Merge branch 'master' of github.com:taddeus/peephole

benchmarks/build/test.s

@@ -6,7 +6,7 @@
  # -mgas -mgpOPT
 
  # Cc1 arguments (-G value = 8, Cpu = default, ISA = 1):
- # -quiet -dumpbase -o
+ # -quiet -dumpbase -O0 -o
 
 gcc2_compiled.:
 __gnu_compiled_c:

report/report.tex

@@ -35,7 +35,7 @@ the keywords in to an action.
 
 \section{Design}
 
-There are two general types of of optimizations of the assembly code, global
+There are two general types of optimizations of the assembly code, global
 optimizations and optimizations on a so-called basic block. These optimizations
 will be discussed separately
 
@@ -99,6 +99,16 @@ Appendix \ref{opt}.
 A more advanced optimization is common subexpression elimination. This means
 that expensive operations as a multiplication or addition are performed only
 once and the result is then `copied' into variables where needed.
+\begin{verbatim}
+
+addu	$2,$4,$3              addu = $t1, $4, $3
+...                        mov = $2, $t1
+...                   ->   ...
+...                        ...
+addu	$5,$4,$3		   mov = $4, $t1
+
+\end{verbatim}
+
 
 A standard method for doing this is the creation of a DAG or Directed Acyclic
 Graph. However, this requires a fairly advanced implementation. Our
@@ -112,27 +122,13 @@ We now add the instruction above the first use, and write the result in a new
 variable. Then all occurrences of this expression can be replaced by a move of
 from new variable into the original destination variable of the instruction.
 
-This is a less efficient method then the DAG, but because the basic blocks are
+This is a less efficient method then the dag, but because the basic blocks are
 in general not very large and the execution time of the optimizer is not a
 primary concern, this is not a big problem.
 
-\subsubsection*{Constant folding}
+\subsubsection*{Fold constants}
 
-Another optimization is to do constant folding. Constant folding is replacing
-a expensive step like addition with a more simple step like loading a constant.
-Of course, this is not always possible. It is possible in cases where you apply
-an operation on two constants, or a constant and a variable of which you know
-for sure that it always has a certain value at that point. For example:
-\begin{verbatim}
-li   $regA, 1               li $regA, 1
-addu $regB, $regA, 2    ->  li $regB, 3
-\end{verbatim}
-Of course, if \texttt{\$regA} is not used after this, it can be removed, which
-will be done by the dead code elimination.
 
-One problem we encountered with this is that the use of a \texttt{li} is that
-the program often also stores this in the memory, so we had to check whether
-this was necessary here as well.
 
 \subsubsection*{Copy propagation}
 
@@ -159,11 +155,12 @@ of the move operation.
 
 An example would be the following:
 \begin{verbatim}
-move $regA, $regB                   move $regA, $regB
-...                                 ...
-Code not writing $regA, $regB   ->  ...
-...                                 ...
-addu $regC, $regA, ...              addu $regC, $regB, ...
+move $regA, $regB           move $regA, $regB
+...                         ...
+Code not writing $regA, ->  ...
+$regB                       ...
+...                         ...
+addu $regC, $regA, ...      addu $regC, $regB, ...
 \end{verbatim}
 This code shows that \texttt{\$regA} is replaced with \texttt{\$regB}. This
 way, the move instruction might have become useless, and it will then be
@@ -171,18 +168,7 @@ removed by the dead code elimination.
 
 \subsubsection*{Algebraic transformations}
 
-Some expression can easily be replaced with more simple once if you look at
-what they are saying algebraically. An example is the statement $x = y + 0$, or
-in Assembly \texttt{addu \$1, \$2, 0}. This can easily be changed into $x = y$
-or \texttt{move \$1, \$2}.
-
-Another case is the multiplication with a power of two. This can be done way
-more efficiently by shifting left a number of times. An example:
-\texttt{mult \$regA, \$regB, 4    ->  sll  \$regA, \$regB, 2}. We perform this
-optimization for any multiplication with a power of two.
 
-There are a number of such cases, all of which are once again stated in
-appendix \ref{opt}. 
 
 \section{Implementation}
 
@@ -206,7 +192,7 @@ languages like we should do otherwise since Lex and Yacc are coupled with C.
 
 The decision was made to not recognize exactly every possible instruction in
 the parser, but only if something is for example a command, a comment or a gcc
-directive. We then transform per line to a object called a Statement. A
+directive. We then transform per line to an object called a Statement. A
 statement has a type, a name and optionally a list of arguments. These
 statements together form a statement list, which is placed in another object
 called a Block. In the beginning there is one block for the entire program, but
@@ -219,7 +205,7 @@ The optimizations are done in two different steps. First the global
 optimizations are performed, which are only the optimizations on branch-jump
 constructions. This is done repeatedly until there are no more changes.
 
-After all possible global optimizations are done, the program is separated into
+After all possible global optimizations are done, the program is seperated into
 basic blocks. The algorithm to do this is described earlier, and means all
 jump and branch instructions are called leaders, as are their targets. A basic
 block then goes from leader to leader.
@@ -231,7 +217,8 @@ steps can be done to optimize something.
 \subsection{Writing}
 
 Once all the optimizations have been done, the IR needs to be rewritten into
-Assembly code, so the xgcc cross compiler can make binary code out of it.
+Assembly code. After this step the xgcc crosscompiler can make binary code from
+the generated Assembly code.
 
 The writer expects a list of statements, so first the blocks have to be
 concatenated again into a list. After this is done, the list is passed on to

src/statement.py

@@ -65,6 +65,11 @@ class Statement:
         return self.is_command() \
                and re.match('^beq|bne|blez|bgtz|bltz|bgez|bct|bcf$', \
                             self.name)
+                            
+    def is_branch_zero(self):
+        """Check if statement is a branch that compares with zero."""
+        return self.is_command() \
+               and re.match('^blez|bgtz|bltz|bgez$', self.name)
 
     def is_shift(self):
         """Check if the statement is a shift operation."""
@@ -75,6 +80,11 @@ class Statement:
         return self.is_command() and self.name in ['lw', 'li', 'dlw', 'l.s', \
                                                    'l.d']
                                                    
+    def is_store(self):
+        """Check if the statement is a store instruction."""
+        return self.is_command() and self.name in ['sw', 's.d', 'dsw', 's.s', \
+                                                   's.b']
+                                                   
     def is_arith(self):
         """Check if the statement is an arithmetic operation."""
         return self.is_command() \
@@ -102,7 +112,7 @@ class Statement:
         return self.is_command() and re.match('^(xor|or|and)i?$', self.name)
     
     def is_double_aritmethic(self):
-        """Check if the statement is a arithmetic .d operator."""
+        """Check if the statement is a aritmethic .d operator."""
         return self.is_command() and \
                 re.match('^(add|sub|div|mul)\.d$', self.name)
                 
@@ -127,6 +137,10 @@ class Statement:
         """Check if the statement is a convert operator."""
         return self.is_command() and re.match('^trunc\.[a-z\.]*$', self.name)
         
+    def is_compare(self):
+        """Check if the statement is a comparison."""
+        return self.is_command() and re.match('^c\.[a-z\.]*$', self.name)
+        
     def jump_target(self):
         """Get the jump target of this statement."""
         if not self.is_jump():
@@ -136,37 +150,51 @@ class Statement:
     
     def get_def(self):
         """Get the variable that this statement defines, if any."""
-        instr = ['move', 'addu', 'subu', 'li', 'mtc1', 'dmfc1']
+        instr = ['move', 'addu', 'subu', 'li', 'mtc1', 'dmfc1', 'mov.d']
         
         if self.is_load_non_immediate() or self.is_arith() \
-                or self.is_logical() or self.is_double_arithmetic() \
+                or self.is_logical() or self.is_double_aritmethic() \
                 or self.is_move_from_spec() or self.is_double_unary() \
                 or self.is_set_if_less() or self.is_convert() \
                 or self.is_truncate() or self.is_load() \
-                or (self.is_command and self.name in instr):
-            return self[0]
+                or self.is_command(*instr):
+            return [self[0]]
 
         return []
 
     def get_use(self):
-        # TODO: Finish with ALL the available commands!
+        """Get the variables that this statement uses, if any."""
+        instr = ['addu', 'subu', 'mult', 'div', 'move', 'mtc1', 'mov.d', \
+            'dmfc1']
         use = []
 
-        if self.is_binop():
-            use += self[1:]
-        elif self.is_command('move'):
+        # Case arg0
+        if self.is_branch() or self.is_store() or self.is_compare()\
+                or self.is_command(*['mult', 'div', 'dsz']):
+            if self.name == 'dsz':
+                m = re.match('^\d+\(([^)]+)\)$', self[0])
+                use.append(m)
+            else:
+                use.append(self[0])
+        # Case arg1 direct adressing
+        if (self.is_branch() and not self.is_branch_zero()) or self.is_shift()\
+                or self.is_double_arithmetic() or self.is_double_unary() \
+                or self.is_logical() or self.is_convert() \
+                or self.is_truncate() or self.is_set_if_less() \
+                or self.is_command(*instr):
             use.append(self[1])
-        elif self.is_command('lw', 'sb', 'sw', 'dsw', 's.s', 's.d'):
+        # Case arg1 relative adressing
+        if self.is_load_non_immediate() or self.is_store():    
             m = re.match('^\d+\(([^)]+)\)$', self[1])
-
             if m:
-                use.append(m.group(1))
-
-            # 'sw' also uses its first argument
-            if self.name in ['sw', 'dsw']:
-                use.append(self[0])
-        elif len(self) == 2:  # FIXME: temporary fix, manually add all commands
-            use.append(self[1])
+                use.append(m)
+            else:
+                use.append(self[1])
+        # Case arg2
+        if self.is_double_arithmetic() or self.is_set_if_less() \
+                or self.is_logical() \
+                or self.is_command(*['addu', 'subu']):
+            use.append(self[2])
 
         return use
 

tests/test_statement.py

@@ -93,3 +93,9 @@ class TestStatement(unittest.TestCase):
         self.assertTrue(S('command', 'addu', '$1', '$2', '$3').is_arith())
         self.assertFalse(S('command', 'foo').is_arith())
         self.assertFalse(S('label', 'addu').is_arith())
+        
+#    def test_get_def(self):
+#        self.assertEqual(S('command', 'addu', '$1', '$2', '$3'), '$1')
+#        
+        
+