Abstract: Representative apparatus, method, and system embodiments are disclosed for a self-scheduling processor which also provides additional functionality. Representative embodiments include a self-scheduling processor, comprising: a processor core adapted to execute a received instruction; and a core control circuit adapted to automatically schedule an instruction for execution by the processor core in response to a received work descriptor data packet. In another embodiment, the core control circuit is also adapted to schedule a fiber create instruction for execution by the processor core, to reserve a predetermined amount of memory space in a thread control memory to store return arguments, and to generate one or more work descriptor data packets to another processor or hybrid threading fabric circuit for execution of a corresponding plurality of execution threads. Event processing, data path management, system calls, memory requests, and other new instructions are also disclosed.

Abstract: Host and accelerator devices can be coupled using various interfaces, such as Compute Express Link (CXL). In an example, user applications can have protected access to a shared set of control parameters for different queues. A protocol can allow an application to use a unique memory page at the accelerator device through which the application can access control parameters, such as can be used to control memory-based communication queues or other queues. In an example, there can be multiple sets of control parameters in a single memory page. The protocol can allow views of the single memory page from respective different application processes. In an example, the protocol can include or use an access check to detect and handle unauthorized accesses to particular parameters.

Abstract: System and techniques for recall pending cache line eviction are described herein. A queue that includes a deferred memory request is kept for a cache line. Metadata for the queue is stored in a cache line tag. When a recall is needed, the metadata is written from the tag to a first recall storage, referenced by a memory request ID. After the recall request is transmitted, the memory request ID is written to a second recall storage referenced by the message ID of the recall request. Upon receipt of a response to the recall request, the queue for the cache line can be restored by using the message ID in the response to lookup the memory request ID from the second recall storage, then using the memory request ID to lookup the metadata from the first recall storage, and then writing the metadata into the tag for the cache line.

Abstract: System and techniques for variable execution time atomic operations are described herein. When an atomic operation for a memory device is received, the run length of the operation is measured. If the run length is beyond a threshold, a cache line for the operation is locked while the operation runs. A result of the operation is queued until it can be written to the cache line. At that point, the cache line is unlocked.

Abstract: System and techniques for evicting a cache line with pending control request are described herein. A memory request—that includes an address corresponding to a set of cache lines—can be received. A determination can be made that a cache line of the set of cache lines will be evicted to process the memory request. Another determination can be made that a control request has been made to a host from the memory device and that the control request pending when it is determined that the cache line will be evicted. Here, a counter corresponding to the set of cache lines can be incremented (e.g., by one) to track the pending control request in face of eviction. Then, the cache line can be evicted.

Abstract: System and techniques for memory side cache request handling are described herein. When a memory request is received, a cache set for the memory request is determined. Here, the cache set has multiple ways and each way corresponds to a cache line. It can be detected that a way of the multiple ways is not ready for the memory request. In this case, a representation of the memory request is stored in a queue of multiple queues based on an interface upon which the memory request was received and the present ways of the cache set. Entries from the multiple queues can be dequeued in a defined order to determine a next memory request to process. The defined order gives priority to memory requests for a present way and then for external over internal requests.

Abstract: Representative apparatus, method, and system embodiments are disclosed for configurable computing. A representative system includes an asynchronous packet network; a plurality of configurable circuits arranged in an array, each configurable circuit coupled to the asynchronous packet network and adapted to perform a plurality of computations; and a dispatch interface circuit adapted to partition the plurality of configurable circuits into one or more separate partitions of configurable circuits and to load one or more computation kernels into each partition of configurable circuits. The dispatch interface circuit may load balance across the partitions of configurable circuits by starting threads for execution in the partition having the highest number of available thread identifiers. The dispatch interface may also assert a partition enable signal to merge the one or more separate partitions and assert a stop signal to all configurable circuits of the one or more separate partitions of configurable circuits.

Abstract: System and techniques for memory side cache request handling are described herein. When a memory request is received, a cache set for the memory request is determined. Here, the cache set has multiple ways and each way corresponds to a cache line. It can be detected that a way of the multiple ways is not ready for the memory request. In this case, a representation of the memory request is stored in a queue of multiple queues based on an interface upon which the memory request was received and the present ways of the cache set. Entries from the multiple queues can be dequeued in a defined order to determine a next memory request to process. The defined order gives priority to memory requests for a present way and then for external over internal requests.

Abstract: Representative apparatus, method, and system embodiments are disclosed for a self-scheduling processor which also provides additional functionality. Representative embodiments include a self-scheduling processor, comprising: a processor core adapted to execute a received instruction; and a core control circuit adapted to automatically schedule an instruction for execution by the processor core in response to a received work descriptor data packet. In another embodiment, the core control circuit is also adapted to schedule a fiber create instruction for execution by the processor core, to reserve a predetermined amount of memory space in a thread control memory to store return arguments, and to generate one or more work descriptor data packets to another processor or hybrid threading fabric circuit for execution of a corresponding plurality of execution threads. Event processing, data path management, system calls, memory requests, and other new instructions are also disclosed.

Abstract: Disclosed in some examples are methods, systems, memory devices, and machine-readable mediums that allow a memory device to efficiently mark memory extents involved in an enhanced memory operation. An extent is marked if a meta state associated with the extent indicates that the extent is included in the enhanced memory operation. The largest memory extents of the operation are maintained in the memory device as a list of unmarked extents. When a primitive memory operation is received, the memory address is compared to the unmarked extents in the list to the meta state for that memory line. If the address is covered by the list of extents, or that line's meta state is marked, then the memory operation is performed including the enhanced memory operation.

Abstract: Representative apparatus, method, and system embodiments are disclosed for configurable computing. A representative system includes an asynchronous packet network having a plurality of data transmission lines forming a data path transmitting operand data; a synchronous mesh communication network; a plurality of configurable circuits arranged in an array, each configurable circuit of the plurality of configurable circuits coupled to the asynchronous packet network and to the synchronous mesh communication network, each configurable circuit of the plurality of configurable circuits adapted to perform a plurality of computations; each configurable circuit of the plurality of configurable circuits comprising: a memory storing operand data; and an execution or write mask generator adapted to generate an execution mask or a write mask identifying valid bits or bytes transmitted on the data path or stored in the memory for a current or next computation.

Abstract: Disclosed in some examples are methods, systems, memory devices, and machine-readable mediums that allows an application thread to indicate an undo logging operation when calculations are beginning that may need to be rolled back if a crash or other failure occurs. During the undo logging operation, memory writes an identified memory are done to a copy and the original value is preserved. If the undo logging operation is committed, then the copy becomes the correct value and may then be subsequently used in place of the original, or the value stored in the copy is copied to the original. If the undo logging operation is abandoned, the copy is not preserved and the value goes back to the original.

Abstract: Various examples are directed to systems and methods for requesting an atomic operation. A first hardware compute element may send a first request via a network structure, where the first request comprises an atomic opcode indicating an atomic operation to be performed by a second hardware compute element. The network structure may provide an address bus from the first hardware compute element for providing the atomic opcode to the second hardware compute element. The second hardware compute element may execute the atomic operation and send confirmation data indicating completion of the atomic operation. The network structure may provide a second bus from the second hardware compute element and the first hardware compute element. The second bus may be for providing the confirmation data from the second hardware compute element to the first hardware compute element.

Abstract: Memory devices, systems including memory devices, and methods of operating memory devices are described, in which memory devices are configured to provide row clear features. In some embodiments, the memory device may receive a command from a host device directed to a row of a memory array included in the memory device. The memory device may determine that the command is directed to two or more columns associated with the row, where each column is coupled with a group of memory cells. The memory device may activate the row to write the two or more columns using a set of predetermined data stored in a register of the memory device. Subsequently, the memory device may deactivate the word line based on writing the set of predetermined data to the two or more columns.

Abstract: Representative apparatus, method, and system embodiments are disclosed for configurable computing. In a representative embodiment, a system includes an interconnection network, a processor, a host interface, and a configurable circuit cluster. The configurable circuit cluster may include a plurality of configurable circuits arranged in an array; an asynchronous packet network and a synchronous network coupled to each configurable circuit of the array; and a memory interface circuit and a dispatch interface circuit coupled to the asynchronous packet network and to the interconnection network. Each configurable circuit includes instruction or configuration memories for selection of a current data path configuration, a master synchronous network input, and a data path configuration for a next configurable circuit.

Abstract: Representative apparatus, method, and system embodiments are disclosed for configurable computing. A representative system includes an interconnection network; a processor; and a plurality of configurable circuit clusters. Each configurable circuit cluster includes a plurality of configurable circuits arranged in an array; a synchronous network coupled to each configurable circuit of the array; and an asynchronous packet network coupled to each configurable circuit of the array.

Abstract: Disclosed in some examples, are methods, systems, devices, and machine-readable mediums which provide for more efficient CGRA execution by assigning different initiation intervals to different PEs executing a same code base. The initiation intervals may be a multiple of each other and the PE with the lowest initiation interval may be used to execute instructions of the code that is to be executed at a greater frequency than other instructions than other instructions that may be assigned to PEs with higher initiation intervals.

Abstract: A reconfigurable compute fabric can include multiple nodes, and each node can include multiple tiles with respective processing and storage elements. The tiles can be arranged in an array or grid and can be communicatively coupled. In an example, the tiles can be arranged in a one-dimensional array and each tile can be coupled to its respective adjacent neighbor tiles using a direct bus coupling. Each tile can be further coupled to at least one non-adjacent neighbor tile that is one tile, or device space, away using a passthrough bus. The passthrough bus can extend through intervening tiles.

Abstract: Representative apparatus, method, and system embodiments are disclosed for configurable computing. A representative memory interface circuit comprises: a plurality of registers storing a plurality of tables, a state machine circuit, and a plurality of queues. The plurality of tables include a memory request table, a memory request identifier table, a memory response table, a memory data message table, and a memory response buffer. The state machine circuit is adapted to receive a load request, and in response, to obtain a first memory request identifier from the load request, to store the first memory request identifier in the memory request identifier table, to generate one or more memory load request data packets having the memory request identifier for transmission to the memory circuit, and to store load request information in the memory request table. The plurality of queues store one or more data packets for transmission.

Abstract: Representative apparatus, method, and system embodiments are disclosed for a self-scheduling processor which also provides additional functionality. Representative embodiments include a self-scheduling processor, comprising: a processor core adapted to execute a received instruction; and a core control circuit adapted to automatically schedule an instruction for execution by the processor core in response to a received work descriptor data packet. In another embodiment, the core control circuit is also adapted to schedule a fiber create instruction for execution by the processor core, to reserve a predetermined amount of memory space in a thread control memory to store return arguments, and to generate one or more work descriptor data packets to another processor or hybrid threading fabric circuit for execution of a corresponding plurality of execution threads. Event processing, data path management, system calls, memory requests, and other new instructions are also disclosed.