Floating-point division alternative techniques

A method, comprising:

• performing a floating-point operation to divide a first operand by a second operand, wherein the first and second operands are represented using a first precision, including:
• determining a reciprocal of the second operand to generate a reciprocal output, using a second precision that is greater than the first precision;
• multiplying the reciprocal output by the first operand, using the second precision, to generate a multiplication output;
• clearing a least significant bit of an integer representation of the multiplication output to generate a modified multiplication output;
• and
• converting the modified multiplication output to a representation using the first precision to generate a division output.

A non-transitory computer readable storage medium having stored thereon design information that specifies a design of at least a portion of a hardware integrated circuit in a format recognized by a semiconductor fabrication system that is configured to use the design information to produce the circuit according to the design, including:

• floating-point circuitry configured to perform a floating-point operation to divide a first operand by a second operand, wherein the first and second operands are represented using a first precision, including:
• reciprocal circuitry configured to determine a reciprocal of the second operand to generate a reciprocal output, using a second precision that is greater than the first precision;
• multiplication circuitry configured to multiply the reciprocal output by the first operand, using the second precision, to generate a multiplication output;
• circuitry configured to clear a least significant bit of an integer representation of the multiplication output to generate a modified multiplication output;
• and
• circuitry configured to convert the modified multiplication output to a representation using the first precision to generate a division output.