摘要:
A RAM mounted so as to mix with logic circuits has a plurality of memory mats and one control circuit provided for the plurality of memory mats. Arithmetic circuits for respectively performing +1 or -1 arithmetic operations are respectively provided so as to correspond to the respective memory mats and are electrically connected in cascade form. An input terminal of the initial-stage arithmetic circuit is supplied with address-setting fixed address signals. Input signals supplied to the next and subsequent arithmetic circuits or signals outputted therefrom are defined as own-assigned address signals (those assigned to the corresponding memory mats). A comparator provided in association with each arithmetic circuit referred to above makes comparisons for coincidence between the address signals and address signals input upon memory access. The corresponding memory mat is selected based on the resultant coincidence signal.
摘要:
A RAM mounted so as to mix with logic circuits has a plurality of memory mats and one control circuit provided for the plurality of memory mats. Arithmetic circuits for respectively performing +1 or −1 arithmetic operation are respectively provided so as to correspond to the respective memory mats and are electrically connected in cascade form. An input terminal of the initial-stage arithmetic circuit is supplied with address-setting fixed address signals. Input signals supplied to the next and subsequent arithmetic circuits or signals outputted therefrom are defined as own-assigned address signals (those assigned to the corresponding memory mats). A comparator provided in association with each arithmetic circuit referred to above makes comparisons for coincidence between the address signals and address signals input upon memory access. The corresponding memory mat is selected based on the resultant coincidence signal.
摘要:
A RAM mounted so as to mix with logic circuits has a plurality of memory mats and one control circuit provided for the plurality of memory mats. Arithmetic circuits for respectively performing +1 or -1 arithmetic operations are respectively provided so as to correspond to the respective memory mats and are electrically connected in cascade form. An input terminal of the initial-stage arithmetic circuit is supplied with address-setting fixed address signals. Input signals supplied to the next and subsequent arithmetic circuits or signals outputted therefrom are defined as own-assigned address signals (those assigned to the corresponding memory mats). A comparator provided in association with each arithmetic circuit referred to above makes comparisons for coincidence between the address signals and address signals input upon memory access. The corresponding memory mat is selected based on the resultant coincidence signal.
摘要:
A semiconductor device is connected to a CPU, a memory and I/O devices to serve as a data transfer bridge for efficient data transfer between the memory and the I/O devices. A CPU interface and a plurality of I/O interfaces included in a bridge chip are connected through an internal bus to a memory interface included in the bridge chip. Each I/O interface has a read/write buffer and a DMAC. An arbiter included in the bridge chip determines a bus master for which data transfer is permitted in response to requests for data transfer from each of the CPU interface and the DMAC to the memory. Each of the I/O interfaces has a control function to skip part of areas in the memory when transferring data between the memory and the I/O interface.
摘要:
A data transfer apparatus has a casing with an entrance slot in which a magnetic tape cassette is to be inserted. Upon full insertion of the cassette to a preassigned standby position, a cassette shift mechanism is activated to transport the cassette from the standby position to a data transfer position opposite a substantially fixed magnetic head. A load/eject lever on the front panel of the casing is to be manually turned following the shifting of the cassette to the data transfer position, in order to cause a pair of drive spindles to move into driving engagement with the hubs of the cassette. Since the drive spindles remain retracted, instead of being automatically sprung into driving engagement with the cassette hubs, unless the load/eject lever is manipulated following the shifting of the cassette to the data transfer position, a cleaning cassette can be used with the apparatus for cleaning the magnetic head without the danger of ruining the drive spindles as a result of forced contact with the cleaning cassette.
摘要:
The present invention can be introduced to an architecture such as a personal computer or an amusement equipment for realizing a high-speed graphic processing. In the case where a frame buffer, a command memory and an image processor are integrated in one chip in order to improve the drawing performance of an image processing device, each of the frame buffer and the command memory is constructed by a plurality of identical memory modules and the same row address is allotted to each memory module, thereby increasing the memory address depth. Thereby, it is possible to realize an incorporated frame buffer and an incorporated command memory each of which has a large capacity when seen from the image processor.
摘要:
The present invention can be introduced to an architecture such as a personal computer or an amusement equipment for realizing a high-speed graphic processing. In the case where a frame buffer, a command memory and an image processor are integrated in one chip in order to improve the drawing performance of an image processing device, each of the frame buffer and the command memory is constructed by a plurality of identical memory modules and the same row address is allotted to each memory module, thereby increasing the memory address depth. Thereby, it is possible to realize an incorporated frame buffer and an incorporated command memory each of which has a large capacity when seen from the image processor.
摘要:
The present invention can be introduced to an architecture such as a personal computer or an amusement equipment for realizing a high-speed graphic processing. In the case where a frame buffer, a command memory and an image processor are integrated in one chip in order to improve the drawing performance of an image processing device, each of the frame buffer and the command memory is constructed by a plurality of identical memory modules and the same row address is allotted to each memory module, thereby increasing the memory address depth. Thereby, it is possible to realize an incorporated frame buffer and an incorporated command memory each of which has a large capacity when seen from the image processor.
摘要:
The present invention may be introduced to an architecture such as a personal computer or an amusement equipment for realizing a high-speed graphic processing and provides an optimum arrangement along the flow of information in the case where a frame buffer, a command memory and an image processor are incorporated in one chip in order to improve the drawing performance of an image processing device. Thereby, unnecessary drawing-around of wiring is eliminated and it is possible to reduce the chip area. Further, since the wiring length is shortened, signal delay becomes small, thereby enabling a high-speed operation.