Abstract: A system on chip (SoC) adjusts power of a memory through a handshake. The SoC includes a memory controller and a power manager. The memory controller is configured to control a memory. The power manager is configured to manage a supply power level of the memory. The memory controller is configured to output, to the power manager, a memory access level indicating a frequency of accesses to the memory. The power manager is configured to adjust the supply power level of the memory according to the memory access level.

Abstract: A system on chip (SoC) adjusts power of a memory through a handshake. The SoC includes a memory controller and a power manager. The memory controller is configured to control a memory. The power manager is configured to manage a supply power level of the memory. The memory controller is configured to output, to the power manager, a memory access level indicating a frequency of accesses to the memory. The power manager is configured to adjust the supply power level of the memory according to the memory access level.

Abstract: A system on chip (SoC) includes a plurality of intellectual property (IP) blocks and a clock management unit (CMU) configured to perform clock gating on at least one of the IP blocks. The IP blocks and the CMU interface with one another using a full handshake method. The full handshake method may include at least one of the IP blocks sending a request signal to the CMU to begin providing a clock signal or to stop providing the clock signal, and the CMU sending an acknowledgement signal to the corresponding IP block in response to receipt of the request signal.

Abstract: An integrated circuit included in a device for performing a neural network operation includes a buffer configured to store feature map data in units of cells each including at least one feature, wherein the feature map data is for use in the neural network operation; and a multiplexing circuit configured to receive the feature map data from the buffer, and output extracted data by extracting feature data of one of features that are included within a plurality of cells in the received feature map data, the features each corresponding to an identical coordinate value.

Abstract: An integrated circuit included in a device for performing a neural network operation includes a buffer configured to store feature map data in units of cells each including at least one feature, wherein the feature map data is for use in the neural network operation; and a multiplexing circuit configured to receive the feature map data from the buffer, and output extracted data by extracting feature data of one of features that are included within a plurality of cells in the received feature map data, the features each corresponding to an identical coordinate value.

Abstract: A neural processing system includes a first frontend module, a second frontend module, a first backend module, and a second backend module. The first frontend module executes a feature extraction operation using a first feature map and a first weight, and outputs a first operation result and a second operation result. The second frontend module executes the feature extraction operation using a second feature map and a second weight, and outputs a third operation result and a fourth operation result. The first backend module receives an input of the first operation result provided from the first frontend module and the fourth operation result provided from the second frontend module via a second bridge to sum up the first operation result and the fourth operation result.

Abstract: A neural processing system includes a first frontend module, a second frontend module, a first backend module, and a second backend module. The first frontend module executes a feature extraction operation using a first feature map and a first weight, and outputs a first operation result and a second operation result. The second frontend module executes the feature extraction operation using a second feature map and a second weight, and outputs a third operation result and a fourth operation result. The first backend module receives an input of the first operation result provided from the first frontend module and the fourth operation result provided from the second frontend module via a second bridge to sum up the first operation result and the fourth operation result.

Abstract: A system on chip (SoC) adjusts power of a memory through a handshake. The SoC includes a memory controller and a power manager. The memory controller is configured to control a memory. The power manager is configured to manage a supply power level of the memory. The memory controller is configured to output, to the power manager, a memory access level indicating a frequency of accesses to the memory. The power manager is configured to adjust the supply power level of the memory according to the memory access level.

Abstract: A neural processing system includes a first frontend module, a second frontend module, a first backend module, and a second backend module. The first frontend module executes a feature extraction operation using a first feature map and a first weight, and outputs a first operation result and a second operation result. The second frontend module executes the feature extraction operation using a second feature map and a second weight, and outputs a third operation result and a fourth operation result. The first backend module receives an input of the first operation result provided from the first frontend module and the fourth operation result provided from the second frontend module via a second bridge to sum up the first operation result and the fourth operation result.

Abstract: A system on chip (SoC) includes a plurality of intellectual property (IP) blocks and a clock management unit (CMU) configured to perform clock gating on at least one of the IP blocks. The IP blocks and the CMU interface with one another using a full handshake method. The full handshake method may include at least one of the IP blocks sending a request signal to the CMU to begin providing a clock signal or to stop providing the clock signal, and the CMU sending an acknowledgement signal to the corresponding IP block in response to receipt of the request signal.

Abstract: A system on chip (SoC) adjusts power of a memory through a handshake. The SoC includes a memory controller and a power manager. The memory controller is configured to control a memory. The power manager is configured to manage a supply power level of the memory. The memory controller is configured to output, to the power manager, a memory access level indicating a frequency of accesses to the memory. The power manager is configured to adjust the supply power level of the memory according to the memory access level.

Abstract: A system on chip (SoC) includes a plurality of intellectual property (IP) blocks and a clock management unit (CMU) configured to perform clock gating on at least one of the IP blocks. The IP blocks and the CMU interface with one another using a full handshake method. The full handshake method may include at least one of the IP blocks sending a request signal to the CMU to begin providing a clock signal or to stop providing the clock signal, and the CMU sending an acknowledgement signal to the corresponding IP block in response to receipt of the request signal.

Abstract: In one embodiment, the clock management circuitry includes a first master clock controller configured to provide a first command to a first slave clock controller via a first channel based on a received first clock request. The clock management circuitry also includes the first slave clock controller configured to control outputting a first clock signal based on the first command.

Abstract: A neural network processor for performing a neural network operation may include a memory storing computer-readable instructions, and kernel intermediate data, the kernel intermediate data including a plurality of kernel intermediate values calculated based on a plurality of weight values included in kernel data; and at least one processor to execute the computer-readable instructions to perform a convolution operation by selecting at least one kernel intermediate value among the plurality of kernel intermediate values based on an input feature map.

Abstract: A system on chip (SoC) includes a plurality of intellectual property (IP) blocks and a clock management unit (CMU) configured to perform clock gating on at least one of the IP blocks. The IP blocks and the CMU interface with one another using a full handshake method. The full handshake method may include at least one of the IP blocks sending a request signal to the CMU to begin providing a clock signal or to stop providing the clock signal, and the CMU sending an acknowledgement signal to the corresponding IP block in response to receipt of the request signal.

Abstract: A device includes a first divider circuit connected to a first data lane and configured to receive a first data lane value having a first index, to receive a second index corresponding to a second data lane value from a second data lane, and to selectively output a first adding value or the first data lane value based on whether the first index is equal to the second index and a first adder circuit connected to the second data lane and the first divider circuit and configured to receive the first adding value from the first divider circuit, to receive the second data lane value, and to add the first adding value to the second data lane value to generate an addition result.

Abstract: A system on chip (SoC) includes a plurality of intellectual property (IP) blocks and a clock management unit (CMU) configured to perform clock gating on at least one of the IP blocks. The IP blocks and the CMU interface with one another using a full handshake method. The full handshake method may include at least one of the IP blocks sending a request signal to the CMU to begin providing a clock signal or to stop providing the clock signal, and the CMU sending an acknowledgement signal to the corresponding IP block in response to receipt of the request signal.

Abstract: In one embodiment, the clock management circuitry includes a first master clock controller configured to provide a first command to a first slave clock controller via a first channel based on a received first clock request. The clock management circuitry also includes the first slave clock controller configured to control outputting a first clock signal based on the first command.

Abstract: A system-on-chip (SoC) comprises a clock management unit (CMU) including a first clock generator and a second clock generator, the first and second clock generators being configured to generate clock signals. The SoC comprises at least one logic block configured to request the clock signals from the CMU according to a full handshake method and receive the clock signals from the CMU in response to the request. The first clock generator and the second clock generator are configured to communicate according to the full handshake method.

Abstract: In one embodiment, the clock management circuitry includes a first master clock controller configured to provide a first command to a first slave clock controller via a first channel based on a received first clock request. The clock management circuitry also includes the first slave clock controller configured to control outputting a first clock signal based on the first command.