Abstract: The present disclosure relates to a method of accessing a n-dimensional tensor of elements in a memory by a computer system. The multidimensional tensor comprises two-dimensional arrays, herein referred to as pages, each page being configured to comprise a predefined number of one-dimensional arrays of elements, herein referred to as sticks. The method includes linearly loading page per page of the tensor, and doing the following for each page: loading the non-empty sticks of the page from the memory using a base address of the page and determining a base address for the subsequent page using the number of loaded sticks and using an address offset indicative of potential empty sticks of the page. In case the number of loaded pages reaches a chunk size, the chunk page counter may be reinitialized and the linear loading may be continued with a subsequent page.

Abstract: Processing input data for transmittal to a data consumer such as an artificial intelligence engine is performed by arranging the input data into a uniform structure made up of sticks of data combined to form pages of sticks. A stick is any well-sized set of input data elements whereby the size of the stick is fixed. A masking pattern is established for sticks of data having certain ranges of invalid data for consumption of partial sticks while maintaining validity of the input data being transferred. The mask pattern is derived based on set-active-mask-and-value (SAMV) instructions. The derived mask pattern is carried forward for subsequent load instructions to the data consumer.

Abstract: A computer system configured to perform operations for validating memory access patterns of a static variant of a program instruction stream, the operations including randomizing a first set of input arguments, generating an address translation list for virtual addresses based on memory access patterns and storing memory accesses in a first table, and executing the static variant of the program instruction stream on the accelerator processing unit. During execution, the virtual addresses may be discarded and replaced by the addresses provided in the address translation list. The operations may include recording and storing every memory access of executing the static variant of the program instruction stream in a second table and comparing the memory access patterns stored in the second table to memory accesses patterns stored in the first table. Memory access patterns may be validated or discarded.

Abstract: A computer system configured to perform operations for validating memory access patterns of a static variant of a program instruction stream, the operations including randomizing a first set of input arguments, generating an address translation list for virtual addresses based on memory access patterns and storing memory accesses in a first table, and executing the static variant of the program instruction stream on the accelerator processing unit. During execution, the virtual addresses may be discarded and replaced by the addresses provided in the address translation list. The operations may include recording and storing every memory access of executing the static variant of the program instruction stream in a second table and comparing the memory access patterns stored in the second table to memory accesses patterns stored in the first table. Memory access patterns may be validated or discarded.

Abstract: Determining simulation test coverage for a design of an electronic circuit, where graph-based verification tools are used to verify functional correctness of said design. A test coverage is determined from specified coverage points, and hardware test coverage is measured based on the occurrence of selected events. A specification for simulation test scenarios, and a hardware design language specification for the design comprising hardware events are provided. A list of event groups belonging to one simulation test scenario is created. For each group a temporal property coverage checker in the simulation model is generated that comprises a switch to enable or disable it.

Abstract: Disclosed aspects relate to controlling an electronic circuit having multiple units with at least one signal input each. A set of signal resources is determined by tracing back a dependency tree for each unit signal input until an endpoint representing a signal resource is reached. For each signal resource in the set a resource manager may be provided in dependence of its signal type. That resource manager may be assigned a set of signal inputs comprising each signal input in the circuit which was traced back to its respective signal resource. The resource manager is configured for controlling the signal resource. A control device may be provided to receive technical implementation requirements for one or more of the resource managers, detect conflicting requirements received for the one or more resource managers, and enable or disable one or more of the resource managers in response to the detected conflicting requirements.

Abstract: Disclosed aspects relate to controlling an electronic circuit having multiple units with at least one signal input each. A set of signal resources is determined by tracing back a dependency tree for each unit signal input until an endpoint representing a signal resource is reached. For each signal resource in the set a resource manager may be provided in dependence of its signal type. That resource manager may be assigned a set of signal inputs comprising each signal input in the circuit which was traced back to its respective signal resource. The resource manager is configured for controlling the signal resource. A control device may be provided to receive technical implementation requirements for one or more of the resource managers, detect conflicting requirements received for the one or more resource managers, and enable or disable one or more of the resource managers in response to the detected conflicting requirements.

Abstract: The invention relates to a method for verifying a design of an electronic circuit. The electronic circuit comprises at least one register including one or more parts. After receiving specification information of said register, a register monitor module is automatically created based on said received specification information. The register monitor module comprises a scoreboard for each part of the register. Said scoreboard comprises an expected data value queue for receiving expected data values, an actual data value queue for receiving actual data values. Furthermore, the register monitor module provides a matching strategy for comparing expected data values with actual data values. Expected data values and actual data values are compared for each scoreboard based on the matching strategy and an error indication is generated if the result of the comparison step does not fulfill the requirements specified in the matching strategy.

Abstract: Disclosed aspects relate to controlling an electronic circuit having multiple units with at least one signal input each. A set of signal resources is determined by tracing back a dependency tree for each unit signal input until an endpoint representing a signal resource is reached. For each signal resource in the set a resource manager may be provided in dependence of its signal type. That resource manager may be assigned a set of signal inputs comprising each signal input in the circuit which was traced back to its respective signal resource. The resource manager is configured for controlling the signal resource. A control device may be provided to receive technical implementation requirements for one or more of the resource managers, detect conflicting requirements received for the one or more resource managers, and enable or disable one or more of the resource managers in response to the detected conflicting requirements.

Abstract: Disclosed aspects relate to controlling an electronic circuit having multiple units with at least one signal input each. A set of signal resources is determined by tracing back a dependency tree for each unit signal input until an endpoint representing a signal resource is reached. For each signal resource in the set a resource manager may be provided in dependence of its signal type. That resource manager may be assigned a set of signal inputs comprising each signal input in the circuit which was traced back to its respective signal resource. The resource manager is configured for controlling the signal resource. A control device may be provided to receive technical implementation requirements for one or more of the resource managers, detect conflicting requirements received for the one or more resource managers, and enable or disable one or more of the resource managers in response to the detected conflicting requirements.

Abstract: The invention relates to a method for verifying a design of an electronic circuit. The electronic circuit comprises at least one register including one or more parts. After receiving specification information of said register, a register monitor module is automatically created based on said received specification information. The register monitor module comprises a scoreboard for each part of the register. Said scoreboard comprises an expected data value queue for receiving expected data values, an actual data value queue for receiving actual data values. Furthermore, the register monitor module provides a matching strategy for comparing expected data values with actual data values. Expected data values and actual data values are compared for each scoreboard based on the matching strategy and an error indication is generated if the result of the comparison step does not fulfil the requirements specified in the matching strategy.

Abstract: A scan circuit (JTAG 1149 extension) for a microprocessor utilizes transport logic and scan chains which operate at a faster clock speed than the external JTAG clock. The transport logic converts the input serial data stream (TDI) into input data packets which are sent to scan chains, and converts output data packets into an output data stream (TDO). The transport logic includes a deserializer having a sliced input buffer, and a serializer having a sliced output buffer. The scan circuit can be used for testing with boundary scan latches, or to control internal functions of the microprocessor. Local clock buffers can be used to distribute the clock signals, controlled by thold signals generated from oversampling of the external clock. The result is a JTAG scanning system which is not limited by the external JTAG clock speed, allowing multiple internal scan operations to complete within a single external JTAG cycle.

Abstract: A scan circuit (JTAG 1149 extension) for a microprocessor utilizes transport logic and scan chains which operate at a faster clock speed than the external JTAG clock. The transport logic converts the input serial data stream (TDI) into input data packets which are sent to scan chains, and converts output data packets into an output data stream (TDO). The transport logic includes a deserializer having a sliced input buffer, and a serializer having a sliced output buffer. The scan circuit can be used for testing with boundary scan latches, or to control internal functions of the microprocessor. Local clock buffers can be used to distribute the clock signals, controlled by thold signals generated from oversampling of the external clock. The result is a JTAG scanning system which is not limited by the external JTAG clock speed, allowing multiple internal scan operations to complete within a single external JTAG cycle.

Abstract: A scan circuit (JTAG 1149 extension) for a microprocessor utilizes transport logic and scan chains which operate at a faster clock speed than the external JTAG clock. The transport logic converts the input serial data stream (TDI) into input data packets which are sent to scan chains, and converts output data packets into an output data stream (TDO). The transport logic includes a deserializer having a sliced input buffer, and a serializer having a sliced output buffer. The scan circuit can be used for testing with boundary scan latches, or to control internal functions of the microprocessor. Local clock buffers can be used to distribute the clock signals, controlled by thold signals generated from oversampling of the external clock. The result is a JTAG scanning system which is not limited by the external JTAG clock speed, allowing multiple internal scan operations to complete within a single external JTAG cycle.

Abstract: A scan circuit (JTAG 1149 extension) for a microprocessor utilizes transport logic and scan chains which operate at a faster clock speed than the external JTAG clock. The transport logic converts the input serial data stream (TDI) into input data packets which are sent to scan chains, and converts output data packets into an output data stream (TDO). The transport logic includes a deserializer having a sliced input buffer, and a serializer having a sliced output buffer. The scan circuit can be used for testing with boundary scan latches, or to control internal functions of the microprocessor. Local clock buffers can be used to distribute the clock signals, controlled by thold signals generated from oversampling of the external clock. The result is a JTAG scanning system which is not limited by the external JTAG clock speed, allowing multiple internal scan operations to complete within a single external JTAG cycle.

Abstract: The present invention relates to a system for performing a co-simulation and/or emulation of hardware and software. The system includes a hardware simulator with an integrated hardware model, a hardware and/or software environment for controlling the hardware simulator and performing a software simulation and/or a direct software application, at least one synchronization facility within the hardware model for indicating a request from the hardware and/or software environment, a receiver for setting the synchronization facility into a predetermined state, and a controller for switching the hardware simulator between a free-running state and a request-handling state.

Abstract: The present invention relates to a system for performing a co-simulation and/or emulation of hardware and software. The system includes a hardware simulator with an integrated hardware model, a hardware and/or software environment for controlling the hardware simulator and performing a software simulation and/or a direct software application, at least one synchronization facility within the hardware model for indicating a request from the hardware and/or software environment, a receiver for setting the synchronization facility into a predetermined state, and a controller for switching the hardware simulator between a free-running state and a request-handling state.

Abstract: The present invention relates to the processing of hardware simulator instruction requests. A request broker is processing high-level simulator instruction requests submitted by different drivers. A high-level instruction request comprises multiple simulator instructions. The request broker is receiving and splitting the requests into simulator instructions. The instructions are put in a request queue associated to the driver originating the request. The request broker is then processing the request queues in a round-robin fashion and submits the instructions in a queue to the simulator until a clock instruction needs to be submitted. Then the next queue is processed. When only clock instructions need to be submitted, the minimum number of clock cycles is determined and submitted in a new instruction to the simulator. This minimum number is then subtracted from the clock instructions in the queues, and the drivers are queried for new requests.