Mosaid Technologies Corporation

Empire Technology Development LLC

Conversant Intellectual Property Management Incorporated

Nagi Mekhiel

Technologies are generally described herein for bandwidth amplification using a pre-clock signal to latch data at a latch in an input register of a sender section while passing the data through a multiplexer of the sender section in a serial manner. In some configurations, pre-clocking the multiplexer can allow for parallel operations to occur within the sender section, thus hiding or reducing the effects of certain serialization delays associated with the multiplexer. Furthermore, the pre-clocking of the multiplexer, in some configurations, hides or reduces the register latch hold and setup delays. A method may create three levels of parallelization of latencies between a sender circuit, a serialization circuit, and a receiver circuit by overlapping them at same time.

Bandwidth amplification using pre-clocking

Technologies are generally described herein for a reconfigurable row dynamic random access memory device. The reconfigurable row may correspond to a logically addressable row, where multiple row segments can be mapped to different physical DRAM rows. In some examples, a reconfigurable row dynamic random access memory may use a row segment activator to allow memory operation access to a row segment, while maintaining the remaining part of the same row available for other memory access operations. The reconfigurable row dynamic random access memory may be operated in various modes of operation, including a pipeline mode and a burst mode.

Reconfigurable row DRAM

Memory access in data processing is provided using a time-based technique in which memory locations are mapped to respectively corresponding periods of time during which they are made available for access.

Data processing with time-based memory access

A method and apparatus used within memory and data processing that reduces the number of references allowed in processor cache by using active rows to reject references that are less frequently used from the cache. Comparators within a memory controller are used to generate a signal indicative of a row hit or miss, which signal is then applied to one or more demultiplexers to enable or disable transfer of a memory reference to processor cache locations. The cache may be level one (L1) or level two (L2) caches including data and or instructions or some combination of L1, L2, data, and instructions.

Cache filtering method and apparatus

A memory controller controls a buffer which stores the most recently used addresses and associated data, but the data stored in the buffer is only a portion of a row of data (termed row head data) stored in main memory. In a memory access initiated by the CPU, both the buffer and main memory are accessed simultaneously. If the buffer contains the address requested, the buffer immediately begins to provide the associated row head data in a burst to the cache memory. Meanwhile, the same row address is activated in the main memory bank corresponding to the requested address found in the buffer. After the buffer provides the row head data, the remainder of the burst of requested data is provided by the main memory to the CPU.

Growing community of inventors

Markham, Canada

Nagi Mekhiel