Abstract: Embodiments herein relate to a three-transistor gain cell which is provided using a complementary field-effect transistor device to achieve scaling. The cell includes an n-type layer arranged above a p-type layer. In one implementation, two nMOS transistors are arranged above one pMOS transistor and a conductive path is provided to connect the gate of one of the nMOS transistors to a storage node in the p-type layer, where the storage node is coupled to a drain of the pMOS transistor. In another implementation, one nMOS transistor is arranged above two pMOS transistors and a conductive path is provided to connect the gate of one of the pMOS transistors to a storage node in the n-type layer, where the storage node is coupled to a source of the nMOS transistor.

Abstract: Embodiments herein relate to scaling of Static Random Access Memory (SRAM) cells. An SRAM cell include nMOS transistors on one level above pMOS transistors on a lower level. Transistors on the two levels can have overlapping footprints to save space. Additionally, the SRAM cell can use pMOS access transistors in place of nMOS access transistors to allow reuse of areas of the cell which would otherwise be used by the nMOS access transistors. In one approach, gate interconnects are provided in these areas, which have an overlapping footprint with underlying pMOS access transistors to save space. The SRAM cells can be connected to bit lines and word lines in overhead and/or bottom metal layers. In another aspect, SRAM cells of a column are connected to bit lines in an overlying M0 metal layer and an underlying BM0 metal layers to reduce capacitance.

Abstract: Embodiments herein relate to a balanced eight-transistor (8T) static random-access memory (SRAM) cell having four n-type metal-oxide-semiconductor field-effect transistors (nMOSFETs) and four p-type MOSFETS. An nMOS write port and two pMOS read ports are optimized with a complementary field-effect transistor (CFET) process to achieve a high density. The cell is reconfigurable for various port configurations including 1R1W (1-read 1-write), 2R1W (2-read 1-write), 3R1W (3-read 1-write), 4R1W (4-read 1-write) and single/dual-ported SRAM with appropriate Vt (voltage threshold) targeting.

Abstract: Embodiments herein relate to a memory cell having n-type metal-oxide-semiconductor field-effect transistor (nMOSFETs) in one layer in the cell and pMOSFET transistors in another, lower layer of the cell, and one or more intermediate metal (IM) layers between the nMOS and pMOS transistors. The IM layers can provide routing between the nMOS and pMOS transistors, to one or more top metal layers, above the nMOS transistors, and to one or more bottom metal layers, below the pMOS transistors. An example six-transistor cell can include four nMOS transistors and two pMOS transistors, and an example eight-transistor cell can include four nMOS transistors and four pMOS transistors.

Abstract: Systems and methods for providing standard cell yield information in a library (i.e., creating “defect-aware” libraries). The method includes accessing a library of a plurality of standard cells characterized on a foundry process node and revision. A geometric analysis is performed on individual ones of the standard cells to identify potential defects, such as shorts and opens. A defect is injected (i.e., “realized” or “actualized”) at the location of the identified potential defects. The standard cells in the library are then simulated with the defects injected to generate simulated yield information. Additionally, methods can access silicon failure analysis data representing test chips designed with the library and generate an inferred failure rate for the individual standard cells in the library, as a function of the silicon failure analysis and the simulated yield information.

Abstract: Examples include techniques to utilize near memory compute circuitry for memory-bound workloads. Examples include the near memory compute circuitry being resident on an input/output (I/O) arranged to couple with a plurality of memory devices configured as a memory pool that is accessible to a host central processing unit (CPU) through the I/O switch. The near memory compute circuitry may receive a request to obtain data from the memory pool and generate a result that is made available to the host CPU to facilitate acceleration of a memory-bound workload.

Abstract: An apparatus includes a first write bit line (WBL), a first P-channel metal oxide semiconductor (PMOS) transistor including a source coupled to the WBL, a first inverter including an input coupled to a drain of the first PMOS transistor, and a second PMOS transistor including a source coupled to an output of the first inverter. The first PMOS transistor and the second PMOS transistor are disposed in at least one PMOS layer configured between a first metal layer and a second metal layer. The register file circuit further includes a first via connecting a gate of the first PMOS transistor and a gate of the second PMOS transistor in the at least one PMOS layer to the first metal layer.

Abstract: Embodiments herein relate to a three-transistor gain cell which is provided using a complementary field-effect transistor device to achieve scaling. The cell includes an n-type layer arranged above a p-type layer. In one implementation, two nMOS transistors are arranged above one pMOS transistor and a conductive path is provided to connect the gate of one of the nMOS transistors to a storage node in the p-type layer, where the storage node is coupled to a drain of the pMOS transistor. In another implementation, one nMOS transistor is arranged above two pMOS transistors and a conductive path is provided to connect the gate of one of the pMOS transistors to a storage node in the n-type layer, where the storage node is coupled to a source of the nMOS transistor.

Abstract: Described is an apparatus which comprises: a plurality of transistors coupled to an input power supply and to a load; a first comparator with a first node coupled to the load, and a second node coupled to a first reference; a second comparator with a first node coupled to the load, and a second node coupled to a second reference, the second reference being different from the first reference; and a logic unit to receive output of the first comparator and output of the second comparator, the logic unit to turn on or off transistors of the plurality of transistors according to outputs of the first and second comparators.

Abstract: An apparatus, system, and method for register file circuits are provided. A register file circuit can include a first write bit line (WBL), a first P-channel metal oxide semiconductor (PMOS) transistor including a source coupled to the WBL, a first inverter including an input coupled to a drain of the first PMOS transistor, a second PMOS transistor including a source coupled to an output of the first inverter, and a second WBL (WBLB) coupled to a drain of the second PMOS transistor. 1R1W register file and 2R1W register file designs are provided.

Abstract: Embodiments herein relate to scaling of Static Random Access Memory (SRAM) cells. An SRAM cell include nMOS transistors on one level above pMOS transistors on a lower level. Transistors on the two levels can have overlapping footprints to save space. Additionally, the SRAM cell can use pMOS access transistors in place of nMOS access transistors to allow reuse of areas of the cell which would otherwise be used by the nMOS access transistors. In one approach, gate interconnects are provided in these areas, which have an overlapping footprint with underlying pMOS access transistors to save space. The SRAM cells can be connected to bit lines and word lines in overhead and/or bottom metal layers. In another aspect, SRAM cells of a column are connected to bit lines in an overlying M0 metal layer and an underlying BM0 metal layers to reduce capacitance.

Abstract: A system for autonomous and proactive power management for energy efficient execution of machine learning workloads may include an apparatus such as system-on-chip (SoC) comprising an accelerator configurable to load and execute a neural network and circuitry to receive a profile of the neural network. The profile may be received from a compiler and include information regarding a plurality of layers of the neural network. Responsive to the profile and the information regarding the plurality of layers, circuitry may adjust, using a local power management unit (PMU) included the apparatus, a power level to the accelerator while the accelerator executes the neural network. The power level adjustment may be based on whether the particular layer is a compute-intensive layer or a memory-intensive layer.

Abstract: A system includes a compute circuit that preemptively performs a computation on a data word before receiving an indication of data errors from an error checking and correction (ECC) circuit. The ECC circuit reads the data word from a memory array and performs error detection and error correction on the data word. The compute circuit reads the data word and performs the computation on the data word to generate an output value, without waiting for the ECC circuit to check and correct the data word. In response to error detection in the data word by the ECC circuit, the compute circuit delays outputting the output value until correction of the output value in accordance with the error detection by the ECC circuit.

Abstract: An ultra-deep compute Static Random Access Memory (SRAM) with high compute throughput and multi-directional data transfer capability is provided. Compute units are placed in both horizontal and vertical directions to achieve a symmetric layout while enabling communication between the compute units. An SRAM array supports simultaneous read and write to the left and right section of the same SRAM subarray by duplicating pre-decoding logic inside the SRAM array. This allows applications with non-overlapping read and write address spaces to have twice the bandwidth as compared to a baseline SRAM array.

Abstract: Embodiments include apparatuses, methods, and systems to implement a multi-read and/or multi-write process with a set of memory cells. The set of memory cells may be multiplexed with a same sense amplifier. As part of a multi-read process, a memory controller coupled to a memory circuit may precharge the bit lines associated with the set of memory cells, provide a single assertion of a word line signal on the word line, and then sequentially read data from the set of memory cells (using the sense amplifier) based on the precharge and the single assertion of the word line signal. Additionally, or alternatively, a multi-write process may be performed to sequentially write data to the set of memory cells based on one precharge of the associated bit lines. Other embodiments may be described and claimed.

Abstract: A system includes a compute circuit that preemptively performs a computation on a data word before receiving an indication of data errors from an error checking and correction (ECC) circuit. The ECC circuit reads the data word from a memory array and performs error detection and error correction on the data word. The compute circuit reads the data word and performs the computation on the data word to generate an output value, without waiting for the ECC circuit to check and correct the data word. In response to error detection in the data word by the ECC circuit, the compute circuit delays outputting the output value until correction of the output value in accordance with the error detection by the ECC circuit.

Abstract: Embodiments include apparatuses, methods, and systems to implement a multi-read and/or multi-write process with a set of memory cells. The set of memory cells may be multiplexed with a same sense amplifier. As part of a multi-read process, a memory controller coupled to a memory circuit may precharge the bit lines associated with the set of memory cells, provide a single assertion of a word line signal on the word line, and then sequentially read data from the set of memory cells (using the sense amplifier) based on the precharge and the single assertion of the word line signal. Additionally, or alternatively, a multi-write process may be performed to sequentially write data to the set of memory cells based on one precharge of the associated bit lines. Other embodiments may be described and claimed.

Abstract: An apparatus, vision processing unit, and method are provided for clustering motion events in a content addressable memory. A motion event is received including coordinates in an image frame that have experienced a change and a timestamp of the change. A determination is made as to whether determine whether there is a valid entry in the memory having coordinates within a predefined range of coordinates included in the motion event. In response to a determination that there is the valid entry having the coordinates within the predefined range of coordinates included in the motion event, write to the valid entry the coordinates and the timestamp in the motion event.

Abstract: A spike sent from a first artificial neuron in a spiking neural network (SNN) to a second artificial neuron in the SNN is identified, with the spike sent over a particular artificial synapse in the SNN. The membrane potential of the second artificial neuron at a particular time step, corresponding to sending of the spike, is compared to a threshold potential, where the threshold potential is set lower than a firing potential of the second artificial neuron. A change to the synaptic weight of the particular artificial synapse is determined based on the spike, where the synaptic weight is to be decreased if the membrane potential of the second artificial neuron is lower than the threshold potential at the particular time step and the synaptic weight is to be increased if the membrane potential of the second artificial neuron is higher than the threshold potential at the particular time step.

Abstract: Described is an apparatus which comprises: a plurality of transistors coupled to an input power supply and to a load; a first comparator with a first node coupled to the load, and a second node coupled to a first reference; a second comparator with a first node coupled to the load, and a second node coupled to a second reference, the second reference being different from the first reference; and a logic unit to receive output of the first comparator and output of the second comparator, the logic unit to turn on or off transistors of the plurality of transistors according to outputs of the first and second comparators.