欢迎访问ic37.com |
会员登录 免费注册
发布采购

326769-002 参数 Datasheet PDF下载

326769-002图片预览
型号: 326769-002
PDF下载: 下载PDF文件 查看货源
内容描述: 移动第三代英特尔®科雷亚?? ¢处理器家族 [Mobile 3rd Generation Intel® Core™ Processor Family]
分类和应用:
文件页数/大小: 342 页 / 2513 K
品牌: INTEL [ INTEL ]
 浏览型号326769-002的Datasheet PDF文件第35页浏览型号326769-002的Datasheet PDF文件第36页浏览型号326769-002的Datasheet PDF文件第37页浏览型号326769-002的Datasheet PDF文件第38页浏览型号326769-002的Datasheet PDF文件第40页浏览型号326769-002的Datasheet PDF文件第41页浏览型号326769-002的Datasheet PDF文件第42页浏览型号326769-002的Datasheet PDF文件第43页  
Processor Configuration Registers  
The processor also forwards accesses to the Legacy VGA I/O ranges according to the  
settings in the PEG configuration registers BCTRL (VGA Enable) and PCICMD (IOAE),  
unless a second adapter (monochrome) is present on the DMI Interface/PCI (or ISA).  
The presence of a second graphics adapter is determined by the MDAP configuration  
bit. When MDAP is set, the processor will decode legacy monochrome I/O ranges and  
forward them to the DMI Interface. The I/O ranges decoded for the monochrome  
adapter are 3B4h, 3B5h, 3B8h, 3B9h, 3BAh, and 3BFh.  
Note:  
The PEG I/O address range registers defined above are used for all I/O space allocation  
for any devices requiring such a window on PCI Express.  
The PCICMD register can disable the routing of I/O cycles to PCI Express.  
2.3.12  
MCTP and KVM Flows  
Refer to THE DMI2 specification for details.  
MCTP cycles are not processed within the processor. MCTP cycles are merely passed  
from input port to destination port based on routing ID.  
2.3.13  
Decode Rules and Cross-Bridge Address Mapping  
2.3.13.1  
DMI Interface Decode Rules  
All “SNOOP semantic” PCI Express transactions are kept coherent with processor  
caches.  
All “Snoop not required semantic” cycles must reference the main DRAM address  
range. PCI Express non-snoop initiated cycles are not snooped.  
The processor accepts accesses from DMI Interface to the following address ranges:  
• All snoop memory read and write accesses to Main DRAM including PAM region  
(except stolen memory ranges, TSEG, A0000h–BFFFFh space)  
• Write accesses to enabled VGA range, MBASE/MLIMIT, and PMBASE/PMLIMIT will  
be routed as peer cycles to the PCI Express interface.  
• Write accesses above the top of usable DRAM and below 4 GB (not decoding to PCI  
Express or GMADR space) will be treated as master aborts.  
• Read accesses above the top of usable DRAM and below 4 GB (not decoding to PCI  
Express) will be treated as unsupported requests.  
• Reads and accesses above the TOUUD will be treated as unsupported requests on  
VC0/VCp.  
DMI Interface memory read accesses that fall between TOLUD and 4 GB are considered  
invalid and will master abort. These invalid read accesses will be reassigned to address  
000C_0000h and dispatch to DRAM. Reads will return unsupported request completion.  
Writes targeting PCI Express space will be treated as peer-to-peer cycles.  
There is a known usage model for peer writes from DMI to PEG. A video capture card  
can be plugged into the PCH PCI bus. The video capture card can send video capture  
data (writes) directly into the frame buffer on an external graphics card (writes to the  
PEG port). As a result, peer writes from DMI to PEG must be supported.  
I/O cycles and configuration cycles are not supported in the upstream direction. The  
result will be an unsupported request completion status.  
Datasheet, Volume 2  
39