Method for encoding an instruction set with a load with conditional fault instruction
AssigneeIntel Corporation
InventorsOpher D. Kahn, Robert C. Valentine
Life of this patent
Estimating the term…
Loading patent…
AssigneeIntel Corporation
InventorsOpher D. Kahn, Robert C. Valentine
Estimating the term…
The present invention relates to a method and system for providing a load with conditional fault instruction that includes an associated conditional operator, which enables load operations to be advanced above program branches by the compiler without causing unwarranted fault conditions. Specifically, the load instruction can be executed out of normal program order to enable information to be retrieved from memory before the information is needed, to permit the retrieved information to begin to be used before the conditional operator can be evaluated. Likewise, a dynamically scheduled processor can advance components of the instruction and further improve performance without having faults effect the normal program flow. The load instruction can stop the use of the information and replace the information with a predetermined, generally deterministic, value if the conditional operator indicates a faulty load operation.
A machine-readable medium having stored thereon executable instructions to perform a method comprising:
A computer system comprising:
The computer system of 10 wherein the predetermined value is a deterministic value.
A processor comprising:
A method comprising:
Dependencies are inferred from the claim text.