Components of "restricted data flow" execution
Out-of-order superscalar processors
Article REF: H1011 V1
Components of "restricted data flow" execution
Out-of-order superscalar processors

Authors : François ANCEAU, Daniel ETIEMBLE

Publication date: January 10, 2018, Review date: August 3, 2022 | Lire en français

Logo Techniques de l'Ingenieur You do not have access to this resource.
Request your free trial access! Free trial

Already subscribed?

4. Components of "restricted data flow" execution

As the various techniques are not totally independent, we introduce them in an order that avoids redundancy of presentation.

4.1 Ordered instruction termination

To allow for clean exceptions, instructions must terminate strictly in program order, as they would in a strictly sequential processor. In-order termination is implemented by a reorder buffer (ROB), which functions as a circular buffer. When an instruction is started, it is allocated an entry in the ROB that will contain the instruction's execution status. An instruction is only completed and removed from the ROB if it is guaranteed (no more speculative execution, no more possibility of interruptions) and all preceding instructions in the program's sequential order are completed from the point of view...

You do not have access to this resource.
Logo Techniques de l'Ingenieur

Exclusive to subscribers. 97% yet to be discovered!

You do not have access to this resource. Click here to request your free trial access!

Already subscribed?


Article included in this offer

"Software technologies and System architectures"

( 227 articles )

Complete knowledge base

Updated and enriched with articles validated by our scientific committees

Services

A set of exclusive tools to complement the resources

View offer details