21264/EV68A Hardware Reference Manual
InternalArchitecture 2–13
Pipeline Organization
Miss addressfile (MAF)
Dstreamtranslation buffer (DTB)
2.1.6.1 Load Qu eue
The load queue (LQ) is a reorder buffer for load instructions. It contains32 entriesand
maintainsthe state associated with load instructions that have been issued to the Mbox,
but for whichresults have not been delivered to the processor and the instructions
retired.The Mbox assigns load instructions to LQ slots basedon the order in which
they were fetched from the Icache, then places them i nto the LQ after they are issued by
the IQ. The LQ helps ensure correct Alpha memory reference behavior.
2.1.6.2 Store Q ueue
The storequeue (SQ) is a reorder buffer and graduation unit for store instructions.It
contains32 entries and maintains the state associated with store instructions that have
beenissued to the Mbox, but for which data has not been written to the Dcache and the
instructionretired. The Mbox assigns store instructions to SQ slots based on the order
in which theywe re fetchedfrom the Icache and places them into the SQ after they are
issued by theI Q.The S Q holds dataassociated with store instructions issued from the
IQ untilthey are retired, at which point the store can be allowed to update theDca che.
The SQ also helps ensure correct Alpha memory reference behavior.
2.1.6.3 M iss Address File
The 8-entrym issaddress file (MAF) holds physical addresses associated with pending
Icache andDcache fill requests and pending I/O space read transactions.
2.1.6.4 Dstrea m TranslationBuffer
The Mbox includes a 128-entry, fully associative Dstr eam translation buffer (DTB) used
tostore Dstream address translations and page protection information. Each of the entries
in the DTB can map 1, 8, 64, or 512 c ontiguous 8KB pages. The alloca tion scheme is
round-robin. The DTB supports a n 8-bit ASN and contains an AS M bit.

2.1.7 SROM Interface

The serialread-only memory (SROM) interface provides the initialization data load
path froma systemSROM tothe Icache. Refer to Chapter 7 for more information.
2.2 Pipeline Orga nization
The 7-stagepipeline provides an optimized environment for executing Alpha instruc-
tions.The pipeline stages (0 to 6) are shown in Figure 2–8 and described in the follow-
ing paragraphs.