-
公开(公告)号:US10282250B1
公开(公告)日:2019-05-07
申请号:US15808852
申请日:2017-11-09
Applicant: Cadence Design Systems, Inc.
Inventor: Bikram Banerjee , Anne Rodgers Hughes , John Michael MacLaren
Abstract: Embodiments of the invention provide an apparatus and method for a coherent, efficient, and configurable cyclic check redundancy retry implementation for synchronous dynamic random access memory. The process includes storing write commands as groups of bursts in a storage location where those commands are stored at least until a time frame has passed for receiving a corresponding cyclic redundancy check failure message. In some embodiments, the process includes retrying corresponding groups of bursts after receiving a failure message where retried groups of bursts are given priority over other memory access commands. In some embodiments, when a read command is received corresponding to a write command that is not beyond the relevant time frame the read command will also be held back from execution until the corresponding time frame has passed without notification of cyclic redundancy check value failure.
-
公开(公告)号:US10534565B1
公开(公告)日:2020-01-14
申请号:US15951107
申请日:2018-04-11
Applicant: Cadence Design Systems, Inc.
Inventor: Bikram Banerjee , Anne Hughes , John M. MacLaren
IPC: G06F3/06 , G11C11/4094 , G11C11/408 , G11C11/4096 , G11C11/4076
Abstract: A device including an address extraction for a data burst associated with a host processor and to map the data burst to a memory according to a rotation is provided. The device includes a splitter to separate a first command that associates the data burst with a first round in the rotation, and a selection logic to select, from the first round in the rotation, a first bank group at the address in the memory to execute the first command, and execution logic to receive the data burst and the address in the memory to activate the first bank group at the address in the memory, and to schedule an execution of the first command based on an availability of a second bank group from the first round in the rotation. A system and a non-transitory computer readable medium storing instructions to use the device are also provided.
-
3.
公开(公告)号:US10176126B1
公开(公告)日:2019-01-08
申请号:US14754508
申请日:2015-06-29
Applicant: Cadence Design Systems, Inc.
Inventor: Bikram Banerjee , Anish Mathew
Abstract: Disclosed are peripheral component interconnect (PCI) implementations and methods for implementing PCI implementations handling posted transaction layer packets (TLPs) and completion TLPs. PCI implementations include one or more receive buffers storing completion TLPs and posted TLPs, a set of write and read pointers for the receive buffers, a token manager to associate ordering tokens with posted TLPs, and a pointer-based ordering mechanism to determine an order for handling posted and completion TLPs. PCI implementations may further include an identification-based ordering mechanism to revise the order. The methods identify a completion TLP and multiple posted TLPs, associate a posted TLP with an ordering token, and determine the order for handling the completion and posted TLPs with at least the pointer-based ordering mechanism. The methods may further optionally revise the order with at least the identification-based ordering mechanism.
-
公开(公告)号:US09940260B1
公开(公告)日:2018-04-10
申请号:US15400235
申请日:2017-01-06
Applicant: CADENCE DESIGN SYSTEMS, INC.
Inventor: Anne Hughes , Bikram Banerjee
CPC classification number: G06F12/10 , G06F3/0604 , G06F3/0631 , G06F3/0653 , G06F3/0673 , G06F2212/65 , G11C5/02
Abstract: A memory controller system optimally controls access to a memory device having a plurality of integrated circuit (IC) chips disposed in a non-uniform stack configuration within a three-dimensional stacked (3DS) structure. A memory profiling portion executes to determine the non-uniform stack configuration. A virtual rank mapping portion configured to assign virtual ranks to chip locations actually defined by the non-uniform stack configuration. An address conversion portion executes to convert an unoptimized address definable with reference to a uniform stack configuration to an optimized address defined with reference to the non-uniform stack configuration. The addressing overhead during monitoring of data access operations to the memory device is optimized.
-
公开(公告)号:US11960351B1
公开(公告)日:2024-04-16
申请号:US17897334
申请日:2022-08-29
Applicant: Cadence Design Systems, Inc.
CPC classification number: G06F11/0772 , G06F11/004 , G06F11/3068 , H03M13/1131 , H03M13/611
Abstract: Systems and methods for propagating poison information are provided. Embodiments include receiving write data having a poison flag asserted indicating the data to be written to a memory device is erroneous. Embodiments further include converting the write data to a pre-fixed data pattern and generating a parity code, based upon, at least in part, the pre-fixed data pattern. Embodiments may also include injecting a correctable error into the write-data or parity code and writing the write data and parity code into the memory device. The correctable error injection may occur in the data or in the parity code and during the read the comparison may occur accordingly.
-
-
-
-