so close i can smell it, checkpoint

lib/arm/arm_machine.rb

@@ -1,8 +1,35 @@
 require "vm/machine"
+require_relative "instruction"
+require_relative "stack_instruction"
+require_relative "logic_instruction"
+require_relative "memory_instruction"
+require_relative "call_instruction"
 
 module Arm
   class ArmMachine < Vm::Machine
     
+    # defines a method in the current class, with the name inst (first erg) 
+    # the method instantiates an instruction of the given class which gets passed a single hash as arg
+    
+    # gets called for every "standard" instruction. 
+    # may be used for machine specific ones too
+    def define_instruction inst , clazz
+      super
+      return
+      # need to use create_method and move to options hash
+      define_method("#{inst}s") do |*args|
+        instruction clazz , inst , :al , 1 , *args
+      end
+      ArmMachine::COND_CODES.keys.each do |suffix|
+        define_method("#{inst}#{suffix}") do |options|
+          instruction clazz , inst , suffix , 0 , *args
+        end
+        define_method("#{inst}s#{suffix}") do |options|
+          instruction clazz , inst , suffix , 1 , *args
+        end
+      end
+    end
+  
     def word_load value
       "word"
     end
@@ -12,9 +39,17 @@ module Arm
 
     def main_entry
       e = Vm::Block.new("main_entry")
+      e.add_code( mov( :left => :fp , :right => 0 ))
     end
     def main_exit
       e = Vm::Block.new("main_exit")
+      e.join( syscall(0) )
+    end
+    def syscall num
+      e = Vm::Block.new("syscall")
+      e.add_code( MoveInstruction.new( 7 , num ) )
+      e.add_code( CallInstruction.new( :swi ) )
+      e
     end
   end
 end

lib/arm/call_instruction.rb

@@ -1,6 +1,6 @@
 require_relative "instruction"
 
-module Asm
+module Arm
   # There are only three call instructions in arm branch (b), call (bl) and syscall (swi)
   
   # A branch could be called a jump as it has no notion of returning
@@ -13,7 +13,7 @@ module Asm
   # in Arm the register layout is different and so we have to place the syscall code into register 7
   # Registers 0-6 hold the call values as for a normal c call
   
-  class CallInstruction < Instruction
+  class CallInstruction < Vm::CallInstruction
     
     def assemble(io)
       case opcode

lib/arm/constants.rb

@@ -0,0 +1,82 @@
+module Arm
+
+  module Constants
+    OPCODES = {
+      :adc => 0b0101, :add => 0b0100,
+      :and => 0b0000, :bic => 0b1110,
+      :eor => 0b0001, :orr => 0b1100,
+      :rsb => 0b0011, :rsc => 0b0111,
+      :sbc => 0b0110, :sub => 0b0010,
+
+      # for these Rn is sbz (should be zero)
+      :mov => 0b1101,
+      :mvn => 0b1111,
+      # for these Rd is sbz and S=1
+      :cmn => 0b1011,
+      :cmp => 0b1010,
+      :teq => 0b1001,
+      :tst => 0b1000,
+
+      :b => 0b1010,
+      :bl => 0b1011,
+      :bx => 0b00010010
+    }
+    #return the bit patter that the cpu uses for the current instruction @opcode
+    def op_bit_code
+      OPCODES[@opcode] or throw "no code found for #{@opcode.inspect}"
+    end
+
+    #codition codes can be applied to many instructions and thus save branches
+    # :al => always   , :eq => equal  and so on
+    # eq mov if equal :moveq r1 r2 (also exists as function) will only execute if the last operation was 0
+    COND_CODES = {
+      :al => 0b1110, :eq => 0b0000,
+      :ne => 0b0001, :cs => 0b0010,
+      :mi => 0b0100, :hi => 0b1000,
+      :cc => 0b0011, :pl => 0b0101,
+      :ls => 0b1001, :vc => 0b0111,
+      :lt => 0b1011, :le => 0b1101,
+      :ge => 0b1010, :gt => 0b1100,
+      :vs => 0b0110
+    }
+    #return the bit pattern for the @condition_code variable, which signals the conditional code
+    def cond_bit_code
+      COND_CODES[@condition_code] or throw "no code found for #{@condition_code}"
+    end
+    
+    REGISTERS = { 'r0' => 0, 'r1' => 1, 'r2' => 2, 'r3' => 3, 'r4' => 4, 'r5' => 5,
+                  'r6' => 6, 'r7' => 7, 'r8' => 8, 'r9' => 9, 'r10' => 10, 'r11' => 11,
+                  'r12' => 12, 'r13' => 13, 'r14' => 14, 'r15' => 15, 'a1' => 0, 'a2' => 1,
+                  'a3' => 2, 'a4' => 3, 'v1' => 4, 'v2' => 5, 'v3' => 6, 'v4' => 7, 'v5' => 8,
+                  'v6' => 9, 'rfp' => 9, 'sl' => 10, 'fp' => 11, 'ip' => 12, 'sp' => 13,
+                  'lr' => 14, 'pc' => 15 }
+    def reg name
+      raise "no such register #{reg}" unless REGISTERS[name]
+      Asm::Register.new(name , REGISTERS[name])
+    end
+                      
+            
+
+   def calculate_u8_with_rr(arg)
+     parts = arg.value.to_s(2).rjust(32,'0').scan(/^(0*)(.+?)0*$/).flatten
+     pre_zeros = parts[0].length
+     imm_len = parts[1].length
+     if ((pre_zeros+imm_len) % 2 == 1)
+       u8_imm = (parts[1]+'0').to_i(2)
+       imm_len += 1
+     else
+       u8_imm = parts[1].to_i(2)
+     end
+     if (u8_imm.fits_u8?)
+       # can do!
+       rot_imm = (pre_zeros+imm_len) / 2
+       if (rot_imm > 15)
+         return nil
+       end
+       return u8_imm | (rot_imm << 8)
+     else
+       return nil
+     end
+   end
+  end
+end

lib/arm/instruction.rb

@@ -1,24 +1,12 @@
-require_relative "assembly_error"
+require "vm/instruction"
-require_relative "arm_machine"
+require_relative "constants"
 
-module Asm
+  Vm::Instruction.class_eval do
+    include Arm::Constants
 
-  class Code ; end
+    COND_POSTFIXES = Regexp.union( Arm::Constants::COND_CODES.keys.collect{|k|k.to_s} ).source
-  
-  # Not surprisingly represents an cpu instruction. 
-  # This is an abstract base class, with derived classes 
-  # Logic / Move / Compare / Stack / Memory (see there)
-  # 
-  # Opcode is a (<= three) letter accronym (same as in assembly code). Though in arm, suffixes can
-  # make the opcode longer, we chop those off in the constructor
-  # Argurments are registers or labels or string/num Literals
-  
-  class Instruction < Code
-    include ArmMachine
 
-    COND_POSTFIXES = Regexp.union( COND_CODES.keys.collect{|k|k.to_s} ).source
+    def initializ(opcode , condition_code , update_status , args)
-
-    def initialize(opcode , condition_code , update_status , args)
       @update_status_flag = update_status
       @condition_code = condition_code.to_sym
       @opcode = opcode
@@ -43,4 +31,3 @@ module Asm
       4
     end
   end
-end

lib/arm/logic_instruction.rb

@@ -1,12 +1,12 @@
 require_relative "instruction"
 
-module Asm
+module Arm
   # ADDRESSING MODE 1 
   # Logic ,Maths, Move and compare instructions (last three below)
   
-  class LogicInstruction < Instruction
+  class LogicInstruction < Vm::LogicInstruction
 
-    def initialize(opcode , condition_code , update_status , args)
+    def initializ(opcode , condition_code , update_status , args)
       super(opcode , condition_code , update_status , args)
       @rn = nil
       @i = 0      
@@ -84,7 +84,7 @@ module Asm
       io.write_uint32 val
     end
   end
-  class CompareInstruction < LogicInstruction
+  class CompareInstruction < Vm::CompareInstruction
     def initialize(opcode , condition_code , update_status , args)
       super(opcode , condition_code , update_status , args)
       @update_status_flag = 1
@@ -95,11 +95,12 @@ module Asm
       do_build args[1]
     end
   end
-  class MoveInstruction < LogicInstruction
+  class MoveInstruction < Vm::MoveInstruction
-    def initialize(opcode , condition_code , update_status , args)
+    def initializ(opcode , condition_code , update_status , args)
       super(opcode , condition_code , update_status , args)
       @rn = reg "r0" # register zero = zero bit pattern
     end
+    
     def build
       do_build args[1]
     end

lib/arm/memory_instruction.rb

@@ -1,10 +1,10 @@
 require "asm/nodes"
 require_relative "instruction"
 
-module Asm
+module Arm
   # ADDRESSING MODE 2
   # Implemented: immediate offset with offset=0
-  class MemoryInstruction < Instruction
+  class MemoryInstruction < Vm::MemoryInstruction
 
     def initialize(opcode , condition_code , update_status , args)
       super(opcode , condition_code , update_status , args)

lib/arm/stack_instruction.rb

@@ -1,10 +1,10 @@
 require_relative "instruction"
 
-module Asm
+module Arm
   # ADDRESSING MODE 4
-  class StackInstruction < Instruction
+  class StackInstruction < Vm::StackInstruction
 
-    def initialize(opcode , condition_code , update_status , args)
+    def initializ(opcode , condition_code , update_status , args)
       super(opcode , condition_code , update_status , args)
       @update_status_flag= 0
       @rn = reg "r0" # register zero = zero bit pattern

lib/support/hash_attributes.rb

@@ -0,0 +1,24 @@
+# Make hash attributes to object attributes
+
+module Support
+  module HashAttributes
+    # map any function call to an attribute if possible
+    def method_missing name , *args , &block 
+      if args.length > 1 or block_given?
+        puts "NO -#{args.length} BLOCK #{block_given?}"
+        super 
+      else
+        name = name.to_s
+        if args.length == 1        #must be assignemnt for ir attr= val
+          if name.include? "="
+            return @attributes[name.chop] = args[0]
+          else 
+            super
+          end
+        else
+          return @attributes[name]
+        end
+      end
+    end
+  end
+end

lib/vm/block.rb

@@ -16,7 +16,7 @@ module Vm
 
   # See Value description on how to create code/instructions
   
-  class Block < Value
+  class Block < Code
 
     def initialize(name)
       super()
@@ -31,6 +31,20 @@ module Vm
     def verify
     end
 
+    def add_code(kode)
+      kode.at(@position)
+      length = kode.length
+      puts "length #{length}"
+      @position += length
+      @codes << kode
+    end
+
+    def assemble(io)
+      @codes.each do |obj|
+        obj.assemble io
+      end
+    end
+
     # set the next executed block after self.
     # why is this useful? if it's unconditional, why not merge them:
     #    So the second block can be used as a jump target. You standard loop needs a block to setup

lib/vm/code.rb

@@ -1,3 +1,5 @@
+require_relative "values"
+
 module Vm
   # Base class for anything that we can assemble
 
@@ -9,7 +11,7 @@ module Vm
   # All code is position independant once assembled.
   # But for jumps and calls two passes are neccessary. 
   # The first setting the position, the second assembling
-  class Code
+  class Code < Value
     
     # just sets position to nil, so we can sell that it has not been set
     def initialize

lib/vm/context.rb

@@ -5,28 +5,13 @@ module Vm
   
   #currently just holding the program in here so we can have global access
   class Context
+    # Make hash attributes to object attributes
+    include Support::HashAttributes
+    
     def initialize program
       @attributes = {}
       @attributes["program"] = program
     end
     
-    # map any function call to an attribute if possible
-    def method_missing name , *args , &block 
-      if args.length > 1 or block_given?
-        puts "NO -#{args.length} BLOCK #{block_given?}"
-        super 
-      else
-        name = name.to_s
-        if args.length == 1        #must be assignemnt for ir attr= val
-          if name.include? "="
-            return @attributes[name.chop] = args[0]
-          else 
-            super
-          end
-        else
-          return @attributes[name]
-        end
-      end
-    end
   end
 end

lib/vm/instruction.rb

@@ -1,16 +1,11 @@
-
+require_relative "code"
+require "support/hash_attributes"
 module Vm
-  # Instruction represent the actions that affect change on Values
-  # In an OO way of thinking the Value is data, Instruction the functionality
 
-  # But to allow flexibility, the value api bounces back to the machine api, so machines instantiate
+  # Because the idea of what one instruction does, does not always map one to one to real machine
-  # intructions.
-  
-  # When Instructions are instantiated the create a linked list of Values and Instructions.
-  # So Value links to Instruction and Instruction links to Value
-  # Also, because the idea of what one instruction does, does not always map one to one to real machine
   # instructions, and instruction may link to another instruction thus creating an arbitrary list
   # to get the job (the original instruciton) done
+  
   # Admittately it would be simpler just to create the (abstract) instructions and let the machine 
   # encode them into what-ever is neccessary, but this approach leaves more possibility to 
   # optimize the actual instruction stream (not just the crystal instruction stream). Makes sense?
@@ -25,10 +20,14 @@ module Vm
   # - Call
   
   # Instruction derives from Code, for the assembly api
-  class Code ; end
+  
-
   class Instruction < Code
+    # Make hash attributes to object attributes
+    include Support::HashAttributes
     
+    def initialize options
+      @options = options
+    end
   end
   
   class StackInstruction < Instruction

lib/vm/machine.rb

@@ -11,13 +11,17 @@ module Vm
   # * Note that register content is typed externally. Not as in mri, where int's are tagged. Floats can's
   #   be tagged and lambda should be it's own type, so tagging does not work
   
-  # Programs are created by invoking methods on subclasses of Value. 
-  # But executable code is a sequence of Instructions and subclasses.
-  
   # A Machines main responsibility in the framework is to instantiate Instruction
+
   # Value functions are mapped to machines by concatenating the values class name + the methd name
   # Example:  SignedValue.plus( value ) ->  Machine.signed_plus (value )
   
+  # Also, shortcuts are created to easily instantiate Instruction objects. The "standard" set of instructions
+  # (arm-influenced) provides for normal operations on a register machine, 
+  # Example:  pop -> StackInstruction.new( {:opcode => :pop}.merge(options) )
+  # Instructions work with options, so you can pass anything in, and the only thing the functions does
+  # is save you typing the clazz.new. It passes the function name as the :opcode
+   
   class Machine
   
     # hmm, not pretty but for now
@@ -32,6 +36,51 @@ module Vm
     # consistency in this code, but also because that is what is actually done
     attr_reader :status  
 
+    
+    # here we create the shortcuts for the "standard" instructions, see above
+    # Derived machines may use own instructions and define functions for them if so desired
+    def initialize
+      [:push, :pop].each do |inst|
+        define_instruction(inst , StackInstruction)
+      end
+
+      [:adc, :add, :and, :bic, :eor, :orr, :rsb, :rsc, :sbc, :sub].each do |inst|
+        define_instruction(inst , LogicInstruction)
+      end
+      [:mov, :mvn].each do |inst|
+        define_instruction(inst , MoveInstruction)
+      end
+      [:cmn, :cmp, :teq, :tst].each do |inst|
+        define_instruction(inst , CompareInstruction)
+      end
+      [:strb, :str , :ldrb, :ldr].each do |inst|
+        define_instruction(inst , MemoryInstruction)
+      end
+      [:b, :bl , :swi].each do |inst|
+        define_instruction(inst , CallInstruction)
+      end
+  
+    end
+
+    def create_method(name,  &block)
+        self.class.send(:define_method, name , &block)
+    end
+
+    def define_instruction(inst , clazz )
+      c_name = clazz.name
+      my_module = self.class.name.split("::").first
+      clazz_name = clazz.name.split("::").last
+      if(my_module != Vm )
+        module_class = eval("#{my_module}::#{clazz_name}") rescue nil
+        clazz = module_class if module_class
+      end
+      create_method(inst) do |options|
+        options = {} if options == nil
+        options[:opcode] = inst
+        clazz.new(options)
+      end
+    end
+
     def self.instance
       @@instance
     end

test/test_runner.rb

@@ -21,8 +21,6 @@ class TestRunner < MiniTest::Test
     syntax    = Parser::Composed.new.parse(string)
     tree      = Parser::Transform.new.apply(syntax)
     
-    puts tree.to_yaml
-
     program = Vm::Program.new "Arm"
     expression = tree.to_value
     compiled = expression.compile( program.context )
@@ -30,7 +28,7 @@ class TestRunner < MiniTest::Test
     program.wrap_as_main compiled
     puts program.to_yaml
     program.verify
-    puts program.to_yaml
+#    puts program.to_yaml
   end
 
 end