Renesas M32R-FPU, Software Manual

Page: 168 / 194

APPENDICES
APPENDICES-10
M32R-FPU Software Manual (Rev.1.01)
Appendix Figure 3.2.1 Pipeline Flow with no Stall (1)
Appendix 3.2 Pipeline Basic Operation
(1) Pipeline Flow with no Stall
The following diagram shows an ideal pipeline flow that has no stall and executes each
instruction in 1 clock cycle. (Since this is just an ideal case, all instructions may not be
piplined in.)
APPENDIX 3
Appendix 3 Pipeline Processing
<Case 1> Integer instructions (register-to-register) are executed continuously
IF D E WB
IF D WB E
D WB E
IF D WB E
<Case 2> Load/store instructions to destination are accessed in 1 cycle continuously
IF D E WB
ST R0,@-R15
ST R1,@-R15
LDI R0,#1
ADD R0,R1
OR R0,R2
CMP R0,R3
IF D WB MEM2
MEM1 MEM2
E MEM1
IF D E WB
LD R2,@R15+
LD R3,@R15+
IF D WB MEM2
MEM1 MEM2
E MEM1
IF D E WB
LD R0,@R2
LDI R1,#1
IF D WB
MEM1 MEM1 MEM2
E
IF D E WB
ADD R1,R3
OR R1,R4 IF D WB E
<Case 3> Register-register instructions are executed with no register dependency following
a load/store instruction (out-of-order-completion)
IF
* A multi-cycle instruction, such as multiply or divide, executes
multiple cycles in the E stage.
* A multi-cycle instruction, such as multiply or divide, executes multiple
cycles in the E stage.