One-dimensional zero padding in a stream of matrix elements

A system comprising:

• a system memory;
• a streaming engine coupled to the system memory, wherein the streaming engine comprises:
• a stream template register to hold stream parameters, wherein the stream parameters define a size for each dimension of a multidimensional array and a specified width for a selected dimension of the multidimensional array;
• address generation logic coupled to the stream template register and configured to generate a set of addresses based on the stream parameters;
• a register file with inputs coupled to receive a vector fetched from the system memory using the set of addresses;
• an alignment network with inputs coupled to outputs of the register file, the alignment network having outputs coupled to outputs of the streaming engine to provide a stream vector responsive to the stream parameters;
• and
• control logic coupled to control the alignment network and configured to:
• based on a fetch of a first address not exceeding the specified width, cause the alignment network to provide a data element of the vector fetched from the system memory as a first element of the stream vector;
• and
• based on a fetch of a second address exceeding the specified width, cause the alignment network to provide a null element as a second element of the stream vector without an access of the system memory.

A system comprising:

• a system memory;
• a streaming engine coupled to access the system memory to form a stream of stream vectors, wherein the streaming engine is configured to:
• insert a null element into a selected stream vector without accessing the system memory based on a determination that a memory access exceeds a specified width of a multidimensional array by:
• generating a set of addresses associated with the stream of stream vectors;
• based on a first access associated with a first address not exceeding a specified array width:
• fetching a data element from the system memory;
• and
• providing the data element in the stream of stream vectors;
• and
• based on a second access associated with a second address that is associated with the selected stream vector exceeding the specified array width, providing the null element in the selected stream vector without accessing the system memory;
• and
• a processing unit coupled to outputs of the streaming engine to receive the stream of stream vectors.