A computing system, having a cache-memory management system, provides selectable access modes for addressable memory, providing cacheable and noncacheable access modes, definable on a fixed page boundary basis. The various access modes can be intermixed on a page by page basis within the translation logic of the cache-memory management system. The cache-memory management system provides high speed virtual to real address translation along with associated system tag data defining access priorities and access modes associated with each respective address translation. The selectable access modes provides software definable features, such as cacheable data or non-cacheable data, write-through or copyback main memory update strategies for cacheable data, and real memory address space selection as main memory real address space, versus Boot ROM real address space versus input/output real address space. Page tables are loaded into main memory which contain address translation data and associated system tags. Upon initialization of the modifiable translation logic in the cache-memory management system, the address translations and associated system tags are loaded into the address translation logic of the cache-memory management system. Thereafter, as a part of the virtual to real address translation performed by the cache-memory management system, access modes and attributes are determined for each address translation, to provide for proper memory access of cacheable versus non-cacheable storage, etc., as part of the address translation and memory management function.
BACKGROUND OF THE INVENTION
This is a continuation of application Ser. No. 06/915,132, filed 10/03/86 now abandoned, which is a continuation in part of U.S. patent application Ser. No. 794,248 filed 10/31/85, now abandoned.
Disclosed are a circuit and method for learning attributes of computer memory (such as cacheability and writability) in a computer system. The circuit is coupled to a central processing unit ("CPU") and memory units within the computer system. The circuit is capable of retrieving an attribute relating to performance or operation of a particular memory unit when the CPU accesses the particular memory unit and storing the attribute in random-access memory ("RAM") within the circuit, subsequent accesses by the CPU of the memory unit made more efficient by use of the stored attribute. Operation of the circuit is transparent to the CPU and the memory unit. In an alternative embodiment, the circuit is within the CPU itself.
A data processing system (10 or 28) and method uses a memory management unit (MMU 14). The processor has two privileged modes of operations, such as a user mode and a supervisor mode of operation. The MMU 14 has a first mode of operation wherein logical address translation is performed via cache accesses and tablewalks, and a second mode of operation. The second mode of operation involves providing translation attribute bits from one of either a first transparent translation register (TTR 16), a second transparent translation register (TTR 18), or a default location (22). The TTRs (16 and 18) can each map different address spaces and different addressed memory sizes and the default location (22) covers all memory that is not mapped by one of the TTRs (16 or 18). The default location (22) is programmable, provides write protection, and provides attribute bits independent from the privilege mode.
A system and method for performing conditionally cache allocate operations to a data cache in a computer system. As supervisor mode operations typically do not experience data locality of accesses frequently found in user mode operations, it has been determined that performance benefits can be achieved by inhibiting cache allocate operations during supervisor mode. When a write miss to the cache occurs, the memory management unit checks the state of the processor status register to determine the mode of the processor. If the processor status register indicates that the processor is in supervisor mode, the memory management unit issues a signal to the data cache controller that the data is non-cacheable. When the data cache controller receives a non-cacheable signal, the cache allocate process is not performed. The non-cacheable signal is issued by the memory management unit while the processor is in supervisor mode regardless of the state of the cacheable status bit associated with the memory. Thus, if the processor is not in supervisor mode, the memory management unit will issue a non-cacheable signal to-the data cache controller based upon the state of the cacheable status bit associated with the memory. This status bit is typically found in the corresponding page table entry in the page table of a translation look aside buffer. Therefore, although a supervisor mode operation inhibits a cache allocate operation, subsequent non-supervisor mode operations to the same data will proceed based upon the state of the cacheable status bit associated with the memory.
Methods and apparatus for maintaining cache integrity in a computing system that includes a central processing unit (CPU), Random Access Memory (RAM), Read Only Memory (ROM), and a local memory controller for controlling cooperation between said CPU, RAM and ROM, wherein said computing system is capable of supporting a ROM mapped to RAM mode of operation, and further wherein said local memory controller, whenever said ROM mapped to RAM mode is enabled, (1) implements a snoop cycle to detect CPU write ROM operations and, upon detecting such an operation, (2) provides a cache invalidation signal to the CPU. The CPU utilizes the invalidation signal, along with the invalidation address on the local bus coupling the CPU and memory controller, to invalidate any cache data entry corresponding to the main memory address targeted by the CPU write ROM operation. The invalidation takes place while the write operation is in progress.
A data cache, for use in a memory having an address space including tag addresses for identifying blocks of storage locations and a set of select addresses for identifying storage locations in a block, includes a set select decoder that decodes only a subset of said set of select addresses that identify sub-blocks of storage locations located at the upper and lower boundaries of a block. Thus, data in storage locations accessed by addresses near block boundaries which have a high number of bit transitions is registered to the cache so that the high number of bit transitions does not have to be driven on an external bus so that noise is reduced.
