Abstract:
Systems, methods, and computer programs are disclosed for kernel masking dynamic random access memory (DRAM) defects. One such method comprises: detecting and correcting a single-bit error associated with a physical address in a dynamic random access memory (DRAM); receiving error data associated with the physical address from the DRAM; storing the received error data in a failed address table located in a non-volatile memory; and retiring a kernel page corresponding to the physical address if a number of errors associated with the physical address exceeds an error count threshold.
Abstract:
Heterogeneous memory systems, and related methods and computer-readable media for supporting heterogeneous memory access requests in processor-based systems are disclosed. A heterogeneous memory system is comprised of a plurality of homogeneous memories that can be accessed for a given memory access request. Each homogeneous memory has particular power and performance characteristics. In this regard, a memory access request can be advantageously routed to one of the homogeneous memories in the heterogeneous memory system based on the memory access request, and power and/or performance considerations. The heterogeneous memory access request policies may be predefined or determined dynamically based on key operational parameters, such as read/write type, frequency of page hits, and memory traffic, as non-limiting examples. In this manner, memory access request times can be optimized to be reduced without the need to make tradeoffs associated with only having one memory type available for storage.
Abstract:
Memory devices may send information related to refresh rates to a memory controller. The memory controller may instruct the memory devices to refresh based on the received information.
Abstract:
A method of reading from and writing to a resistive memory cache includes receiving a write command and dividing the write command into multiple write sub-commands. The method also includes receiving a read command and executing the read command before executing a next write sub-command.
Abstract:
Systems and methods relate to a read operation on a magnetoresistive random access memory (MRAM). Prior to determining whether there is a hit in the MRAM for a first address corresponding to the read operation, a dummy word line is activated, based on at least a subset of bits of the first address. A settling process for a reference voltage for reading MRAM bit cells at the first address is initiated, based on dummy cells connected to the dummy word line and a settled reference voltage is obtained. If there is a hit, a first word line is activated based on a row address determined from the first address, and the MRAM bit cells at the first address are read using the settled reference voltage.
Abstract:
A method of reading from and writing to a resistive memory cache includes receiving a write command and dividing the write command into multiple write sub-commands. The method also includes receiving a read command and executing the read command before executing a next write sub-command.
Abstract:
In a particular embodiment, a device includes a resistance-based memory cell having multiple source lines and multiple access transistors. A coupling configuration of the multiple access transistors to multiple source lines encodes a data value.
Abstract:
Systems and methods for integrated magnetoresistive random access memory (MRAM) modules. An integrated circuit includes a processor without a last level cache integrated on a first chip a MRAM module comprising a MRAM last level cache and a MRAM main memory integrated on a second chip, wherein the MRAM module is a unified structure fabricated as monolithic package or a plurality of packages. The second package further includes memory controller logic. A simplified interface structure is configured to couple the first and the second package. The MRAM module is designed for high speed, high data retention, aggressive prefetching between the MRAM last level cache and the MRAM main memory, improved page handling, and improved seal ability.
Abstract:
A system and method to defragment a memory is disclosed. In a particular embodiment, a method includes loading data stored at a first physical memory address of a memory from the memory into a cache line of a data cache. The first physical memory address is mapped to a first virtual memory address. The method further includes initiating modification, at the data cache, of lookup information associated with the first virtual memory address so that the first virtual memory address corresponds to a second physical memory address of the memory. The method also includes modifying, at the data cache, information associated with the cache line to indicate that the cache line corresponds to the second physical memory address instead of the first physical memory address.
Abstract:
Systems and methods for integrated magnetoresistive random access memory (MRAM) modules. An integrated circuit includes a processor without a last level cache integrated on a first chip a MRAM module comprising a MRAM last level cache and a MRAM main memory integrated on a second chip, wherein the MRAM module is a unified structure fabricated as monolithic package or a plurality of packages. The second package further includes memory controller logic. A simplified interface structure is configured to couple the first and the second package. The MRAM module is designed for high speed, high data retention, aggressive prefetching between the MRAM last level cache and the MRAM main memory, improved page handling, and improved seal ability.