecting preceding vehicles, pedestrians, obstacles, traffic lights, traffic signs, lanes, and the like.
- FIG. 22 shows an example of the imaging range of the imaging units 12101 to 12104.
- the imaging range 12111 indicates the imaging range of the imaging unit 12101 provided in the front nose
- the imaging ranges 12112 and 12113 indicate the imaging ranges of the imaging units 12102 and 12103 provided in the side mirrors, respectively
- the imaging range 12114 The imaging range of an imaging unit 12104 provided in the rear bumper or back door is shown. For example, by superimposing the image data captured by the imaging units 12101 to 12104, a bird's-eye view image of the vehicle 12100 viewed from above can be obtained.
- At least one of the imaging units 12101 to 12104 may have a function of acquiring distance information.
- at least one of the imaging units 12101 to 12104 may be a stereo camera composed of a plurality of imaging elements, or may be an imaging element having pixels for phase difference detection.
- the microcomputer 12051 determines the distance to each three-dimensional object within the imaging ranges 12111 to 12114 and changes in this distance over time (relative velocity with respect to the vehicle 12100). , it is possible to extract, as the preceding vehicle, the closest three-dimensional object on the course of the vehicle 12100, which runs at a predetermined speed (for example, 0 km/h or more) in substantially the same direction as the vehicle 12100. can. Furthermore, the microcomputer 12051 can set the inter-vehicle distance to be secured in advance in front of the preceding vehicle, and perform automatic brake control (including following stop control) and automatic acceleration control (including following start control). In this way, cooperative control can be performed for the purpose of automatic driving in which the vehicle runs autonomously without relying on the operation of the driver.
- automatic brake control including following stop control
- automatic acceleration control including following start control
- the microcomputer 12051 converts three-dimensional object data related to three-dimensional objects to other three-dimensional objects such as motorcycles, ordinary vehicles, large vehicles, pedestrians, and utility poles. It can be classified and extracted and used for automatic avoidance of obstacles. For example, the microcomputer 12051 distinguishes obstacles around the vehicle 12100 into those that are visible to the driver of the vehicle 12100 and those that are difficult to see. Then, the microcomputer 12051 judges the collision risk indicating the degree of danger of collision with each obstacle, and when the collision risk is equal to or higher than the set value and there is a possibility of collision, an audio speaker 12061 and a display unit 12062 are displayed. By outputting an alarm to the driver via the drive system control unit 12010 and performing forced deceleration and avoidance steering via the drive system control unit 12010, driving support for collision avoidance can be performed.
- At least one of the imaging units 12101 to 12104 may be an infrared camera that detects infrared rays.
- the microcomputer 12051 can recognize a pedestrian by determining whether or not the pedestrian exists in the captured images of the imaging units 12101 to 12104 .
- recognition of a pedestrian is performed by, for example, a procedure for extracting feature points in images captured by the imaging units 12101 to 12104 as infrared cameras, and performing pattern matching processing on a series of feature points indicating the outline of an object to determine whether or not the pedestrian is a pedestrian.
- the audio image output unit 12052 outputs a rectangular outline for emphasis to the recognized pedestrian. is superimposed on the display unit 12062 . Also, the audio/image output unit 12052 may control the display unit 12062 to display an icon or the like indicating a pedestrian at a desired position.
- the technology according to the present disclosure can be applied to, for example, the imaging unit 12031 among the configurations described above.
- the imaging device 1 can be applied to the imaging unit 12031 .
- highly accurate control using captured images can be performed in the moving body control system.
- the technology (the present technology) according to the present disclosure can be applied to various products.
- the technology according to the present disclosure may be applied to an endoscopic surgery system.
- FIG. 23 is a diagram showing an example of a schematic configuration of an endoscopic surgery system to which the technology (this technology) according to the present disclosure can be applied.
- FIG. 23 shows how an operator (physician) 11131 is performing surgery on a patient 11132 on a patient bed 11133 using an endoscopic surgery system 11000 .
- an endoscopic surgery system 11000 includes an endoscope 11100, other surgical instruments 11110 such as a pneumoperitoneum tube 11111 and an energy treatment instrument 11112, and a support arm device 11120 for supporting the endoscope 11100. , and a cart 11200 loaded with various devices for endoscopic surgery.
- An endoscope 11100 is composed of a lens barrel 11101 whose distal end is inserted into the body cavity of a patient 11132 and a camera head 11102 connected to the proximal end of the lens barrel 11101 .
- an endoscope 11100 configured as a so-called rigid scope having a rigid lens barrel 11101 is illustrated, but the endoscope 11100 may be configured as a so-called flexible scope having a flexible lens barrel. good.
- the tip of the lens barrel 11101 is provided with an opening into which the objective lens is fitted.
- a light source device 11203 is connected to the endoscope 11100, and light generated by the light source device 11203 is guided to the tip of the lens barrel 11101 by a light guide extending inside the lens barrel 11101, where it reaches the objective. Through the lens, the light is irradiated toward the observation object inside the body cavity of the patient 11132 .
- the endoscope 11100 may be a straight scope, a perspective scope, or a side scope.
- An optical system and an imaging element are provided inside the camera head 11102, and the reflected light (observation light) from the observation target is focused on the imaging element by the optical system.
- the imaging element photoelectrically converts the observation light to generate an electric signal corresponding to the observation light, that is, an image signal corresponding to the observation image.
- the image signal is transmitted to a camera control unit (CCU: Camera Control Unit) 11201 as RAW data.
- CCU Camera Control Unit
- the CCU 11201 is composed of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), etc., and controls the operations of the endoscope 11100 and the display device 11202 in an integrated manner. Further, the CCU 11201 receives an image signal from the camera head 11102 and performs various image processing such as development processing (demosaicing) for displaying an image based on the image signal.
- CPU Central Processing Unit
- GPU Graphics Processing Unit
- the display device 11202 displays an image based on an image signal subjected to image processing by the CCU 11201 under the control of the CCU 11201 .
- the light source device 11203 is composed of a light source such as an LED (Light Emitting Diode), for example, and supplies the endoscope 11100 with irradiation light for photographing a surgical site or the like.
- a light source such as an LED (Light Emitting Diode), for example, and supplies the endoscope 11100 with irradiation light for photographing a surgical site or the like.
- the input device 11204 is an input interface for the endoscopic surgery system 11000.
- the user can input various information and instructions to the endoscopic surgery system 11000 via the input device 11204 .
- the user inputs an instruction or the like to change the imaging conditions (type of irradiation light, magnification, focal length, etc.) by the endoscope 11100 .
- the treatment instrument control device 11205 controls driving of the energy treatment instrument 11112 for tissue cauterization, incision, blood vessel sealing, or the like.
- the pneumoperitoneum device 11206 inflates the body cavity of the patient 11132 for the purpose of securing the visual field of the endoscope 11100 and securing the operator's working space, and injects gas into the body cavity through the pneumoperitoneum tube 11111. send in.
- the recorder 11207 is a device capable of recording various types of information regarding surgery.
- the printer 11208 is a device capable of printing various types of information regarding surgery in various formats such as text, images, and graphs.
- the light source device 11203 that supplies the endoscope 11100 with irradiation light for photographing the surgical site can be composed of, for example, a white light source composed of an LED, a laser light source, or a combination thereof.
- a white light source is configured by a combination of RGB laser light sources
- the output intensity and output timing of each color (each wavelength) can be controlled with high accuracy. It can be carried out.
- the observation target is irradiated with laser light from each of the RGB laser light sources in a time division manner, and by controlling the drive of the imaging device of the camera head 11102 in synchronization with the irradiation timing, each of RGB can be handled. It is also possible to pick up images by time division. According to this method, a color image can be obtained without providing a color filter in the imaging device.
- the driving of the light source device 11203 may be controlled so as to change the intensity of the output light every predetermined time.
- the drive of the imaging device of the camera head 11102 in synchronism with the timing of the change in the intensity of the light to obtain an image in a time-division manner and synthesizing the images, a high dynamic A range of images can be generated.
- the light source device 11203 may be configured to be able to supply light in a predetermined wavelength band corresponding to special light observation.
- special light observation for example, by utilizing the wavelength dependence of light absorption in body tissues, by irradiating light with a narrower band than the irradiation light (i.e., white light) during normal observation, the mucosal surface layer So-called narrow band imaging is performed, in which a predetermined tissue such as a blood vessel is imaged with high contrast.
- fluorescence observation may be performed in which an image is obtained from fluorescence generated by irradiation with excitation light.
- the body tissue is irradiated with excitation light and the fluorescence from the body tissue is observed (autofluorescence observation), or a reagent such as indocyanine green (ICG) is locally injected into the body tissue and the body tissue is A fluorescence image can be obtained by irradiating excitation light corresponding to the fluorescence wavelength of the reagent.
- the light source device 11203 can be configured to be able to supply narrowband light and/or excitation light corresponding to such special light observation.
- FIG. 24 is a block diagram showing an example of functional configurations of the camera head 11102 and CCU 11201 shown in FIG.
- the camera head 11102 has a lens unit 11401, an imaging section 11402, a drive section 11403, a communication section 11404, and a camera head control section 11405.
- the CCU 11201 has a communication section 11411 , an image processing section 11412 and a control section 11413 .
- the camera head 11102 and the CCU 11201 are communicably connected to each other via a transmission cable 11400 .
- a lens unit 11401 is an optical system provided at a connection with the lens barrel 11101 . Observation light captured from the tip of the lens barrel 11101 is guided to the camera head 11102 and enters the lens unit 11401 .
- a lens unit 11401 is configured by combining a plurality of lenses including a zoom lens and a focus lens.
- the imaging unit 11402 is composed of an imaging element.
- the imaging device constituting the imaging unit 11402 may be one (so-called single-plate type) or plural (so-called multi-plate type).
- image signals corresponding to RGB may be generated by each image pickup element, and a color image may be obtained by synthesizing the image signals.
- the imaging unit 11402 may be configured to have a pair of imaging elements for respectively acquiring right-eye and left-eye image signals corresponding to 3D (Dimensional) display.
- the 3D display enables the operator 11131 to more accurately grasp the depth of the living tissue in the surgical site.
- a plurality of systems of lens units 11401 may be provided corresponding to each imaging element.
- the imaging unit 11402 does not necessarily have to be provided in the camera head 11102 .
- the imaging unit 11402 may be provided inside the lens barrel 11101 immediately after the objective lens.
- the drive unit 11403 is configured by an actuator, and moves the zoom lens and focus lens of the lens unit 11401 by a predetermined distance along the optical axis under control from the camera head control unit 11405 . Thereby, the magnification and focus of the image captured by the imaging unit 11402 can be appropriately adjusted.
- the communication unit 11404 is composed of a communication device for transmitting and receiving various information to and from the CCU 11201.
- the communication unit 11404 transmits the image signal obtained from the imaging unit 11402 as RAW data to the CCU 11201 via the transmission cable 11400 .
- the communication unit 11404 receives a control signal for controlling driving of the camera head 11102 from the CCU 11201 and supplies it to the camera head control unit 11405 .
- the control signal includes, for example, information to specify the frame rate of the captured image, information to specify the exposure value at the time of imaging, and/or information to specify the magnification and focus of the captured image. Contains information about conditions.
- the imaging conditions such as the frame rate, exposure value, magnification, and focus may be appropriately designated by the user, or may be automatically set by the control unit 11413 of the CCU 11201 based on the acquired image signal. good.
- the endoscope 11100 is equipped with so-called AE (Auto Exposure) function, AF (Auto Focus) function, and AWB (Auto White Balance) function.
- the camera head control unit 11405 controls driving of the camera head 11102 based on the control signal from the CCU 11201 received via the communication unit 11404.
- the communication unit 11411 is composed of a communication device for transmitting and receiving various information to and from the camera head 11102 .
- the communication unit 11411 receives image signals transmitted from the camera head 11102 via the transmission cable 11400 .
- the communication unit 11411 transmits a control signal for controlling driving of the camera head 11102 to the camera head 11102 .
- Image signals and control signals can be transmitted by electrical communication, optical communication, or the like.
- the image processing unit 11412 performs various types of image processing on the image signal, which is RAW data transmitted from the camera head 11102 .
- the control unit 11413 performs various controls related to imaging of the surgical site and the like by the endoscope 11100 and display of the captured image obtained by imaging the surgical site and the like. For example, the control unit 11413 generates control signals for controlling driving of the camera head 11102 .
- control unit 11413 causes the display device 11202 to display a captured image showing the surgical site and the like based on the image signal that has undergone image processing by the image processing unit 11412 .
- the control unit 11413 may recognize various objects in the captured image using various image recognition techniques. For example, the control unit 11413 detects the shape, color, and the like of the edges of objects included in the captured image, thereby detecting surgical instruments such as forceps, specific body parts, bleeding, mist during use of the energy treatment instrument 11112, and the like. can recognize.
- the control unit 11413 may use the recognition result to display various types of surgical assistance information superimposed on the image of the surgical site. By superimposing and presenting the surgery support information to the operator 11131, the burden on the operator 11131 can be reduced and the operator 11131 can proceed with the surgery reliably.
- a transmission cable 11400 connecting the camera head 11102 and the CCU 11201 is an electrical signal cable compatible with electrical signal communication, an optical fiber compatible with optical communication, or a composite cable of these.
- wired communication is performed using the transmission cable 11400, but communication between the camera head 11102 and the CCU 11201 may be performed wirelessly.
- the technology according to the present disclosure can be preferably applied to, for example, the imaging unit 11402 provided in the camera head 11102 of the endoscope 11100 among the configurations described above.
- the technology according to the present disclosure it is possible to provide the endoscope 11100 with high accuracy.
- a first inverter having a first input and a first output; a second inverter having a second input connected to the first output and a second output connected to the first input for outputting a first signal; a first transistor to which the first signal is input from the second output section; a resistor connected in series with the first transistor;
- a computing device comprising a memory cell array including a plurality of memory cells each having (2) the first transistor having a gate connected to the first output; The arithmetic device according to (1), wherein the resistor is connected to a source or a drain of the first transistor.
- the memory cell includes a second transistor connectable between the first output section and a first bit line, and a third transistor connectable between the second output section and a second bit line.
- a signal processing circuit that processes the second signal The arithmetic device according to any one of (1) to (6), wherein the signal processing circuit performs at least one of analog-to-digital conversion processing, activation function processing, and pooling processing.
- the signal processing circuit performs at least one of analog-to-digital conversion processing, activation function processing, and pooling processing.
- (8) According to any one of (1) to (7), further comprising a signal line electrically connected to the first transistor of each of the plurality of memory cells and transmitting a second signal subjected to a sum-of-products operation. Arithmetic unit.
- a control circuit that controls the memory cell, the signal processing circuit and the signal line are provided side by side in a first direction, The arithmetic device according to any one of (1) to (8), wherein the control circuit and the signal line are provided side by side in a direction orthogonal to the first direction.
- the resistor is a resistive element having a tunnel junction.
- the resistance element includes a magnetic material.
- the resistive element includes a ferroelectric.
- a solid-state imaging device comprising a memory cell array including a plurality of memory cells each having
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Neurology (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Microelectronics & Electronic Packaging (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Neurosurgery (AREA)
- Physiology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Solid State Image Pick-Up Elements (AREA)
Abstract
Description
本開示の一実施形態の固体撮像装置は、第1入力部および第1出力部を有する第1インバータと、第1出力部に接続される第2入力部および第1入力部に接続されて第1信号を出力する第2出力部を有する第2インバータと、第2出力部から第1信号が入力される第1トランジスタと、第1トランジスタに直列に接続される抵抗と、をそれぞれ有するメモリセルを複数含むメモリセルアレイを備える。
1.実施の形態
2.変形例
3.適用例
4.応用例
図1は、本開示の実施の形態に係る演算装置の一例である撮像装置1の全体構成の一例を示すブロック図である。撮像装置1は、固体撮像装置であり、入射した光を光電変換し、被写体の像を撮像する。撮像装置1は、積和演算を実行可能なメモリセルアレイを有し、非ノイマン型演算器であるメモリセルアレイ上で演算を行うCIM(Computing in memory)を実現している。メモリセルアレイをニューラルネットワークの積和演算に利用することで、ノイマン型演算器の課題である回路規模や消費電力の増大を解決することが期待できる。固体撮像装置である撮像装置1は、例えばCMOS(Complementary Metal Oxide Semiconductor)イメージセンサである。
撮像装置1は、複数の画素Pが2次元状に配置された画素部100を、撮像エリアとして有している。画素部100は、画素Pが行列状に配置される画素アレイともいえる。また、撮像装置1は、複数のメモリセル20が行列状に配置されたメモリセルアレイ200を有する。図1に示す例では、撮像装置1は、第1基板101及び第2基板201を備える。第1基板101及び第2基板201は、それぞれ半導体基板(例えばシリコン基板)により構成され、互いに重なり合って積層される。
図5は、本開示の実施の形態に係る撮像装置1のメモリセルアレイ200の構成例を示す図である。図5に示すように、撮像装置1のメモリセルアレイ200では、複数のメモリセル20が、第1方向である水平方向(行方向)、及び第1方向と直交する第2方向である垂直方向(列方向)に配置される。複数のメモリセル20が、左右方向(紙面横方向)及び上下方向(紙面縦方向)に配置されるともいえる。
図6は、本開示の実施の形態に係る撮像装置1のメモリセル20の構成例を示す図である。図7は、メモリセル20のレイアウト例を示す図である。メモリセル20は、第1インバータINV1と、第2インバータINV2と、トランジスタM5と、トランジスタM6と、トランジスタM7と、抵抗Rとを有する。メモリセル20は、1ビットの情報を記憶可能な記憶素子である。メモリセル20は、第1インバータINV1及び第2インバータINV2を含むフリップフロップ回路30を有し、フリップフロップ型のメモリセルともいえる。
本実施の形態に係る演算装置(撮像装置1)は、第1入力部(入力部21a)および第1出力部(出力部21b)を有する第1インバータ(INV1)と、第1出力部に接続される第2入力部(入力部22a)および第1入力部に接続されて第1信号を出力する第2出力部(出力部22b)を有する第2インバータ(INV2)と、第2出力部から第1信号が入力される第1トランジスタ(トランジスタM7)と、第1トランジスタに直列に接続される抵抗(抵抗R)と、をそれぞれ有するメモリセル20を複数含むメモリセルアレイ200を備える。
(2-1.変形例1)
図12は、本開示の変形例1に係る撮像装置1のメモリセルアレイ200の構成例を示す図である。図12に示す例では、メモリセルアレイ200では、垂直方向に配置された複数のメモリセル20毎に、第1の積和信号が伝送される信号線L2aと、第2の積和信号が伝送される信号線L2bとが設けられる。垂直方向に並ぶ複数のメモリセル20により構成されるメモリセル列に対して、信号線L2a及び信号線L2bが設けられるともいえる。例えば、信号線L2a及び信号線L2bは、上述したメモリ信号処理回路212に接続される。メモリ信号処理回路212には、信号線L2aを介して第1の積和信号が入力され、信号線L2bを介して第2の積和信号が入力される。
図14は、本開示の変形例2に係る撮像装置1のメモリセル20の構成例を示す図である。トランジスタM7のソース及びドレインの一方は、第1保持ノード31と電気的に接続される。トランジスタM7のソース及びドレインの他方は、抵抗Rに直列に接続され、信号Actが入力される信号線L1に電気的に接続される。積和演算を行う場合、トランジスタM7は、入力される第1保持ノード31の電位と信号Actの電位とに応じた電流を生成可能であり、生成した電流を第1のビット線BLに供給し得る。
図17は、本開示の変形例3に係る撮像装置1のメモリセル20の構成例を示す図である。トランジスタM3及びトランジスタM4の各々のバックゲートが、ワード線WLに電気的に接続される。トランジスタM3のソースは、第1のビット線BLに接続され、トランジスタM4のソースは、第2のビット線BLBに接続される。第1のビット線BL、第2のビット線BLBは、それぞれ、トランジスタM3、トランジスタM4に対する電源線でもある。本変形例では、データの書き込みを行う場合、ワード線WLを介してトランジスタM3,M4のバークゲートに与えられる電位によって、トランジスタM3,M4のしきい値電圧が調整される。これにより、トランジスタM3,M4のオンオフ制御を行うことができ、第1のビット線BL及び第2のビット線BLBの信号に応じて、メモリセル20にデータを書き込むことが可能となる。
上記撮像装置1等は、例えば、デジタルスチルカメラやビデオカメラ等のカメラシステムや、撮像機能を有する携帯電話等、撮像機能を備えたあらゆるタイプの電子機器に適用することができる。図20は、電子機器1000の概略構成を表したものである。
(移動体への応用例)
本開示に係る技術(本技術)は、様々な製品へ応用することができる。例えば、本開示に係る技術は、自動車、電気自動車、ハイブリッド電気自動車、自動二輪車、自転車、パーソナルモビリティ、飛行機、ドローン、船舶、ロボット等のいずれかの種類の移動体に搭載される装置として実現されてもよい。
本開示に係る技術(本技術)は、様々な製品へ応用することができる。例えば、本開示に係る技術は、内視鏡手術システムに適用されてもよい。
(1)
第1入力部および第1出力部を有する第1インバータと、
前記第1出力部に接続される第2入力部および前記第1入力部に接続されて第1信号を出力する第2出力部を有する第2インバータと、
前記第2出力部から前記第1信号が入力される第1トランジスタと、
前記第1トランジスタに直列に接続される抵抗と、
をそれぞれ有するメモリセルを複数含むメモリセルアレイを備えた
演算装置。
(2)
前記第1トランジスタは、前記第1出力部に接続されるゲートを有し、
前記抵抗は、前記第1トランジスタのソースまたはドレインに接続される
前記(1)に記載の演算装置。
(3)
第1のビット線および第2のビット線を有し、
前記メモリセルは、前記第1出力部と第1のビット線とを接続可能な第2トランジスタと、前記第2出力部と第2のビット線とを接続可能な第3トランジスタと、を有する
前記(1)または(2)に記載の演算装置。
(4)
前記メモリセルは、フリップフロップ型のメモリセルである
前記(1)から(3)のいずれか1つに記載の演算装置。
(5)
前記メモリセルアレイは、前記メモリセル毎の前記第1信号に基づく積和演算を行う
前記(1)から(4)のいずれか1つに記載の演算装置。
(6)
前記メモリセルアレイは、積和演算によりアナログ信号である第2信号を生成する
前記(1)から(5)のいずれか1つに記載の演算装置。
(7)
前記第2信号を処理する信号処理回路を備え、
前記信号処理回路は、アナログデジタル変換処理、活性化関数による処理、プーリング処理の少なくとも一つを行う
前記(1)から(6)のいずれか1つに記載の演算装置。
(8)
複数の前記メモリセルの各々の前記第1トランジスタに電気的に接続され、積和演算された第2信号を伝送する信号線を備える
前記(1)から(7)のいずれか1つに記載の演算装置。
(9)
前記メモリセルを制御する制御回路を備え、
前記信号処理回路と前記信号線とは、第1方向に並んで設けられ、
前記制御回路と前記信号線とは、前記第1方向と直交する方向に並んで設けられる
前記(1)から(8)のいずれか1つに記載の演算装置。
(10)
前記抵抗は、トンネル接合を有する抵抗素子である
前記(9)に記載の演算装置。
(11)
前記抵抗素子は、磁性体を含んで構成されている
前記(10)に記載の演算装置。
(12)
前記抵抗素子は、強誘電体を含んで構成されている
前記(10)に記載の演算装置。
(13)
第1入力部および第1出力部を有する第1インバータと、
前記第1出力部に接続される第2入力部および前記第1入力部に接続されて第1信号を出力する第2出力部を有する第2インバータと、
前記第2出力部から前記第1信号が入力される第1トランジスタと、
前記第1トランジスタに直列に接続される抵抗と、
をそれぞれ有するメモリセルを複数含むメモリセルアレイを備えた
固体撮像装置。
Claims (13)
- 第1入力部および第1出力部を有する第1インバータと、
前記第1出力部に接続される第2入力部および前記第1入力部に接続されて第1信号を出力する第2出力部を有する第2インバータと、
前記第2出力部から前記第1信号が入力される第1トランジスタと、
前記第1トランジスタに直列に接続される抵抗と、
をそれぞれ有するメモリセルを複数含むメモリセルアレイを備えた
演算装置。 - 前記第1トランジスタは、前記第1出力部に接続されるゲートを有し、
前記抵抗は、前記第1トランジスタのソースまたはドレインに接続される
請求項1に記載の演算装置。 - 第1のビット線および第2のビット線を有し、
前記メモリセルは、前記第1出力部と第1のビット線とを接続可能な第2トランジスタと、前記第2出力部と第2のビット線とを接続可能な第3トランジスタと、を有する
請求項1に記載の演算装置。 - 前記メモリセルは、フリップフロップ型のメモリセルである
請求項1に記載の演算装置。 - 前記メモリセルアレイは、前記メモリセル毎の前記第1信号に基づく積和演算を行う
請求項1に記載の演算装置。 - 前記メモリセルアレイは、積和演算によりアナログ信号である第2信号を生成する
請求項5に記載の演算装置。 - 前記第2信号を処理する信号処理回路を備え、
前記信号処理回路は、アナログデジタル変換処理、活性化関数による処理、プーリング処理の少なくとも一つを行う
請求項6に記載の演算装置。 - 複数の前記メモリセルの各々の前記第1トランジスタに電気的に接続され、積和演算された第2信号を伝送する信号線を備える
請求項7に記載の演算装置。 - 前記メモリセルを制御する制御回路を備え、
前記信号処理回路と前記信号線とは、第1方向に並んで設けられ、
前記制御回路と前記信号線とは、前記第1方向と直交する方向に並んで設けられる
請求項8に記載の演算装置。 - 前記抵抗は、トンネル接合を有する抵抗素子である
請求項1に記載の演算装置。 - 前記抵抗素子は、磁性体を含んで構成されている
請求項10に記載の演算装置。 - 前記抵抗素子は、強誘電体を含んで構成されている
請求項10に記載の演算装置。 - 第1入力部および第1出力部を有する第1インバータと、
前記第1出力部に接続される第2入力部および前記第1入力部に接続されて第1信号を出力する第2出力部を有する第2インバータと、
前記第2出力部から前記第1信号が入力される第1トランジスタと、
前記第1トランジスタに直列に接続される抵抗と、
をそれぞれ有するメモリセルを複数含むメモリセルアレイを備えた
固体撮像装置。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202280078010.XA CN118302813A (zh) | 2021-11-30 | 2022-10-13 | 运算装置和固态成像装置 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2021193741 | 2021-11-30 | ||
| JP2021-193741 | 2021-11-30 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023100490A1 true WO2023100490A1 (ja) | 2023-06-08 |
Family
ID=86611927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2022/038204 Ceased WO2023100490A1 (ja) | 2021-11-30 | 2022-10-13 | 演算装置および固体撮像装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN118302813A (ja) |
| WO (1) | WO2023100490A1 (ja) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117786291A (zh) * | 2023-07-12 | 2024-03-29 | 香港科技大学 | 一种计算单元、卷积计算器及卷积计算器的计算方法 |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021215112A1 (ja) * | 2020-04-22 | 2021-10-28 | ソニーセミコンダクタソリューションズ株式会社 | 半導体装置 |
-
2022
- 2022-10-13 CN CN202280078010.XA patent/CN118302813A/zh active Pending
- 2022-10-13 WO PCT/JP2022/038204 patent/WO2023100490A1/ja not_active Ceased
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021215112A1 (ja) * | 2020-04-22 | 2021-10-28 | ソニーセミコンダクタソリューションズ株式会社 | 半導体装置 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117786291A (zh) * | 2023-07-12 | 2024-03-29 | 香港科技大学 | 一种计算单元、卷积计算器及卷积计算器的计算方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118302813A (zh) | 2024-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12191326B2 (en) | Solid-state imaging device | |
| JP7341141B2 (ja) | 撮像装置および電子機器 | |
| WO2021106732A1 (ja) | 撮像装置および電子機器 | |
| KR20220068990A (ko) | 촬상 장치 | |
| JP7520804B2 (ja) | 信号処理方法および撮像装置 | |
| WO2021235101A1 (ja) | 固体撮像装置 | |
| WO2018225306A1 (ja) | 固体撮像素子および撮像装置 | |
| WO2021029269A1 (ja) | 情報処理装置、情報処理方法、および情報処理プログラム | |
| WO2023100490A1 (ja) | 演算装置および固体撮像装置 | |
| WO2023210203A1 (ja) | 固体撮像装置 | |
| US20230005993A1 (en) | Solid-state imaging element | |
| WO2021132102A1 (ja) | 撮像装置および電子機器 | |
| WO2023153086A1 (ja) | 撮像素子および撮像素子の駆動方法 | |
| WO2023105935A1 (ja) | 撮像装置 | |
| CN116325782A (zh) | 摄像装置 | |
| WO2021100446A1 (ja) | 固体撮像装置及び電子機器 | |
| EP4618394A1 (en) | Failure determination circuit, image capturing device, and voltage detection circuit | |
| JP7414569B2 (ja) | 固体撮像素子 | |
| JP2019022020A (ja) | 固体撮像素子、固体撮像素子の駆動方法および電子機器 | |
| WO2023210194A1 (ja) | 固体撮像装置 | |
| WO2024057810A1 (ja) | 撮像装置、撮像システム、及び、撮像装置の駆動方法 | |
| WO2024024269A1 (ja) | 固体撮像装置およびその製造方法 | |
| WO2026079140A1 (ja) | 光検出装置および電子機器 | |
| WO2026023245A1 (ja) | 固体撮像装置 | |
| WO2025004580A1 (ja) | 固体撮像装置 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22900924 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 18703917 Country of ref document: US |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202280078010.X Country of ref document: CN |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 22900924 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: JP |