摘要:
A cache memory device comprises a data cache memory, an instruction cache memory, an instruction code area change detector, and an instruction code change processor. The instruction code area change detector decides whether writing access to the data cache memory by the processor is to a data area or to an instruction area of a main memory. The instruction code change processor passes the data cache memory to perform direct writing into the main memory when the writing access is to the instruction area, and, when data for a processor address is cached in a tag section of the instruction cache memory, invalidates the effective flag of the tag section.
摘要:
Each register of an internal register unit of a microprocessor has a pair of register cells consisting of first and second cells having the same register address. When one of these cells is selected, the other cell non-selected serves as a "back-up cell" for the selected cell. Each register of the register unit has a flag bit for storing a selector flag representing which cell of the pair of cells of the register is currently selected, and a flag bit for storing a change flag representing whether register information of the register is rewritten after a selected cell is changed between the first and second cells of the register. When the register information is stored in one of the pair of cells currently being selected of a certain register and is to be rewritten with another new information, the other cell of the register is selected to store the new information therein. The original register information is held in the first cell, thereby eliminating necessity of saving the original register information to a main memory at this stage. When the original register information is required again, the original register information can be rapidly restored, by only selecting the first cell again, in the corresponding register without executing save/restore processing between the register unit and the main memory.
摘要:
A register device includes a register set group, a switching control unit, a write control unit, a write flag memory unit, and a read control unit. The register set group consists of a plurality of register sets each constituted by a plurality of registers. The switching control unit selects a register set to be used in processing from the register set group in response to a saving/recovery instruction. The write control unit writes data in registers of the register set selected by the switching control unit in response to a write instruction. A write flag representing whether data is written in each of the registers is held by the write flag memory unit. The read control unit determines, in response to a read instruction, a register in which data is written most recently of a plurality of registers corresponding to each other between the register sets with reference to the write flags, thereby reading out data from the register.
摘要:
In a semiconductor memory device wherein a plurality of memory cell units formed by connecting a plurality of memory cells in series are provided and each of the memory cell units is connected to a bit line, the semiconductor memory device comprises control circuit for directly reading data of a register cell during a reading operation when the previous row address designates the same memory cell as the present row address, and a data changing controlling circuit for changing data of an arbitrary memory cell of the memory cell unit to data of the memory cell closest to the bit line contact in the memory cell unit, and a row decoder for corresponding row addresses which select the memory of memory cell units, to the upper addresses than the parts of the row addresses which select a memory unit among the memory cell units.
摘要:
A presentation display apparatus including a data storage section for storing a plurality of explanative image data each having (R), (G) and (B) color image components, a data processing section for adding, to the explanative image data from the data storage section, function select image data different in color component from the explanative image data, an image memory for storing the image data of one screen image output from the data processing section, a listener's first display device for displaying the image data which is delivered from image memory and a speaker's second display device. The image data output from the image memory is supplied through a first color converter to the listener's display device and through a second color converter to the speaker's display device. In the first color converter, the explanative image data is alone directly delivered as conversion image data in spite of function select menu image data, so that only the explanative (R)/(G)/(B) image is displayed on the listener's display device. In the second converter, the (R)/(G)/(B) input data are directly output as conversion image data when the function select image data is "0" and otherwise converted to all "1" when the function select menu image is "1" so that the function select menu and (R)/(G)/(B) explanative image are overlappingly displayed on the second display device.
摘要:
A parallel processing type processor system with trap and stall control functions capable of operating without increasing the cycle time, such that the lowering of the clock frequency in the system can be prevented. In the system, the processor units are controlled such that when an exception is caused in an execution of at least one of the instructions supplied to the processor units concurrently, the processings of all of the instructions supplied to the processor units concurrently are aborted. In addition, the processings of the instructions supplied to the processor units concurrently are stalled when it is not possible to deny a possibility for an occurrence of an exception in the execution of the instructions supplied to the processor units concurrently.
摘要:
The branch prediction using a branch prediction table formed by an associative memory which is applicable to a super scalar processor without causing confusion in the branch prediction. The branch prediction uses a branch prediction table for registering entries, each entry including a branching address, a branch target address, and an instruction position indicating a position of the predicted branch instruction in group of instructions to be executed concurrently, or an entry address indicating a position of each entry in the associative memory of the table. A correctness of the predicted branch instruction is checked by using actual branch target address and/or actual instruction position of actual branch instruction encountered in the actual execution of presently fetched instructions. When the predicted branch instruction is incorrect, instructions fetched at a next processing timing are invalidated and the entry in the table is rewritten.
摘要:
A three-dimensional graphic processing apparatus includes n arithmetic ICs (Integrated Circuits) for performing linear interpolation calculations for each scan line of a triangle polygon to obtain intensity values and depth coordinate values of pixels, and two types of n memories for storing the calculation results. The n arithmetic ICs parallelly execute linear interpolation calculations of n different pixels successive on a single scan line of a single triangle polygon in one processing cycle. Each arithmetic IC calculates for each of every n pixels in one processing cycle, and a corresponding one of the memories stores the calculation result.
摘要:
A memory system includes a memory which consists of a plurality of bit memory cells each capable of being independently accessible and of storing bit data in at least a first and a second different predetermined bit width access mode. A multiplexer and address decoder are provided together with a bit width register for producing first and second write control signals corresponding to the first and second access modes respectively for enabling writing within the independently accessible memory cells of data having respectively first and a different second bit width.
摘要:
A computer for simultaneously executing plural instructions decides the kind of operation and the possibility of simultaneous execution for the plural instructions as the instructions are read out from a main memory to a cache memory. The plural instructions and a corresponding decision result are stored in the cache memory. The decision process is performed for several groups of the plural instructions read out from the main memory to the cache memory in order. Then, the plural instructions are respectively assigned to a corresponding operation unit according to the decision result, and are subsequently executed by the corresponding operation unit. As a result of this arrangement, the repeated decision process for the plural instructions is not necessary when they are later read out from the cache memory to the operation unit.