延迟值

L1 cache reference                                              0.5ns

一级缓存引用

Branch mispredict                                                    5ns

分支错误预测

L2 cache reference                                                  7ns

二级缓存引用

Mutex lock                                                          100ns

互斥锁定

Main memory reference                                      100ns

主存引用

Compress 1K bytes with Zippy                            10,000ns

用Zippy压缩1K字节

Send 2K bytes over 1 Gbps network                  20,000ns

通过1Gbps网络发送2K字节

Read 1 MB sequentially from memory              250,000ns

从内存中读取1MB

Round trip within same datacenter                    500,000ns

数据中心的往返路程

Disk seek                                                        10,000,000ns

磁盘寻道

Read 1 MB sequentially from network            10,000,000ns

从网络连续读取1MB

Read 1 MB sequentially from disk                  30,000,000ns

从磁盘连续读取1MB

Send packet CA->Netherlands->CA                150,000,000ns

在CA向荷兰发包再返回

补充一段关于Branch mispredict的介绍：来自Wiki

Branch misprediction occurs when a central processing unit (CPU) mispredicts the next instruction to process in branch prediction, which is aimed at speeding up execution.

During the execution of certain programs there are places where the program execution flow can continue in several ways. These are called branches, or conditional jumps. The CPU also uses a pipeline which allows several instructions to be processed at the same time. When the code for a conditional jump is read we do not yet know the next instruction to execute and insert into the execution pipeline. This is where branch prediction comes in.