The cache reload time in small computer systems is improved by using a distributed cache located on the memory chips. The large bandwidth between the main memory and cache is the usual on-chip interconnecting lines which avoids pin input/output problems. This distributed cache is achieved by the use of communicating random access memory chips of the type incorporating a primary port (10) and a secondary port (14). Ideally, the primary and secondary ports can run totally independently of each other. The primary port functions as in a typical dynamic random access memory and is the usual input/output path for the memory chips. The secondary port, which provides the distributed cache, makes use of a separate master/slave row buffer (15) which is normally isolated from the sense amplifier/latches. Once this master/slave row buffer is loaded, it can be accessed very fast, and the large bandwidth between the main memory array and the on-chip row buffer provides a very fast reload time for a cache miss.
The sense amplifier registers (SARs) servicing the arrays of a dynamic random access memory (DRAM) located on a semiconductor chip with a processor are all maintained at full power while unaccessed arrays are powered down to conserve power. Accessing circuits for the DRAM permit accessing by the processor of word length segments of each of the SARs independently of one another so that the SARs function as a read/write cache for the processor.
A dynamic random access memory with a fast serial access mode for use in a simple cache system includes a plurality of memory cell blocks prepared by division of a memory cell array, a plurality of data latches each provided for each column in the memory cell blocks and a block selector. When a cache miss signal is produced by the cache system, data on the column in the cell block selected by the block decoder are transferred into the data latches provided for the columns in the selected block after selection. When a cache hit signal is produced by the cache system, the data latches are isolated from the memory cell array. Accessing is made to at least one of the data latches based on an externally applied column address on cache hit, and to at least one of the columns in the selected block based on the column address on cache miss.
A signal input buffer attains a through state when an external clock signal Ka is in an inactive state and generates an internal signal in response to an external signal, and attains a latch state when the external clock signal is in an inactive state. Data transfer from a master data register which stores data in an DRAM array through a slave data register is executed in response to a detection of the slave data register of being in use. The slave data register stores data to be transferred to an SRAM array or data to be externally accessed. Thus, a synchronous semiconductor memory device accessible at a high speed and with no wait is provided. In addition, internal clock signal is activated for a predetermined time in response to activation of an external clock signal to secure a precise internal operating timing.
The sense amplifier registers (SARs) servicing the arrays of a dynamic random access memory (DRAM) located on a semiconductor chip with a processor are all maintained at full power while unaccessed arrays are powered down to conserve power. Accessing circuits for the DRAM permit accessing by the processor of word length segments of each of the SARs independently of one another so that the SARs function as a read/write cache for the processor.
Disclosed is a buffer memory control apparatus, in which a translation lookaside buffer for translating a logical address into a real address to make an access to a buffer storage has a logical address storage portion and a real address storage portion to each of which logical address bits are entered at its column. Column identifying address bits for the logical address storage portion partly overlap on column identifying address for a buffer address array for holding a real address to be supplied to the buffer storage, so that the buffer address array, the real address storage portion, and a comparator circuit for comparing the contents held by the buffer address array and the real address storage portion are divided into sections corresponding to the overlapping bits and the sections are suitably combined and arranged as circuits.
