摘要:
Some embodiments provide a memory cell comprising a body region doped with charge carriers of a first type, a source region disposed in the body region and doped with charge carriers of a second type, and a drain region disposed in the body region and doped with charge carriers of the second type. According to some embodiments, the body region, the source region, and the drain region are oriented in a first direction, the body region and the source region form a first junction, and the body region and the drain region form a second junction. Moreover, a conductivity of the first junction from the body region to the source region in a case that the first junction is unbiased is substantially less than a conductivity of the second junction from the body region to the drain region in a case that the second junction is unbiased. Some embodiments further include a transistor oriented in a second direction, wherein the second direction is not parallel to the first direction.
摘要:
The invention provides a structure, method and apparatus for receiving a reference frequency and a variable frequency, differentiating the frequencies, and generating a logic pulse in response to a first frequency leading a second frequency, the frequencies having a small phase difference. In an aspect, the invention maintains a signal when the reference frequency and the variable frequency transition. In another aspect, the invention provides additional timing balance to prevent early generation of the logic pulses. In another aspect, the logic pulses drive a charge pump used in one of a phase-locked loop and a delay-locked loop.
摘要:
The present invention is in the field of memory architecture and management. More particularly, the present invention provides a method, apparatus, system, and machine-readable medium to hide refresh cycles of a memory array such as dynamic random access memory.
摘要:
A modified least recently allocated cache enables a computer to use a modified least recently allocated cache block replacement policy. In a first embodiment, an indicator of the least recently allocated cache block is tracked. When a cache block is referenced, the referenced cache block is compared with the least recently allocated cache block indicator. If the two identify the same cache block, the least recently allocated cache block indicator is adjusted to identify a different cache block. This adjustment prevents the most recently referenced cache block from being replaced. In an alternative embodiment, the most recently referenced cache block is similarly tracked, but the least recently allocated cache block is not immediately adjusted. Only when a new cache block is to be a located are the least recently allocated cache block indicator and the most recently referenced cache block indicator compared. Then, if the two indicators identify the same block, a different cache block is selected for the allocating the new cache block.
摘要:
An open bit line dynamic random access memory (DRAM) architecture uses a multiple layer bit line configuration to reduce coupling between switching bit lines in the device. In one approach, each successive cell within a row of DRAM cells is coupled to a bit line segment that is on a different metallization layer than a previous cell in the row. Shielding members are also provided between adjacent bit lines on a common metallization layer to further reduce noise coupling. Functionality is also provided for reducing the effect of word line to bit line coupling in the DRAM device using dummy signal injection techniques. In this manner, common mode noise that could otherwise saturate one or more sense amplifiers within the DRAM device is reduced or eliminated before such saturation can take place. In one approach, dummy cells and reference cells are provided for use in performing the signal injection. The principles of the present invention are particularly well suited for use within embedded DRAM structures where low charge storage capacity within individual cells reduces the signal voltage levels that are achievable.
摘要:
A planar capacitor for use within a dynamic random access memory (DRAM) cell is operated within semiconductor depletion during normal storage operations to increase the charge retention time of the capacitor. Operation within semiconductor depletion allows a significant increase in charge retention time in a capacitor for which gate oxide leakage is the predominant leakage mechanism. The voltages that are applied to the storage cell during DRAM operation are controlled so that the storage capacitor within the cell remains in depletion during storage of both a logic zero and a logic one. Although the capacitance of the cell is decreased by operating in depletion, the charge retention time of the cell can be increased by multiple orders of magnitude. In one application, the inventive structures and techniques are implemented within a DRAM device that is embedded within logic circuitry.
摘要:
Embodiments including systems, methods, and apparatuses associated with reordering data retrieved from a dynamic random access memory (DRAM). A memory controller may be configured to receive an instruction from a central processing unit (CPU) and, based on the instruction, retrieve a sequential data from a DRAM. The memory controller may then be configured to reorder the sequential data and place the reordered data in one or more locations of a vector register file.
摘要:
A processor includes a cache, a prefetcher module to select information according to a prefetcher algorithm, and a prefetcher algorithm selection module. The prefetcher algorithm selection module includes logic to select a candidate prefetcher algorithm determine and store memory addresses of predicted memory accesses of the candidate prefetcher algorithm when performed by the prefetcher module, determine cache lines accessed during memory operations, and evaluate whether the determined cache lines match the stored memory addresses. The prefetcher algorithm selection module further includes logic to adjust an accuracy ratio of the candidate prefetcher algorithm, compare the accuracy ratio with a threshold accuracy ratio, and determine whether to apply the first candidate prefetcher algorithm to the prefetcher module.
摘要:
An apparatus is provided that comprises a processor. The processor comprises a cache to store data, a decoder, an error classification module, and an error correction module. The cache stores data, the data encoded as a codeword. The decoder reads the codeword from cache and calculates a syndrome of the codeword using an H-matrix. The error classification module determines an error type of the syndrome. The H-matrix is redesigned such that the columns form a geometrical sequence, and as a result not only t-bit random errors but also (t+1) bit adjacent errors can be corrected. The error correction module, triggered by the enhanced error classification module, takes one of two sets of inputs depending on error type (either random error or adjacent error) and produces corrected data from the syndrome when the syndrome comprises a detectable and correctable error.