Apparatus and Method for Execution and Retirement of Auto-Predicated Program Code Regions

A method, comprising:

• decoding sequences of instructions, including one or more branch instructions, into sequences of microoperations (uops);
• executing the sequences of uops;
• predicting, by a branch predictor circuit, whether the one or more branch instructions will be taken;
• selectively performing predication operations by auto-predication circuitry, the predication operations performed within an auto-predication region of uops associated with the one or more branch instructions;
• and
• inserting, by uop insertion circuitry, a selection uop at an end of the auto-predication region, the selection uop to select between a first value stored in a first physical register and a second value stored in a second physical register based on whether the auto-predicated region is determined to be not taken or taken, respectively.

A non-transitory machine-readable medium that stores program code that when executed by a hardware processor causes the hardware processor to perform a method comprising:

• decoding sequences of instructions, including one or more branch instructions, into sequences of microoperations (uops);
• executing the sequences of uops;
• predicting, by a branch predictor circuit, whether the one or more branch instructions will be taken;
• selectively performing predication operations by auto-predication circuitry, the predication operations performed within an auto-predication region of uops associated with the one or more branch instructions;
• and
• inserting, by uop insertion circuitry, a selection uop at an end of the auto-predication region, the selection uop to select between a first value stored in a first physical register and a second value stored in a second physical register based on whether the auto-predicated region is determined to be not taken or taken, respectively.