Abstract:
A digital compute-in-memory (DCIM) system includes a first DCIM macro. The first DCIM macro includes a first memory cell array and a first arithmetic logic unit (ALU). The first memory cell array has N rows that are configured to store weight data of a neural network in a single weight data download session, wherein N is a positive integer not smaller than two. The first ALU is configured to receive a first activation input, and perform convolution operations upon the first activation input and a single row of weight data selected from the N rows of the first memory cell array to generate first convolution outputs.
Abstract:
A method for controlling a task migration of a task in a heterogeneous multi-core system having at least a first cluster and a second cluster is provided. The method may include at least the following steps: dynamically adjusting a migration threshold; comparing a load of the task running on one core of the first cluster with the migration threshold, and accordingly generating a comparison result; and selectively controlling the task to migrate to the second cluster according to at least the comparison result, wherein each core in the first cluster has first processor architecture, and each core in the second cluster has second processor architecture different from the first processor architecture.
Abstract:
A digital compute-in-memory (DCIM) macro includes a memory cell array and an arithmetic logic unit (ALU). The memory cell array stores weight data of a neural network. The ALU receives parallel bits of a same input channel in an activation input, and generates a convolution computation output of the parallel bits and target weight data in the memory cell array.
Abstract:
A system for accessing data among at least two different electronic devices is provided. The system includes a demanding electronic device and a providing electronic device. The demanding electronic device is utilized to establish an input virtual device to execute an application on the demanding electronic device. The providing electronic device is utilized to establish an output virtual device for transmitting data from the providing electronic device to the demanding electronic device via the output virtual device, wherein the data corresponds to the application, and the providing electronic device is physically separated from the demanding electronic device. The input virtual device is established to use a first peripheral of the providing electronic device as a built-in peripheral of the demanding electronic device.
Abstract:
A technique, as well as select implementations thereof, pertaining to cross-mounting a device is described. The technique may involve an apparatus detecting a presence of a device not a part of the apparatus. The technique may also involve the apparatus performing an update in response to the detecting of the presence of the device. The technique may additionally involve the apparatus establishing a communication connection with the device. The technique may further involve the apparatus utilizing the device to perform one or more tasks.
Abstract:
A system receives a neural network model that includes asymmetric operations. Each asymmetric operation includes one or more fixed-point operands that are asymmetrically-quantized from corresponding floating-point operands. The system compiles a given asymmetric operation of the neural network model into a symmetric operation that includes a combined bias value. A compiler computes the combined bias value is a constant by merging at least zero points of input and output of the given asymmetric operation. The system then generates a symmetric neural network model including the symmetric operation for inference hardware to execute in fixed-point arithmetic.
Abstract:
A technique, as well as select implementations thereof, pertaining to cross-mounting a device is described. The technique may involve an apparatus detecting a presence of a device not a part of the apparatus. The technique may also involve the apparatus performing an update in response to the detecting of the presence of the device. The technique may additionally involve the apparatus establishing a communication connection with the device. The technique may further involve the apparatus utilizing the device to perform one or more tasks.