Protocol layer tunneling for a data processing system

A computer-based method for transferring data over an interconnect, comprising:

• at a home node coupled to the interconnect:
• receiving, from a request node coupled to the interconnect, a sequence of dynamic requests including at least a first dynamic request followed by a second dynamic request;
• sending, to the request node, a sequence of retry requests associated with the sequence of dynamic requests, the sequence of retry requests including at least a first retry request associated with the first dynamic request followed by a second retry request associated with the second dynamic request;
• determining plurality of credit grants associated with the sequence of retry requests, the plurality of credit grants including at least a first credit grant and a second credit grant;
• sending, to the request node, the plurality of credit grants;
• receiving, from the request node, a sequence of static requests associated with the sequence of dynamic requests, the sequence of static requests including at least a first static request associated with the first dynamic request followed by a second static request associated with the second dynamic request;
• and
• sending, to the request node, a first completion response associated with the first static request,
• where the second static request is received from the request node prior to sending the first completion response to the request node.

A system, comprising:

• an interconnect;
• a request node, coupled to the interconnect, including a request node processor;
• and
• a home node, coupled to the interconnect, including a home node processor,
• the request node processor configured to:
• send, to the home node, a sequence of dynamic requests including at least a first dynamic request followed by a second dynamic request,
• receive, from the home node, a sequence of retry requests associated with the sequence of dynamic requests, the sequence of retry requests including at least a first retry request associated with the first dynamic request followed by a second retry request associated with the second dynamic request,
• in response to receiving a plurality of credit grants from the home node, send, to the home node, a sequence of static requests associated with the sequence of dynamic requests, the sequence of static requests including at least a first static request associated with the first dynamic request followed by a second static request associated with the second dynamic request, and
• receive, from the home node, a first completion response associated with the first static request,
• where the second static request is sent to the home node prior to receiving the first completion response from the home node, and
• the home node processor configured to:
• in response to receiving the sequence of dynamic requests, send, to the request node, the sequence of retry requests associated with the sequence of dynamic requests,
• determine the plurality of credit grants associated with the sequence of retry requests, the plurality of credit grants including at least a first credit grant and a second credit grant,
• send, to the request node, the plurality of credit grants, and
• send, to the request node, the first completion response.