发明名称 |
Circuitry and method for performing branching without pipeline delay |
摘要 |
The pipeline architecture minimizes delays incurred during execution of branch instructions. While a first instruction is executing, a second instruction is fetched and is ready for execution at the beginning of the next clock cycle. Control logic examines the fetched instruction during the first clock cycle to determine whether the instruction is a branch instruction which may indicate that the address of the next instruction is not the next sequential address. Flags which indicate the state of the system are examined to determine if the address of the instruction is the next sequential address or the address indicated in the branch instruction. As this is performed during the fetch clock cycle of the branch instruction, during execution of the branch instruction, the instruction at the address selected is fetched and is ready for execution without delay.
|
申请公布号 |
US5928357(A) |
申请公布日期 |
1999.07.27 |
申请号 |
US19970878659 |
申请日期 |
1997.06.19 |
申请人 |
INTEL CORPORATION |
发明人 |
UNDERWOOD, KEITH FREDERICK;DURANTE, RICHARD JOSEPH |
分类号 |
G06F9/32;G06F9/38;(IPC1-7):G06F9/00;G06F9/06 |
主分类号 |
G06F9/32 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|