Broadcom Corporation

Oracle America, Inc.

Qualcomm Incorporated

Sun Microsystems, Inc.

Qualcomm Technologies, Inc.

Nvidia Corporation

Sun Microsystems Technology Ltd.

Laurent Rene Moll

Manu Gulati

Joseph Byron Rowlands

Peter N Glaskowsky

Barton Sano

Seungyoon Peter Song

Yu Qing Cheng

Jean-Jacques Lecler

John Gregory Favor

Philippe Boucard

Koray Oner

James B Keller

Dexter Tamio Chun

Jungwon Suh

Carlos Puchol

Sagheer Ahmad

Anand Srinivasan

Subbarao Palacharla

Alain Artieri

Michael Hawjing Lo

Olivier Alavoine

Kedar Bhole

Daniel Fung

Xavier Loic Leloup

Brian K Langendorf

James D Kelly

Vinod Chamarty

Shyamkumar Thoziyoor

Edward L Riegelsberger

Samir Vijay Ginde

Chun Hung Ning

Raghu Sankuratri

Kwong-Tak Chui

Tony Yuhsiang Cheng

Thomas Albert Petersen

Rakesh Kumar Gupta

Philippe Martin

Jay Gupta

Christophe Avoinne

Gopi Tummala

Donald Alpert

Jorel D Hartman

Shun Wai Go

Syed Minhaj Hassan

Piyush Shashikant Jamkhandi

Sparsh Singhai

Joe Rowlands

Carlo Spitale

Luigi Vinci

Jonah Proujansky-Bell

Yu-Quin Cheng

Methods and apparatuses for a system error-correction code function are presented. The apparatus includes a memory configured to communicate with a host via at least one data connection and at least one non-data connection. The memory includes a memory array. The memory array includes a first portion and a second portion. The memory is further configured to, in a first mode, store and output data in the first portion and the second portion of the memory array. The first portion is addressable by a first address, and the second portion is addressable by a second address. The memory is further configured to, in a second mode, receive ECC of the data from the host via the at least one non-data connection, store the data in the first portion of the memory array, and store the ECC of the data in the second portion of the memory array based on the first address.

System and memory with configurable metadata portion

System and memory with configurable error-correction code (ECC) data protection and related methods

Data caching may include storing data associated with DRAM transaction requests in data storage structures organized in a manner corresponding to the DRAM bank, bank group and rank organization. Data may be selected for transfer to the DRAM by selecting among the data storage structures.

Dram-aware caching

Methods and apparatuses for a system error-correcting code function are presented. The apparatus includes a memory configured to communicate with a host. The memory includes a memory array configured to store data. The memory is configured to provide the data stored in the memory array to the host in performing computing functions and configured to provide an error-correction code (ECC) associated with the data to the host. The ECC is not stored in the memory array in a first configuration of the memory and is stored in the memory array in a second configuration of the memory.

Memory with system ECC

Methods and apparatuses for to memories using dynamic voltage scaling are presented. The apparatus includes memory configured to communicate with a host. The memory includes a peripheral portion and a memory array. The memory is further configured to receive, from at least one power management circuit, a first supply voltage and a second supply voltage. The memory further includes a switch circuit. The switch circuit is configured to selectively provide the first supply voltage and the second supply voltage to the peripheral portion. The first supply voltage is static and has a first voltage range. The second supply voltage has a low second voltage range and a high second voltage range.

Memory with dynamic voltage scaling

A multi-dimension engine, connected to a system TLB, generates sequences of addresses to request page address translation prefetch requests in advance of predictable accesses to elements within data arrays. Prefetch requests are filtered to avoid redundant requests of translations to the same page. Prefetch requests run ahead of data accesses but are tethered to within a reasonable range. The number of pending prefetches are limited. A system TLB stores a number of translations, the number being relative to the dimensions of the range of elements accessed from within the data array.

STLB prefetching for a multi-dimension engine

An electronic system for multiple agents, both coherent and non-coherent, to communicate with a hybrid cache, the hybrid cache to provide functionality associated with a cache for coherent agents in an outer shareable domain, and to provide functionality associated with a cache for non-coherent agents in a system shareable domain, the functionality provided by tag fields in cache lines stored in the hybrid cache. The tag fields are configured to indicate if a cache line of the hybrid cache belongs to at least one of a logical coherent cache or a logical system cache.

Hybrid cache comprising coherent and non-coherent lines

A cache controller adaptively partitions a shared cache. The adaptive partitioning cache controller includes tag comparison and staling logic and selection logic that are responsive to client access requests and various parameters. A component cache is assigned a target occupancy which is compared to a current occupancy. A conditional identification of stale cache lines is used to manage data stored in the shared cache. When a conflict or cache miss is identified, selection logic identifies candidates for replacement preferably among cache lines identified as stale. Each cache line is assigned to a bucket with a fixed number of buckets per component cache. Allocated cache lines are assigned to a bucket as a function of the target occupancy. After a select number of buckets are filled, subsequent allocations result in the oldest cache lines being marked stale. Cache lines are deemed stale when their respective component cache active indicator is de-asserted.

System and method for a shared cache with adaptive partitioning

A coherency controller with a data buffer store that is smaller than the volume of pending read data requests. Data buffers are allocated only for requests that match the ID of another pending request. Buffers are deallocated if all snoops receive responses, none of which contain data. Buffers containing clean data have their data discarded and are reallocated to later requests. The discarded data is later read from the target. When all buffers are full of dirty data requests with a pending order ID are shunted into request queues for later service. Dirty data may be foisted onto coherent agents to make buffers available for reallocation. Accordingly, the coherency controller can issue snoops and target requests for a volume of data that exceeds the number of buffers in the data store.

Coherency controller with reduced data buffer

A coherency controller, such as one used within a system-on-chip, is capable of issuing different types of snoops to coherent caches. The coherency controller chooses the type of snoop based on the type of request that caused the snoops or the state of the system or both. By so doing, coherent caches provide data when they have sufficient throughput, and are not required to provide data when they do not have insufficient throughput.

Adaptive tuning of snoops

A system with a prefetch address generator coupled to a system translation look-aside buffer that comprises a translation cache. Prefetch requests are sent for page address translations for predicted future normal requests. Prefetch requests are filtered to only be issued for address translations that are unlikely to be in the translation cache. Pending prefetch requests are limited to a configurable or programmable number. Such a system is simulated from a hardware description language representation.

DMA engine with STLB prefetch capabilities and tethered prefetching

System TLBs are integrated within an interconnect, use a and share a transport network to connect to a shared walker port. Transactions are able to pass STLB allocation information through a second initiator side interconnect, in a way that interconnects can be cascaded, so as to allow initiators to control a shared STLB within the first interconnect. Within the first interconnect, multiple STLBs share an intermediate-level translation cache that improves performance when there is locality between requests to the two STLBs.

System translation look-aside buffer integrated in an interconnect

A simplified coherency controller supports multiple exclusively active fully coherent agent interfaces and any number of active I/O (partially) coherent agent interfaces. A state controller determines which fully coherent agent is active. Multiple fully coherent agents can be simultaneously active during a short period of a transition of processing from one to another processor. Multiple fully coherent agents can be simultaneously active, though without a mutually consistent view of memory, which is practical in cases such as when running multiple operating systems on different processors.

Simplified controller with partial coherency

A system TLB accepts translation prefetch requests from initiators. Misses generate external translation requests to a walker port. Attributes of the request such as ID, address, and class, as well as the state of the TLB affect the allocation policy of translations within multiple levels of translation tables. Translation tables are implemented with SRAM, and organized in groups.

System translation look-aside buffer with request-based allocation and prefetching

A system and method for power management by providing advance notice of events. The method includes snooping a register of an operating system timer to determine a timer period associated with a scheduled event. A unit of a computer system is identified that is in a low power state. A wake up latency of the unit is determined that is based on the low power state. An advance period is determined based on the wake up latency. An advance notice of the operating system timer is triggered based on the timer period and the advance period to wake up the unit.

Method and system for advance wakeup from low-power sleep states

Growing community of inventors

San Jose, CA, United States of America

Laurent Rene Moll