Sun Microsystems, Inc.

Oracle International Corporation

Other

Oracle America, Inc.

California Institute of Technology

Ivan E Sutherland

Robert J Drost

Josephus Ebergen

William Stuart Coates

Ian W Jones

Ronald Ho

Charles E Molnar

Robert F Sproull

Scott M Fairbanks

David L Harris

Robert J Bosnyak

Robert David Hopkins

Danny Cohen

Bernard Tourancheau

Jon Lexau

Jo C Ebergen

Navaneeth P Jamadagni

Charles E Molnar, Deceased

Howard Lee Davidson

Gary R Lauterbach

Alex Chow

Craig Stephen Forrest

Charles L Seitz

Lee S Tavrow

Bruce A Reichlen

Justin M Schauer

Gregory M Papadopoulos

Jonathan K Gainsley

Wesley A Clark

Henri Gouraud

Jon K Lexau

The disclosed embodiments disclose techniques for performing quotient selection in an iterative carry-save division operation that divides a dividend, R, by a divisor, D, to produce an approximation of a quotient, Q=R/D. During a divide operation, a divider approximates Q by iteratively selecting an operation to perform for each iteration of the carry-save division operation and then performing the selected operation. The operation for each iteration is selected based on the current partial sum bits of a partial remainder in carry-save form (rs) and the current partial carry bits of a partial remainder in carry-save form (rc). More specifically, the operation is selected from a set of operations that includes: (1) a 2X* operation; (2) an S1 & 2X* operation; (3) an S2 & 2X* operation; (4) an A1 & 2X* operation; and (5) an A2 & 2X* operation.

Performing quotient selection for a carry-save division operation

The disclosed embodiments disclose techniques for using a split division circuit that includes a first divider that is optimized for a first range of divisor values and a second divider that is optimized for a second range of divisor values; the first range is distinct from the second range. During operation, the circuit receives a divisor for the division operation. The circuit: determines whether the divisor is in the first range or the second range to determine whether the first divider or the second divider should perform the division operation; performs the division operation in the selected host divider; and then outputs the result that was generated by the selected host divider.

Performing a division operation using a split division circuit

An integrated circuit includes a first pipeline with multiple stages of asynchronous circuits. Note that a stage in the first pipeline communicates with a stage in a corresponding second pipeline with multiple stages of asynchronous circuits on another integrated circuit via connectors. Furthermore, a first state wire preceding the stage in the first pipeline provides advanced notice to a first state wire preceding the stage in the second pipeline of subsequent communication between the stage in the first pipeline and the stage in the second pipeline so that the stage in the second pipeline has time to amplify a signal received from the stage in the first pipeline, thereby facilitating approximately synchronous operation of the stages in the first and second pipelines.

Synchronizing timing of communication between integrated circuits

A semiconductor die is described. This semiconductor die includes a driver, and a spatial alignment transducer that is electrically coupled to the driver and which is proximate to a surface of the semiconductor die. The driver establishes a spatially varying electric charge distribution in at least one direction in the spatial alignment transducer, thereby facilitating determination of a vertical spacing between a surface of the semiconductor die and a surface of another semiconductor die. In particular, a spatial alignment sensor proximate to the surface of the other semiconductor die may detect an electrical field (or an associated electrostatic potential) associated with the spatially varying electric charge distribution. This detected electric field may allow the vertical spacing between the surfaces of the semiconductor dies to be determined.

Determining spacing using a spatially varying charge distribution

A semiconductor die is described. This semiconductor die includes a driver, and a spatial alignment transducer that is electrically coupled to the driver and which is proximate to a surface of the semiconductor die. The driver establishes a spatially varying electric charge distribution in at least one direction in the spatial alignment transducer, thereby facilitating determination of a spatial alignment in more than one direction between the semiconductor die and another semiconductor die. In particular, a spatial alignment sensor proximate to the surface of the other semiconductor die may detect an electrical field (or an associated electrostatic potential) associated with the spatially varying electric charge distribution. This detected electric field may allow the vertical spacing between the surfaces of the semiconductor dies and/or an angular alignment of the semiconductor dies to be determined.

Determining alignment using a spatially varying charge distribution

Embodiments of the present invention provide a system that electronically aligns mini-bars on different semiconductor chips which are situated face-to-face to facilitate communication between the semiconductor chips through capacitive coupling. During operation, the system selects a group of transmitter mini-bars on the first chip to form a transmitter bit position and selects a group of receiver mini-bars on the second chip to form a receiver bit position. The system then associates transmitter bit positions on the first chip with proximate receiver bit positions on the second chip. In this way, the system allows data signals transmitted by the mini-bars within a transmitter bit position on the first chip to be collectively received by the mini-bars within an associated receiver bit position on the second chip.

Method and apparatus for electronically aligning capacitively coupled mini-bars

A memory module is formed of multiple memory chips and an optical interface chip fixed on a substrate. The chips are interconnected by proximity communication (PxC) in which each chip includes transmitting and receiving elements, such as electrical pads which form capacitively coupled links when the chips are placed together with their pads facing each other. The PxC links may be directly between the chips or through an intermediate passive bridge chip. The interface chip is coupled to an external optical channel and includes converters between optical and electrical signals, control circuitry, buffers, and PxC elements for communicating with the memory chips. The array of memories may be a linear or two-dimensional array around the interface chip forming a redundant PxC network, optionally with redundant PxC connections. Multiple rectangular memory chips may present their narrow sides to the interface chip to maximize bandwidth.

Proximity optical memory module having an electrical-to-optical and optical-to-electrical converter

One embodiment of the present invention provides a system that performs a carry-save division operation that divides a numerator, N, by a denominator, D, to produce an approximation of the quotient, Q=N/D. The system approximates Q by iteratively selecting an operation to perform based on higher order bits of a remainder, r, and then performing the operation, wherein the operation can include, subtracting D from r and adding a coefficient c to a quotient calculated thus far q, or adding D to r and subtracting c from q. These subtraction and addition operations maintain r and q in carry-save form, which eliminates the need for carry propagation and thereby speeds up the division operation. Furthermore, the selection logic is simpler than previous SRT division implementations, which provides another important speed up.

Method and apparatus for performing a carry-save division operation

One embodiment of the present invention provides a system that asynchronously controls sending data items from a sender to a receiver. This system includes a set of sending FIFOs, a set of receiving FIFOs, as well as a shared data path between the sender and the receiver. The system also includes a set of control paths that operate in parallel between the sender and the receiver, wherein a given control path controls the transmission of data items between a corresponding sending FIFO and a corresponding receiving FIFO through the shared data path. The system further includes a round-robin scheduling mechanism which activates one control path at a time in a predetermined sequence. An activated control path asynchronously controls the sending of a data item from a corresponding sending FIFO to a corresponding receiving FIFO. By operating the control paths in parallel in the predetermined sequence, the system does not have to wait a request-acknowledge cycle time between the sender and the receiver before sending consecutive data items through the shared data path, but can instead send multiple data items through the shared data path within a single request-acknowledge cycle time.

Apparatus and method for high-throughput asynchronous communication with flow control

A system, including at least one central processing unit, at least one memory unit, and a plurality of integrated circuits that form a switching fabric configured to propagate data packets between the at least one central processing unit and the at least one memory unit, wherein the switching fabric is constructed using at least two directed acyclic graph (DAG) networks.

Implementation of a graph property in a switching fabric for fast networking

One embodiment of the present invention provides a system for high-throughput asynchronous communication that includes a sender and a receiver. A sender's first-in, first-out (FIFO) buffer is coupled to an input of the sender, a receiver's FIFO buffer is coupled to an input of the receiver, a forward communication channel is coupled between the sender and the receiver's FIFO buffer, and a reverse communication channel is coupled between the receiver and the sender's FIFO buffer. The forward communication channel, the receiver's FIFO buffer, the reverse communication channel, and the sender's FIFO buffer operate collectively as a network FIFO between the sender and the receiver. The network FIFO is configured to ensure that asynchronous communication between the sender and the receiver takes place reliably and without unnecessary waiting by the sender or the receiver.

Apparatus and method for high-throughput asynchronous communication

One embodiment of the present invention provides a system that electronically aligns mini-bars on different semiconductor chips which are situated face-to-face to facilitate communication between the semiconductor chips through capacitive coupling. During operation, the system measures an alignment between a first chip and a second chip. The system then selects a group of transmitter mini-bars on the first chip to form a transmitter bit position based on the measured alignment. In this way, the system allows a data signal to be distributed to and transmitted by the mini-bars that form the transmitter bit position. The system also selects a group of receiver mini-bars on the second chip to form a receiver bit position based on the measured alignment. Next, the system associates transmitter bit positions on the first chip with proximate receiver bit positions on the second chip based on the measured alignment. In this way, the system allows data signals transmitted by the mini-bars within a transmitter bit position on the first chip to be collectively received by the mini-bars within an associated receiver bit position on the second chip.

One embodiment of the present invention provides a system that facilitates capacitive inter-chip communication. During operation, the system first determines an alignment between a first semiconductor die and a second semiconductor die. Next, electrical signals are selectively routed to at least one interconnect pad in a plurality of interconnect pads based on the alignment thereby facilitating communication between the first semiconductor die and the second semiconductor die. The plurality of interconnect pads can include transmitting pads, receiving pads, and transmitting and receiving pads. The alignment may be determined continuously or at times separated by an interval, where the interval is fixed or variable. Several variations on this embodiment are provided.

Enhanced electrically-aligned proximity communication

One embodiment of the present invention provides a circuit that preferentially grants requests. This circuit monitors at least two inputs for request signals and at least two inputs for enable signals, wherein each request signal is associated with a corresponding enable signal. If any enable signal is asserted and only one request signal is asserted, the circuit asserts a grant signal associated with the asserted request signal. Otherwise, if a single enable signal is asserted and multiple request signals are asserted, the circuit preferentially asserts the grant signal of the request signal associated with the asserted enable signal.

Arbiters with preferential enables for asynchronous circuits

One embodiment of the present invention provides an electronic circuit and method for measuring a capacitance. A signal generating mechanism generates a signal having a predefined frequency and predefined low and high voltage levels on one terminal of the capacitance. The other terminal of the capacitance is coupled to a switching mechanism. The switching mechanism is set to couple the other terminal of the capacitance to a first amplifier or a second amplifier for a portion of each signal cycle thereby full-wave rectifying a transient current flowing between the two terminals in the capacitance. Outputs of the first amplifier and the second amplifier are coupled to a current measurement mechanism for measuring the current. The capacitance is determined from the measured current. Several variations on this embodiment are provided.

Growing community of inventors

Santa Monica, CA, United States of America

Ivan E Sutherland