64-bit processor 相关

 

      In more specific terms, the labels "64-bit," 32-bit," etc. designate the number of bits that each of the processor's general-purpose registers (GPRs) can hold. So when someone uses the term "64-bit processor," what they mean is "a processor with GPRs that store 64-bit numbers." And in the same vein, a "64-bit instruction" is an instruction that operates on 64-bit numbers.
      运算速度:64位CPU GPRs(General-Purpose Registers，通用寄存器)的数据宽度为64位，64位指令集可以运行64位数据指令，也就是说处理器一次可提取64位数据，理论上性能会相应提升。

 

     寻址能力:64位处理器的优势还体现在系统对内存的控制上。由于地址使用的是特殊的整数，因此一个ALU（算术逻辑运算器）和寄存器可以处理更大的整数，也就是更大的地址。比如，Windows Vista x64 Edition支持多达128 GB的内存和多达16 TB的虚拟内存，而32位CPU和操作系统最大只可支持4G内存。

      A 64-bit operating system supports far more physical memory than a 32-bit operating system. For example, most 32-bit Windows systems support a maximum of 4 GigaBytes of physical memory, with up to 3 GigaBytes of address space for each process(进程), while 64-bit Windows supports up to 2 TeraBytes of physical memory with 8 TeraBytes of address space for each process.

      By default, 64-bit Microsoft Windows-based applications have a user-mode address space of 8 TeraBytes (7 terabytes on Itanium-based systems).

      但Win64目前支持16TB(由44位表示)，而没有在计算机中加载到16EB以使用全部64位。

      In the LLP64 data model, only pointers expand to 64 bits; all other basic data types (integer and long) remain 32 bits in length.     
      Win64上的指针是8字节，而int，long，DWORD和HANDLE仍然是4字节，但是HANDLE作为指针定义的话将为8字节。

 

64-bit data models Data model short (integer) int long (integer) long long pointers Sample operating systems LLP64 LP64 ILP64 SILP64

16	32	32	64	64	Microsoft Win64 (X64/IA64)
16	32	64	64	64	Most Unix (like Solaris) and Unix-like systems (like Linux)
16	64	64	64	64	HAL
64	64	64	64	64	?

 

Intel® 64 provides support for:

• 64-bit flat virtual address space
• 64-bit pointers
• 64-bit wide general purpose registers
• 64-bit integer support
• Up to one terabyte (TB) of platform address space

-------------------------------------------------------------------------

关于字长：

   难道不是通用寄存器的位宽吗？

   Some computer architectures define the term dword (double word) to be a unit of data that is twice the size of a word. The x86 platform originally had a word size of 16 bits (2 bytes) and that usage of the term is confusingly retained even though the actual processor word size is now 32 bits or even 64 bits. In that platform, a dword designates a 32-bit (4-byte) unit.

   在x86,win32操作系统中, windows SDK------>WORD 16bit : unsigned short,DWORD 32bit : unsigned long,似乎这个WORD由操作系统和编译器决定，而不是处理器？？？？？？

   也许我们的电脑已经是64-bit processor,只是装的是win32的操作系统,GetNativeSystemInfo,wProcessorArchitecture?

或者使用windows优化大师来检测.