TI AR7 (MIPS 4KEc) 150 MHz
| Size | Latency | Description |
|---|---|---|
| 16 K | 2 | TLB + L1 |
| 128 K | 2 + 240 ns | + 240 ns (RAM) |
| ... | 2 + 460 ns | + 220 ns (TLB miss) |
| # | Name | Description |
|---|---|---|
| 1 | Instruction | I-TLB translation. An instruction is fetched from the ICache. |
| An instruction is fetched from the ICache. | ||
| 2 | Execution | Instruction decode. Operands are fetched from the register file. Instruction logic selects an instruction address. |
| ALU operation begins. ALU calculates the data virtual address for load and store instructions. ALU resolves branch conditions and calculates branch target address. Instruction logic selects an instruction address. | ||
| 3 | Memory | ALU operation completes. Data TLB and data cache lookup. The data cache fetch and VA->PA translation. |
| The data cache fetch and VA->PA translation. | ||
| 4 | Align / Accumulate | A separate aligner aligns loaded data with its word boundary. |
| . | ||
| 5 | Writeback | Result is written back to the register file. |
| . |