IP Library › Granted Patent US 11,315,654
Granted Patent B2
US 11,315,654 · App. 16/151,220 · Granted Apr 26, 2022

Memory testing techniques

Inventors: Andy Wangkun Chen (Austin, TX); Yannis Jallamion-Grive (Mouans Sartoux, FR); Cyrille Nicolas Dray (Antibes, FR); Frank David Frederick (Austin, TX)
Assignee: Arm Limited
G11C29/44G11C29/14G11C29/42G11C29/52G11C29/81G11C2029/0409
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,315,654
App. No.
16/151,220
Granted
Apr 26, 2022
Kind
B2
Abstract

Various implementations described herein refer to an integrated circuit having first circuitry and second circuitry. The first circuitry receives first input data and bypasses error correction circuitry to determine whether the first input data has one or more first errors. The second circuitry receives second input data and enables the error correction circuitry to determine whether the second input data has one or more second errors.

Claims (36)

1. An integrated circuit, comprising:

first circuitry that receives first input data and bypasses first error correction circuitry to determine whether the first input data has one or more first errors, wherein the first circuitry comprises a first multiplexer and is part of a write input path;

second circuitry that receives second input data and enables the first error correction circuitry to determine whether the second input data has one or more second errors, wherein the second circuitry comprises a second multiplexer and is part of the write input path; and

third circuitry that is part of a read output path, wherein the third circuitry comprises second error correction circuitry.

2. The integrated circuit of claim 1 , wherein the first input data comprises full width data having a first number of bits, wherein the second input data comprises functional data having a second number of bits, and wherein the first number of bits includes the second number of bits and a third number of check-bits for error correction coding (ECC).

3. The integrated circuit of claim 1 , wherein the third circuitry determines whether the second input data has multi-bit errors.

4. The integrated circuit of claim 3 , wherein the third circuitry generates a multi-bit error flag after detecting the multi-bit errors in the second input data.

5. The integrated circuit of claim 3 , wherein the multi-bit errors include 3-bit errors, and wherein the third circuitry detects 3-bit errors in the second input data.

6. The integrated circuit of claim 1 , further comprising single memory built-in self-test (MBIST) circuitry coupled to the first circuitry and the second circuitry so as to provide the first input data to the first circuitry and the second input data to the second circuitry.

7. The integrated circuit of claim 1 , further comprising multiple memory built-in self-test (MBIST) circuitry coupled to the first circuitry and the second circuitry so as to provide the first input data to the first circuitry and the second input data to the second circuitry.

8. The integrated circuit of claim 1 , wherein the first circuitry bypasses use of the first error correction circuitry during MBIST (memory built-in self-test) testing of the first input data.

9. The integrated circuit of claim 1 , wherein the first circuitry allows for redundancy to repair the one or more first errors in the first input data.

10. The integrated circuit of claim 1 , wherein the second circuitry allows for error correction coding (ECC) to repair the one or more second errors in the second input data.

11. A method, comprising:

receiving first input data and second input data;

bypassing first error correction circuitry using at least a first multiplexer that is part of write input path circuitry to determine whether the first input data has one or more first errors;

enabling the first error correction circuitry using at least a second multiplexer that is part of the write input path circuitry to determine whether the second input data has one or more second errors; and

determining whether the second input data has multi-bit errors via read output path circuitry, wherein the read output path circuitry includes second error correction circuitry.

12. The method of claim 11 , wherein the first input data comprises full width data having a first number of bits, wherein the second input data comprises functional data having a second number of bits, and wherein the first number of bits includes the second number of bits and a third number of check-bits for error correction coding (ECC).

13. The method of claim 11 , further comprising:

generating via the read output path circuitry a multi-bit error flag after detecting the multi-bit errors in the second input data.

14. The method of claim 13 , wherein the multi-bit errors include 3-bit errors, and wherein determining whether the second input data has multi-bit errors includes determining whether the second input data has 3-bit errors.

15. The method of claim 11 , wherein bypassing the first error correction circuitry occurs during MBIST (memory built-in self-test) testing of the first input data.

16. The method of claim 11 , further comprising allowing for repair of the one or more first errors in the first input data by using redundancy.

17. The method of claim 11 , further comprising allowing for repair of the one or more second errors in the second input data by using error correction coding (ECC).

18. A method, comprising:

receiving full width data having a first number of bits, wherein the first number of bits includes a second number of bits and a third number of check-bits for error correction coding (ECC);

bypassing first error correction circuitry using at least a first multiplexer that is part of write input path circuitry to determine whether the full width data has one or more first errors;

allowing for repair of the one or more first errors in the full width data by using redundancy;

receiving functional data having the second number of bits;

enabling the first error correction circuitry using at least a second multiplexer that is part of the write input path circuitry to determine whether the functional data has one or more second errors;

allowing for repair of the one or more second errors in the functional data by using error correction coding (ECC); and

determining whether the full width data has multi-bit errors via read output path circuitry, wherein the read output path circuitry includes second error correction circuitry.

19. The method of claim 18 , further comprising:

generating via the read output path circuitry a multi-bit error flag after detecting the multi-bit errors in the full width data.

20. The method of claim 19 , wherein the multi-bit errors include 3-bit errors, and wherein determining whether the full width data has multi-bit errors includes determining whether the full width data has 3-bit errors.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 3, 2018
From: CHEN, ANDY WANGKUN; JALLAMION-GRIVE, YANNIS; DRAY, CYRILLE NICOLAS; FREDERICK, FRANK DAVID
To: ARM LIMITED
Reel/Frame 047060/0785 →
Continuity (1)
Related Publication 20200111537A1 · Apr 9, 2020