Lenovo (singapore) Pte. Ltd.

International Business Machines Corporation

Juan Q Hernandez

Tu T Dang

Sumeet Kochar

Jung H Yoon

Sumanta Kumar Bahali

Michael Charles Elles

Dwayne A Lowe

Jeffrey Ross Hamilton

Challis Llewellyn Purrington

Michael Leo Scollard

Ivan R Zapata

Peter Robert Seidel

Brian E Bigelow

Challis L Purrington, Sr

An apparatus for memory management a high-speed fabric controller and a memory controller connected between a high-speed memory and a processor. The memory controller is configured to control processor access to the high-speed memory over a memory bus between the processor and the high-speed memory. The apparatus includes a high-speed data connection between the memory controller and the high-speed fabric controller and a data connection between a tier of persistent data storage and the high-speed fabric controller. The high-speed fabric controller is configured to control data transfers between the tier of persistent data storage over and the high-speed memory independent of the processor.

Controlling data transfers between a tier of persistent data storage and processor memory with a high-speed fabric controller

One embodiment provides a method for scalable predictive failure analysis. Embodiments of the method may include gathering memory information for memory on a user computer system having at least one processor. Further, the method includes selecting one or more memory-related parameters. Further still, the method includes calculating based on the gathering and the selecting, a single bit error value for the scalable predictive failure analysis through calculations for each of the one or more memory-related parameters that utilize the memory information. Yet further, the method includes setting, based on the calculating, the single bit error value for the user computer system.

Scalable prediction failure analysis for memory used in modern computers

An approach to determine a power-on-hour offset for a memory device that is newly-installed into a computer system is provided, which subtracts a current power-on-hour count of the memory device from a current power-on-hour value of a power supply that supplies operative power to the memory device within the computer system. In response to the computer system powering down, an accumulated power-on-hour for the memory device is determined by subtracting the power-on-hour offset of the memory from a current power-on-hour value of the computer system power supply. The determined power-on-hour offset and accumulated power-on-hour values are saved into one or more designated bytes of a free area of electrically erasable programmable read-only memory of the memory device that are available for data storage by a memory controller, and wherein data stored therein persists after operative power is lost to the memory device, the memory controller or the computer system.

Using persistent memory regions within memory devices to collect serial presence detect and performance data

One embodiment provides an error detection method wherein single-bit errors in a memory module are detected and identified as being a random error or a repeat error. Each identified random error and each identified repeat error occurring in a time interval is counted. An alert is generated in response to a number of identified random errors reaching a random-error threshold or a number of identified repeat errors reaching a repeat-error threshold during the predefined interval. The repeat-error threshold is set lower than the random-error threshold. A hashing process may be applied to the memory address of each detected error to map the location of the error in the memory system to a corresponding location in an electronic table.

Use of hashing function to distinguish random and repeat errors in a memory system

Growing community of inventors

Garner, NC, United States of America

Juan Q Hernandez