Provided are a method and apparatus for determining a timing adjustment of output to a host memory controller in a first memory module coupled to a host memory controller and a second memory module over a bus. A determination is made of a timing adjustment based on at least one component in at least one of the first memory module and the second memory module. A timing of output to the host memory controller is adjusted based on the determined timing adjustment to match a timing of output at the second memory module.

When performing non-sequential accesses to large data sets, hot spots may be avoided by permuting the memory locations being accesses to more evenly spread those accesses across the memory and across multiple memory channels. A permutation step may be used when accessing data, such as to improve the distribution of those memory accesses within the system. Instead of accessing one memory address, that address may be permuted so that another memory address is accessed. Non-sequential accesses to an array may be modified such that each index to the array is permuted to another index in the array. Collisions between pre- and post-translation addresses may be prevented and one-to-one mappings may be used. Permutation mechanisms may be implemented in software, hardware, or a combination of both, with or without the knowledge of the process performing the memory accesses.

A memory architecture for storing information units, the memory architecture comprising a plurality of memory banks or a plurality of memory devices and a memory controller for initiating storage of an information unit and a number of replicas of the information unit in the memory banks or in the memory devices, the memory controller discriminating the replicas in dependence on a size of the information unit.

Provided are an apparatus and method for a non-power-of-2 size cache in a first level memory device to cache data present in a second level memory device having a 2.sup.n cache size. A request is to a target address having n bits directed to the second level memory device. A determination is made whether a target index, comprising m bits of the n bits of the target address, is within an index set of the first level memory device. A determination is made of a modified target index in the index set of the first level memory device having at least one index bit that differs from a corresponding at least one index bit in the target index. The request is processed with respect to data in a cache line at the modified target index in the first level memory device.

Herein are data storage devices to transfer a data object between memory regions during a storage operation. These data storage devices include a host controller configured to identify an object stored in a host region of a memory system for writing to a storage media controlled by a drive controller. The host controller initiates a memory transfer operation to transfer an object from the host region of the memory system to a drive region of the memory system. The host controller transfers a storage command to the drive controller to write the object to the storage media. The drive controller may be configured to transfer an object from the drive region to the host region when reading the object.

Methods and apparatus relating to mid-thread pre-emption with software assisted context switch are described. In an embodiment, one or more threads executing on a Graphics Processing Unit (GPU) are stopped at an instruction level granularity in response to a request to pre-empt the one or more threads. The context data of the one or more threads is copied to memory in response to completion of the one or more threads at the instruction level granularity and/or one or more instructions. Other embodiments are also disclosed and claimed.

Provided is a device for use in a memory module coupled to a host memory controller over a bus, comprising memory module control logic to generate a request signal to a host memory controller having a pulse width greater than or equal to a minimum pulse width, wherein the minimum pulse width comprises a number of clock cycles needed to guarantee that the host memory controller detects the request signal, and wherein the pulse width of the request signal indicates at least one function in addition to the request signal to the host memory controller.

A system and method for providing dynamic I/O virtualization is herein disclosed. According to one embodiment, a device capable of performing hypervisor-agnostic and device-agnostic I/O virtualization includes a host computer interface, memory, I/O devices (GPU, disk, NIC), and efficient communication mechanisms for virtual machines to communicate their intention to perform I/O operations on the device. According to one embodiment, the communication mechanism may use shared memory. According to some embodiments, the device may be implemented purely in hardware, in software, or using a combination of hardware and software. According to some embodiments, the device may share its memory with guest processes to perform optimizations including but not limited to a shared page cache and a shared heap.

Aspects of the present disclosure involve a system and method for verifying and validating accurate memory module placement on a printed circuit board. In one embodiment, the printed circuit board is configured to include actuating elements that can be used to verify correct memory module location placement on the printed circuit board. In another embodiment, the actuating elements can be used to validate accurate memory module placement. The actuating elements can be in the form of buttons that may be depressed and configured to trigger light emitting diodes (LEDs) that correspond to the slots on the printed circuit board.

Methods and systems for efficiently processing input/output requests are provided. A network interface card (NIC) is coupled to a storage device via a peripheral link and accessible to a processor of a computing device executing instructions out of a memory device. The NIC is configured to receive a read/write request to read/write data; translate the read/write request to a storage device protocol used by the storage device coupled to the NIC; notify the storage device of the read/write request, without using the processor of the computing device, where the storage device reads/writes the data and notifies the NIC; and then the NIC prepares a response to the read/write request without having to use the processor of the computing device.