Abstract: A non-robust test pattern, which causes a transition on a path of interest as well as off-paths, may be selected as being suitable for performing delay analysis of the path of interest (e.g., critical path) if the transitions caused on the off-paths would not overlap with the transition caused on the path of interest. In other words, an aspect of the present invention enables at least some non-robust test patterns to be used for performing delay analysis. As non-robust test patterns (as well as robust test patterns) can be used to perform delay analysis, the number of possible test patterns for performing speed analysis can be increased.

Abstract: Multiple register input multiplexors select a respective one of the results generated by operation units, and store the selected results in respective architecture registers as specified by the corresponding instructions (from which the results are generated). A forwarding multiplexor receives the results before the results are provided to the register input multiplexors, and selects one of the results for use as an operand for execution of a dependent instruction. As the forwarding multiplexor receives the results at a point before the inputs of the register input multiplexors, the time duration required to forward the results may be minimized, and a greater instruction throughput performance may be attained in a processor.

Abstract: A launch multiplexor which enables a desired bit to be stored into a desired memory element when using sequential scanning techniques (e.g., automatic test pattern generation (ATPG)). The launch multiplexor may be employed in addition to a scan multiplexor, which enables the test pattern bits or normal operating input to be selected and stored in the desired memory element. The scan multiplexor is used to scan-in a test pattern and evaluate a first input, and the launch multiplexor provides the control to store a desired bit into the corresponding memory element. Another output may be evaluated after storing the desired bit. In an embodiment, launch multiplexors are used associated with only memory elements in the critical paths, and the delay in transitioning from one output to another may be conveniently measured.

Abstract: A non-robust test pattern, which causes a transition on a path of interest as well as off-paths, may be selected as being suitable for performing delay analysis of the path of interest (e.g., critical path) if the transitions caused on the off-paths would not overlap with the transition caused on the path of interest. In other words, an aspect of the present invention enables at least some non-robust test patterns to be used for performing delay analysis. As non-robust test patterns (as well as robust test patterns) can be used to perform delay analysis, the number of possible test patterns for performing speed analysis can be increased.

Abstract: A launch multiplexor which enables a desired bit to be stored into a desired memory element when using sequential scanning techniques (e.g., automatic test pattern generation (ATPG)). The launch multiplexor may be employed in addition to a scan multiplexor, which enables the test pattern bits or normal operating input to be selected and stored in the desired memory element. The scan multiplexor is used to scan-in a test pattern and evaluate a first input, and the launch multiplexor provides the control to store a desired bit into the corresponding memory element. Another output may be evaluated after storing the desired bit. In an embodiment, launch multiplexors are used associated with only memory elements in the critical paths, and the delay in transitioning from one output to another may be conveniently measured.

Abstract: An emulation device is provided that has a processor core that is a programmable digital signal processor (DSP). Several blocks of memory within the emulation device can be configured to emulate blocks of memory on a target processor system. Each block of memory responds to three different memory buses and can receive up the three simultaneous memory requests. Arbitration circuitry selects the highest priority memory request for service on each cycle. Each memory block is configured to respond to a block of addresses beginning at a selected starting address. Two blocks of memory can be linked to form a single merged block of memory in which both arbitration circuits operate in lock step by masking a most significant address bit of the block of address selected for the memory block.

Abstract: Multiple register input multiplexors select a respective one of the results generated by operation units, and store the selected results in respective architecture registers as specified by the corresponding instructions (from which the results are generated). A forwarding multiplexor receives the results before the results are provided to the register input multiplexors, and selects one of the results for use as an operand for execution of a dependent instruction. As the forwarding multiplexor receives the results at a point before the inputs of the register input multiplexors, the time duration required to forward the results may be minimized, and a greater instruction throughput performance may be attained in a processor.