Abstract: A pulse width of a simulated external system clock is set by determining a least common multiple of the frequency of selected internal clock signals relative to the frequency of the external system clock. The pulse width can be further adjusted based on the frequency of simulated external clocks. By setting the pulse width of the simulated external system clock based on the least common multiple value, the time required to complete the simulation can be reduced while ensuring proper operation of the simulated clock signals during the simulation.

Abstract: A method includes storing a first transaction entry to a first software configurable storage location, storing a second transaction entry to a second software configurable storage location, determining that a first transaction indicated by the first transaction entry has occurred, determining that a second transaction indicated by the second transaction entry has occurred subsequent to the first transaction, and, in response to determining that the first transaction occurred and the second transaction occurred, storing at least one transaction attribute captured during at least one clock cycle subsequent to the second transaction. The first and second software configurable storage locations may be located in a trace buffer, where the at least one transaction attribute is stored to the trace buffer and overwrites the first and second transaction attributes. Each transaction entry may include a dead cycle field, a consecutive transaction requirement field, and a last entry field.

Abstract: Techniques have been developed to introduce processor core functional pattern tests into a memory space addressable by at least one processor core of an integrated circuit. In general, such functional pattern tests can include both instruction sequences and data patterns and, in some embodiments in accordance with the present invention, are introduced (at least in part) into on-chip cache memory using facilities of an on-chip loader. Instruction opcodes used in functional test sequences may be efficiently introduced into a plurality of target locations in memory (e.g., at locations corresponding to multiple interrupt handlers or at locations from which a multiplicity of cores execute their functional tests) using facilities of the on-chip loader. In some embodiments, instruction selections together with a base address, extent and stride indications may be used to direct operation of the on-chip loader.

Abstract: A pulse width of a simulated external system clock is set by determining a least common multiple of the frequency of selected internal clock signals relative to the frequency of the external system clock. The pulse width can be further adjusted based on the frequency of simulated external clocks. By setting the pulse width of the simulated external system clock based on the least common multiple value, the time required to complete the simulation can be reduced while ensuring proper operation of the simulated clock signals during the simulation.

Abstract: Techniques have been developed to introduce processor core functional pattern tests into a memory space addressable by at least one processor core of an integrated circuit. In general, such functional pattern tests can include both instruction sequences and data patterns and, in some embodiments in accordance with the present invention, are introduced (at least in part) into on-chip cache memory using facilities of an on-chip loader. Instruction opcodes used in functional test sequences may be efficiently introduced into a plurality of target locations in memory (e.g., at locations corresponding to multiple interrupt handlers or at locations from which a multiplicity of cores execute their functional tests) using facilities of the on-chip loader. In some embodiments, instruction selections together with a base address, extent and stride indications may be used to direct operation of the on-chip loader.

Abstract: A method for simulating an integrated circuit having a plurality of clock control modules includes simulating the integrated circuit, and automatically receiving from each clock control model during simulation an indication of a simulated power state of the clock control model. Accordingly, the simulated power state of the portion of the integrated circuit model to be clocked by a clock control model can be monitored based on the indicator from the clock control model, rather than on a higher level analysis of the simulated input/output behavior of the integrated circuit model.

Abstract: A method for simulating an integrated circuit having a plurality of clock control modules includes simulating the integrated circuit, and automatically receiving from each clock control model during simulation an indication of a simulated power state of the clock control model. Accordingly, the simulated power state of the portion of the integrated circuit model to be clocked by a clock control model can be monitored based on the indicator from the clock control model, rather than on a higher level analysis of the simulated input/output behavior of the integrated circuit model.

Abstract: A method includes storing a first transaction entry to a first software configurable storage location, storing a second transaction entry to a second software configurable storage location, determining that a first transaction indicated by the first transaction entry has occurred, determining that a second transaction indicated by the second transaction entry has occurred subsequent to the first transaction, and, in response to determining that the first transaction occurred and the second transaction occurred, storing at least one transaction attribute captured during at least one clock cycle subsequent to the second transaction. The first and second software configurable storage locations may be located in a trace buffer, where the at least one transaction attribute is stored to the trace buffer and overwrites the first and second transaction attributes. Each transaction entry may include a dead cycle field, a consecutive transaction requirement field, and a last entry field.

Abstract: A method and apparatus for verification of designed logic in a processing unit (100) that performs multiprocessing functions is presented. Once the multiprocessing unit to be exercised as the device under test (350) is defined, an irritator (330) is constructed to provide the stimuli to the interface of the device under test (350) such that the device under test (350) is exercised. The irritator (330) receives instructions (314) as its input, where relevant instructions are converted to transactional stimulus that is applied to the device under test (350). The irritator (330) also monitors the interface of the device under test (350) to detect when multiprocessing operations executed by other processing units (340) included in the system (5) require a response. The response is produced via signal stimulus on the interface of the device under test (350) to which the irritator (330) is coupled.

Abstract: A cache model apparatus and method are implemented. A set of predetermined protocols for generating cache block movement events driving level one (L1) cache to level two (L2) cache traffic in a simulation environment are provided. An event protocol is selected for a test case in response to user input, or alternatively, a random selection is made. In accordance with the protocol selected, castouts of modified L1 cache lines are generated.

Abstract: A method for verifying a source-synchronous communication interface of a processor is disclosed. A software model of a first device having a source-synchronous communication interface and a software model of a second device capable of communicating with the first device via the source-synchronous communication interface are provided. The source-synchronous communication interface includes an applied clock line, an address line, an echo clock line, and a data line. A simulation of a data request from the first device model to the second device model via an applied clock signal along with an address on the applied clock line and the address line is initially performed. The requested data is then received by the first device model from the second device model via the data line after various delays between the applied clock signal and an echo clock signal on the applied clock line and the echo clock line, respectively. Finally, the requested data received by the first device model is verified as to its veracity.

Abstract: For simulation of a multiprocessor system having a multi-level cache hierarchy, possible and legal cache coherency state combinations are classified based on the state of one level one cache, and subclassified within the major classes to define unique combinations, a number significantly less than the number of all possible combinations. For data words in the test case, a cache coherency state combination is randomly selected from a combination table listing all subclasses. Stale data generated by inverting all or part of the original data from the test case may be preloaded with the coherency states as necessary. Existing coherency is maintained when test case data is preloaded to a cache location already preloaded to avoid previously loaded stale data from becoming valid with the new coherency state. Coherency state combinations which are preloaded are tracked to help ensure that all subclasses an are preloaded and tested during simulation prior to tapeout.