Project

General

Profile

MMU description » History » Version 55

Taya Sergeeva, 02/22/2013 01:20 PM

1 24 Alexander Kamkin
h1. MMU Description
2 1 Taya Sergeeva
3 35 Alexander Kamkin
A _memory management unit_ (_MMU_) is known to be one of the most complex and error-prone components of a modern microprocessor. MicroTESK has a special subsystem, called _MMU subsystem_, intended for (1) specifying memory devices and (2) deriving testing knowledge from such specifications. The subsystem provides unified facilities for describing memory buffers (like _L1_ and _L2 caches_, _translation look-aside buffers_ (_TLBs_), etc.) as well as a means for connecting several buffers into a memory hierarchy.
4 34 Alexander Kamkin
5 38 Alexander Kamkin
h2. Address Description
6
7 40 Alexander Kamkin
A buffer is accessed by an _address_, which is typically a _bit vector_ of a fixed length (width). Different buffers are allowed to have a common address space (e.g., L1 and L2 are usually both addressed by physical addresses). However, in general case, each buffer has its own domain.
8
9 43 Alexander Kamkin
An address space is described using a construct *address*. A couple of examples are given below.
10 38 Alexander Kamkin
11 1 Taya Sergeeva
<pre>
12 42 Alexander Kamkin
address Void { width = 0  }
13 45 Alexander Kamkin
</pre>
14 46 Alexander Kamkin
15 45 Alexander Kamkin
<pre>
16 41 Alexander Kamkin
address PA   { width = 40 }
17 38 Alexander Kamkin
</pre>
18
19 55 Taya Sergeeva
The code above defines two address spaces: (1) a single-element space @Void@ and (2) a space @PA@ consisting of 40-bit addresses (_PA_ usually stands for _physical address_). It also can be virtual (_VA_).
20 10 Alexander Kamkin
21 2 Taya Sergeeva
h2. Buffer Description
22
23 48 Taya Sergeeva
Buffer can be described by different parameters, such as the associativity, the number of sets, the tag computing function, the index computing function, the structure of data unit, the controlling bits, the strategies of data changing when ''miss'' occurs, and so on. 
24
25
For instance, there is an example of the buffer below:
26 2 Taya Sergeeva
27
<pre>
28
buffer L1 
29
{
30 53 Taya Sergeeva
	sets = 4;
31
	lines = 128;
32
	line = (tag:30, data:256);
33
	index(addr:PA) = addr<9..8>;
34
	match(addr:PA) = line.tag == addr<39..10>;
35
	policy = lru;
36 10 Alexander Kamkin
}
37 1 Taya Sergeeva
</pre>
38
39
40
_Description of each constructor_ in the buffer example is below:
41 19 Taya Sergeeva
42
h3. buffer
43 49 Taya Sergeeva
44 21 Taya Sergeeva
<pre>
45 55 Taya Sergeeva
  has a name, ''L1'' in our example; it can have names ''L2'' and ''TLB'' also;
46 52 Taya Sergeeva
  _buffer_ can be described by different parameters, such _sets_, _lines_, _index_, _match_, _policy_, and so on, which number is infixed;
47 21 Taya Sergeeva
</pre>
48 1 Taya Sergeeva
49 51 Taya Sergeeva
h3.  sets 
50 16 Taya Sergeeva
51 15 Taya Sergeeva
<pre>
52 54 Taya Sergeeva
  _sets_ is an associativity of a buffer; it returns the number of lines in a one set;
53 15 Taya Sergeeva
</pre>
54 1 Taya Sergeeva
55 49 Taya Sergeeva
h3.  lines
56 17 Taya Sergeeva
57 15 Taya Sergeeva
<pre>
58 54 Taya Sergeeva
  _lines_ is the number of sets in a given buffer;
59 15 Taya Sergeeva
</pre>
60 13 Taya Sergeeva
61 49 Taya Sergeeva
h3.  line
62 1 Taya Sergeeva
63 17 Taya Sergeeva
<pre>
64 54 Taya Sergeeva
  _line_ is an optional description of line''s fields;
65
  it designates each line of the cache; 
66 1 Taya Sergeeva
  _line_ includes its own parameters in the braces: _tag_ and _data_, each of them has an appropriate width of the fields kept in bytes;
67 52 Taya Sergeeva
  in our example _line_ has only two parameters, but in general case it can include more;
68 54 Taya Sergeeva
  it contains a 30-bit tag and a 256-bit data;
69 14 Taya Sergeeva
</pre>
70 1 Taya Sergeeva
71
h3.  index
72 49 Taya Sergeeva
73 17 Taya Sergeeva
<pre>
74 54 Taya Sergeeva
   _index_ is the function for index calculation;
75
   returns the initial and the final points of the field kept in bytes; they are marked in a three-cornered brackets, after _addr_; in our case index has 2 bits;
76 1 Taya Sergeeva
  _index_ depends on an _address_, which is ''physical'' (PA) in our case; the type of an address is set in the braces after _index_; 
77
</pre>
78
79
h3.  match 
80 49 Taya Sergeeva
81 17 Taya Sergeeva
<pre>
82 54 Taya Sergeeva
  _match_ is a predicate checking whether the line and the address match each other or not;
83
  it returns ''true'' or ''false'' depending on if the data required is in the given line or not; 
84
  it returns ''true'' if there is a ''hit'' in the line, and returns ''false'' otherwise; if the set contains a line with the tag equal to the 30 upper bits of the physical address, this is a ''hit''; if the set does not contain the line, this is a ''miss'' situation;
85 1 Taya Sergeeva
  _match_ description contains the the initial and the final points of the address field in the triangle brackets after _addr_; 
86
  as _index_ in the round braces _match_ also has the type of the address used; ''PA'' in our case;
87 52 Taya Sergeeva
</pre>
88 1 Taya Sergeeva
89
h3.  policy
90 49 Taya Sergeeva
91 1 Taya Sergeeva
<pre>
92 54 Taya Sergeeva
  _policy_ is the strategy of data displacement; 
93
  sets a policy which will be applied to our buffer, ''lru'' (Least Recently Used) in our example; i.e. if the ''miss'' occured, the cache displaces the least-recently-used line of the set; 
94 52 Taya Sergeeva
  policy also can be ''plru'' (Pseudo LRU) and ''fifo'' (First Input First Out).
95 1 Taya Sergeeva
</pre>
96 25 Alexander Kamkin
97
h2. Code Structure
98
99
The MMU grammar is in ru.ispras.microtesk.translator.mmu.grammar folder. It contains Lexer, Parser and TreeWalker files. These files can be compiled by build.xml file (microtesk++/build.xml). The files generated (MMULexer.java, MMUParser.java, MMUTreeWalker.java) are in microtesk++.gen.ru.ispras.microtesk.translator.mmu.grammar folder. 
100
101
The folders ru.ispras.microtesk.translator.mmu.ir.* contain the inner representation of the MMU hierarchy of one buffer.  
102
103
MMU translator is in the ru.ispras.microtesk.translator.mmu.translator folder. 
104 1 Taya Sergeeva
105
Files in ru.ispras.microtesk.model.api.mmu folder contain different policies of cache. Folder ru.ispras.microtesk.model.api.mmu.buffer contains the model of MMU - the files which describe Buffer, Set, Line, Address expressions.  
106 26 Alexander Kamkin
107
After grammar files being generated the file ''BufferExample'' can be loaded to the translator.