Abstract: Program code intended to be copied into the cache memory of a microprocessor is transferred encrypted between the random-access memory and the processor, and the decryption is carried out at the level of the cache memory. A checksum may be inserted into the cache lines in order to allow integrity verification, and this checksum is then replaced with a specific instruction before delivery of an instruction word to the central unit of the microprocessor.

Abstract: A scan chain for testing a combinatorial logic circuit includes a first scan chain path of flip-flops connected to the combinatorial logic circuit for functional mode operation during runtime of the combinatorial logic circuit. A second scan chain path of flip-flops is also connected to the combinatorial logic circuit and supports both a shift mode and a capture mode. The second scan chain path operates in shift mode while the first scan chain path is connected to the combinatorial logic circuit for functional mode operation. The second scan chain is then connected to the combinatorial logic circuit when run time is interrupted and operates in capture mode to apply the test data to the combinatorial logic circuit.

Abstract: A scan chain for testing a combinatorial logic circuit includes a first scan chain path of flip-flops connected to the combinatorial logic circuit for functional mode operation during runtime of the combinatorial logic circuit. A second scan chain path of flip-flops is also connected to the combinatorial logic circuit and supports both a shift mode and a capture mode. The second scan chain path operates in shift mode while the first scan chain path is connected to the combinatorial logic circuit for functional mode operation. The second scan chain is then connected to the combinatorial logic circuit when run time is interrupted and operates in capture mode to apply the test data to the combinatorial logic circuit.

Abstract: A scan chain for testing a combinatorial logic circuit includes a first scan chain path of flip-flops connected to the combinatorial logic circuit for functional mode operation during runtime of the combinatorial logic circuit. A second scan chain path of flip-flops is also connected to the combinatorial logic circuit and supports both a shift mode and a capture mode. The second scan chain path operates in shift mode while the first scan chain path is connected to the combinatorial logic circuit for functional mode operation. The second scan chain is then connected to the combinatorial logic circuit when run time is interrupted and operates in capture mode to apply the test data to the combinatorial logic circuit.

Abstract: A scan chain for testing a combinatorial logic circuit includes a first scan chain path of flip-flops connected to the combinatorial logic circuit for functional mode operation during runtime of the combinatorial logic circuit. A second scan chain path of flip-flops is also connected to the combinatorial logic circuit and supports both a shift mode and a capture mode. The second scan chain path operates in shift mode while the first scan chain path is connected to the combinatorial logic circuit for functional mode operation. The second scan chain is then connected to the combinatorial logic circuit when run time is interrupted and operates in capture mode to apply the test data to the combinatorial logic circuit.

Abstract: Program code intended to be copied into the cache memory of a microprocessor is transferred encrypted between the random-access memory and the processor, and the decryption is carried out at the level of the cache memory. A checksum may be inserted into the cache lines in order to allow integrity verification, and this checksum is then replaced with a specific instruction before delivery of an instruction word to the central unit of the microprocessor.

Abstract: A computer system supplies instructions simultaneously to a plurality of parallel execution pipelines in either superscalar mode or very long instruction word mode with checks for vertical and horizontal dependency between instructions, the horizontal dependency checks between instructions supplied in the same machine cycle being effective in superscalar mode but disabled in very long instruction word mode.

Abstract: Instructions in a computer system are executed in a plurality of parallel execution pipelines, a horizontal dependency check is carried out between instructions supplied to the parallel pipelines and in response to detecting horizontal dependency a control signal of a first or second type is generated depending on whether the dependency can be resolved by activating a by-pass or whether a temporary stall is required in one of the pipelines.

Abstract: A computer system has a memory which holds a computer program consisting of a sequence of program instructions. The format of the program instructions depends on an instruction mode of the computer system. A decoder is arranged to receive and decode program instructions. A microinstruction generator is responsive to information from the decoder to generate microinstructions according to a predetermined microinstruction format which is independent of the instruction mode of the computer system. The computer system has a plurality of parallel execution units for receiving and executing the microinstructions.

Abstract: A computer system has a plurality of parallel execution units for executing instructions with assigned guard indicators, one execution unit including a master guard value store and another execution unit having a shadow guard value store, together with guard ownership circuitry to indicate whether the shadow guard value store owns the current value of the guard indicator and transfer circuitry operable to transfer a guard value from the master store to another execution unit.

Abstract: A computer system has a processor, a cache and a main memory. A cache coherency mechanism ensures that the contents of the cache are coherent with respect to main memory by the provision of cache coherency instructions which each specify: 1) an operation to be executed on the contents of a location in the cache; and 2) an address in main memory. The operation is executed for the contents of the location in the cache which could be filled by an access to that address in main memory if the executing process normally has access to that address in main memory, regardless of whether or not the contents of the specified address in main memory are held at that location in the cache. This provides an extra degree of freedom because it is not necessary for the cache coherency operation to be requested in respect of a particular address stored in the cache. The instruction can specify any address which would map onto that cache location.

Abstract: A cache system and method of operating are described in which a cache is connected between a processor and a main memory of a computer. The cache system includes a cache memory having a set of cache partitions. Each cache partition has a plurality of addressable storage locations for holding items fetched from said main memory for use by the processor. The cache system also includes a cache refill mechanism arranged to fetch an item from the main memory and to load said item into the cache memory at one of said addressable storage locations in a cache partion wich depends on the address of said item in the main memory. This is achieved by a cache partition access table holding in association with addresses of items to be cached respective multi-bit partition indications identifying one or more cache partition into which the item is to be loaded.

Abstract: A computer system has a processor, a cache and a main memory. A cache coherency mechanism ensures that the contents of the cache are coherent with respect to main memory by the provision of cache coherency instructions which each specify: 1) an operation to be executed on the contents of a location in the cache; and 2) an address in main memory. The operation is executed for the contents of the location in the cache which could be filled by an access to that address in main memory if the executing process normally has access to that address in main memory, regardless of whether or not the contents of the specified address in main memory are held at that location in the cache.

Abstract: Disclosed is an integrated circuit memory comprising at least one column of memory cells parallel connected with one another and connected to at least one bit line, each memory cell being connected to a bit line by at least one access transistor, wherein said memory contains a protection transistor that is connected to the bit line and controlled so as to be made conductive so as to limit the voltage drop on the bit line, during the stages of the reading of the memory, when this drop in voltage goes beyond a threshold having a value smaller than a value that prompts the writing of an information element in a memory cell.