Leveraging chip variability

• US 8,412,882 B2
• Filed: 06/18/2010
• Issued: 04/02/2013
• Est. Priority Date: 06/18/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Zorn, Benjamin, Bittner, Ray, Kirovski, Darko, Pattabiraman, Karthik
• Primary Examiner(s): Ho, Hoai V
• Assistant Examiner(s): HOANG, TRI M
• Application Number:
  US12/819,100
• Publication Number:
  US 20110314210A1
• Time in Patent Office: 1,019 Days
• Field of Search: 365/174, 365/51, 714/763, 714/5, 711/105, 711/154
• US Class Current: 711/105
• CPC Class Codes: G06F 11/1048 using arrangements adapted for a specific error detection or correction feature
• CPC Class Codes: G06F 11/14 Error detection or correction of the data by redundancy in operation G06F11/16 takes precedence
• CPC Class Codes: G11C 29/38 Response verification devices
• CPC Class Codes: G11C 29/44 Indication or identification of errors, e.g. for repair
• CPC Class Codes: G11C 29/56008 Error analysis, representation of errors

Abstract

Embodiments are described that leverage variability of a chip. Different areas of a chip vary in terms of reliability under a same operating condition. The variability may be captured by measuring errors over different areas of the chip. A physical factor that affects or controls the likelihood of an error on the chip can be varied. For example, the voltage supplied to a chip may be provided at different levels. At each level of the physical factor, the chip is tested for errors within the regions. Some indication of the error statistics for the regions is stored and then used to adjust power used by the chip, to adjust reliability behavior of the chip, to allow applications to control how the chip is used, to compute a signature uniquely identifying the chip, etc.

Claims

1. A method of obtaining an error profile for a chip, the method comprising:

measuring error statistics for respective regions of a chip over a range of values of a physical characteristic of the chip, the error statistics comprising, for each region, an error statistic for each value in the range of values, such that for each value there is a corresponding measured error statistic for each region, wherein the error statistics are able to map, at a given time, for each region, varying values of the physical characteristic to respective error statistics, where for any given one of the regions and any given one of the varying values, the error statistics are able to provide, at the given time, a corresponding error statistic that is specific to the given one of the regions and is specific to the given one of the varying values;

storing indicia of the error statistics; and

using the indicia of the error statistics to control operation of the chip.

2. A method according to claim 1, wherein the chip comprises a memory chip.

3. A method according to claim 1, wherein the physical characteristic comprises a temperature, an age or time of use of the chip, a voltage of the chip, a refresh rate of the chip, or a clock speed of the chip.

4. A method according to claim 1, wherein the using the indicia of the error statistics comprises adjusting a refresh rate of the chip, or adjusting a voltage of the chip, or adjusting a clock speed of the chip, or adjusting a temperature of the chip, or adjusting power consumption of the chip.

5. A method according to claim 4, further comprising obtaining a current value of the physical characteristic of the chip while the chip is in operation as a component of a computer, and the using comprises obtaining indicia of error statistics of the regions of the chip based on the current value.

6. A method according to claim 5, wherein an application or operating system running on a computer that includes the chip specifies an error level, and the using comprises identifying one or more regions of the chip.

7. A method according to claim 6, wherein the identified regions are either used to set a voltage or refresh rate or clock rate of the chip, or the identified regions are marked or prioritized such that the operating system or application uses memory according to the marked or prioritized regions.

8. One or more computer-readable storage storing information that causes a computer to perform a process, the process comprising:

obtaining a desired value of an operational parameter of the chip;

accessing regional error statistic information describing error statistics of respective regions of the chip, the regional error statistic information able to map, at a given time, for each region, varying values of the operational parameter to respective error statistics, where for any given one of the regions and any given one of the varying values, the regional error statistic information is able to provide, at the given time, a corresponding error statistic that is specific to the given one of the regions and is specific to the given one of the varying values; and

using the regional error statistic information to operate the chip at the desired value of the operational parameter.

9. One or more computer-readable storage according to claim 8, wherein the desired operational parameter comprises a clock rate, a refresh rate, a temperature, a power consumption, or a voltage.

10. One or more computer-readable storage according to claim 8, wherein the desired operational parameter comprises an indication of a desired error setting, and the using comprises determining a clock rate, refresh rate, temperature, power consumption, or voltage based on one or more regional error statistics of one or more respective regions of the chip provided by the error statistic information.

11. One or more computer-readable storage according to claim 10, wherein the chip is operated at the determined clock rate, refresh rate, temperature, power consumption, or voltage.

12. One or more computer-readable storage according to claim 8, further comprising receiving a measure of a current physical attribute of the chip, the regional error statistic information comprises indicia of error statistics of the regions according to the measure, and a subset of the regions are identified based on the regional error statistic information.

13. One or more computer-readable storage according to claim 12, wherein the operational parameter comprises a setting for the chip that determines a power consumption of the chip and the using increases the overall likelihood of errors occurring on the chip.

14. One or more computer-readable storage according to claim 8, wherein the error statistics comprise error rates.