欢迎访问ic37.com |
会员登录 免费注册
发布采购

30070-53 参数 Datasheet PDF下载

30070-53图片预览
型号: 30070-53
PDF下载: 下载PDF文件 查看货源
内容描述: 的Geode ™ GXLV处理器系列的低功耗X86集成解决方案 [Geode⑩ GXLV Processor Series Low Power Integrated x86 Solutions]
分类和应用: 外围集成电路时钟
文件页数/大小: 247 页 / 4117 K
品牌: NSC [ National Semiconductor ]
 浏览型号30070-53的Datasheet PDF文件第229页浏览型号30070-53的Datasheet PDF文件第230页浏览型号30070-53的Datasheet PDF文件第231页浏览型号30070-53的Datasheet PDF文件第232页浏览型号30070-53的Datasheet PDF文件第234页浏览型号30070-53的Datasheet PDF文件第235页浏览型号30070-53的Datasheet PDF文件第236页浏览型号30070-53的Datasheet PDF文件第237页  
Instruction Set (Continued)  
Instruction Issues for Instruction Set Summary  
k. JMP, CALL, INT, RET, and IRET instructions referring to  
another code segment will cause an exception 13, if an appli-  
cable privilege rule is violated.  
Issues a through c apply to real address mode only:  
a. This is a protected mode instruction. Attempted execution in  
real mode will result in exception 6 (invalid opcode).  
l. An exception 13 fault occurs if CPL is greater than 0 (0 is the  
most privileged level).  
b. Exception 13 fault (general protection) will occur in real mode  
if an operand reference is made that partially or fully extends  
beyond the maximum CS, DS, ES, FS, or GS segment limit  
(FFFFH). Exception 12 fault (stack segment limit violation or  
not present) will occur in real mode if an operand reference is  
made that partially or fully extends beyond the maximum SS  
limit.  
m. An exception 13 fault occurs if CPL is greater than IOPL.  
n. The IF bit of the Flags register is not updated if CPL is greater  
than IOPL. The IOPL and VM fields of the Flags register are  
updated only if CPL = 0.  
o. The PE bit of the MSW (CR0) cannot be reset by this instruc-  
tion. Use MOV into CR0 if desiring to reset the PE bit.  
c. This instruction may be executed in real mode. In real mode,  
its purpose is primarily to initialize the CPU for protected  
mode.  
p. Any violation of privilege rules as apply to the selector oper-  
and does not cause a Protection exception, rather, the zero  
flag is cleared.  
d.  
-
q. If the processors memory operand violates a segment limit or  
segment access rights, an exception 13 fault will occur before  
the ESC instruction is executed. An exception 12 fault will  
occur if the stack limit is violated by the operands starting  
address.  
Issues e through g apply to real address mode and protected  
virtual address mode:  
e. An exception may occur, depending on the value of the oper-  
and.  
f. LOCK# is automatically asserted, regardless of the presence  
or absence of the LOCK prefix.  
r. The destination of a JMP, CALL, INT, RET, or IRET must be in  
the defined limit of a code segment or an exception 13 fault  
will occur.  
g. LOCK# is asserted during descriptor table accesses.  
Issues h through r apply to protected virtual address mode  
only:  
Issue s applies to National Semiconductor-specific SMM in-  
structions:  
h. Exception 13 fault will occur if the memory operand in CS,  
DS, ES, FS, or GS cannot be used due to either a segment  
limit violation or an access rights violation. If a stack limit is  
violated, an exception 12 occurs.  
s. All memory accesses to SMM space are non-cacheable. An  
invalid opcode exception 6 occurs unless SMI is enabled and  
SMAR size > 0, and CPL = 0 and [SMAC is set or if in an SMI  
handler].  
i. For segment load operations, the CPL, RPL, and DPL must  
agree with the privilege rules to avoid an exception 13 fault.  
The segments descriptor must indicate presentor exception  
11 (CS, DS, ES, FS, GS not present). If the SS register is  
loaded and a stack segment not present is detected, an  
exception 12 occurs.  
Issue t applies to cache invalidation instruction with the  
cache operating in write-back mode:  
t. The total clock count is the clock count shown plus the num-  
ber of clocks required to write all modifiedcache lines to  
external memory.  
j. All segment descriptor accesses in the GDT or LDT made by  
this instruction will automatically assert LOCK# to maintain  
descriptor integrity in multiprocessor systems.  
Revision 1.1  
233  
www.national.com  
 复制成功!