Apparatus, methods, and systems for low latency communication in a configurable spatial accelerator

A method comprising:

• overlaying an input of a dataflow graph comprising a plurality of nodes into a spatial array of processing elements with each node represented as a dataflow operator in the spatial array of processing elements;
• coupling a plurality of request address file circuits to the spatial array of processing elements and a cache memory with each request address file circuit of the plurality of request address file circuits accessing data in the cache memory in response to a request for data access from the spatial array of processing elements;
• providing an output of a physical address for an input of a virtual address into a translation lookaside buffer of a plurality of translation lookaside buffers comprising a translation lookaside buffer in each of the plurality of request address file circuits;
• and
• receiving, with a function controller, an interrupt that includes a first field that is set to a first value to cause a shootdown message to be broadcast to the plurality of translation lookaside buffers to cause a shootdown in the plurality of translation lookaside buffers.

An apparatus comprising:

• a first accelerator section and a second accelerator section that each comprise:
• a spatial array of processing elements to receive an input of a dataflow graph comprising a plurality of nodes, wherein the dataflow graph is to be overlaid into the spatial array of processing elements with each node represented as a dataflow operator in the spatial array of processing elements, and the spatial array of processing elements is to perform an operation by a respective, incoming operand set arriving at each of the dataflow operators;
• a device manager;
• a first function controller of the first accelerator section to receive an interrupt that includes a first field from the device manager, that when the first field is set to a first value, causes a first message to be broadcast within the first accelerator section that causes a first non-interrupt function to be performed in the first accelerator section;
• and
• a second function controller of the second accelerator section to receive the interrupt that includes the first field from the device manager, that when the first field is set to the first value, causes a second message to be broadcast within the second accelerator section that causes the first non-interrupt function to be performed in the second accelerator section.