Vector cross-compare count and sequence instructions

Patent metadata

Field	Value
Publication number	US-10564964-B2
Application number	US-201615244570-A
Country	US
Kind code	B2
Filing date	Aug 23, 2016
Priority date	Aug 23, 2016
Publication date	Feb 18, 2020
Grant date	Feb 18, 2020

Abstract

Systems and methods are provided for executing an instruction. The method may include loading a first vector into a first location, the first vector including a plurality of first data elements and loading a second vector into a second location, the second vector including a plurality of second data elements. The method may further include comparing the plurality of first data elements of the first vector to the plurality of data elements of the second vector and performing one or more operations on the plurality of first and second data elements based on at least one vector cross-compare instruction. The one or more operations include counting a number of data elements of the plurality of first and second data elements that satisfy at least one condition, counting a number of times specified values occur in the plurality of first and second data elements, and generating sequence counts for duplicated values.

First claim

What is claimed is:

1. A computer-implemented method for executing a Single Instruction, Multiple Data (SIMD) instruction on a processor, the method comprising:
loading a first vector into a first location, the first vector including a plurality of first data elements;
loading a second vector into a second location, the second vector including a plurality of second data elements;
comparing the plurality of first data elements of the first vector to the plurality of second data elements of the second vector; and
performing one or more operations on the plurality of first and second data elements by applying a plurality of different vector cross-compare instructions processed by sequentially partitioning the plurality of different vector cross-compare instructions into comparison, selection, and reduction steps via a common partitioning implementation structure where all vector comparisons are completed before performing all selections, and all selections are completed before performing all reductions.

2. The method of claim 1 , further comprising counting a number of data elements of the plurality of first and second data elements that satisfy at least one condition.

3. The method of claim 1 , further comprising counting a number of times specified values occur in the plurality of first and second data elements.

4. The method of claim 1 , further comprising generating sequence counts for duplicated values identified in the plurality of first and second data elements.

5. The method of claim 1 , wherein one of the vector cross-compare instructions is a vector cross-compare and count instruction.

6. The method of claim 1 , wherein one of the vector cross-compare instructions is a vector cross-compare and sequence instruction.

7. The method of claim 1 , wherein one of the vector cross-compare instructions is a vector cross-compare equal instruction.

8. The method of claim 1 , further comprising determining whether each fullword of the second vector is equal to at least one fullword of the first vector.

9. The method of claim 1 , further comprising counting a number of fullwords in the first vector equal to each fullword in the second vector.

10. The method of claim 1 , further comprising counting a rank of a word for each fullword in the second vector.

11. A computer system for executing a Single Instruction, Multiple Data (SIMD) machine instruction in a central processing unit, the computer system comprising:
a memory; and
a processor in communications with the memory, wherein the computer system is configured to perform the steps of:
loading a first vector into a first location, the first vector including a plurality of first data elements;
loading a second vector into a second location, the second vector including a plurality of second data elements;
comparing the plurality of first data elements of the first vector to the plurality of second data elements of the second vector; and
performing one or more operations on the plurality of first and second data elements by applying a plurality of different vector cross-compare instructions processed by sequentially partitioning the plurality of different vector cross-compare instructions into comparison, selection, and reduction steps via a common partitioning implementation structure where all vector comparisons are completed before performing all selections, and all selections are completed before performing all reductions.

12. The computer system of claim 11 , wherein the one or more operations include counting a number of data elements of the plurality of first and second data elements that satisfy at least one condition.

13. The computer system of claim 11 , wherein the one or more operations include counting a number of times specified values occur in the plurality of first and second data elements.

14. The computer system of claim 11 , wherein the one or more operations include generating sequence counts for duplicated values identified in the plurality of first and second data elements.

15. The computer system of claim 11 , wherein one of the vector cross-compare instructions is a vector cross-compare and count instruction.

16. The computer system of claim 11 , wherein one of the vector cross-compare instructions is a vector cross-compare and sequence instruction.

17. The computer system of claim 11 , wherein one of the vector cross-compare instructions is a vector cross-compare equal instruction.

18. A non-transitory computer readable storage medium comprising a computer readable program for executing a Single Instruction, Multiple Data (SIMD) instruction on a processor, wherein the computer readable program when executed on a computer causes the computer to perform the steps of:
loading a first vector into a first location, the first vector including a plurality of first data elements;
loading a second vector into a second location, the second vector including a plurality of second data elements;
comparing the plurality of first data elements of the first vector to the plurality of data elements of the second vector; and
performing one or more operations on the plurality of first and second data elements by applying a plurality of different vector cross-compare instructions processed by sequentially partitioning the plurality of different vector cross-compare instructions into comparison, selection, and reduction steps via a common partitioning implementation structure where all vector comparisons are completed before performing all selections, and all selections are completed before performing all reductions.

19. The non-transitory computer readable storage medium of claim 18 , wherein the one or more operations include:
counting a number of data elements of the plurality of first and second data elements that satisfy at least one condition;
counting a number of times specified values occur in the plurality of first and second data elements; and
generating sequence counts for duplicated values identified in the plurality of first and second data elements.

20. The non-transitory computer readable storage medium of claim 19 , wherein the vector cross-compare instructions are selected from the group consisting of a vector cross-compare and count instruction, a vector cross-compare and sequence instruction, and a vector cross-compare equal instruction.

Assignees

• IBM

Inventors

• Derby Jeffrey H
• Montoye Robert K
• Sreedhar Dheeraj

Classifications

• G06F9/30021 Primary

  Compare instructions, e.g. Greater-Than, Equal-To, MINMAX · CPC title

• G06F9/30036

  Instructions to perform operations on packed data, e.g. vector, tile or matrix operations · CPC title