International Business Machines Corporation

Loral Federal Systems Company

John Stanley Bialas, Jr

Stephen P Glancy

Warren Edward Maule

Gary A Van Huben

David D Cadigan

Richard J Daniels

William J Mruk

Saravanan Sethuraman

John E Gersbach

Dale A Rickard

Daniel L Stanley

Johnny James LeBlanc

Jacob D Sloat

Joseph W Yoder

Ralph David Kilmoyer

Steven A King

Timothy B Brodnax

Ryan Patrick King

Charles R London

Yelena M Tsyrkina

Clark J Spencer

Joseph A Hoffman

Siva Pr Boosa

A double data rate (DDR) memory controller writes a test pattern to a location in a DDR memory for a coarse calibration test, delayed by a first number of cycles set in a tunable write delay setting. The DDR memory controller simulates a single data rate (SDR) mode for the coarse calibration test by only comparing every other read beat of the test pattern read from the DDR memory, delayed by a second number of cycles set in tunable read delay setting, wherein every other read beat is latched for a full cycle. The DDR memory controller, responsive to every other read beat of the test pattern matching an expected result, sets the first number of cycles and the second number of cycles as coarse calibration settings for a DRAM.

Simulating a single data rate (SDR) mode on a dual data rate (DDR) memory controller for calibrating DDR memory coarse alignment

In an example, a method includes monitoring a memory bus for one or more commands sent by a memory controller to a memory device and determining whether the one or more commands have a value indicating an operation mode of the memory device. Information associated with the one or more commands may be assessed based on the operation mode, and the information may be stored to one or more registers of the memory controller. The operation mode may be a per dynamic random access memory (DRAM) addressability (PDA) mode, a per buffer addressability (PBA) mode, or a per rank mode. Accessing the information may include a first set of configuration values in response to the value indicating the PDA mode or the PBA mode, and a second set of configuration values in response to the value indicating the per rank mode.

Per-DRAM and per-buffer addressability shadow registers and write-back functionality

A system and method for efficient data eye training reduces the time and resources spent calibrating one or more memory devices. A temporal calibration mechanism reduces the time and resources for calibration by reducing the number tests needed to sufficiently determine the boundaries of the data eye of the memory device. For one or more values of the voltage reference, the temporal calibration mechanism performs a minimal number of tests to find the edges of the data eye for the hold and setup times.

Efficient calibration of a data eye for memory devices

In an example, a system includes a memory controller that includes a plurality of memory components. The system also includes a memory controller configured to receive a plurality of memory settings to be applied to the plurality of memory components. The memory controller is configured to, based on the received memory settings, transmit a first command to the plurality of memory components, the first command causing each memory component of the plurality of memory components to be configured to a first memory setting. The memory controller is configured to, based on the received memory settings, transmit a second command to a subset of the plurality of memory components after transmitting the first command, the second command causing each memory component of the subset to be configured to a second memory setting.

Efficient configuration of memory components

Embodiments herein describe a digital simulation environment that changes the delay of a digital signal to represent different analog reference voltages. For example, changing the length of time the digital signal is at the logical one state versus the time the digital signal is at the logical zero state may represent an analog reference voltage that is below or above an optimal value. Put differently, the digital simulation environment can insert unequal delay shifts relative to the logical one and zero states of the digital signal to represent different analog voltages. Using these unequal delay shifts, a digital simulation system can test the simulated operation of logic representing a physical system that uses an analog reference voltage as an input to determine if the logic behaves as expected.

Simulating reference voltage response in digital simulation environments

A system and method for efficient data eye training reduces the time and resources spent calibrating one or more memory devices. A reference voltage (Vref) calibration mechanism reduces the time and resources for calibration by reducing the number of tests needed to sufficiently determine the boundaries of the data eye of the memory device by using a combination of small steps and small steps to find a preferred reference voltage. In one example, the Vref calibration mechanism uses small steps of the reference voltage in a first range above a nominal reference voltage to find a maximum eye width then uses small steps to more precisely find the maximum eye width. If a maximum reference voltage is found in the first range then the second range below the nominal reference voltage does not need to be tested thereby saving additional time and resources.

Efficient calibration of memory devices

An apparatus for performing stuck fault testings within an integrated circuit is disclosed. A delay chain structure includes a first select register, a second select register, a decoder and a chain of multiplexors. With a set of select signals, the first select register generates a set of true encoded select signals, and the second select register generates a set of complement encoded select signals. Coupled to the first and second select registers, the decoder decodes the set of true encoded select signals and the set of complement encoded signals for controlling the chain of multiplexors. Each multiplexor within the chain of multiplexors is connected to one of the outputs of the decoder. The chain of multiplexors generates a single output value based on the set of select signals.

Apparatus for performing stuck fault testings within an integrated circuit

A voltage translation circuit translates an input signal having a first voltage level and a second voltage level to an output signal having the second voltage level and a third voltage level respectively. The voltage translation circuit according to the present invention includes a regenerative circuit having a first terminal and a second terminal. The voltage level at the first terminal increases responsive to the voltage level at the second terminal decreasing. The voltage level at the second terminal increases responsive to the voltage level at the first terminal decreasing. The voltage level at the first terminal defines the output signal. A first switch is coupled to the first terminal of said regenerative circuit, such that closing the first switch decreases the voltage level at the first terminal. A second switch is coupled to the second terminal of said regenerative circuit, such that closing the second switch decreases the voltage level at the second terminal.

Low power voltage translation circuit

A fault-tolerant computer system having shadow registers for storing the contents of a primary array into a shadow array at the completion of a stored instruction execution. This is accomplished in one clock cycle with all registers being shadowed simultaneously. During rollback of execution steps for a checkpoint retry, the shadow register files provide a signal cycle unload of the shadow array into the primary array. LSSD latches are used in the shadow register file.

Shadow register file for instruction rollback

A single event upset hardened bi-stable CMOS circuit has a pair of cross coupled invertors with an isolation resistor in the path coupling the drains of the transistors in each invertor. Each invertor includes a PFET and a NFET pair coupled source to drain. An isolation resistor couples together the drains of each PFET-NFET pair and two low impedance conductive paths provide a direct coupling between the drains of each transistor of one invertor to common gate node of the other invertor.

Single event upset immune register with fast write access

A soft error protection circuit is disclosed for a storage cell, such as a latch having a first input/output node and a second input/output node which are respectively connected to a charging source, the first node being selectively charged at least during a write interval, to represent a stored, first binary logic state for the latch. The circuit includes an insulated gate, field effect capacitor having a diffusion electrode connected to the second node and having a gate electrode, for selectively loading the second node with an additional capacitance. An inverter circuit has an input connected to the second node and an output connected to the gate electrode of the capacitor, for applying a capacitance enhancing bias to the gate electrode in at least a read interval following the write interval, when the first binary logic state has been stored in the latch, to apply the additional capacitance to the second node. The charging source supplies charge to both the first node and the second node at least following a soft error event which has caused the first node to become at least partially discharged during the read interval. In accordance with the invention, the additional capacitance applied to the second node prevents the second node from recharging as fast as the first node following the soft error event, by sinking a portion of the charge supplied from the charging source to the second node. In this manner, the first node will resume its previously charged condition, thereby preserving the stored logic state.

Growing community of inventors

South Burlington, VT, United States of America

John Stanley Bialas, Jr