Abstract: An integrated circuit may include an AI logic circuit, and an embedded one-time programmable (OTP) MRAM memory electrically coupled to the AI logic circuit. The embedded OTP MRAM memory may include multiple storage cells, one or more reference resistors, and a memory-reading circuit for determining the state of each storage cell. The reading circuit may include: a multiplexer configured to electrically couple each storage cell to a reference resistor; a source line selectively providing an input electrical signal to each storage cell to generate a first output signal; a driving circuit providing an input electrical signal to the reference resistor to generate a second output signal; and a comparator configured to compare the first output signal and the second output signal to generate an output signal that indicates the state of each storage cell. Each reference resistor may be shared among multiple storages in an array or multiple storage arrays.

Abstract: Fabrication methods of forming memory subsystem of CNN based digital IC for AI are disclosed. The method in SLC technology includes: providing a metal layer, forming a via layer, forming a HSL, forming a MTJ element layer and then etching out unmasked portions of the MTJ element layer to form at least two groups of different sized MTJ elements. The method in MLC technology includes: providing a metal layer, forming a via layer, forming a first HSL, forming a first MTJ element layer, etching out unmasked portions of the first MTJ element layer to form lower MTJ elements, forming a second HSL, forming a second MTJ element layer and etching out unmasked portions of the second MTJ element layer to form upper MTJ elements. Same sized first MTJ element layer and the second HSL are formed together.

Abstract: An integrated circuit includes an artificial intelligence (AI) logic and an embedded memory coupled to the AI logic and connectable to an external processor. The embedded memory includes multiple storage cells and multiple reference units. One or more reference units in the memory are selected for memory access through configuration at chip packaging level by the external processor. The external processor may execute a self-test process to select or update the one or more reference units for memory access so that the error rate of memory is below a threshold. The self-test process may be performed, via a memory initialization controller in the memory, to test and reuse the reference cells in the memory at chip level. The embedded memory may be a STT-MRAM, SOT, OST MRAM, and/or MeRAM memory.

Abstract: Systems and methods for forming embedded memory in a processing unit. The methods include: depositing a dielectric layer on a metal landing pad of a logic circuit of a processing unit; opening vias in the dielectric layer; filling in the vias; performing chemical mechanical polishing (CMP); depositing an adhesion and topography planarization (ATP) layer; etching away portions of the ATP layer; filling in with inter layer dielectric (ILD) materials; performing CMP; depositing a MTJ film layer; patterning and etching away portions of the MTJ film layer; filling in with dielectric materials; performing CMP; and forming a bit line on the top layer. The methods may also include annealing in a forming gas during different steps of the above processed to reduce the high stress from the making of multi-metal layers of the processing unit at high temperature. This may prevent wafer warpage and/or significant topography in the fabrication process.

Abstract: A method of forming a sensor array comprising a series connection of parallel GMR sensor stripes that provides a sensitive mechanism for detecting the presence of magnetized particles bonded to biological molecules that are affixed to a substrate. The adverse effect of hysteresis on the maintenance of a stable bias point for the magnetic moment of the sensor free layer is eliminated by a combination of biasing the sensor along its longitudinal direction rather than the usual transverse direction and by using the overcoat stress and magnetostriction of magnetic layers to create a compensatory transverse magnetic anisotropy. By making the spaces between the stripes narrower than the dimension of the magnetized particle and by making the width of the stripes equal to the dimension of the particle, the sensitivity of the sensor array is enhanced.

Abstract: Systems and methods for forming embedded memory in a processing unit. The methods include: depositing a dielectric layer on a metal landing pad of a logic circuit of a processing unit; opening vias in the dielectric layer; filling in the vias; performing chemical mechanical polishing (CMP); depositing an adhesion and topography planarization (ATP) layer; etching away portions of the ATP layer; filling in with inter layer dielectric (ILD) materials; performing CMP; depositing a MTJ film layer; patterning and etching away portions of the MTJ film layer; filling in with dielectric materials; performing CMP; and forming a bit line on the top layer. The methods may also include annealing in a forming gas during different steps of the above processed to reduce the high stress from the making of multi-metal layers of the processing unit at high temperature. This may prevent wafer warpage and/or significant topography in the fabrication process.

Abstract: Fabrication methods of forming memory subsystem of CNN based digital IC for AI are disclosed. The method in SLC technology includes: providing a metal layer, forming a via layer, forming a HSL, forming a MTJ element layer and then etching out unmasked portions of the MTJ element layer to form at least two groups of different sized MTJ elements. The method in MLC technology includes: providing a metal layer, forming a via layer, forming a first HSL, forming a first MTJ element layer, etching out unmasked portions of the first MTJ element layer to form lower MTJ elements, forming a second HSL, forming a second MTJ element layer and etching out unmasked portions of the second MTJ element layer to form upper MTJ elements. Same sized first MTJ element layer and the second HSL are formed together.

Abstract: CNN (Cellular Neural Networks or Cellular Nonlinear Networks) based digital Integrated Circuit for artificial intelligence contains multiple CNN processing units. Each CNN processing unit contains CNN logic circuits operatively coupling to a memory subsystem having first and second memories. The first memory contains magnetic random access memory (MRAM) cells for storing weights (e.g., filter coefficients) while the second memory is for storing input signals (e.g., imagery data). The first memory may store one-time-programming weights. The memory subsystem may contain a third memory that contains MRAM cells for storing one-time-programming data for security purpose. The second memory contains MRAM cells or static random access memory cells. Each MRAM cell contains a Spin-Orbit-Torque (SOT) based magnetic tunnel junction (MTJ) element.

Abstract: Embedded memory subsystems in a digital integrated circuit for artificial intelligence are disclosed. A semi-conductor substrate contains CNN processing units. Each CNN processing unit includes CNN logic circuits and an embedded memory subsystem. The memory subsystem includes first memory and second memory. The first memory contains an array of MTJ STT-RAM cells with each cell has a circular planar area with a diameter in a range of 40-120 nm. The second memory contains an array of MTJ STT-RAM cells with each cell has a circular planar area having a diameter in a range of 30-75 nm.

Abstract: CNN based digital IC for AI contains a number of CNN processing units. Each CNN processing unit contains CNN logic circuits operatively coupling to a memory subsystem having first and second memories. The first memory includes an array of magnetic random access memory (RAM) cells for storing weights (e.g., filter coefficients) and the second memory contains SRAM for storing input signals (e.g., imagery data). The first memory may store one-time-programming weights. The memory subsystem may contain a third memory that contains magnetic RAM cells for storing one-time-programming data for security purpose. The magnetic RAM includes STT-RAM or OST-MRAM in SLC or MLC technology.

Abstract: CNN (Cellular Neural Networks or Cellular Nonlinear Networks) based digital Integrated Circuit for artificial intelligence contains multiple CNN processing units. Each CNN processing unit contains CNN logic circuits operatively coupling to a memory subsystem having first and second memories. The first memory contains magnetic random access memory (MRAM) cells for storing weights (e.g., filter coefficients) while the second memory is for storing input signals (e.g., imagery data). The first memory may store one-time-programming weights or filter coefficients. The memory subsystem may contain a third memory that contains MRAM cells for storing one-time-programming data for security purpose. The second memory contains MRAM cells or static random access memory cells. Each MRAM cell contains a voltage-controlled magnetic anisotropy (VCMA) based magnetic tunnel junction (MTJ) element. Magnetization direction in VCMA based MTJ element can be in-plane or out-of-plane.

Abstract: CNN based digital IC for AI contains a number of CNN processing units. A first CNN processing unit contains CNN logic circuits operatively coupling to a memory subsystem, which includes a first one-time-programming (OTP) memory for filter coefficients and a second memory for imagery data. A second CNN processing unit contains CNN logic circuits operatively coupling to a memory subsystem that includes a first memory for filter coefficients, a second memory for imagery data and a third OTP memory for unique data pattern (e.g., security purpose). Either STT-RAM or OST-MRAM can be configured as different memories of the memory subsystem.

Abstract: CNN based digital IC for AI contains a number of CNN processing units. Each CNN processing unit contains CNN logic circuits operatively coupling to a memory subsystem. A first subsystem includes an array of first magnetic random access memory (RAM) cells for storing weights and an array of second magnetic RAM cells for storing input signals. A second subsystem includes an array of first magnetic RAM cells for storing one-time-programming weights and an array of second magnetic RAM cells for storing input signals. A third subsystem includes an array of first magnetic RAM cells for storing weights, an array of second magnetic RAM cells for storing input signals and an array of third magnetic RAM cells for storing one-time-programming unique data pattern for security identification. Either MLC STT-RAM or MLC OST-MRAM containing at least two MTJ elements can be configured as different memories for forming memory subsystem.

Abstract: An integrated circuit processor having a processing unit that includes a logical circuit with multiple transistors and a top metal landing pad, and an embedded STT memory. The STT memory includes a dielectric layer formed on the top metal landing pad, an adhesion and topography planarization (ATP) layer formed on the dielectric layer, and an MTJ film layer disposed on the ATP layer. The memory may also include bit lines formed on the MTJ film layer. The ATP layer may have multiple layers such as a top layer and a bottom layer. The top layer may act as an etch stop for etching the MTJ film layer on the top. The ATP layer may have a total thickness of 500 A to 4000 A. The bit lines can be configured to send data to the logic circuit of the processing unit to perform one or more convolution neural network computations.

Abstract: A method of forming a sensor array comprising a series connection of parallel GMR sensor stripes that provides a sensitive mechanism for detecting the presence of magnetized particles bonded to biological molecules that are affixed to a substrate. The adverse effect of hysteresis on the maintenance of a stable bias point for the magnetic moment of the sensor free layer is eliminated by a combination of biasing the sensor along its longitudinal direction rather than the usual transverse direction and by using the overcoat stress and magnetostriction of magnetic layers to create a compensatory transverse magnetic anisotropy. By making the spaces between the stripes narrower than the dimension of the magnetized particle and by making the width of the stripes equal to the dimension of the particle, the sensitivity of the sensor array is enhanced.

Abstract: A MTJ in an MRAM array is disclosed with a composite free layer having a lower crystalline layer contacting a tunnel barrier and an upper amorphous layer for improved bit switching performance. According to one embodiment, the amorphous layer has a NiFeM1/NiFeM2 configuration where M1 and M2 are Mg, Hf, Zr, Nb, or Ta, and M1 is unequal to M2. The crystalline layer is Fe, Ni, or FeB with a thickness of at least 6 Angstroms that affords a high magnetoresistive ratio. The M1 and M2 elements in the NiFeM1 and NiFeM2 layers each have a content of 5 to 30 atomic %. The NiFeM1/NiFeM2 configuration substantially reduces bit line switching current and number of shorted bits. In an alternative embodiment, the crystalline layer may be a Fe/NiFe bilayer. Annealing at 300° C. to 360° C. provides a high magnetoresistive ratio of about 150%.

Abstract: A sensor array comprising a series connection of parallel GMR sensor stripes provides a sensitive mechanism for detecting the presence of magnetized particles bonded to biological molecules that are affixed to a substrate. The adverse effect of hysteresis on the maintenance of a stable bias point for the magnetic moment of the sensor free layer is eliminated by a combination of biasing the sensor along its longitudinal direction rather than the usual transverse direction and by using the overcoat stress and magnetostriction of magnetic layers to create a compensatory transverse magnetic anisotropy. By making the spaces between the stripes narrower than the dimension of the magnetized particle and by making the width of the stripes equal to the dimension of the particle, the sensitivity of the sensor array is enhanced.

Abstract: A MTJ in an MRAM array is disclosed with a composite free layer having a lower crystalline layer contacting a tunnel barrier and an upper amorphous layer for improved bit switching performance. According to one embodiment, the amorphous layer has a NiFeM1/NiFeM2 configuration where M1 and M2 are Mg, Hf, Zr, Nb, or Ta, and M1 is unequal to M2. The crystalline layer is Fe, Ni, or FeB with a thickness of at least 6 Angstroms that affords a high magnetoresistive ratio. The M1 and M2 elements in the NiFeM1 and NiFeM2 layers each have a content of 5 to 30 atomic %. The NiFeM1/NiFeM2 configuration substantially reduces bit line switching current and number of shorted bits. In an alternative embodiment, the crystalline layer may be a Fe/NiFe bilayer. Annealing at 300° C. to 360° C. provides a high magnetoresistive ratio of about 150%.

Abstract: The structure and method of formation of an integrated CMOS level and active device level that can be a memory device level. The integration includes the formation of a “super-flat” interface between the two levels formed by the patterning of a full complement of active and dummy interconnecting vias using two separate patterning and etch processes. The active vias connect memory devices in the upper device level to connecting pads in the lower CMOS level. The dummy vias may extend up to an etch stop layer formed over the CMOS layer or may be stopped at an intermediate etch stop layer formed within the device level. The dummy vias thereby contact memory devices but do not connect them to active elements in the CMOS level.

Abstract: A MTJ in an MRAM array is disclosed with a composite free layer having a lower crystalline layer contacting a tunnel barrier and an upper amorphous NiFeX layer for improved bit switching performance. The crystalline layer is Fe, Ni, or FeB with a thickness of at least 6 Angstroms which affords a high magnetoresistive ratio. The X element in the NiFeX layer is Mg, Hf, Zr, Nb, or Ta with a content of 5 to 30 atomic %. NiFeX thickness is preferably between 20 to 40 Angstroms to substantially reduce bit line switching current and number of shorted bits. In an alternative embodiment, the crystalline layer may be a Fe/NiFe bilayer. Optionally, the amorphous layer may have a NiFeM1/NiFeM2 configuration where M1 and M2 are Mg, Hf, Zr, Nb, or Ta, and M1 is unequal to M2. Annealing at 300° C. to 360° C. provides a high magnetoresistive ratio of about 150%.