Techniques in advanced deep learning provide improvements in one or more of accuracy, performance, and energy efficiency. An array of processing elements performs flow-based computations on wavelets of data. Each processing element has a compute element and a routing element. Each router enables communication via wavelets with at least nearest neighbors in a 2D mesh. Routing is controlled by virtual channel specifiers in each wavelet and routing configuration information in each router. Execution of an activate instruction or completion of a fabric vector operation activates one of the virtual channels. A virtual channel is selected from a pool comprising previously activated virtual channels and virtual channels associated with previously received wavelets. A task corresponding to the selected virtual channel is activated by executing instructions corresponding to the selected virtual channel.

An apparatus and method are provided for managing use of capabilities. The apparatus has processing circuitry to execute instructions, and a plurality of capability storage elements accessible to the processing circuitry and arranged to store capabilities used to constrain operations performed by the processing circuitry when executing instructions. The processing circuitry is operable at a plurality of exception levels, each exception level having different software execution privilege. Further, capability configuration storage is provided to identify capability configuration information for each of the plurality of exception levels. For each exception level, the capability configuration information identifies at least whether the operations performed by the processing circuitry when executing instructions at that exception level are constrained by capabilities. During a switch operation from a source exception level to a target exception level, the capability configuration information in the capability configuration storage pertaining to at least one of the source exception level and the destination exception level is used to determine how execution state of the processing circuitry is managed during the switch operation. This provides a great deal of flexibility in the management of capabilities.

A method performed in a processor, includes: receiving, in the processor, a branch instruction in the processing; determining, by the processor, an address of an instruction after the branch instruction as a candidate for speculative execution, the address including an object identification and an offset; and determining, by the processor, whether or not to perform speculative execution of the instruction after the branch instruction based on the object identification of the address.

A data processing system utilizes non-volatile storage to store constant values. An instruction decoder decodes program instructions to generate control signals to control processing circuitry to perform processing operations which may include processing operations corresponding to constant-using program instructions. Such constant-using program instructions may include one or more operation specifying fields and one or more argument specifying fields which control the processing circuitry to generate an output value equal to that given by reading one or more constant values from the non-volatile storage, optionally modifying such a value, and then performing the processing operation upon the value, or the modified value, to generate an output value.

A computer system includes processor hardware and memory hardware storing instructions for execution by the processor hardware. The instructions include, in response to receiving a first script from a user device, compiling the first script, generating an image representation of the compiled first script, and determining an estimated runtime of the first script using a machine learning algorithm. The instructions include transmitting the estimated runtime for display on a display of the user device, categorizing the estimated runtime, and transmitting the first script to a queue based on the categorization. The instructions include, in response to the first script reaching a front of the queue, executing the first script on a server of the plurality of servers that corresponds to the queue. The instructions include, in response to the first script being executed, transforming the display of the user device according to instructions of the first script.

Method, apparatus, and program means for performing a string comparison operation. In one embodiment, an apparatus includes execution resources to execute a first instruction. In response to the first instruction, said execution resources store a result of a comparison between each data element of a first and second operand corresponding to a first and second text string, respectively.

A computer system having an address system of a first predetermined width in which each address of the first predetermined width in the address system includes a first portion identifying an object and a second portion identifying an offset relative to the object, where a static identifier for the first portion is predetermined to identify an address space having a second predetermined width that is smaller than the first predetermined width, or a space of kernel objects.

A method performed in a processor, includes: receiving, in the processor, a branch instruction in the processing; determining, by the processor, an address of an instruction after the branch instruction as a candidate for speculative execution, the address including an object identification and an offset; and determining, by the processor, whether or not to perform speculative execution of the instruction after the branch instruction based on the object identification of the address.

The present disclosure provides a data processing method and an apparatus and a related product. The products include a control module including an instruction caching unit, an instruction processing unit, and a storage queue unit. The instruction caching unit is configured to store computation instructions associated with an artificial neural network operation; the instruction processing unit is configured to parse the computation instructions to obtain a plurality of operation instructions; and the storage queue unit is configured to store an instruction queue, where the instruction queue includes a plurality of operation instructions or computation instructions to be executed in the sequence of the queue. By adopting the above-mentioned method, the present disclosure can improve the operation efficiency of related products when performing operations of a neural network model.

An apparatus has processing circuitry to execute a sequence of instructions, an integer storage element to store an integer value for access by the processing circuitry, and a capability storage element for storing a capability for access by the processing circuitry. A capability usage storage is then used to store capability usage information. The processing circuitry is responsive to execution of at least one instruction in the sequence of instructions to generate, in dependence on the capability usage information, a result to be stored in a destination storage element, when the capability usage information identifies a capability state, the result is generated as a capability, and the capability storage element is selected as the destination storage element, and when the capability usage information identifies a non-capability state, the result is generated as an integer value, and the integer storage element is selected as the destination storage element.