Instructions and logic to vectorize conditional loops

1. A processor comprising:

mask physical registers to store a vector conditions mask;

vector physical registers to store:

a source vector having a first plurality of n data fields having a variable partition size of m bytes, and

a destination vector comprising a second plurality of data fields corresponding to the first plurality of data fields, wherein each of the second plurality of data fields in the destination vector corresponds to a mask value in said vector conditions mask;

a decode stage to decode processor instructions, a first processor instruction specifying a vector expand operation and a data partition size; and

one or more execution units, responsive to the decoded processor instructions, to:

set elements of the source vector to n count values;

obtain a decisions vector;

generate said vector conditions mask according to the decisions vector; and

responsive to executing the first processor instruction, copy data from consecutive vector elements in the source vector, into unmasked vector elements of the destination vector, without copying data from the source vector into masked vector elements of the destination vector.

2. The processor of claim 1 , wherein the data is copied into unmasked vector elements of the destination vector and any masked vector elements of the destination vector are set to a value of zero.

3. The processor of claim 1 , wherein the data is copied into unmasked vector elements of the destination vector without modifying any masked vector elements of the destination vector.

4. The processor of claim 1 , wherein when the first processor instruction executed expands 32-bit integers, and n is a value selected from the group consisting of 4, 8 and 16.

5. The processor of claim 1 , wherein when the first processor instruction executed expands 64-bit integers, and n is a value selected from the group consisting of 2, 4 and 8.

6. A computer implemented method comprising:

receiving a set of processor instructions, a first processor instruction of the set specifying: a vector expand operation, a source vector, a mask register to hold a vector conditions mask, and a destination vector to hold a plurality of n consecutive vector elements, each having a variable partition size of m bytes; and

in response to receiving the set of processor instructions,

setting elements of the source vector to n count values;

obtaining a decisions vector;

generating said vector conditions mask according to the decisions vector; and

executing the first processor instruction, by copying data from consecutive vector elements in the source vector, into unmasked vector elements of the specified destination vector, without copying data into masked vector elements of the specified destination vector.

7. The method of claim 6 , wherein the data is copied into unmasked vector elements of the destination vector and any masked vector elements of the destination vector are set to a value of zero.

8. The method of claim 6 , wherein the data is copied into unmasked vector elements of the destination vector without modifying any masked vector elements of the destination vector.

9. The method of claim 6 , wherein the source vector is a source vector register.

10. The method of claim 6 , wherein the destination vector is a destination vector register.

11. A processing system comprising:

a memory unit; and

a plurality of processors including a first processor core and a second processor core each processor comprising:

mask physical registers to store a vector conditions mask;

vector physical registers to store:

a source vector having a first plurality of n data fields, each having a variable partition size of m bytes, and

a destination vector comprising a second plurality of data fields corresponding to the first plurality of data fields, wherein each of the second plurality of data fields in the destination vector corresponds to a mask value in said vector conditions mask;

a decode stage to decode processor instructions, a first processor instruction specifying a vector expand operation and a data partition size; and

one or more execution units, responsive to the decoded processor instructions, to:

set elements of the source vector to n count values;

obtain a decisions vector;

generate said vector conditions mask according to the decisions vector; and

responsive to executing the first processor instruction, copy data from consecutive vector elements in the source vector, into unmasked vector elements of the destination vector, without copying data from the source vector into masked vector elements of the destination vector.

12. The processing system of claim 11 , wherein the data is copied into unmasked vector elements of the destination vector and any masked vector elements of the destination vector are set to a value of zero.

13. The processing system of claim 11 , wherein the data is copied into unmasked vector elements of the destination vector without modifying any masked vector elements of the destination vector.

14. The processing system of claim 11 , wherein when the first processor instruction executed expands 32-bit integers, and n is a value selected from the group consisting of 4, 8 and 16.

15. The processing system of claim 11 , wherein when the first processor instruction executed expands 64-bit integers, and n is a value selected from the group consisting of 2, 4 and 8.

16. A non-transitory machine-readable storage medium storing instructions which, when executed, cause a processing device to perform operations comprising:

receiving a set of processor instructions, a first processor instruction of the set specifying: a vector expand operation, a source vector, a mask register to hold a vector conditions mask, and a destination vector to hold a plurality of n consecutive vector elements, each having a variable partition size of m bytes; and

in response to receiving the set of processor instructions,

setting elements of the source vector to n count values;

obtaining a decisions vector;

generating said vector conditions mask according to the decisions vector; and

executing the first processor instruction, by copying data from consecutive vector elements in the source vector, into unmasked vector elements of the specified destination vector, without copying data into masked vector elements of the specified destination vector.

17. The non-transitory machine-readable medium of claim 16 , wherein the data is copied into unmasked vector elements of the destination vector and any masked vector elements of the destination vector are set to a value of zero.

18. The non-transitory machine-readable medium of claim 16 , wherein the data is copied into unmasked vector elements of the destination vector without modifying any masked vector elements of the destination vector.

19. The non-transitory machine-readable medium of claim 16 , wherein the source vector is a source vector register.

20. The non-transitory machine-readable medium of claim 16 , wherein the destination vector is a destination vector register.