5
TSC695F
4118J–AERO–08/04
Product Description
Integer Unit The Integer Unit (IU) is designed for hi ghly dependable sp ace and military a pplications,
and inclu des support for error det ect ion. Th e RI SC arch itecture mak es the c reat ion of a
processor that can execute instructions at a rate approaching one instruction per pro-
cessor clock possible.
To a chiev e that rate of exe cution, the I U emp loys a four-s tage in struct ion p ipeline that
permits parallel execution of mul tiple instructions.
• Fetc h - The processor outputs the instruction address to fetch the instruction.
• Dec ode - The instruction is placed in the in struction register and is decoded. The
processor reads the operands from the register file and computes the next
instruction address.
• Execute - The processor executes t he instruction and saves the results in t emporary
registers. Pending traps are prioritized and internal t raps are t a ken during this stage.
• Write - If no trap is taken, the processo r writes the result to the destination register.
All four stages operate in parallel, working on up to four different instructions at a time. A
basic ‘single-cycle’ instruction enters the pipeline and completes infour cycles.
By the time it reaches the write stage, three more instructions have entered and are
moving through the pipeline behind it. So, after the first four cycles, a single-cycle
instruction exits the pipeline and a single-cycle instruction enters the pipeline on every
cycle. Of course, a ’single-cy cle’ instruction actually takes four cycles to comp lete, but
they are called single cycle because with this type of instruction the processor can com-
plete one instruction per cycle after the initial four-cycle delay.
Floating-point Unit Th e FL oa ting Poin t Un it ( FPU) is desi gned to prov ide exec uti on of sin gle and do uble -
precision floating-point instructions concurrently with execution of integer instructions by
the IU. The FPU is compliant to the ANSI/IEEE-754 (1985) floating-point standard.
The FPU is designed for highly dependable space and military applications, and
includes su pport for concurrent error detection and testability.
The FPU us es a f our stage ins truction pipe line consi sting of fetch, decode, exec ute and
write stages (F, D, E and W). The fetch unit captures instructions and their addresses
from t he data and address buses. The decode unit contains logic to decode the floating-
point instruction opcodes. The execution unit handle s all instruction execution. The exe-
cution unit includes a floating-point queue (FP queue), which contains stored floating-
point operate (FPop) instructions under execution and their addresses. The execution
unit con trols the loa d unit, the st ore unit, and t he dat apath unit . The F PU depends up on
the IU to acces s all addresses and control signals for memory acces s. Floating-point
loads and stores are executed in conjunction wit h the IU, which provides addresses and
control signals while the FPU supplies or stores the data. Instruction fetch for integer
and floating-point instructions is provided by the IU.
The FPU provides t hree ty pes of r egisters: f r egisters, FSR, and the FP queue. The FSR
is a 32-bit status and control register. It keeps track of rounding modes, floating-point
trap ty pes, queue s ta tus, condi tion c odes, and various IEE E exce ption in formation. T he
floating-point queue contains the floating-point instruction currently under execution,
along with its corresponding add ress.