Reducing store operation busy times

• US 9,015,423 B2
• Filed: 06/14/2012
• Issued: 04/21/2015
• Est. Priority Date: 06/14/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Berger, Deanna Postles Dunn, Fee, Michael F., Jones, Christine C., O'Neill, Arthur J., Orf, Diane L.
• Primary Examiner(s): Bertram, Ryan
• Application Number:
  US13/523,567
• Publication Number:
  US 20130339606A1
• Time in Patent Office: 1,041 Days
• Field of Search: 711/118, 711/140
• US Class Current: 711/140
• CPC Class Codes: G06F 12/0806 Multiuser, multiprocessor or multiprocessing cache systems
• CPC Class Codes: G06F 12/0855 Overlapped cache accessing, e.g. pipeline G06F12/0846 takes precedence
• CPC Class Codes: G06F 9/38 Concurrent instruction execution, e.g. pipeline or look ahead
• CPC Class Codes: G06F 9/3856 Reordering of instructions, e.g. using queues or age tags
• CPC Class Codes: G11C 2207/229 Timing of a write operation sense amplifier timing G11C7/06, G11C7/08
• CPC Class Codes: G11C 7/22 Read-write [R-W] timing or clocking circuits; Read-write [R-W] control signal generators or management
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A computer product for reducing store operation busy times is provided and relates to associating first and second platform registers with a cache array, determining that first and second store operations target a same wordline of the cache array, loading control information and data of the store operations into the platform registers and delaying a commit of the first store operation until the loading of the second platform register is complete. The method further includes committing the data from the platform registers using the control information from the platform registers to the wordline of the cache array at a same time to thereby reduce a busy time of the wordline of the cache array.

Claims

1. A non-transitory computer-readable storage medium for reducing store operation busy times, the computer program product comprising:

a tangible storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising;

associating first and second platform registers with a cache array such that the first and second platform registers are disposed along a same wordline of the cache array;

determining, by a comparator, that first and second store operations target the same wordline of the cache array on which the first and second platform registers are disposed;

loading control information and data of the first and second store operation into the first and second platform registers;

delaying, by a buffer, a commit of the first store operation to the same wordline of the cache array until the control information and data of the second store operation is loaded into the second platform register; and

committing the data from the first and second platform registers using the control information from the first and second platform registers to the same wordline of the cache array at a same time to thereby reduce a busy time of the same wordline of the cache array.

2. The computer program product according to claim 1, wherein the first platform register comprises a primary platform register and the second platform register comprises an alternate platform register, and wherein the method further comprises associating multiple alternate platform registers with the cache array.

3. The computer program product according to claim 1, wherein the method further comprises activating the same wordline of the cache array once for the first and second store operations.

4. The computer program product according to claim 1, wherein the determining that the first and second store operations target the same wordline of the cache array comprises comparing the first and second store operations.

5. The computer program product according to claim 4, wherein the comparing of the first and second store operations comprises comparing store operation addresses of the first and second store operations.

6. The computer program product according to claim 1, wherein the method further comprises issuing a delay signal based on a determination that the first and second store operations target the same wordline of the cache array.

7. A system for reducing penalties for reducing store operation busy times, the system comprising:

a cache array;

a first platform register associated with the cache array such that the first platform register is disposed on a wordline of the cache array;

multiple second platform registers associated with the cache array such that one second platform is disposed on the same wordline of the cache array as the first platform register and other second platform registers are disposed on another wordline of the cache array;

a comparator; and

a buffer,

the system being configured to perform a method comprising;

determining, by the comparator, that first and second store operations target the same wordline of the cache array on which the first platform register and the one second platform register are disposed;

loading control information and data of the first and second store operation into the first and second platform registers;

delaying, by the buffer, a commit of the first store operation to the same wordline of the cache array until the control information and data of the second store operation is loaded into the second platform register; and

committing the data from the first and second platform registers using the control information from the first and second platform registers to the same wordline of the cache array at a same time to thereby reduce a busy time of the same wordline of the cache array.

8. The system according to claim 7, wherein the first platform register comprises a primary platform register and the multiple second platform registers respectively comprise alternate platform registers.

9. The system according to claim 7, wherein the method further comprises activating the same wordline of the cache array.

10. The system according to claim 7, wherein the method further comprises activating the same wordline of the cache array once for the first and second store operations.

11. The system according to claim 7, wherein the determining that the first and second store operations targets the same wordline of the cache array comprises comparing the first and second store operations.

12. The system according to claim 11, wherein the comparing of the first and second store operations comprises comparing store operation addresses of the first and second store operations.

13. The system according to claim 7, wherein the method further comprises issuing a delay signal based on a determination that the first and second store operations target the same wordline of the cache array.