Embedded control system with floating-point conversion
An embedded control system capable of ensuring precision in arithmetic with data in the floating-point format and also avoiding a shortage of the storage area of a memory is provided. According to an embedded control system in the present invention, when discrete data in the floating-point format is stored in a read-only memory, the discrete data in the floating-point format is converted into data in a significand-reduced floating-point format before being stored. Here, a significand-reduced floating-point number is a number obtained by deleting low-order bits of the significand of a floating-point number. Further, an interpolation search is performed using discrete data, the discrete data in the significand-reduced floating-point format stored in the read-only memory is brought back to the discrete data in the floating-point format before an interpolation search being performed.
1. An embedded control system provided with a microcomputer having a memory for storing data in a floating-point format and a central processing unit for performing arithmetic operations on the data in the floating-point format, wherein
the central processing unit converts discrete data in the floating-point format into discrete data in a significand-reduced floating-point format in which low-order bits of the significand of the discrete data in the floating-point format are deleted before the discrete data in the significand-reduced floating-point format is stored in the memory, and
the central processing unit performs an interpolation search on the discrete data in the floating- point format after the discrete data in the significand-reduced floating-point format is temporarily converted into the discrete data in the floating-point format in another memory while maintaining the discrete data in the significand-reduced floating-point format in the memory, and
wherein the discrete data in the floating-point format is 4-byte data including a 1-bit sign bit, an 8-bit exponent part, and the 23-bit significand, and the discrete data in the significand-reduced floating-point format is 2-byte data including the 1-bit sign bit, the 8-bit exponent part, and the 16-bit significand and is obtained by deleting 16 low-order bits of the significand of the data in the floating-point format.
2. The embedded control system according to claim 1 , wherein the central processing unit appends a predetermined value to the deleted low-order bits of the significand when the discrete data in the significand-reduced floating-point format is converted into the discrete data in the floating-point format.
3. The embedded control system according to claim 2 , wherein the predetermined value is 0.
4. The embedded control system according to claim 2 , wherein the predetermined value is a value substantially half of a maximum value of the predetermined value.
5. The embedded control system according to claim 1 , wherein when the central processing unit converts the discrete data in the floating-point format into the discrete data in the significand-reduced floating-point format, if a highest-order bit of the deleted low-order bits of the data in the floating-point format is “1”, the central processing unit adds 1 to high-order bits of the significand of the data in the significand-reduced floating-point format.
6. The embedded control system according to claim 1 , wherein the discrete data in the significand-reduced floating-point format includes an identification bit indicating a number of bytes of the discrete data in the significand-reduced floating-point format.
7. The embedded control system according to claim 6 , wherein the identification bit is arranged at the head of the discrete data in the significand-reduced floating-point format.
8. The embedded control system according to claim 1 , wherein the discrete data in the floating-point format is 4-byte data including a 1-bit sign bit, an 8-bit exponent part, and the 23-bit significand and the discrete data in the significand-reduced floating-point format is 2-byte data including a 1-bit identification bit, the 1-bit sign bit, the 8-bit exponent part, and the 6-bit significand and is obtained by deleting 16 low-order bits of the significand of the data in the floating-point format.
9. The embedded control system according to claim 1 , wherein the discrete data in the floating-point format is 4-byte data including a 1-bit sign bit, an 8-bit exponent part, and the 23-bit significand and the discrete data in the significand-reduced floating-point format is 3-byte data including a 1-bit identification bit, the 1-bit sign bit, the 8-bit exponent part, and the 14-bit significand and is obtained by deleting 8 low-order bits of the significand of the data in the floating-point format.
10. The embedded control system according to claim 1 , further comprising a random access memory for temporarily storing data in the floating-point format and a backup memory for storing saved data identical to data temporarily stored in the random access memory, wherein
when the central processing unit stores data in the floating-point format stored in the random access memory in the backup memory, the central processing unit converts the data in the floating-point format into the data in the significand-reduced floating-point format before the data being stored.
11. The embedded control system according to claim 1 , wherein
the discrete data represents controlled values of monitored parameters of a vehicle; and
the central processing unit produces a controlled value for a controlled component of the vehicle by performing the interpolation search and outputs the controlled value to the controlled component.