Abstract: Graphics processing systems and methods are described. A graphics processing apparatus may comprise one or more graphics processing engines, a memory, a memory management unit (MMU) including a GPU second level page table and GPU dirty bit tracking, and a provisioning agent to receive a request from a virtual machine monitor (VMM) to provision a subcluster of graphics processing apparatuses, the subcluster including a plurality of graphics processing engines from a plurality of graphics processing apparatuses connected using a scale-up fabric, provision the scale-up fabric to route data within the subcluster of graphics processing apparatuses, and provision a plurality of resources on the graphics processing apparatus for the subcluster based on the request from the VMM.

Abstract: Disclosed embodiments relate to systems and methods to skip inconsequential matrix operations. In one example, a processor includes decode circuitry to decode an instruction having fields to specify an opcode and locations of first source, second source, and destination matrices, the opcode indicating that the processor is to multiply each element at row M and column K of the first source matrix with a corresponding element at row K and column N of the second source matrix, and accumulate a resulting product with previous contents of a corresponding element at row M and column N of the destination matrix, the processor to skip multiplications that, based on detected values of corresponding multiplicands, would generate inconsequential results; scheduling circuitry to schedule execution of the instruction; and execution circuitry to execute the instructions as per the opcode.

Abstract: Graphics processing systems and methods are described. A graphics processing apparatus may comprise one or more graphics processing engines, a memory, a memory management unit (MMU) including a GPU second level page table and GPU dirty bit tracking, and a provisioning agent to receive a request from a virtual machine monitor (VMM) to provision a subcluster of graphics processing apparatuses, the subcluster including a plurality of graphics processing engines from a plurality of graphics processing apparatuses connected using a scale-up fabric, provision the scale-up fabric to route data within the subcluster of graphics processing apparatuses, and provision a plurality of resources on the graphics processing apparatus for the subcluster based on the request from the VMM.

Abstract: Disclosed embodiments relate to systems and methods to skip inconsequential matrix operations. In one example, a processor includes decode circuitry to decode an instruction having fields to specify an opcode and locations of first source, second source, and destination matrices, the opcode indicating that the processor is to multiply each element at row M and column K of the first source matrix with a corresponding element at row K and column N of the second source matrix, and accumulate a resulting product with previous contents of a corresponding element at row M and column N of the destination matrix, the processor to skip multiplications that, based on detected values of corresponding multiplicands, would generate inconsequential results; scheduling circuitry to schedule execution of the instruction; and execution circuitry to execute the instructions as per the opcode.

Abstract: Disclosed embodiments relate to systems and methods to skip inconsequential matrix operations. In one example, a processor includes decode circuitry to decode an instruction having fields to specify an opcode and locations of first source, second source, and destination matrices, the opcode indicating that the processor is to multiply each element at row M and column K of the first source matrix with a corresponding element at row K and column N of the second source matrix, and accumulate a resulting product with previous contents of a corresponding element at row M and column N of the destination matrix, the processor to skip multiplications that, based on detected values of corresponding multiplicands, would generate inconsequential results, scheduling circuitry to schedule execution of the instruction; and execution circuitry to execute the instructions as per the opcode.

Abstract: Disclosed embodiments relate to deep learning implementations using systolic arrays and fused operations. In one example, a processor includes fetch and decode circuitry to fetch and decode an instruction having fields to specify an opcode and locations of a destination and N source matrices, the opcode indicating the processor is to load the N source matrices from memory, perform N convolutions on the N source matrices to generate N feature maps, and store results of the N convolutions in registers to be passed to an activation layer, wherein the processor is to perform the N convolutions and the activation layer with at most one memory load of each of the N source matrices. The processor further includes scheduling circuitry to schedule execution of the instruction and execution circuitry to execute the instruction as per the opcode.

Abstract: Disclosed embodiments relate to systems and methods to skip inconsequential matrix operations. In one example, a processor includes decode circuitry to decode an instruction having fields to specify an opcode and locations of first source, second source, and destination matrices, the opcode indicating that the processor is to multiply each element at row M and column K of the first source matrix with a corresponding element at row K and column N of the second source matrix, and accumulate a resulting product with previous contents of a corresponding element at row M and column N of the destination matrix, the processor to skip multiplications that, based on detected values of corresponding multiplicands, would generate inconsequential results, scheduling circuitry to schedule execution of the instruction; and execution circuitry to execute the instructions as per the opcode.

Abstract: Graphics processing systems and methods are described. A graphics processing apparatus may comprise one or more graphics processing engines, a memory, a memory management unit (MMU) including a GPU second level page table and GPU dirty bit tracking, and a provisioning agent to receive a request from a virtual machine monitor (VMM) to provision a subcluster of graphics processing apparatuses, the subcluster including a plurality of graphics processing engines from a plurality of graphics processing apparatuses connected using a scale-up fabric, provision the scale-up fabric to route data within the subcluster of graphics processing apparatuses, and provision a plurality of resources on the graphics processing apparatus for the subcluster based on the request from the VMM.

Abstract: In one embodiment, Quality of Service (QoS) criteria based server side binary translation and execution of applications is performed on multiple servers utilizing distributed translation and execution in either a virtualized or native execution environment. The translated applications are executed to generate output display data, the output display data is encoded in a media format suitable for video streaming, and the video stream is delivered over a network to a client device. In one embodiment, one or more graphics processors assist the central processors of the servers by accelerating the rendering of the application output, and a media encoder encodes the application output into a media format.

Abstract: In one embodiment, Quality of Service (QoS) criteria based server side binary translation and execution of applications is performed on multiple servers utilizing distributed translation and execution in either a virtualized or native execution environment. The translated applications are executed to generate output display data, the output display data is encoded in a media format suitable for video streaming, and the video stream is delivered over a network to a client device. In one embodiment, one or more graphics processors assist the central processors of the servers by accelerating the rendering of the application output, and a media encoder encodes the application output into a media format.

Abstract: A processor is provided that implements a replay mechanism to recover from soft errors. The processor includes a protected execution unit, a check unit to detect errors in results generated by the protected execution unit, and a replay unit to track selected instructions issued to the protected execution unit. When the check unit detects an error, it triggers the replay unit to reissue the selected instructions to the protected execution unit. One embodiment of the replay unit provides an instruction buffer that includes pointers to track issue and retirement status of in-flight instructions. When the check unit indicates an error, the replay unit resets a pointer to reissue the instruction for which the error was detected.

Abstract: A processor is provided that implements a replay mechanism to recover from soft errors. The processor includes a protected execution unit, a check unit to detect errors in results generated by the protected execution unit, and a replay unit to track selected instructions issued to the protected execution unit. When the check unit detects an error, it triggers the replay unit to reissue the selected instructions to the protected execution unit. One embodiment of the replay unit provides an instruction buffer that includes pointers to track issue and retirement status of in-flight instructions. When the check unit indicates an error, the replay unit resets a pointer to reissue the instruction for which the error was detected.

Abstract: A processor is provided that implements a replay mechanism to recover from soft errors. The processor includes a protected execution unit, a check unit to detect errors in results generated by the protected execution unit, and a replay unit to track selected instructions issued to the protected execution unit. When the check unit detects an error, it triggers the replay unit to reissue the selected instructions to the protected execution unit. One embodiment of the replay unit provides an instruction buffer that includes pointers to track issue and retirement status of in-flight instructions. When the check unit indicates an error, the replay unit resets a pointer to reissue the instruction for which the error was detected.

Abstract: A processor is provided having dual execution cores that may be switched between high reliability and high performance execution modes dynamically, according to the type of code segment to be executed. When the processor is in high performance mode, the dual execution cores operate in lock step on identical instructions, and the execution results generated by each execution core are compared to detect any errors. In high performance monde, the dual execution cores operate independently.