Intel Corporation

Sandisk Technologies Inc.

Zenith Data Systems Corporation

Packard Bell Nec

Plx Technology, Inc.

William S Wu

Peter D MacWilliams

Norman J Rasmussen

Sergey Anatolievich Gorobets

Alan David Bennett

Stephen S Pawlowski

Steven Theodore Sprouse

Muthurajan Jayakumar

Shai Traister

Bindi A Prasad

Andrew John Tomlin

Suresh K Marisetty

Nicholas D Wade

Puthiya K Nizar

Alexander Paley

Eugene Zilberman

Bum Suck So

Dilip K Sampath

Len J Schultz

Thomas F Joyce

Jian-Kuo Shen

Chester M Nibby, Jr

Mani Azimi

Jeffrey S Somers

Bruno DiPlacido, Jr

Thomas L Murray, Jr

Michelle A Pence

James F Bertone

G Lewis Steiner

Marc Sanfacon

Lance J McNally

Martin Massucci

Daniel G Lau

Marielle Bundukin

Nian Niles Yang

Jianmin Huang

Liam Michael Parker

Uday Chandrasekhar

Jack Regula

Neil David Hutchison

Yichao Huang

Alexandra Bauche

Sunny C Huang

Ameen Aslam

Jhy-Ping Shaw

Thomas Hugh Shippey

Leonard J Schultz

Tom Hugh Shippey

Yauheni Yaromenka

M Jayakumar

Ronald A Simmons

Curtis Winward

Ralph Woodard

Stephen T Sprouse

A system and method for clearing data from a cache in a storage device is disclosed. The method may include analyzing the cache for the least recently fragmented logical group, and evicting the entries from the least recently fragmented logical group. Or, the method may also include analyzing compaction history and selecting entries for eviction based on the analysis of the compaction history. The method may also include scheduling of different eviction mechanisms during various operations of the storage device. The system may include a cache storage, a main storage and a controller configured to evict entries associated with a least recently fragmented logical group, configured to evict entries based on analysis of compaction history, or configured to schedule different eviction mechanisms during various operations of the storage device.

Method and system for binary cache cleanup

A non-volatile memory organized into flash erasable blocks sorts units of data according to a temperature assigned to each unit of data, where a higher temperature indicates a higher probability that the unit of data will suffer subsequent rewrites due to garbage collection operations. The units of data either come from a host write or from a relocation operation. The data are sorted either for storing into different storage portions, such as SLC and MLC, or into different operating streams, depending on their temperatures. This allows data of similar temperature to be dealt with in a manner appropriate for its temperature in order to minimize rewrites. Examples of a unit of data include a logical group and a block.

Non-volatile memory and method having block management with hot/cold data sorting

A system and method for reducing the need to check both a secondary address table and a primary address table for logical to physical translation tasks is disclosed. The method may include generating a fast translation indicator, such as a logical group bitmap, indicating whether there is an entry in the secondary address table that contains desired information pertaining to a particular logical address. Upon a host request relating to the particular logical address, the storage device may check the bitmap to determine if retrieval and parsing of the secondary table is necessary. The system may include a storage device having RAM cache storage, flash storage and a controller configured to generate and maintain at least one fast translation indicator to reduce the need to check both secondary and primary address tables during logical to physical address translation operations of the storage device.

Fast translation indicator to reduce secondary address table checks in a memory device

In a flash memory, erase blocks containing shorted or broken word lines may be used, at least in part, to store user data. Such blocks may use different parameters to those used by non-defective blocks, may be subject to different wear leveling, and may store data selected to reduce the number of access operations.

Defective block management

A method and system for cache management in a storage device is disclosed. A portion of unused memory in the storage device is used for temporary data cache so that two levels of cache may be used (such as a permanent data cache and a temporary data cache). The storage device may manage the temporary data cache in order to maintain clean entries in the temporary data cache. In this way, the storage area associated with the temporary data cache may be immediately reclaimed and retasked for a different purpose without the need for extraneous copy operations.

Expandable data cache

A system and method for reducing write amplification while maintaining a desired level of sequential read and write performance is disclosed. A controller in a multi-bank flash storage device may receive host data for writing to the plurality of flash memory banks. The controller may organize the received data in multi-page logical groups greater than a physical page and less than a physical block and interleave writes of the host data to the memory banks with that striping factor. A buffer RAM is associated with each bank of the multi-bank memory where the buffer RAM is sized as equal to or greater than the size of the multi-page logical group.

System and method for minimizing write amplification while maintaining sequential performance using logical group striping in a multi-bank system

A portion of a nonvolatile memory is partitioned from a main multi-level memory array to operate as a cache. The cache memory is configured to store at less capacity per memory cell and finer granularity of write units compared to the main memory. In a block-oriented memory architecture, the cache has multiple functions, not merely to improve access speed, but is an integral part of a sequential update block system. Decisions to archive data from the cache memory to the main memory depend on the attributes of the data to be archived, the state of the blocks in the main memory portion and the state of the blocks in the cache portion.

Nonvolatile memory with write cache having flush/eviction methods

A method and system pre-emptively perform garbage collection operations of a forced amount on update blocks in a memory device. The amount of garbage collection needed by a certain data write is monitored and adjusted to match the forced amount if necessary. Update blocks may be selected on the basis of their recent usage or the amount of garbage collection required. Another method and system may store control information about update blocks in a temporary storage area so that a greater number of update blocks are utilized. The sequential write performance measured by the Speed Class test may be optimized by using this method and system.

Pre-emptive garbage collection of memory blocks

A portion of a nonvolatile memory is partitioned from a main multi-level memory array to operate as a cache. The cache memory is configured to store at less capacity per memory cell and finer granularity of write units compared to the main memory. In a block-oriented memory architecture, the cache has multiple functions, not merely to improve access speed, but is an integral part of a sequential update block system. The cache memory has a capacity dynamically increased by allocation of blocks from the main memory in response to a demand to increase the capacity. Preferably, a block with an endurance count higher than average is allocated. The logical addresses of data are partitioned into zones to limit the size of the indices for the cache.

Non-volatile memory and method with write cache partition management methods

A portion of a nonvolatile memory is partitioned from a main multi-level memory array to operate as a cache. The cache memory is configured to store at less capacity per memory cell and finer granularity of write units compared to the main memory. In a block-oriented memory architecture, the cache has multiple functions, not merely to improve access speed, but is an integral part of a sequential update block system. Decisions to write data to the cache memory or directly to the main memory depend on the attributes and characteristics of the data to be written, the state of the blocks in the main memory portion and the state of the blocks in the cache portion.

Non-volatile memory and method with write cache partitioning

A bus agent defers an ordered transaction if the transaction cannot be completed in order. When an ordered transaction is deferred, its visibility for the next ordered transaction is asserted if it can guarantee a sequential order of the ordered transaction and the next ordered transaction. This visibility indication allows the bus agent to proceed with the next ordered transaction without waiting for the completion status of the deferred transaction. The visibility indication provides fast processing of ordered transactions.

Mechanism for efficiently processing deferred order-dependent memory access transactions in a pipelined system

A system for communication on a chip. The system includes an on-chip communication bus including plural tracks, and a plurality of stations that couple a plurality of on-chip components to the on-chip communication bus, whereby the plurality of on-chip components use the tracks to communicate. Each station preferably includes an initiator that requests permission to transmit outgoing data over a track to another station and that transmits the outgoing data, an arbiter that evaluates requests from other stations and selects a track on which to receive incoming data, and a target that receives the incoming data. The initiator can be connected to a grant multiplexor for selecting a grant line, with the grant multiplexor further including plural smaller multiplexors distributed across the chip. Likewise, the arbiter can be connected to a track multiplexor for selecting a track, with the track multiplexor further including plural smaller multiplexors distributed across the chip. Each station also can include a source queue for queuing outgoing data and a destination queue for queuing incoming data. Preferably, the queues are first-in-first-out registers. The source queue and the destination queue can serve to separate a first clock domain for the on-chip communication bus from a second clock domain for one of the plurality of on-chip components. More than one of the plurality of on-chip components can be coupled to the on-chip communication bus through one of the stations.

On-chip switch fabric

A method and apparatus for transferring data between bus agents in a computer system. The present invention includes transmitting a control signal, from a first agent to a second agent, via a first transfer protocol; and, transmitting data corresponding to the control signal, from the first agent to the second agent, via a second transfer protocol. In one embodiment, the control signals are transmitted from the first agent to the second agent via a synchronous transmission with respect to a bus clock; and, the data is transmitted via an asynchronous transmission with respect to the bus clock, which has a data width greater than the synchronous transmission. In addition, in one embodiment of the present invention, the synchronous transmission is a common clock data transfer protocol, and the asynchronous transmission is a source clock data transfer protocol.

Transmission of signals synchronous to a common clock and transmission of data synchronous to strobes in a multiple agent processing system

A high-throughput memory access interface allows higher data transfer rates between a system memory controller and video/graphics adapters than is possible using standard local bus architectures. The interface enables data to be written directly to a peripheral device at either one of two selectable speeds. The peripheral device may be a graphics adapter. A signal indicative of whether the adapter's write buffers are full is used to determine whether a write transaction to the adapter can proceed. If the transaction can not proceed at that time, it can be enqueued in the interface.

High-throughput interface between a system memory controller and a peripheral device

Method and apparatus for transferring data in source-synchronous protocol and transferring signals in common clock protocol in multiple agent processing system

Growing community of inventors

Cupertino, CA, United States of America

William S Wu