Systems and methods of memory bit flip identification for debugging and power management

• US 9,846,612 B2
• Filed: 08/11/2015
• Issued: 12/19/2017
• Est. Priority Date: 08/11/2015
• Status: Expired due to Fees

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Krishnappa, Madan, Tran, Chinh, Zhang, Li, Young, Alan, Bainbridge, William, Rychlik, Bohuslav
• Primary Examiner(s): Decady, Albert
• Assistant Examiner(s): DORMAN, CHRISTIAN M
• Application Number:
  US14/823,879
• Publication Number:
  US 20170046219A1
• Time in Patent Office: 861 Days
• CPC Class Codes: G06F 1/3206 Monitoring of events, devices or parameters that trigger a change in power modality
• CPC Class Codes: G06F 1/3296 by lowering the supply or operating voltage
• CPC Class Codes: G06F 11/10 Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
• CPC Class Codes: G06F 11/1008 in individual solid state devices G06F11/1004 takes precedence
• CPC Class Codes: G06F 11/1048 using arrangements adapted for a specific error detection or correction feature
• CPC Class Codes: G06F 11/3058 Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations thermal management in cooling arrangements of a computing system G06F1/206
• CPC Class Codes: G06F 11/3062 where the monitored property is the power consumption power management in a computing system G06F1/3203
• CPC Class Codes: G11B 20/1816 Testing
• CPC Class Codes: H03M 13/11 using multiple parity bits
• CPC Class Codes: H03M 13/611 Specific encoding aspects, e.g. encoding by means of decoding
• CPC Class Codes: H03M 13/6505 Memory efficient implementations
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Various embodiments of methods and systems for bit flip identification for debugging and/or power management in a system on a chip (“SoC”) are disclosed. Exemplary embodiments seek to identify bit flip occurrences near in time to the occurrences by checking parity values of data blocks as the data blocks are written into a memory component. In this way, bit flips occurring in association with a write transaction may be differentiated from bit flips occurring in association with a read transaction. The distinction may be useful, when taken in conjunction with various parameter levels identified at the time of a bit flip recognition, to debug a memory component or, when in a runtime environment, adjust thermal and power policies that may be contributing to bit flip occurrences.

Claims

1. A method for power management in a system on a chip (“

SoC”

), the method comprising;

monitoring one or more parameters of the SoC that are associated with bit flips;

calculating baseline parity values for data blocks of bits queued to be written to bit cell arrays of a random access memory (RAM) component and assigning the baseline parity values to parity bits uniquely associated with the data blocks;

writing the data blocks to the bit cell arrays of the RAM component and a buffer of the RAM component;

for each data block as it is written to the buffer, calculating a write-side parity value;

for each data block, comparing its baseline parity value to its write-side parity value;

for each data block, if the baseline parity value differs from the write-side parity value, recording the occurrence of a bit flip;

based on determining that a rate of bit flip occurrences has exceeded a threshold, adjusting a thermal and power management policy associated with one or more thermally aggressive components of the SoC located in thermal proximity to the RAM component to reduce thermal energy generation by the one or more thermally aggressive components.

2. The method of claim 1, wherein adjusting the thermal and power management policy comprises modifying a temperature threshold associated with a thermally aggressive component.

3. The method of claim 1, wherein adjusting the thermal and power management policy comprises modifying a power supply level associated with a thermally aggressive component.

4. The method of claim 1, wherein adjusting the thermal and power management policy comprises modifying a workload level associated with a thermally aggressive component.

5. The method of claim 1, further comprising increasing a power supply level to the RAM component.

6. The method of claim 1, further comprising:

determining that the rate of bit flip occurrences has dropped below the threshold; and

based on determining that the rate of bit flip occurrences has dropped below the threshold, readjusting the thermal and power management policy.

7. The method of claim 6, wherein readjusting the thermal and power management policy comprises one or more of modifying a temperature threshold associated with a thermally aggressive component, modifying a power supply level associated with thermally aggressive component, modifying a workload level associated with the thermally aggressive component, and decreasing a power supply level to the RAM component.

8. The method of claim 1, wherein the RAM component comprises error correcting code (“

ECC”

).

9. A method for power management in a system on a chip (“

SoC”

), the method comprising;

monitoring one or more parameters of the SoC that are associated with bit flips;

calculating baseline parity values for data blocks of bits queued to be written to bit cell arrays of a random access memory (RAM) component and assigning the baseline parity values to parity bits uniquely associated with the data blocks;

writing the data blocks to the bit cell arrays of the RAM component;

for each data block as it is written to the bit cell arrays, calculating a write-side parity value;

for each data block, comparing its baseline parity value to its write-side parity value;

for each data block, if the baseline parity value differs from the write-side parity value, recording the occurrence of a bit flip;

based on determining that a rate of bit flip occurrences has exceeded a threshold, adjusting a thermal and power management policy associated with one or more thermally aggressive components of the SoC located in thermal proximity to the RAM component to reduce thermal energy generation by the one or more thermally aggressive components.

10. The method of claim 9, wherein adjusting the thermal and power management policy comprises modifying a temperature threshold associated with a thermally aggressive component.

11. The method of claim 9, wherein adjusting the thermal and power management policy comprises modifying a power supply level associated with a thermally aggressive component.

12. The method of claim 9, wherein adjusting the thermal and power management policy comprises modifying a workload level associated with a thermally aggressive component.

13. The method of claim 9, further comprising increasing a power supply level to the RAM component.

14. The method of claim 9, further comprising:

determining that the rate of bit flip occurrences has dropped below the threshold; and

based on determining that the rate of bit flip occurrences has dropped below the threshold, readjusting the thermal and power management policy.

15. The method of claim 14, wherein readjusting the thermal and power management policy comprises one or more of modifying a temperature threshold associated with a thermally aggressive component, modifying a power supply level associated with a thermally aggressive component, modifying a workload level associated with a thermally aggressive component, and decreasing a power supply level to the RAM component.

16. The method of claim 9, wherein the RAM component comprises error correcting code (“

ECC”

).

17. A system for power management in a system on a chip (“

SoC”

), the system comprising;

means for monitoring one or more parameters of the SoC that are associated with bit flips;

means for calculating baseline parity values for data blocks of bits queued to be written to bit cell arrays of a random access memory (RAM) component and assigning the baseline parity values to parity bits uniquely associated with the data blocks;

means for writing the data blocks to the bit cell arrays and a buffer of the RAM component;

for each data block as it is written to the buffer, means for calculating a write-side parity value;

for each data block, means for comparing its baseline parity value to its write-side parity value;

for each data block, if the baseline parity value differs from the write-side parity value, means for recording the occurrence of a bit flip;

based on determining that a rate of bit flip occurrences has exceeded a threshold, means for adjusting a thermal and power management policy associated with one or more thermally aggressive components of the SoC located in thermal proximity to the RAM component to reduce thermal energy generation by the one or more thermally aggressive components.

18. The system of claim 17, wherein the means for adjusting the thermal and power management policy comprises means for modifying a temperature threshold associated with a thermally aggressive component.

19. The system of claim 17, wherein the means for adjusting the thermal and power management policy comprises means for modifying a power supply level associated with a thermally aggressive component.

20. The system of claim 17, wherein the means for adjusting the thermal and power management policy comprises means for modifying a workload level associated with a thermally aggressive component.

21. The system of claim 17, further comprising means for increasing a power supply level to the RAM component.

22. The system of claim 17, further comprising:

means for determining that the rate of bit flip occurrences has dropped below the threshold; and

based on determining that the rate of bit flip occurrences has dropped below the threshold, means for readjusting the thermal and power management policy.

23. The system of claim 22, wherein the means for readjusting the thermal and power management policy comprises one or more of means for modifying a temperature threshold associated with a thermally aggressive component, means for modifying a power supply level associated with a thermally aggressive component, means for modifying a workload level associated with a thermally aggressive component, and means for decreasing a power supply level to the RAM component.

24. A system for power management in a system on a chip (“

SoC”

), the system comprising;

means for monitoring one or more parameters of the SoC that are associated with bit flips;

means for calculating baseline parity values for data blocks of bits queued to be written to bit cell arrays of a random access memory (RAM) component and assigning the baseline parity values to parity bits uniquely associated with the data blocks;

means for writing the data blocks to the bit cell arrays of the RAM component;

for each data block as it is written to the bit cell arrays, means for calculating a write-side parity value;

for each data block, means for comparing its baseline parity value to its write-side parity value;

for each data block, if the baseline parity value differs from the write-side parity value, means for recording the occurrence of a bit flip;

based on determining that a rate of bit flip occurrences has exceeded a threshold, means for adjusting a thermal and power management policy associated with one or more thermally aggressive components of the SoC located in thermal proximity to the RAM component to reduce thermal energy generation by the one or more thermally aggressive components.

25. The system of claim 24, wherein the means for adjusting the thermal and power management policy comprises means for modifying a temperature threshold associated with a thermally aggressive component.

26. The system of claim 24, wherein the means for adjusting the thermal and power management policy comprises means for modifying a power supply level associated with a thermally aggressive component.

27. The system of claim 24, wherein the means for adjusting the thermal and power management policy comprises means for modifying a workload level associated with a thermally aggressive component.

28. The system of claim 24, further comprising means for increasing a power supply level to the RAM component.

29. The system of claim 24, further comprising:

means for determining that the rate of bit flip occurrences has dropped below the threshold; and

based on determining that the rate of bit flip occurrences has dropped below the threshold, means for readjusting the thermal and power management policy.

30. The system of claim 29, wherein the means for readjusting the thermal and power management policy comprises one or more of means for modifying a temperature threshold associated with a thermally aggressive component, means for modifying a power supply level associated with a thermally aggressive component, means for modifying a workload level associated with a thermally aggressive component, and means for decreasing a power supply level to the RAM component.