Updated CPI table in README

This commit is contained in:
Clifford Wolf 2015-06-06 21:43:33 +02:00
parent 90ff3380a4
commit 44ea992fed
1 changed files with 11 additions and 9 deletions

View File

@ -50,13 +50,15 @@ The average Cycles per Instruction (CPI) is 5 to 7, depending on the
mix of instructions in the code. The CPI for the individual instructions is: mix of instructions in the code. The CPI for the individual instructions is:
| Instruction | CPI | | Instruction | CPI |
| ------------------- | ---:| | ---------------------| ---:|
| direct jump (jal) | 4 |
| ALU reg + immediate | 4 | | ALU reg + immediate | 4 |
| ALU reg + reg | 5 | | ALU reg + reg | 5 |
| branch (not taken) | 5 |
| memory load | 7 | | memory load | 7 |
| memory store | 8 | | memory store | 8 |
| branch, taken | 8 | | branch (taken) | 8 |
| branch, not taken | 5 | | indirect jump (jalr) | 8 |
| shift operations | 5+ | | shift operations | 5+ |
Dhrystone benchmark results: 0.146 DMIPS/MHz (258 Dhrystones/Second/MHz) Dhrystone benchmark results: 0.146 DMIPS/MHz (258 Dhrystones/Second/MHz)