JPS63181050A - Storing access control system - Google Patents

Abstract

PURPOSE:To accelerate access in a unit of storage, by finding a time limit in the case of starting the access of a second data from a leading element in a forward direction immediately after sending the access request of a first data, and the time limit in the case of starting the access from a final element in a reverse direction, respectively, and selecting an access processing in a direction in which the time limit is smaller. CONSTITUTION:A calculating means 8 which calculates a first time limit until the start of the access of a second data is enabled when the access of the second data is started in order from the leading element to a final element, and a calculating means 9 which calculates a second time limit by using each information until the start of the access of the second data is enabled in the case where the access is started in order from the final element by reversing the access direction of the second data, are provided. And the access of the second data is performed in the access direction corresponding to the time limit smaller out of the first and the second time limits. In such a way, it is possible to accelerate continuous access.

Description

DETAILED DESCRIPTION OF THE INVENTION Technical Field The present invention relates to a storage access control method, and in particular to a storage access control method for controlling data including 391! The present invention relates to a storage access control method for controlling continuous access.

BACKGROUND ART Conventionally, when sequentially controlling access to data consisting of a plurality of elements such as vector data, the following procedure is used. First, the address information of the storage unit of the last element of the data to be accessed in advance is obtained from the address information of the storage unit of the first element, for example, the bank address and the number of elements. Then, access to the subsequent data is started using the difference between the address information of the storage unit of the first element of the subsequent data to be accessed and the address information of the storage unit of the last element of the held preceding data. The number of clock cycles from when the storage unit of the last element of the preceding data is accessed is determined. Furthermore, the obtained number of clock cycles is compared with the cycle time of the storage unit, and the calculation is performed so that the same storage unit is not accessed within the cycle time of the storage unit in subsequent data access and preceding data access. The waiting time from the end of accessing the preceding data until the start of accessing the subsequent data is calculated.

Such a conventional technique is disclosed in, for example, Japanese Patent Laid-Open No. 126748/1983.

The conventional storage access method described above assumes that data access starts from the first element.
In the worst case, when the storage units of the final elements of the preceding accesses match, the start of accessing the subsequent data will be delayed by the cycle time of the storage units, so there is a drawback that high-speed continuous access cannot be achieved.

Therefore, the present invention has been made to solve these drawbacks of the prior art, and its purpose is to speed up continuous access. The purpose of this invention is to provide a storage access control method that

Structure of the Invention According to the present invention, a plurality of elements are successively arranged and stored on a storage device that is composed of a plurality of storage units that can be accessed independently of each other and that are sequentially addressed for each storage unit. A storage access control method that controls access to first data consisting of and access to second data following this access, the storage access control method controlling access to first data consisting of The first storage unit address information and the last storage unit address information of the first data, the address information of the first element of the second data, the element array direction information of the second data, and the first data When access to the second data is sequentially started from the first element to the last element using the number of elements of the second data and the cycle time information of the storage unit, the second data calculation means for calculating a first waiting time until it is possible to start accessing the second data, and using each of the above information, when the access direction of the second data is reversed and access is started sequentially from the last element, the above a calculation means for calculating a second waiting time until it becomes possible to start accessing the second data;
There is obtained a storage access control method characterized in that the second data is accessed in an access direction corresponding to the minimum of the second waiting time and the second waiting time.

Example Hereinafter, the present invention will be explained in detail using the drawings.

FIG. 1 is a block diagram of an embodiment of the invention.

The embodiment of the present invention includes registers 1-7. Waiting time calculation circuit 8.
9 and a comparison circuit 10.

Now, of two pieces of data that should be accessed consecutively, the preceding data is assumed to be the first data, and the subsequent data is assumed to be the second data. Both of these pieces of data are mutually composed of a plurality of elements, and some elements are different from each other. It is assumed that they are common.

Therefore, when these data are respectively stored and arranged in storage units on a storage device, the storage unit addresses of both data partially overlap. For example, the start and end addresses of the first data storage unit are r100J and rl16J, respectively, and the start and end addresses of the second data storage unit are r113j and "126", respectively.

In this case, registers 1.2 and 3 each contain the storage unit address N15J of the first element of the second data, the number of elements r14J (=126-113+1), and the array direction information "0" (correct direction, and “1” for the opposite direction.
) is stored. Registers 6 and 7 contain the first storage address (this address is now referred to as r102J) and the final storage unit address r of the storage unit in use at the end of sending the first data access request, respectively.
116J is stored.

Register 4 stores the cycle time of the memory unit,
Let's now set this value to "16". Register 5 stores the total number of storage units in the storage device, and this value is now r256J.
shall be.

When accessing the second data sequentially from the first element to the last element (forward access), the waiting time calculation circuit 8 starts accessing the second data from the time when the sending of the access request for the first data ends. This calculates the waiting time until the start. Calculation of this waiting time is for each register 1 to 7 above.
This is done using the stored information.

Furthermore, when accessing the second data sequentially from the last element to the first element (reverse direction access), the waiting time calculation circuit 9 calculates the second data from the end of sending the access request for the first data. This is to calculate the waiting time until the start of access.

The calculation of this waiting time is also performed using the information stored in each of the registers 1-7.

These dedicated results from the holding time calculation circuits 8 and 9 are compared in magnitude in a comparison circuit 10. This comparison circuit 10 outputs rOJ when the waiting time is shorter when accessing the second data in the forward direction, and outputs "1" when the waiting time is shorter when accessing the second data in the reverse direction.

FIG. 2 is a diagram illustrating the waiting time calculation process by the waiting time calculation circuit 8, and is a diagram for calculating the waiting time Two during so-called forward access in which second data is sequentially accessed from the first element. In the figure, the horizontal axis represents time, and the vertical axis represents storage unit addresses. Each numerical value in the figure is the aforementioned numerical value, and corresponds to the information stored in each register 1 to 7, respectively.

The figure shown as a parallelogram shows the relationship between the access time of the first data and the storage unit address. A figure indicated by a dashed-dotted parallelogram C shows the relationship between time and storage unit address when the second data is accessed in immediate response to an access request for the second data.

However, at this time, since the storage unit address 102 and subsequent parts of the first data (shaded area) are in use, the second data cannot be accessed until after the waiting time TwO. Data access will be performed and this is shown by parallelogram B.

The waiting time TWO at this time is a time proportional to the difference address between the first storage unit address 102 in the usage state of the first data and the first storage unit address 113 of the second data. As is clear, the waiting time TWO
is proportional to "12".

Expressing this mathematically, TwO = “first storage unit address of second data” - (
[Start storage unit address J-1 in use in first data access)=113-(102-1>=12) This calculation is performed by the waiting time calculation circuit 8.

A diagram showing the process of calculating the waiting time in the reverse access in the waiting time calculating circuit 9 is shown in FIG. 3, and the same parts as those in FIG. 2 are indicated by the same reference numerals.

In this case as well, as is clear from the figure, the waiting time TWI is "4".
It will be proportional to.

Expressing this numerically, 7w1=rNumber of storage units in use when accessing the first data'' - (``Final storage unit address of the second data'' - ``Number of storage units in use for the first data'' Final storage unit address"+1)=15-(126-116+1)=4. This calculation is performed by the waiting time calculation circuit 9.

In the comparison circuit 10, the dual holding times TWO and TW1 obtained by the dual holding time calculation circuits 8 and 9 are compared, and since TWO>TWl in the above example, the second data is in the opposite direction with a smaller waiting time. Access will be processed from

As described above, according to the present invention, the waiting time when accessing the second data starts in the forward direction from the first element immediately after sending an access request for the first data, and the waiting time from the last element Since the waiting time when starting in the opposite direction is calculated and the access processing in the direction with the smaller waiting time is selected and executed, there is an effect that the memory unit access can be speeded up.

[Brief explanation of the drawing]

FIG. 1 is a block diagram of an embodiment of the present invention, FIG. 2 is a diagram explaining the waiting time calculation process during forward access operation, and FIG. 3 is a diagram explaining the waiting time calculation process during reverse access operation. It is. Explanation of symbols of main parts 1 to 7...Registers 8.9...Waiting time calculation circuit 10...Comparison circuit

Claims (1)

[Claims] Accessing first data consisting of a plurality of elements arranged and stored consecutively on a storage device that is composed of a plurality of storage units that can be accessed independently of each other and sequentially addressed for each storage unit; A storage access control method that controls access to second data following this access, the first storage unit address information of the storage unit in use at the end of the first data access request, and the first storage unit address information final storage unit address information of the data, further address information of the first element of the second data, element array direction information of the second data, and element number information of the second data, and further Also, using the cycle time information of the storage unit, when accessing the second data is sequentially started from the first element to the last element, Using the calculation means for calculating the waiting time of step 1 and each of the above information, it is possible to start accessing the second data when the access direction of the second data is reversed and access is started sequentially from the last element. calculation means for calculating a second waiting time until the second waiting time is reached, and the second data is accessed in an access direction corresponding to the smallest one of the first and second waiting times. A storage access control method characterized by: