BLOCK NUMBER CONVERSION
Techniques for converting block format numbers are described. In some examples, a single instruction is used that is to at least include fields for an opcode, a first source operand, and a destination operand, wherein the opcode is to at least indicate execution circuitry is to perform a conversion of one or more block format numbers associated with the first source operand that each have a value of a scale multiplied by a value of a data element to a non-block format and store the non-block formatted numbers in the destination operand.
1 . An apparatus comprising:
decoder circuitry to decode an instance of a single instruction, the single instruction to at least include fields for an opcode, a first source operand, and a destination operand, wherein the opcode is to at least indicate execution circuitry is to perform a conversion of one or more block format numbers associated with the first source operand that each have a value of a scale multiplied by a value of a data element to a non-block format and store the non-block formatted numbers in the destination operand; and
execution circuitry to execute the decoded instruction according to the opcode to perform the conversion.
2 . The apparatus of claim 1 , wherein the opcode is to identify a first datatype for the first source operand and a second datatype for the destination operand.
3 . The apparatus of claim 2 , wherein at least one of the datatypes is a floating point datatype.
4 . The apparatus of claim 3 , wherein the floating point datatype is one of an 8-bit floating point, a 6-bit floating point, and a 4-bit floating point.
5 . The apparatus of claim 1 , wherein the first source operand is to store a plurality of scalar elements and the scale.
6 . The apparatus of claim 1 , wherein the first source operand is to store a plurality of scalar elements and a second source operand is to store the scale.
7 . The apparatus of claim 1 , wherein the first source operand is to store the block formatted numbers in a compact format wherein the scale is stored adjacent to a plurality of scalar data elements.
8 . The apparatus of claim 1 , wherein the first source operand is to store the block formatted numbers in a format wherein the scale is not stored adjacent to a plurality of scalar data elements.
9 . A method comprising:
decoding an instance of a single instruction, the single instruction to at least include fields for an opcode, a first source operand, and a destination operand, wherein the opcode is to at least indicate execution circuitry is to perform a conversion of one or more block format numbers associated with the first source operand that each have a value of a scale multiplied by a value of a data element to a non-block format and store the non-block formatted numbers in the destination operand; and
executing the decoded instruction according to the opcode to perform the conversion.
10 . The method of claim 9 , wherein the opcode is to identify a first datatype for the first source operand and a second datatype for the destination operand.
11 . The method of claim 10 , wherein at least one of the datatypes is a floating point datatype.
12 . The method of claim 11 , wherein the floating point datatype is one of an 8-bit floating point, a 6-bit floating point, and a 4-bit floating point.
13 . The method of claim 9 , wherein the first source operand is to store a plurality of scalar elements and the scale.
14 . The method of claim 9 , wherein the first source operand is to store a plurality of scalar elements and a second source operand is to store the scale.
15 . The method of claim 9 , wherein the first source operand is to store the block formatted numbers in a compact format wherein the scale is stored adjacent to a plurality of scalar data elements.
16 . The method of claim 9 , wherein the first source operand is to store the block formatted numbers in a format wherein the scale is not stored adjacent to a plurality of scalar data elements.
17 . A system comprising:
memory to at least store an instance of a single instruction, the single instruction to at least include fields for an opcode, a first source operand, and a destination operand, wherein the opcode is to at least indicate execution circuitry is to perform a conversion of one or more block format numbers associated with the first source operand that each have a value of a scale multiplied by a value of a data element to a non-block format and store the non-block formatted numbers in the destination operand;
a processor core to support execution of a decoded instance of the single instruction, the processor core to at least include execution circuitry to execute the decoded instance of the single instruction according to the opcode to perform the conversion.
18 . The system of claim 17 , wherein the opcode is to identify a first datatype for the first source operand and a second datatype for the destination operand.
19 . The system of claim 18 , wherein at least one of the datatypes is a floating point datatype.
20 . The system of claim 18 , wherein at least one of the datatypes is an integer datatype.