Method, apparatus and instructions for parallel data conversions
AssigneeIntel Corporation
InventorGopalan Ramanujam
Life of this patent
Estimating the term…
Abstract
Method, apparatus, and program means for performing a conversion. In one embodiment, a disclosed apparatus includes a destination storage location corresponding to a first architectural register. A functional unit operates responsive to a control signal, to convert a first packed first format value selected from a set of packed first format values into a plurality of second format values. Each of the first format values has a plurality of sub elements having a first number of bits. The second format values have a greater number of bits. The functional unit stores the plurality of second format values into an architectural register.
Claims3
A reduced instruction set computer (RISC) processor comprising:
- a register file, within the RISC processor, including a first packed data register and a second packed data register;
- register rename logic within the RISC processor;
- a decoder, within the RISC processor, to decode instructions, the instructions to include a first instruction;
- schedule logic, within the RISC processor, to queue operations that correspond to the instructions for execution;
- and
- execution logic, within the RISC processor, coupled to the decoder, the register rename logic, and the schedule logic, the execution logic to perform out-of-order execution of at least some of the instructions;
- wherein, responsive to a decode of the first instruction by the decoder, the execution logic is to convert a first plurality of packed signed data elements to be stored in the first packed data register to a second plurality of packed unsigned data elements in the second packed data register, one or more of the second plurality of packed unsigned data elements to be saturated;
- the first plurality of packed signed data elements to include floating point data elements and the second plurality of packed unsigned data elements to include integer data elements;
- at least one of the packed signed data elements to have a first number of bits, at least one of the packed unsigned data elements to have a second number of bits, wherein the second number of bits is one half the first number of bits.
Dependencies are inferred from the claim text.