Abstract: An electronic device including a memory device with improved reliability is provided. The semiconductor device comprises a data pin configured to transmit a data signal, a command/address pin configured to transmit a command and an address, a command/address receiver connected to the command/address pin, and a computing unit connected to the command/address receiver, wherein the command/address receiver receives a first command and a first address from the outside through the command/address pin and generates a first instruction on the basis of the first command and the first address, and the computing unit receives the first instruction and performs computation based on the first instruction.

Abstract: A semiconductor device including a memory device which has improved reliability is provided. The semiconductor device comprises at least one data pin configured to transfer a data signal, at least one command address pin configured to transfer a command and an address, at least one serial pin configured to transfer a serial data signal, and processing circuitry connected to the at least one data pin and the at least one serial pin. The processing circuitry is configured to receive the data signal from outside through the at least one data pin, and the processing circuitry is configured to output the serial data signal through the at least one serial pin in response to the received data signal.

Abstract: An electronic device includes a graphic processor and a memory device. The graphic processor includes an artificial neural network engine that makes an object recognition model learn by using learning data and weights to provide a learned object recognition model. The memory device, divides a feature vector into a first sub feature vector and a second feature vector, and performs a first calculation to apply the second sub feature vector and the weights to the learned object recognition model to provide a second object recognition result. The artificial neural network engine performs a second calculation to apply the first sub feature vector and the weights to the learned object recognition model to provide a first object recognition result and provides the first object recognition result to the memory device. The second calculation is performed in parallel with the first calculation.

Abstract: A memory module includes a memory device configured to receive a first refresh command from a host, and perform a refresh operation in response to the first refresh command during a refresh time, and a computing unit configured to detect the first refresh command provided from the host to the memory device, and write a first error pattern at a first address of the memory device during the refresh time.

Abstract: An electronic device includes a graphic processor and a memory device. The graphic processor includes an artificial neural network engine that makes an object recognition model learn by using learning data and weights to provide a learned object recognition model. The memory device divides a feature vector into a first sub feature vector and a second feature vector, and performs a first calculation to apply the second sub feature vector and the weights to the learned object recognition model to provide a second object recognition result. The artificial neural network engine performs a second calculation to apply the first sub feature vector and the weights to the learned object recognition model to provide a first object recognition result and provides the first object recognition result to the memory device. The second calculation is performed in parallel with the first calculation.

Abstract: A semiconductor device including a memory device which has improved reliability is provided. The semiconductor device comprises at least one data pin configured to transfer a data signal, at least one command address pin configured to transfer a command and an address, at least one serial pin configured to transfer a serial data signal, and processing circuitry connected to the at least one data pin and the at least one serial pin. The processing circuitry is configured to receive the data signal from outside through the at least one data pin, and the processing circuitry is configured to output the serial data signal through the at least one serial pin in response to the received data signal.

Abstract: An electronic device including a memory device with improved reliability is provided. The semiconductor device comprises a data pin configured to transmit a data signal, a command/address pin configured to transmit a command and an address, a command/address receiver connected to the command/address pin, and a computing unit connected to the command/address receiver, wherein the command/address receiver receives a first command and a first address from the outside through the command/address pin and generates a first instruction on the basis of the first command and the first address, and the computing unit receives the first instruction and performs computation based on the first instruction.

Abstract: A memory module includes a memory device configured to receive a first refresh command from a host, and perform a refresh operation in response to the first refresh command during a refresh time, and a computing unit configured to detect the first refresh command provided from the host to the memory device, and write a first error pattern at a first address of the memory device during the refresh time.

Abstract: An electronic device includes a graphic processor and a memory device. The graphic processor includes an artificial neural network engine that makes an object recognition model learn by using learning data and weights to provide a learned object recognition model. The memory device divides a feature vector into a first sub feature vector and a second feature vector, and performs a first calculation to apply the second sub feature vector and the weights to the learned object recognition model to provide a second object recognition result. The artificial neural network engine performs a second calculation to apply the first sub feature vector and the weights to the learned object recognition model to provide a first object recognition result and provides the first object recognition result to the memory device. The second calculation is performed in parallel with the first calculation.

Abstract: An electronic device includes a graphic processor and a memory device. The graphic processor includes an artificial neural network engine that makes an object recognition model learn by using learning data and weights to provide a learned object recognition model. The memory device, divides a feature vector into a first sub feature vector and a second feature vector, and performs a first calculation to apply the second sub feature vector and the weights to the learned object recognition model to provide a second object recognition result. The artificial neural network engine performs a second calculation to apply the first sub feature vector and the weights to the learned object recognition model to provide a first object recognition result and provides the first object recognition result to the memory device. The second calculation is performed in parallel with the first calculation.

Abstract: An electronic device includes a graphic processor and a memory device. The graphic processor includes an artificial neural network engine that makes an object recognition model learn by using learning data and weights to provide a learned object recognition model. The memory device, divides a feature vector into a first sub feature vector and a second feature vector, and performs a first calculation to apply the second sub feature vector and the weights to the learned object recognition model to provide a second object recognition result. The artificial neural network engine performs a second calculation to apply the first sub feature vector and the weights to the learned object recognition model to provide a first object recognition result and provides the first object recognition result to the memory device. The second calculation is performed in parallel with the first calculation.