| 1. | Do not use upper 96 floating - point registers
不使用上面的96个浮点寄存器。 |
| 2. | The driver destroys one of the upper floating - point registers
驱动程序破坏了上面的浮点寄存器之一。 |
| 3. | Control passes to the kernel , and the upper 96 floating - point registers are not saved
控制权传递到内核，并且未保存上面的96个浮点寄存器。 |
| 4. | Kernel returns from interrupt , and one of the application s upper floating - point registers is destroyed
内核从中断返回，并且应用程序的上面的浮点寄存器之一被破坏。 |
| 5. | It also had separate floating - point registers and could scale from the low to the high end of the unix workstations it was built for
它还有单独的浮点寄存器，可以适应从低端到高端的unix工作站。 |
| 6. | Even a seemingly innocuous edit can result in changes to some of the least significant bits in a floating - point register
甚至看起来无关紧要的编辑都能引起浮点变量中某些最不重要的数据位发生变化。 |
| 7. | An instruction where each parameter is independent of the others , for example , when moving data from memory to a floating - point register
一条指令，其中每一个参数与其它参数无关，例如，把数据从存储器传送到浮点寄存器的指令。 |
| 8. | Tells the compiler to only use the lower 32 floating - point registers and to not use the upper 96 floating - point registers when compiling for itanium
通知编译器在itanium中进行编译时，只使用下面的32个浮点寄存器，不使用上面的96个浮点寄存器。 |
| 9. | Also enhances the performance of context changes in user mode upper 96 floating - point registers do not have to be saved or reloaded
除了使应用程序能够正确地从内核模式切换到用户模式，还增强了在用户模式中进行上下文更改的性能（不必保存或重新加载上面的96个浮点寄存器） 。 |
| 10. | Sse and sse2 instructions will be used for some scalar floating - point computations , when it is determined that it is faster to use the sse sse2 instructions and registers rather than the x87 floating - point register stack
时，优化程序将选择何时以及如何使用sse和sse2指令。当确定使用sse / sse2指令和寄存器肯定要比使用x87浮点寄存器堆栈更快时， sse和sse2指令将用于某些标量浮点计算。 |
