Abstract: A spin-torque magnetoresistive memory includes array read circuits and array write circuits coupled to an array of magnetic bits. The array read circuits sample magnetic bits in the array, apply a write current pulse to the magnetic bits to set them to a first logic state, resample the magnetic bits using an additional offset current, and compare the results of sampling and resampling to determine the bit state for each magnetic bit. For each of the magnetic bits in the page having the second logic state, the array write circuits initiate a write-back, wherein the write-back includes applying a second write current pulse having opposite polarity in comparison with the first write current pulse to set the magnetic bit to the second state. A read or write operation may be received after initiation of the write-back where the write-back can be aborted for a portion of the bits in the case of a write operation.

Abstract: A method includes destructively reading bits of a spin torque magnetic random access memory, using error correcting code (ECC) for error correction, and storing inverted or non-inverted data in data-store latches. When a subsequent write operation changes the state of data-store latches, parity calculation and majority detection of the bits are initiated. A majority bit detection and potential inversion of write data minimizes the number of write current pulses. A subsequent write operation received within a specified time or before an original write operation is commenced will cause the majority detection operation to abort.

Abstract: A spin-torque magnetoresistive memory includes array read circuits and array write circuits coupled to an array of magnetic bits. The array read circuits sample magnetic bits in the array, apply a write current pulse to the magnetic bits to set them to a first logic state, resample the magnetic bits using an additional offset current, and compare the results of sampling and resampling to determine the bit state for each magnetic bit. For each of the magnetic bits in the page having the second logic state, the array write circuits initiate a write-back, wherein the write-back includes applying a second write current pulse having opposite polarity in comparison with the first write current pulse to set the magnetic bit to the second state. A read or write operation may be received after initiation of the write-back where the write-back can be aborted for a portion of the bits in the case of a write operation.

Abstract: A spin-torque magnetoresistive memory includes array read circuits and array write circuits coupled to an array of magnetic bits. The array read circuits sample magnetic bits in the array, apply a write current pulse to the magnetic bits to set them to a first logic state, resample the magnetic bits, and comparing the results of sampling and resampling to determine the bit state for each magnetic bit. For each of the magnetic bits in the page having the second logic state, the array write circuits initiate a write-back, wherein the write-back includes applying a second write current pulse having opposite polarity in comparison with the first write current pulse to set the magnetic bit to the second state. A read or write operation may be received after initiation of the write-back where the write-back can be aborted for a portion of the bits in the case of a write operation.

Abstract: A spin-torque magnetoresistive memory includes array read circuits and array write circuits coupled to an array of magnetic bits. The array read circuits sample magnetic bits in the array, apply a write current pulse to the magnetic bits to set them to a first logic state, resample the magnetic bits, and comparing the results of sampling and resampling to determine the bit state for each magnetic bit. For each of the magnetic bits in the page having the second logic state, the array write circuits initiate a write-back, wherein the write-back includes applying a second write current pulse having opposite polarity in comparison with the first write current pulse to set the magnetic bit to the second state. A read or write operation may be received after initiation of the write-back where the write-back can be aborted for a portion of the bits in the case of a write operation.

Abstract: A method includes sampling magnetic bits, applying a write current pulse to the magnetic bits to set them to a first logic state, resampling the magnetic bits, and comparing the results of sampling and resampling to determine the bit state for each magnetic bit. A read or write operation may be received after initiation of writing back magnetic bits having the second state, where the write-back can be aborted for a portion of the bits in the case of a write operation. The write-back may be performed such that different portions of the magnetic bits are written back at different times, thereby staggering the write-back current pulses in time. An offset current may also be used during resampling.

Abstract: A method includes destructively reading bits of a spin torque magnetic random access memory, using error correcting code (ECC) for error correction, and storing inverted or non-inverted data in data-store latches. When a subsequent write operation changes the state of data-store latches, parity calculation and majority detection of the bits are initiated. A majority bit detection and potential inversion of write data minimizes the number of write current pulses. A subsequent write operation received within a specified time or before an original write operation is commenced will cause the majority detection operation to abort.

Abstract: A method includes sampling magnetic bits, applying a write current pulse to the magnetic bits to set them to a first logic state, resampling the magnetic bits, and comparing the results of sampling and resampling to determine the bit state for each magnetic bit. A read or write operation may be received after initiation of writing back magnetic bits having the second state, where the write-back can be aborted for a portion of the bits in the case of a write operation. The write-back may be performed such that different portions of the magnetic bits are written back at different times, thereby staggering the write-back current pulses in time. An offset current may also be used during resampling.

Abstract: A method includes destructively reading bits of a spin torque magnetic random access memory, using error correcting code (ECC) for error correction, and storing inverted or non-inverted data in data-store latches. When a subsequent write operation changes the state of data-store latches, parity calculation and majority detection of the bits are initiated. A majority bit detection and potential inversion of write data minimizes the number of write current pulses. A subsequent write operation received within a specified time or before an original write operation is commenced will cause the majority detection operation to abort.

Abstract: A method includes destructively reading bits of a spin torque magnetic random access memory and immediately writing back the original or inverted values. A detection of the majority state of the write back bits and a conditional inversion of write back bits are employed to reduce the number of write back pulses. A subsequent write command received within a specified time or before an original write operation is commenced will cause a portion of the write back pulses or the original write operation pulses to abort. Write pulses during subsequent write operations will follow the conditional inversion determined for the write back bits during destructive read.

Abstract: A method includes destructively reading bits of a spin torque magnetic random access memory and immediately writing back the original or inverted values. A detection of the majority state of the write back bits and a conditional inversion of write back bits are employed to reduce the number of write back pulses. A subsequent write command received within a specified time or before an original write operation is commenced will cause a portion of the write back pulses or the original write operation pulses to abort. Write pulses during subsequent write operations will follow the conditional inversion determined for the write back bits during destructive read.

Abstract: A method includes destructively reading bits of a spin torque magnetic random access memory and immediately writing back the original or inverted values. A detection of the majority state of the write back bits and a conditional inversion of write back bits are employed to reduce the number of write back pulses. A subsequent write command received within a specified time or before an original write operation is commenced will cause a portion of the write back pulses or the original write operation pulses to abort. Write pulses during subsequent write operations will follow the conditional inversion determined for the write back bits during destructive read.

Abstract: A method includes destructively reading bits of a spin torque magnetic random access memory and immediately writing back the original or inverted values. A detection of the majority state of the write back bits and a conditional inversion of write back bits are employed to reduce the number of write back pulses. A subsequent write command received within a specified time or before an original write operation is commenced will cause a portion of the write back pulses or the original write operation pulses to abort. Write pulses during subsequent write operations will follow the conditional inversion determined for the write back bits during destructive read.

Abstract: A method includes destructively reading bits of a spin torque magnetic random access memory, using error correcting code (ECC) for error correction, and storing inverted or non-inverted data in data-store latches. When a subsequent write operation changes the state of data-store latches, parity calculation and majority detection of the bits are initiated. A majority bit detection and potential inversion of write data minimizes the number of write current pulses. A subsequent write operation received within a specified time or before an original write operation is commenced will cause the majority detection operation to abort.