D950-Core
4.3.2 Registers
Data registers
• LS0 / LS1 / LS2: 3 x 16-bit Loop Start address registers,
• LE0 / LE1 / LE2: 3 x 16-bit Loop End address registers,
• LC0 / LC1 / LC2: 3 x 16-bit Loop Count registers.
All these registers are addressed directly by the LSP instruction (see Section 4.3.5)
After reset, LSP = 0. (No hardware loop is selected).
Control registers
• STA: Bits 14 and 15 are dedicated to PCU (see Section 4.5.1).
• CCR: Bits 14 and 15 are dedicated to PCU (see Section 4.5.2).
4.3.3 Instruction pipeline
Instruction execution is performed in a 3-stage pipeline: fetch/decode/execute. While
instruction n is executed, instruction n+1 is decoded and instruction n+2 is fetched.
The instruction cycle period is twice the CLKIN period.
According to the number of words used, D950-Core instructions can be of two types
• One word instruction: Inside this group, most D950-Core instructions are one
cycle instructions (all arithmetic and logic instructions except instructions
performing double precision multiplication and bit manipulations). Some
instructions are multiple cycle instructions. Instructions causing a program flow
change (JUMP, CALL, RTS, RTI, SWI, RESET, BREAK, CONTINUE) are
executed in two or three cycles.
• Instructions with extension words: As one program memory word is fetched
at each cycle, if an instruction needs extension words, they are fetched during
the cycles following the first fetch.
4.3.4 Interrupt Sources
The D950-Core includes three interrupt sources. The following table orders the interrupt
sources from highest to lowest priority
26/89
5