A memory circuit includes a memory cell and a source line transistor. The memory cell includes a first transistor, a second transistor, a third transistor, and a fourth transistor. The second transistor and the third transistor form an inverter electrically connected to a drain of the first transistor. The inverter is configured to store two states with different applied voltages. The fourth transistor is electrically connected to a node of the inverter. The source line transistor is electrically connected to the fourth transistor.

A memory circuit includes a memory cell and a source line transistor. The memory cell includes a first transistor, a second transistor, a third transistor, and a fourth transistor. The second transistor and the third transistor form an inverter electrically connected to a drain of the first transistor. The inverter is configured to store two states with different applied voltages. The fourth transistor is electrically connected to a node of the inverter. The source line transistor is electrically connected to the fourth transistor.

A compact SRAM design in a stacked architecture is provided. Notably, a 6-transistor SRAM bite cell including a bottom device level containing bottom field effect transistors and a top device level, stacked above the bottom device level, containing top field effect transistors of a different conductivity type than the bottom field effect transistors is provided.

A compact SRAM design in a stacked architecture is provided. Notably, a 6-transistor SRAM bite cell including a bottom device level containing bottom field effect transistors and a top device level, stacked above the bottom device level, containing top field effect transistors of a different conductivity type than the bottom field effect transistors is provided.

An in-memory compute (IMC) device includes a compute array having a first plurality of cells. The compute array is arranged as a plurality of rows of cells intersecting a plurality of columns of cells. Each cell of the first plurality of cells is identifiable by its corresponding row and column. The IMC device also includes a plurality of computation engines and a plurality of bias engines. Each computation engine is respectively formed in a different one of a second plurality of cells, wherein the second plurality of cells is formed from cells of the first plurality. Each computation engine is formed at a respective row and column intersection. Each bias engine of the plurality of bias engines is arranged to computationally combine an output from at least one of the plurality of computation engines with a respective bias value.

Memories are provided. A memory includes a first memory array, a second memory array and a read circuit. The first memory array is configured to store first data. The second memory array is configured to store second data that is complementary to the first data. The read circuit includes a decoding circuit, a sensing circuit and an output buffer. The decoding circuit is configured to provide a first signal according to the first data and a second signal according to the second data in response to an address signal. The sensing circuit is configured to provide a first sensing signal according to a reference signal and the first signal, and a second sensing signal according to the reference signal and the second signal. The output buffer is configured to provide the first sensing signal or the second sensing signal as an output according to a control signal.

Stitched dies having a cooling structure are described. For example, an integrated circuit structure includes a first die including a first device layer and a first plurality of metallization layers over the first device layer. The integrated circuit structure also includes a second die including a second device layer and a second plurality of metallization layers over the second device layer, the second die separated from the second die by a scribe region. A common conductive interconnection is coupling the first die and the second die at a first side of the first and second dies. A plurality of microfluidic channels is coupled to the first side of the first and second dies.

In an SRAM circuit mounted in a semiconductor device, power supply voltage reduction circuits generate reduction voltage obtained by reducing an external power supply voltage. A first power supply voltage selection circuit selects one of the external power supply voltage and the reduction voltage as a drive voltage supplied to a word line driver. A second power supply voltage selection circuit selects one of the external power supply voltage and the reduction voltage as a voltage of a power supply line supplying an operating voltage to a memory cell.

The present application discloses a data processing method and apparatus. A specific embodiment of the method includes: preprocessing received to-be-processed input data; obtaining a storage address of configuration parameters of the to-be-processed input data based on a result of the preprocessing and a result obtained by linearly fitting an activation function, the configuration parameters being preset according to curve characteristics of the activation function; acquiring the configuration parameters of the to-be-processed input data according to the storage address; and processing the result of the preprocessing of the to-be-processed input data based on the configuration parameters of the to-be-processed input data and a preset circuit structure, to obtain a processing result. This implementation manner implements the processing of the input data to be processed by using the configuration parameter and the preset circuit structure, without the need to use any special circuit for implementing the activation function, thereby simplifying the circuit structure. In addition, this implementation manner can support multiple types of activation functions, thereby improving the flexibility. With such an embodiment, the processing of the input data to be processed can be realized by using the configuration parameters and the preset circuit structure, without the need of using a special circuit to implement the activation function, thereby simplifying the circuit structure, supporting various activation functions, and improving the flexibility.

The present application discloses a data processing method and apparatus. A specific embodiment of the method includes: preprocessing received to-be-processed input data; obtaining a storage address of configuration parameters of the to-be-processed input data based on a result of the preprocessing and a result obtained by linearly fitting an activation function, the configuration parameters being preset according to curve characteristics of the activation function; acquiring the configuration parameters of the to-be-processed input data according to the storage address; and processing the result of the preprocessing of the to-be-processed input data based on the configuration parameters of the to-be-processed input data and a preset circuit structure, to obtain a processing result. This implementation manner implements the processing of the input data to be processed by using the configuration parameter and the preset circuit structure, without the need to use any special circuit for implementing the activation function, thereby simplifying the circuit structure. In addition, this implementation manner can support multiple types of activation functions, thereby improving the flexibility. With such an embodiment, the processing of the input data to be processed can be realized by using the configuration parameters and the preset circuit structure, without the need of using a special circuit to implement the activation function, thereby simplifying the circuit structure, supporting various activation functions, and improving the flexibility.