A method of performing unsupervised clustering of data points includes determining a number of qubits to include in a quantum processor based on feature dimensions of each data point. The method includes, for each pair of data points, executing a quantum circuit on a quantum processor having the determined number of qubits. The quantum circuit includes a feature map template circuit parameterized with a first plurality of rotations, a backward feature map template circuit parameterized with a second plurality of rotations, and a measurement circuit that outputs a similarity measure. The method includes creating a similarity matrix based on the similarity measure for each pair of data points, and inputting the similarity matrix to a classical clustering algorithm to cluster the data points. The feature map template circuit and the backward feature map template circuit each use quantum properties of superposition and entanglement of the qubits of the quantum processor.

A set of the dies and the package are provided with a plurality of dies each including at least an accelerator core or a CPU core, an external interface, memory interfaces, and a die interface for connecting to another die. At least two dies of the set of dies include a first type die and a second type die each including both the accelerator core and the CPU core, and the core number ratio between the accelerator core and the CPU core in the first type die differs from that in the second type die. The memory interfaces include an interface conforming to TCI. The memory interfaces further include an interface conforming to HBM.

Technologies for providing a scalable architecture to efficiently perform compute operations in memory include a memory having media access circuitry coupled to a memory media. The media access circuitry is to access data from the memory media to perform a requested operation, perform, with each of multiple compute logic units included in the media access circuitry, the requested operation concurrently on the accessed data, and write, to the memory media, resultant data produced from execution of the requested operation.

Embodiments of the invention relate to processor arrays, and in particular, a processor array with interconnect circuits for bonding semiconductor dies. One embodiment comprises multiple semiconductor dies and at least one interconnect circuit for exchanging signals between the dies. Each die comprises at least one processor core circuit. Each interconnect circuit corresponds to a die of the processor array. Each interconnect circuit comprises one or more attachment pads for interconnecting a corresponding die with another die, and at least one multiplexor structure configured for exchanging bus signals in a reversed order.

Provided efficiently and at low cost are: a package for core number ratios appropriate for all types of computers; and dies included in the package. This package includes at least one die provided with: at least one of a first core formed of a CPU core or a latency core and a second core formed of an accelerator core or a throughput core; an external interface; memory interfaces 24 to 26; and a die interface 23 which is connected to another die. The die includes a first type die and a second type die each including both the first core and the second core and the core number ratio between the first core and the second core in the first type die differs from that in the second type die. Moreover, the memory interfaces include an interface conforming to TCI. In addition, the memory interfaces further include an interface conforming to HBM.

A discrete 3-D processor comprises first and second dice. The first die comprises three-dimensional memory (3D-M) arrays, whereas the second die comprises logic circuits and at least an off-die peripheral-circuit component of the 3D-M array(s). The first die does not comprise the off-die peripheral-circuit component. The first and second dice are communicatively coupled by a plurality of inter-die connections. The preferred discrete 3-D processor can be applied to mathematical computing, computer simulation, configurable gate array, pattern processing and neural network.

Techniques and a system for visualization or interaction with a quantum processor are provided. In one example, a system includes a quantum programming component and a visualization component. The quantum programming component manages a quantum programming process to generate topology data for a quantum processor that is indicative of a physical topology of a set of qubits associated with the quantum processor. The visualization component generates visualization data for the topology data that comprises a set of planar slice elements arranged to correspond to the physical topology of the set of qubits. The set of planar slice elements indicate one or more operations performed at a time step associated with the quantum programming process.

Techniques and a system for visualization or interaction with a quantum processor are provided. In one example, a system includes a quantum programming component and a visualization component. The quantum programming component manages a quantum programming process to generate topology data for a quantum processor that is indicative of a physical topology of a set of qubits associated with the quantum processor. The visualization component generates visualization data for the topology data that comprises a set of planar slice elements arranged to correspond to the physical topology of the set of qubits. The set of planar slice elements indicate one or more operations performed at a time step associated with the quantum programming process.

Techniques and a system for visualization or interaction with a quantum processor are provided. In one example, a system includes a quantum programming component and a visualization component. The quantum programming component manages a quantum programming process to generate topology data for a quantum processor that is indicative of a physical topology of a set of qubits associated with the quantum processor. The visualization component generates visualization data for the topology data that comprises a set of planar slice elements arranged to correspond to the physical topology of the set of qubits. The set of planar slice elements indicate one or more operations performed at a time step associated with the quantum programming process.

Technologies for providing a scalable architecture to efficiently perform compute operations in memory include a memory having media access circuitry coupled to a memory media. The media access circuitry is to access data from the memory media to perform a requested operation, perform, with each of multiple compute logic units included in the media access circuitry, the requested operation concurrently on the accessed data, and write, to the memory media, resultant data produced from execution of the requested operation.