diff --git a/docs/tutorial/OCamlLangImpl3.html b/docs/tutorial/OCamlLangImpl3.html index 0edc726480c..079ab1c2b49 100644 --- a/docs/tutorial/OCamlLangImpl3.html +++ b/docs/tutorial/OCamlLangImpl3.html @@ -183,7 +183,7 @@ variables.

let i = build_fcmp Fcmp.Ult lhs_val rhs_val "cmptmp" builder in build_uitofp i double_type "booltmp" builder | _ -> raise (Error "invalid binary operator") - end + end @@ -280,7 +280,7 @@ let codegen_proto = function (* Make the function type: double(double,double) etc. *) let doubles = Array.make (Array.length args) double_type in let ft = function_type double_type doubles in - let f = + let f = match lookup_function name the_module with diff --git a/docs/tutorial/OCamlLangImpl4.html b/docs/tutorial/OCamlLangImpl4.html index fc1caeb1f20..4e267b80f57 100644 --- a/docs/tutorial/OCamlLangImpl4.html +++ b/docs/tutorial/OCamlLangImpl4.html @@ -237,7 +237,7 @@ We do this by running it after our newly created function is constructed (in 
 let codegen_func the_fpm = function
-			...
+      ...
       try
         let ret_val = codegen_expr body in
 
@@ -316,10 +316,9 @@ by adding a global variable and a call in main:

 ...
 let main () =
   ...
-	
-  (* Create the JIT. *)
+  (* Create the JIT. *)
   let the_module_provider = ModuleProvider.create Codegen.the_module in
-	let the_execution_engine = ExecutionEngine.create the_module_provider in
+  let the_execution_engine = ExecutionEngine.create the_module_provider in
   ...
@@ -508,6 +507,17 @@ Here is the complete code listing for our running example, enhanced with the LLVM JIT and optimizer. To build this example, use:

+
+
+# Compile
+ocamlbuild toy.byte
+# Run
+./toy.byte
+
+
+ +

Here is the code:

+
_tags:
diff --git a/docs/tutorial/OCamlLangImpl5.html b/docs/tutorial/OCamlLangImpl5.html new file mode 100644 index 00000000000..ba8c2f791db --- /dev/null +++ b/docs/tutorial/OCamlLangImpl5.html @@ -0,0 +1,1564 @@ + + + + + Kaleidoscope: Extending the Language: Control Flow + + + + + + + + +
Kaleidoscope: Extending the Language: Control Flow
+ + + +
+

+ Written by Chris Lattner + and Erick Tryzelaar +

+
+ + +
Chapter 5 Introduction
+ + +
+ +

Welcome to Chapter 5 of the "Implementing a language +with LLVM" tutorial. Parts 1-4 described the implementation of the simple +Kaleidoscope language and included support for generating LLVM IR, followed by +optimizations and a JIT compiler. Unfortunately, as presented, Kaleidoscope is +mostly useless: it has no control flow other than call and return. This means +that you can't have conditional branches in the code, significantly limiting its +power. In this episode of "build that compiler", we'll extend Kaleidoscope to +have an if/then/else expression plus a simple 'for' loop.

+ +
+ + +
If/Then/Else
+ + +
+ +

+Extending Kaleidoscope to support if/then/else is quite straightforward. It +basically requires adding lexer support for this "new" concept to the lexer, +parser, AST, and LLVM code emitter. This example is nice, because it shows how +easy it is to "grow" a language over time, incrementally extending it as new +ideas are discovered.

+ +

Before we get going on "how" we add this extension, lets talk about "what" we +want. The basic idea is that we want to be able to write this sort of thing: +

+ +
+
+def fib(x)
+  if x < 3 then
+    1
+  else
+    fib(x-1)+fib(x-2);
+
+
+ +

In Kaleidoscope, every construct is an expression: there are no statements. +As such, the if/then/else expression needs to return a value like any other. +Since we're using a mostly functional form, we'll have it evaluate its +conditional, then return the 'then' or 'else' value based on how the condition +was resolved. This is very similar to the C "?:" expression.

+ +

The semantics of the if/then/else expression is that it evaluates the +condition to a boolean equality value: 0.0 is considered to be false and +everything else is considered to be true. +If the condition is true, the first subexpression is evaluated and returned, if +the condition is false, the second subexpression is evaluated and returned. +Since Kaleidoscope allows side-effects, this behavior is important to nail down. +

+ +

Now that we know what we "want", lets break this down into its constituent +pieces.

+ +
+ + +
Lexer Extensions for +If/Then/Else
+ + + +
+ +

The lexer extensions are straightforward. First we add new variants +for the relevant tokens:

+ +
+
+  (* control *)
+  | If | Then | Else | For | In
+
+
+ +

Once we have that, we recognize the new keywords in the lexer. This is pretty simple +stuff:

+ +
+
+      ...
+      match Buffer.contents buffer with
+      | "def" -> [< 'Token.Def; stream >]
+      | "extern" -> [< 'Token.Extern; stream >]
+      | "if" -> [< 'Token.If; stream >]
+      | "then" -> [< 'Token.Then; stream >]
+      | "else" -> [< 'Token.Else; stream >]
+      | "for" -> [< 'Token.For; stream >]
+      | "in" -> [< 'Token.In; stream >]
+      | id -> [< 'Token.Ident id; stream >]
+
+
+ +
+ + +
AST Extensions for + If/Then/Else
+ + +
+ +

To represent the new expression we add a new AST variant for it:

+ +
+
+type expr =
+  ...
+  (* variant for if/then/else. *)
+  | If of expr * expr * expr
+
+
+ +

The AST variant just has pointers to the various subexpressions.

+ +
+ + +
Parser Extensions for +If/Then/Else
+ + +
+ +

Now that we have the relevant tokens coming from the lexer and we have the +AST node to build, our parsing logic is relatively straightforward. First we +define a new parsing function:

+ +
+
+let rec parse_primary = parser
+  ...
+  (* ifexpr ::= 'if' expr 'then' expr 'else' expr *)
+  | [< 'Token.If; c=parse_expr;
+       'Token.Then ?? "expected 'then'"; t=parse_expr;
+       'Token.Else ?? "expected 'else'"; e=parse_expr >] ->
+      Ast.If (c, t, e)
+
+
+ +

Next we hook it up as a primary expression:

+ +
+
+let rec parse_primary = parser
+  ...
+  (* ifexpr ::= 'if' expr 'then' expr 'else' expr *)
+  | [< 'Token.If; c=parse_expr;
+       'Token.Then ?? "expected 'then'"; t=parse_expr;
+       'Token.Else ?? "expected 'else'"; e=parse_expr >] ->
+      Ast.If (c, t, e)
+
+
+ +
+ + +
LLVM IR for If/Then/Else
+ + +
+ +

Now that we have it parsing and building the AST, the final piece is adding +LLVM code generation support. This is the most interesting part of the +if/then/else example, because this is where it starts to introduce new concepts. +All of the code above has been thoroughly described in previous chapters. +

+ +

To motivate the code we want to produce, lets take a look at a simple +example. Consider:

+ +
+
+extern foo();
+extern bar();
+def baz(x) if x then foo() else bar();
+
+
+ +

If you disable optimizations, the code you'll (soon) get from Kaleidoscope +looks like this:

+ +
+
+declare double @foo()
+
+declare double @bar()
+
+define double @baz(double %x) {
+entry:
+  %ifcond = fcmp one double %x, 0.000000e+00
+  br i1 %ifcond, label %then, label %else
+
+then:    ; preds = %entry
+  %calltmp = call double @foo()
+  br label %ifcont
+
+else:    ; preds = %entry
+  %calltmp1 = call double @bar()
+  br label %ifcont
+
+ifcont:    ; preds = %else, %then
+  %iftmp = phi double [ %calltmp, %then ], [ %calltmp1, %else ]
+  ret double %iftmp
+}
+
+
+ +

To visualize the control flow graph, you can use a nifty feature of the LLVM +'opt' tool. If you put this LLVM IR +into "t.ll" and run "llvm-as < t.ll | opt -analyze -view-cfg", a window will pop up and you'll +see this graph:

+ +
Example CFG
+ +

Another way to get this is to call "Llvm_analysis.view_function_cfg +f" or "Llvm_analysis.view_function_cfg_only f" (where f +is a "Function") either by inserting actual calls into the code and +recompiling or by calling these in the debugger. LLVM has many nice features +for visualizing various graphs.

+ +

Getting back to the generated code, it is fairly simple: the entry block +evaluates the conditional expression ("x" in our case here) and compares the +result to 0.0 with the "fcmp one" +instruction ('one' is "Ordered and Not Equal"). Based on the result of this +expression, the code jumps to either the "then" or "else" blocks, which contain +the expressions for the true/false cases.

+ +

Once the then/else blocks are finished executing, they both branch back to the +'ifcont' block to execute the code that happens after the if/then/else. In this +case the only thing left to do is to return to the caller of the function. The +question then becomes: how does the code know which expression to return?

+ +

The answer to this question involves an important SSA operation: the +Phi +operation. If you're not familiar with SSA, the wikipedia +article is a good introduction and there are various other introductions to +it available on your favorite search engine. The short version is that +"execution" of the Phi operation requires "remembering" which block control came +from. The Phi operation takes on the value corresponding to the input control +block. In this case, if control comes in from the "then" block, it gets the +value of "calltmp". If control comes from the "else" block, it gets the value +of "calltmp1".

+ +

At this point, you are probably starting to think "Oh no! This means my +simple and elegant front-end will have to start generating SSA form in order to +use LLVM!". Fortunately, this is not the case, and we strongly advise +not implementing an SSA construction algorithm in your front-end +unless there is an amazingly good reason to do so. In practice, there are two +sorts of values that float around in code written for your average imperative +programming language that might need Phi nodes:

+ +
    +
  1. Code that involves user variables: x = 1; x = x + 1;
    2. +
  2. Values that are implicit in the structure of your AST, such as the Phi node +in this case.
    3. +
+ +

In Chapter 7 of this tutorial ("mutable +variables"), we'll talk about #1 +in depth. For now, just believe me that you don't need SSA construction to +handle this case. For #2, you have the choice of using the techniques that we will +describe for #1, or you can insert Phi nodes directly, if convenient. In this +case, it is really really easy to generate the Phi node, so we choose to do it +directly.

+ +

Okay, enough of the motivation and overview, lets generate code!

+ +
+ + +
Code Generation for +If/Then/Else
+ + +
+ +

In order to generate code for this, we implement the Codegen method +for IfExprAST:

+ +
+
+let rec codegen_expr = function
+  ...
+  | Ast.If (cond, then_, else_) ->
+      let cond = codegen_expr cond in
+
+      (* Convert condition to a bool by comparing equal to 0.0 *)
+      let zero = const_float double_type 0.0 in
+      let cond_val = build_fcmp Fcmp.One cond zero "ifcond" builder in
+
+
+ +

This code is straightforward and similar to what we saw before. We emit the +expression for the condition, then compare that value to zero to get a truth +value as a 1-bit (bool) value.

+ +
+
+      (* Grab the first block so that we might later add the conditional branch
+       * to it at the end of the function. *)
+      let start_bb = insertion_block builder in
+      let the_function = block_parent start_bb in
+
+      let then_bb = append_block "then" the_function in
+      position_at_end then_bb builder;
+
+
+ +

+As opposed to the C++ tutorial, we have to build +our basic blocks bottom up since we can't have dangling BasicBlocks. We start +off by saving a pointer to the first block (which might not be the entry +block), which we'll need to build a conditional branch later. We do this by +asking the builder for the current BasicBlock. The fourth line +gets the current Function object that is being built. It gets this by the +start_bb for its "parent" (the function it is currently embedded +into).

+ +

Once it has that, it creates one block. It is automatically appended into +the function's list of blocks.

+ +
+
+      (* Emit 'then' value. *)
+      position_at_end then_bb builder;
+      let then_val = codegen_expr then_ in
+
+      (* Codegen of 'then' can change the current block, update then_bb for the
+       * phi. We create a new name because one is used for the phi node, and the
+       * other is used for the conditional branch. *)
+      let new_then_bb = insertion_block builder in
+
+
+ +

We move the builder to start inserting into the "then" block. Strictly +speaking, this call moves the insertion point to be at the end of the specified +block. However, since the "then" block is empty, it also starts out by +inserting at the beginning of the block. :)

+ +

Once the insertion point is set, we recursively codegen the "then" expression +from the AST.

+ +

The final line here is quite subtle, but is very important. The basic issue +is that when we create the Phi node in the merge block, we need to set up the +block/value pairs that indicate how the Phi will work. Importantly, the Phi +node expects to have an entry for each predecessor of the block in the CFG. Why +then, are we getting the current block when we just set it to ThenBB 5 lines +above? The problem is that the "Then" expression may actually itself change the +block that the Builder is emitting into if, for example, it contains a nested +"if/then/else" expression. Because calling Codegen recursively could +arbitrarily change the notion of the current block, we are required to get an +up-to-date value for code that will set up the Phi node.

+ +
+
+      (* Emit 'else' value. *)
+      let else_bb = append_block "else" the_function in
+      position_at_end else_bb builder;
+      let else_val = codegen_expr else_ in
+
+      (* Codegen of 'else' can change the current block, update else_bb for the
+       * phi. *)
+      let new_else_bb = insertion_block builder in
+
+
+ +

Code generation for the 'else' block is basically identical to codegen for +the 'then' block.

+ +
+
+      (* Emit merge block. *)
+      let merge_bb = append_block "ifcont" the_function in
+      position_at_end merge_bb builder;
+      let incoming = [(then_val, new_then_bb); (else_val, new_else_bb)] in
+      let phi = build_phi incoming "iftmp" builder in
+
+
+ +

The first two lines here are now familiar: the first adds the "merge" block +to the Function object. The second block changes the insertion point so that +newly created code will go into the "merge" block. Once that is done, we need +to create the PHI node and set up the block/value pairs for the PHI.

+ +
+
+      (* Return to the start block to add the conditional branch. *)
+      position_at_end start_bb builder;
+      ignore (build_cond_br cond_val then_bb else_bb builder);
+
+
+ +

Once the blocks are created, we can emit the conditional branch that chooses +between them. Note that creating new blocks does not implicitly affect the +LLVMBuilder, so it is still inserting into the block that the condition +went into. This is why we needed to save the "start" block.

+ +
+
+      (* Set a unconditional branch at the end of the 'then' block and the
+       * 'else' block to the 'merge' block. *)
+      position_at_end new_then_bb builder; ignore (build_br merge_bb builder);
+      position_at_end new_else_bb builder; ignore (build_br merge_bb builder);
+
+      (* Finally, set the builder to the end of the merge block. *)
+      position_at_end merge_bb builder;
+
+      phi
+
+
+ +

To finish off the blocks, we create an unconditional branch +to the merge block. One interesting (and very important) aspect of the LLVM IR +is that it requires all basic blocks +to be "terminated" with a control flow +instruction such as return or branch. This means that all control flow, +including fall throughs must be made explicit in the LLVM IR. If you +violate this rule, the verifier will emit an error. + +

Finally, the CodeGen function returns the phi node as the value computed by +the if/then/else expression. In our example above, this returned value will +feed into the code for the top-level function, which will create the return +instruction.

+ +

Overall, we now have the ability to execute conditional code in +Kaleidoscope. With this extension, Kaleidoscope is a fairly complete language +that can calculate a wide variety of numeric functions. Next up we'll add +another useful expression that is familiar from non-functional languages...

+ +
+ + +
'for' Loop Expression
+ + +
+ +

Now that we know how to add basic control flow constructs to the language, +we have the tools to add more powerful things. Lets add something more +aggressive, a 'for' expression:

+ +
+
+ extern putchard(char);
+ def printstar(n)
+   for i = 1, i < n, 1.0 in
+     putchard(42);  # ascii 42 = '*'
+
+ # print 100 '*' characters
+ printstar(100);
+
+
+ +

This expression defines a new variable ("i" in this case) which iterates from +a starting value, while the condition ("i < n" in this case) is true, +incrementing by an optional step value ("1.0" in this case). If the step value +is omitted, it defaults to 1.0. While the loop is true, it executes its +body expression. Because we don't have anything better to return, we'll just +define the loop as always returning 0.0. In the future when we have mutable +variables, it will get more useful.

+ +

As before, lets talk about the changes that we need to Kaleidoscope to +support this.

+ +
+ + +
Lexer Extensions for +the 'for' Loop
+ + +
+ +

The lexer extensions are the same sort of thing as for if/then/else:

+ +
+
+  ... in Token.token ...
+  (* control *)
+  | If | Then | Else
+  | For | In
+
+  ... in Lexer.lex_ident...
+      match Buffer.contents buffer with
+      | "def" -> [< 'Token.Def; stream >]
+      | "extern" -> [< 'Token.Extern; stream >]
+      | "if" -> [< 'Token.If; stream >]
+      | "then" -> [< 'Token.Then; stream >]
+      | "else" -> [< 'Token.Else; stream >]
+      | "for" -> [< 'Token.For; stream >]
+      | "in" -> [< 'Token.In; stream >]
+      | id -> [< 'Token.Ident id; stream >]
+
+
+ +
+ + +
AST Extensions for +the 'for' Loop
+ + +
+ +

The AST variant is just as simple. It basically boils down to capturing +the variable name and the constituent expressions in the node.

+ +
+
+type expr =
+  ...
+  (* variant for for/in. *)
+  | For of string * expr * expr * expr option * expr
+
+
+ +
+ + +
Parser Extensions for +the 'for' Loop
+ + +
+ +

The parser code is also fairly standard. The only interesting thing here is +handling of the optional step value. The parser code handles it by checking to +see if the second comma is present. If not, it sets the step value to null in +the AST node:

+ +
+
+let rec parse_primary = parser
+  ...
+  (* forexpr
+        ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression *)
+  | [< 'Token.For;
+       'Token.Ident id ?? "expected identifier after for";
+       'Token.Kwd '=' ?? "expected '=' after for";
+       stream >] ->
+      begin parser
+        | [<
+             start=parse_expr;
+             'Token.Kwd ',' ?? "expected ',' after for";
+             end_=parse_expr;
+             stream >] ->
+            let step =
+              begin parser
+              | [< 'Token.Kwd ','; step=parse_expr >] -> Some step
+              | [< >] -> None
+              end stream
+            in
+            begin parser
+            | [< 'Token.In; body=parse_expr >] ->
+                Ast.For (id, start, end_, step, body)
+            | [< >] ->
+                raise (Stream.Error "expected 'in' after for")
+            end stream
+        | [< >] ->
+            raise (Stream.Error "expected '=' after for")
+      end stream
+
+
+ +
+ + +
LLVM IR for +the 'for' Loop
+ + +
+ +

Now we get to the good part: the LLVM IR we want to generate for this thing. +With the simple example above, we get this LLVM IR (note that this dump is +generated with optimizations disabled for clarity): +

+ +
+
+declare double @putchard(double)
+
+define double @printstar(double %n) {
+entry:
+        ; initial value = 1.0 (inlined into phi)
+  br label %loop
+
+loop:    ; preds = %loop, %entry
+  %i = phi double [ 1.000000e+00, %entry ], [ %nextvar, %loop ]
+        ; body
+  %calltmp = call double @putchard( double 4.200000e+01 )
+        ; increment
+  %nextvar = add double %i, 1.000000e+00
+
+        ; termination test
+  %cmptmp = fcmp ult double %i, %n
+  %booltmp = uitofp i1 %cmptmp to double
+  %loopcond = fcmp one double %booltmp, 0.000000e+00
+  br i1 %loopcond, label %loop, label %afterloop
+
+afterloop:    ; preds = %loop
+        ; loop always returns 0.0
+  ret double 0.000000e+00
+}
+
+
+ +

This loop contains all the same constructs we saw before: a phi node, several +expressions, and some basic blocks. Lets see how this fits together.

+ +
+ + +
Code Generation for +the 'for' Loop
+ + +
+ +

The first part of Codegen is very simple: we just output the start expression +for the loop value:

+ +
+
+let rec codegen_expr = function
+  ...
+  | Ast.For (var_name, start, end_, step, body) ->
+      (* Emit the start code first, without 'variable' in scope. *)
+      let start_val = codegen_expr start in
+
+
+ +

With this out of the way, the next step is to set up the LLVM basic block +for the start of the loop body. In the case above, the whole loop body is one +block, but remember that the body code itself could consist of multiple blocks +(e.g. if it contains an if/then/else or a for/in expression).

+ +
+
+      (* Make the new basic block for the loop header, inserting after current
+       * block. *)
+      let preheader_bb = insertion_block builder in
+      let the_function = block_parent preheader_bb in
+      let loop_bb = append_block "loop" the_function in
+
+      (* Insert an explicit fall through from the current block to the
+       * loop_bb. *)
+      ignore (build_br loop_bb builder);
+
+
+ +

This code is similar to what we saw for if/then/else. Because we will need +it to create the Phi node, we remember the block that falls through into the +loop. Once we have that, we create the actual block that starts the loop and +create an unconditional branch for the fall-through between the two blocks.

+ +
+
+      (* Start insertion in loop_bb. *)
+      position_at_end loop_bb builder;
+
+      (* Start the PHI node with an entry for start. *)
+      let variable = build_phi [(start_val, preheader_bb)] var_name builder in
+
+
+ +

Now that the "preheader" for the loop is set up, we switch to emitting code +for the loop body. To begin with, we move the insertion point and create the +PHI node for the loop induction variable. Since we already know the incoming +value for the starting value, we add it to the Phi node. Note that the Phi will +eventually get a second value for the backedge, but we can't set it up yet +(because it doesn't exist!).

+ +
+
+      (* Within the loop, the variable is defined equal to the PHI node. If it
+       * shadows an existing variable, we have to restore it, so save it
+       * now. *)
+      let old_val =
+        try Some (Hashtbl.find named_values var_name) with Not_found -> None
+      in
+      Hashtbl.add named_values var_name variable;
+
+      (* Emit the body of the loop.  This, like any other expr, can change the
+       * current BB.  Note that we ignore the value computed by the body, but
+       * don't allow an error *)
+      ignore (codegen_expr body);
+
+
+ +

Now the code starts to get more interesting. Our 'for' loop introduces a new +variable to the symbol table. This means that our symbol table can now contain +either function arguments or loop variables. To handle this, before we codegen +the body of the loop, we add the loop variable as the current value for its +name. Note that it is possible that there is a variable of the same name in the +outer scope. It would be easy to make this an error (emit an error and return +null if there is already an entry for VarName) but we choose to allow shadowing +of variables. In order to handle this correctly, we remember the Value that +we are potentially shadowing in old_val (which will be None if there is +no shadowed variable).

+ +

Once the loop variable is set into the symbol table, the code recursively +codegen's the body. This allows the body to use the loop variable: any +references to it will naturally find it in the symbol table.

+ +
+
+      (* Emit the step value. *)
+      let step_val =
+        match step with
+        | Some step -> codegen_expr step
+        (* If not specified, use 1.0. *)
+        | None -> const_float double_type 1.0
+      in
+
+      let next_var = build_add variable step_val "nextvar" builder in
+
+
+ +

Now that the body is emitted, we compute the next value of the iteration +variable by adding the step value, or 1.0 if it isn't present. +'next_var' will be the value of the loop variable on the next iteration +of the loop.

+ +
+
+      (* Compute the end condition. *)
+      let end_cond = codegen_expr end_ in
+
+      (* Convert condition to a bool by comparing equal to 0.0. *)
+      let zero = const_float double_type 0.0 in
+      let end_cond = build_fcmp Fcmp.One end_cond zero "loopcond" builder in
+
+
+ +

Finally, we evaluate the exit value of the loop, to determine whether the +loop should exit. This mirrors the condition evaluation for the if/then/else +statement.

+ +
+
+      (* Create the "after loop" block and insert it. *)
+      let loop_end_bb = insertion_block builder in
+      let after_bb = append_block "afterloop" the_function in
+
+      (* Insert the conditional branch into the end of loop_end_bb. *)
+      ignore (build_cond_br end_cond loop_bb after_bb builder);
+
+      (* Any new code will be inserted in after_bb. *)
+      position_at_end after_bb builder;
+
+
+ +

With the code for the body of the loop complete, we just need to finish up +the control flow for it. This code remembers the end block (for the phi node), then creates the block for the loop exit ("afterloop"). Based on the value of the +exit condition, it creates a conditional branch that chooses between executing +the loop again and exiting the loop. Any future code is emitted in the +"afterloop" block, so it sets the insertion position to it.

+ +
+
+      (* Add a new entry to the PHI node for the backedge. *)
+      add_incoming (next_var, loop_end_bb) variable;
+
+      (* Restore the unshadowed variable. *)
+      begin match old_val with
+      | Some old_val -> Hashtbl.add named_values var_name old_val
+      | None -> ()
+      end;
+
+      (* for expr always returns 0.0. *)
+      const_null double_type
+
+
+ +

The final code handles various cleanups: now that we have the +"next_var" value, we can add the incoming value to the loop PHI node. +After that, we remove the loop variable from the symbol table, so that it isn't +in scope after the for loop. Finally, code generation of the for loop always +returns 0.0, so that is what we return from Codegen.codegen_expr.

+ +

With this, we conclude the "adding control flow to Kaleidoscope" chapter of +the tutorial. In this chapter we added two control flow constructs, and used +them to motivate a couple of aspects of the LLVM IR that are important for +front-end implementors to know. In the next chapter of our saga, we will get +a bit crazier and add user-defined operators +to our poor innocent language.

+ +
+ + +
Full Code Listing
+ + +
+ +

+Here is the complete code listing for our running example, enhanced with the +if/then/else and for expressions.. To build this example, use: +

+ +
+
+# Compile
+ocamlbuild toy.byte
+# Run
+./toy.byte
+
+
+ +

Here is the code:

+ +
+
_tags:
+
+
+<{lexer,parser}.ml>: use_camlp4, pp(camlp4of)
+<*.{byte,native}>: g++, use_llvm, use_llvm_analysis
+<*.{byte,native}>: use_llvm_executionengine, use_llvm_target
+<*.{byte,native}>: use_llvm_scalar_opts, use_bindings
+
+
+ +
myocamlbuild.ml:
+
+
+open Ocamlbuild_plugin;;
+
+ocaml_lib ~extern:true "llvm";;
+ocaml_lib ~extern:true "llvm_analysis";;
+ocaml_lib ~extern:true "llvm_executionengine";;
+ocaml_lib ~extern:true "llvm_target";;
+ocaml_lib ~extern:true "llvm_scalar_opts";;
+
+flag ["link"; "ocaml"; "g++"] (S[A"-cc"; A"g++"]);;
+dep ["link"; "ocaml"; "use_bindings"] ["bindings.o"];;
+
+
+ +
token.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Lexer Tokens
+ *===----------------------------------------------------------------------===*)
+
+(* The lexer returns these 'Kwd' if it is an unknown character, otherwise one of
+ * these others for known things. *)
+type token =
+  (* commands *)
+  | Def | Extern
+
+  (* primary *)
+  | Ident of string | Number of float
+
+  (* unknown *)
+  | Kwd of char
+
+  (* control *)
+  | If | Then | Else
+  | For | In
+
+
+ +
lexer.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Lexer
+ *===----------------------------------------------------------------------===*)
+
+let rec lex = parser
+  (* Skip any whitespace. *)
+  | [< ' (' ' | '\n' | '\r' | '\t'); stream >] -> lex stream
+
+  (* identifier: [a-zA-Z][a-zA-Z0-9] *)
+  | [< ' ('A' .. 'Z' | 'a' .. 'z' as c); stream >] ->
+      let buffer = Buffer.create 1 in
+      Buffer.add_char buffer c;
+      lex_ident buffer stream
+
+  (* number: [0-9.]+ *)
+  | [< ' ('0' .. '9' as c); stream >] ->
+      let buffer = Buffer.create 1 in
+      Buffer.add_char buffer c;
+      lex_number buffer stream
+
+  (* Comment until end of line. *)
+  | [< ' ('#'); stream >] ->
+      lex_comment stream
+
+  (* Otherwise, just return the character as its ascii value. *)
+  | [< 'c; stream >] ->
+      [< 'Token.Kwd c; lex stream >]
+
+  (* end of stream. *)
+  | [< >] -> [< >]
+
+and lex_number buffer = parser
+  | [< ' ('0' .. '9' | '.' as c); stream >] ->
+      Buffer.add_char buffer c;
+      lex_number buffer stream
+  | [< stream=lex >] ->
+      [< 'Token.Number (float_of_string (Buffer.contents buffer)); stream >]
+
+and lex_ident buffer = parser
+  | [< ' ('A' .. 'Z' | 'a' .. 'z' | '0' .. '9' as c); stream >] ->
+      Buffer.add_char buffer c;
+      lex_ident buffer stream
+  | [< stream=lex >] ->
+      match Buffer.contents buffer with
+      | "def" -> [< 'Token.Def; stream >]
+      | "extern" -> [< 'Token.Extern; stream >]
+      | "if" -> [< 'Token.If; stream >]
+      | "then" -> [< 'Token.Then; stream >]
+      | "else" -> [< 'Token.Else; stream >]
+      | "for" -> [< 'Token.For; stream >]
+      | "in" -> [< 'Token.In; stream >]
+      | id -> [< 'Token.Ident id; stream >]
+
+and lex_comment = parser
+  | [< ' ('\n'); stream=lex >] -> stream
+  | [< 'c; e=lex_comment >] -> e
+  | [< >] -> [< >]
+
+
+ +
ast.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Abstract Syntax Tree (aka Parse Tree)
+ *===----------------------------------------------------------------------===*)
+
+(* expr - Base type for all expression nodes. *)
+type expr =
+  (* variant for numeric literals like "1.0". *)
+  | Number of float
+
+  (* variant for referencing a variable, like "a". *)
+  | Variable of string
+
+  (* variant for a binary operator. *)
+  | Binary of char * expr * expr
+
+  (* variant for function calls. *)
+  | Call of string * expr array
+
+  (* variant for if/then/else. *)
+  | If of expr * expr * expr
+
+  (* variant for for/in. *)
+  | For of string * expr * expr * expr option * expr
+
+(* proto - This type represents the "prototype" for a function, which captures
+ * its name, and its argument names (thus implicitly the number of arguments the
+ * function takes). *)
+type proto = Prototype of string * string array
+
+(* func - This type represents a function definition itself. *)
+type func = Function of proto * expr
+
+
+ +
parser.ml:
+
+
+(*===---------------------------------------------------------------------===
+ * Parser
+ *===---------------------------------------------------------------------===*)
+
+(* binop_precedence - This holds the precedence for each binary operator that is
+ * defined *)
+let binop_precedence:(char, int) Hashtbl.t = Hashtbl.create 10
+
+(* precedence - Get the precedence of the pending binary operator token. *)
+let precedence c = try Hashtbl.find binop_precedence c with Not_found -> -1
+
+(* primary
+ *   ::= identifier
+ *   ::= numberexpr
+ *   ::= parenexpr
+ *   ::= ifexpr
+ *   ::= forexpr *)
+let rec parse_primary = parser
+  (* numberexpr ::= number *)
+  | [< 'Token.Number n >] -> Ast.Number n
+
+  (* parenexpr ::= '(' expression ')' *)
+  | [< 'Token.Kwd '('; e=parse_expr; 'Token.Kwd ')' ?? "expected ')'" >] -> e
+
+  (* identifierexpr
+   *   ::= identifier
+   *   ::= identifier '(' argumentexpr ')' *)
+  | [< 'Token.Ident id; stream >] ->
+      let rec parse_args accumulator = parser
+        | [< e=parse_expr; stream >] ->
+            begin parser
+              | [< 'Token.Kwd ','; e=parse_args (e :: accumulator) >] -> e
+              | [< >] -> e :: accumulator
+            end stream
+        | [< >] -> accumulator
+      in
+      let rec parse_ident id = parser
+        (* Call. *)
+        | [< 'Token.Kwd '(';
+             args=parse_args [];
+             'Token.Kwd ')' ?? "expected ')'">] ->
+            Ast.Call (id, Array.of_list (List.rev args))
+
+        (* Simple variable ref. *)
+        | [< >] -> Ast.Variable id
+      in
+      parse_ident id stream
+
+  (* ifexpr ::= 'if' expr 'then' expr 'else' expr *)
+  | [< 'Token.If; c=parse_expr;
+       'Token.Then ?? "expected 'then'"; t=parse_expr;
+       'Token.Else ?? "expected 'else'"; e=parse_expr >] ->
+      Ast.If (c, t, e)
+
+  (* forexpr
+        ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression *)
+  | [< 'Token.For;
+       'Token.Ident id ?? "expected identifier after for";
+       'Token.Kwd '=' ?? "expected '=' after for";
+       stream >] ->
+      begin parser
+        | [<
+             start=parse_expr;
+             'Token.Kwd ',' ?? "expected ',' after for";
+             end_=parse_expr;
+             stream >] ->
+            let step =
+              begin parser
+              | [< 'Token.Kwd ','; step=parse_expr >] -> Some step
+              | [< >] -> None
+              end stream
+            in
+            begin parser
+            | [< 'Token.In; body=parse_expr >] ->
+                Ast.For (id, start, end_, step, body)
+            | [< >] ->
+                raise (Stream.Error "expected 'in' after for")
+            end stream
+        | [< >] ->
+            raise (Stream.Error "expected '=' after for")
+      end stream
+
+  | [< >] -> raise (Stream.Error "unknown token when expecting an expression.")
+
+(* binoprhs
+ *   ::= ('+' primary)* *)
+and parse_bin_rhs expr_prec lhs stream =
+  match Stream.peek stream with
+  (* If this is a binop, find its precedence. *)
+  | Some (Token.Kwd c) when Hashtbl.mem binop_precedence c ->
+      let token_prec = precedence c in
+
+      (* If this is a binop that binds at least as tightly as the current binop,
+       * consume it, otherwise we are done. *)
+      if token_prec < expr_prec then lhs else begin
+        (* Eat the binop. *)
+        Stream.junk stream;
+
+        (* Parse the primary expression after the binary operator. *)
+        let rhs = parse_primary stream in
+
+        (* Okay, we know this is a binop. *)
+        let rhs =
+          match Stream.peek stream with
+          | Some (Token.Kwd c2) ->
+              (* If BinOp binds less tightly with rhs than the operator after
+               * rhs, let the pending operator take rhs as its lhs. *)
+              let next_prec = precedence c2 in
+              if token_prec < next_prec
+              then parse_bin_rhs (token_prec + 1) rhs stream
+              else rhs
+          | _ -> rhs
+        in
+
+        (* Merge lhs/rhs. *)
+        let lhs = Ast.Binary (c, lhs, rhs) in
+        parse_bin_rhs expr_prec lhs stream
+      end
+  | _ -> lhs
+
+(* expression
+ *   ::= primary binoprhs *)
+and parse_expr = parser
+  | [< lhs=parse_primary; stream >] -> parse_bin_rhs 0 lhs stream
+
+(* prototype
+ *   ::= id '(' id* ')' *)
+let parse_prototype =
+  let rec parse_args accumulator = parser
+    | [< 'Token.Ident id; e=parse_args (id::accumulator) >] -> e
+    | [< >] -> accumulator
+  in
+
+  parser
+  | [< 'Token.Ident id;
+       'Token.Kwd '(' ?? "expected '(' in prototype";
+       args=parse_args [];
+       'Token.Kwd ')' ?? "expected ')' in prototype" >] ->
+      (* success. *)
+      Ast.Prototype (id, Array.of_list (List.rev args))
+
+  | [< >] ->
+      raise (Stream.Error "expected function name in prototype")
+
+(* definition ::= 'def' prototype expression *)
+let parse_definition = parser
+  | [< 'Token.Def; p=parse_prototype; e=parse_expr >] ->
+      Ast.Function (p, e)
+
+(* toplevelexpr ::= expression *)
+let parse_toplevel = parser
+  | [< e=parse_expr >] ->
+      (* Make an anonymous proto. *)
+      Ast.Function (Ast.Prototype ("", [||]), e)
+
+(*  external ::= 'extern' prototype *)
+let parse_extern = parser
+  | [< 'Token.Extern; e=parse_prototype >] -> e
+
+
+ +
codegen.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Code Generation
+ *===----------------------------------------------------------------------===*)
+
+open Llvm
+
+exception Error of string
+
+let the_module = create_module "my cool jit"
+let builder = builder ()
+let named_values:(string, llvalue) Hashtbl.t = Hashtbl.create 10
+
+let rec codegen_expr = function
+  | Ast.Number n -> const_float double_type n
+  | Ast.Variable name ->
+      (try Hashtbl.find named_values name with
+        | Not_found -> raise (Error "unknown variable name"))
+  | Ast.Binary (op, lhs, rhs) ->
+      let lhs_val = codegen_expr lhs in
+      let rhs_val = codegen_expr rhs in
+      begin
+        match op with
+        | '+' -> build_add lhs_val rhs_val "addtmp" builder
+        | '-' -> build_sub lhs_val rhs_val "subtmp" builder
+        | '*' -> build_mul lhs_val rhs_val "multmp" builder
+        | '<' ->
+            (* Convert bool 0/1 to double 0.0 or 1.0 *)
+            let i = build_fcmp Fcmp.Ult lhs_val rhs_val "cmptmp" builder in
+            build_uitofp i double_type "booltmp" builder
+        | _ -> raise (Error "invalid binary operator")
+      end
+  | Ast.Call (callee, args) ->
+      (* Look up the name in the module table. *)
+      let callee =
+        match lookup_function callee the_module with
+        | Some callee -> callee
+        | None -> raise (Error "unknown function referenced")
+      in
+      let params = params callee in
+
+      (* If argument mismatch error. *)
+      if Array.length params == Array.length args then () else
+        raise (Error "incorrect # arguments passed");
+      let args = Array.map codegen_expr args in
+      build_call callee args "calltmp" builder
+  | Ast.If (cond, then_, else_) ->
+      let cond = codegen_expr cond in
+
+      (* Convert condition to a bool by comparing equal to 0.0 *)
+      let zero = const_float double_type 0.0 in
+      let cond_val = build_fcmp Fcmp.One cond zero "ifcond" builder in
+
+      (* Grab the first block so that we might later add the conditional branch
+       * to it at the end of the function. *)
+      let start_bb = insertion_block builder in
+      let the_function = block_parent start_bb in
+
+      let then_bb = append_block "then" the_function in
+
+      (* Emit 'then' value. *)
+      position_at_end then_bb builder;
+      let then_val = codegen_expr then_ in
+
+      (* Codegen of 'then' can change the current block, update then_bb for the
+       * phi. We create a new name because one is used for the phi node, and the
+       * other is used for the conditional branch. *)
+      let new_then_bb = insertion_block builder in
+
+      (* Emit 'else' value. *)
+      let else_bb = append_block "else" the_function in
+      position_at_end else_bb builder;
+      let else_val = codegen_expr else_ in
+
+      (* Codegen of 'else' can change the current block, update else_bb for the
+       * phi. *)
+      let new_else_bb = insertion_block builder in
+
+      (* Emit merge block. *)
+      let merge_bb = append_block "ifcont" the_function in
+      position_at_end merge_bb builder;
+      let incoming = [(then_val, new_then_bb); (else_val, new_else_bb)] in
+      let phi = build_phi incoming "iftmp" builder in
+
+      (* Return to the start block to add the conditional branch. *)
+      position_at_end start_bb builder;
+      ignore (build_cond_br cond_val then_bb else_bb builder);
+
+      (* Set a unconditional branch at the end of the 'then' block and the
+       * 'else' block to the 'merge' block. *)
+      position_at_end new_then_bb builder; ignore (build_br merge_bb builder);
+      position_at_end new_else_bb builder; ignore (build_br merge_bb builder);
+
+      (* Finally, set the builder to the end of the merge block. *)
+      position_at_end merge_bb builder;
+
+      phi
+  | Ast.For (var_name, start, end_, step, body) ->
+      (* Emit the start code first, without 'variable' in scope. *)
+      let start_val = codegen_expr start in
+
+      (* Make the new basic block for the loop header, inserting after current
+       * block. *)
+      let preheader_bb = insertion_block builder in
+      let the_function = block_parent preheader_bb in
+      let loop_bb = append_block "loop" the_function in
+
+      (* Insert an explicit fall through from the current block to the
+       * loop_bb. *)
+      ignore (build_br loop_bb builder);
+
+      (* Start insertion in loop_bb. *)
+      position_at_end loop_bb builder;
+
+      (* Start the PHI node with an entry for start. *)
+      let variable = build_phi [(start_val, preheader_bb)] var_name builder in
+
+      (* Within the loop, the variable is defined equal to the PHI node. If it
+       * shadows an existing variable, we have to restore it, so save it
+       * now. *)
+      let old_val =
+        try Some (Hashtbl.find named_values var_name) with Not_found -> None
+      in
+      Hashtbl.add named_values var_name variable;
+
+      (* Emit the body of the loop.  This, like any other expr, can change the
+       * current BB.  Note that we ignore the value computed by the body, but
+       * don't allow an error *)
+      ignore (codegen_expr body);
+
+      (* Emit the step value. *)
+      let step_val =
+        match step with
+        | Some step -> codegen_expr step
+        (* If not specified, use 1.0. *)
+        | None -> const_float double_type 1.0
+      in
+
+      let next_var = build_add variable step_val "nextvar" builder in
+
+      (* Compute the end condition. *)
+      let end_cond = codegen_expr end_ in
+
+      (* Convert condition to a bool by comparing equal to 0.0. *)
+      let zero = const_float double_type 0.0 in
+      let end_cond = build_fcmp Fcmp.One end_cond zero "loopcond" builder in
+
+      (* Create the "after loop" block and insert it. *)
+      let loop_end_bb = insertion_block builder in
+      let after_bb = append_block "afterloop" the_function in
+
+      (* Insert the conditional branch into the end of loop_end_bb. *)
+      ignore (build_cond_br end_cond loop_bb after_bb builder);
+
+      (* Any new code will be inserted in after_bb. *)
+      position_at_end after_bb builder;
+
+      (* Add a new entry to the PHI node for the backedge. *)
+      add_incoming (next_var, loop_end_bb) variable;
+
+      (* Restore the unshadowed variable. *)
+      begin match old_val with
+      | Some old_val -> Hashtbl.add named_values var_name old_val
+      | None -> ()
+      end;
+
+      (* for expr always returns 0.0. *)
+      const_null double_type
+
+let codegen_proto = function
+  | Ast.Prototype (name, args) ->
+      (* Make the function type: double(double,double) etc. *)
+      let doubles = Array.make (Array.length args) double_type in
+      let ft = function_type double_type doubles in
+      let f =
+        match lookup_function name the_module with
+        | None -> declare_function name ft the_module
+
+        (* If 'f' conflicted, there was already something named 'name'. If it
+         * has a body, don't allow redefinition or reextern. *)
+        | Some f ->
+            (* If 'f' already has a body, reject this. *)
+            if block_begin f <> At_end f then
+              raise (Error "redefinition of function");
+
+            (* If 'f' took a different number of arguments, reject. *)
+            if element_type (type_of f) <> ft then
+              raise (Error "redefinition of function with different # args");
+            f
+      in
+
+      (* Set names for all arguments. *)
+      Array.iteri (fun i a ->
+        let n = args.(i) in
+        set_value_name n a;
+        Hashtbl.add named_values n a;
+      ) (params f);
+      f
+
+let codegen_func the_fpm = function
+  | Ast.Function (proto, body) ->
+      Hashtbl.clear named_values;
+      let the_function = codegen_proto proto in
+
+      (* Create a new basic block to start insertion into. *)
+      let bb = append_block "entry" the_function in
+      position_at_end bb builder;
+
+      try
+        let ret_val = codegen_expr body in
+
+        (* Finish off the function. *)
+        let _ = build_ret ret_val builder in
+
+        (* Validate the generated code, checking for consistency. *)
+        Llvm_analysis.assert_valid_function the_function;
+
+        (* Optimize the function. *)
+        let _ = PassManager.run_function the_function the_fpm in
+
+        the_function
+      with e ->
+        delete_function the_function;
+        raise e
+
+
+ +
toplevel.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Top-Level parsing and JIT Driver
+ *===----------------------------------------------------------------------===*)
+
+open Llvm
+open Llvm_executionengine
+
+(* top ::= definition | external | expression | ';' *)
+let rec main_loop the_fpm the_execution_engine stream =
+  match Stream.peek stream with
+  | None -> ()
+
+  (* ignore top-level semicolons. *)
+  | Some (Token.Kwd ';') ->
+      Stream.junk stream;
+      main_loop the_fpm the_execution_engine stream
+
+  | Some token ->
+      begin
+        try match token with
+        | Token.Def ->
+            let e = Parser.parse_definition stream in
+            print_endline "parsed a function definition.";
+            dump_value (Codegen.codegen_func the_fpm e);
+        | Token.Extern ->
+            let e = Parser.parse_extern stream in
+            print_endline "parsed an extern.";
+            dump_value (Codegen.codegen_proto e);
+        | _ ->
+            (* Evaluate a top-level expression into an anonymous function. *)
+            let e = Parser.parse_toplevel stream in
+            print_endline "parsed a top-level expr";
+            let the_function = Codegen.codegen_func the_fpm e in
+            dump_value the_function;
+
+            (* JIT the function, returning a function pointer. *)
+            let result = ExecutionEngine.run_function the_function [||]
+              the_execution_engine in
+
+            print_string "Evaluated to ";
+            print_float (GenericValue.as_float double_type result);
+            print_newline ();
+        with Stream.Error s | Codegen.Error s ->
+          (* Skip token for error recovery. *)
+          Stream.junk stream;
+          print_endline s;
+      end;
+      print_string "ready> "; flush stdout;
+      main_loop the_fpm the_execution_engine stream
+
+
+ +
toy.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Main driver code.
+ *===----------------------------------------------------------------------===*)
+
+open Llvm
+open Llvm_executionengine
+open Llvm_target
+open Llvm_scalar_opts
+
+let main () =
+  (* Install standard binary operators.
+   * 1 is the lowest precedence. *)
+  Hashtbl.add Parser.binop_precedence '<' 10;
+  Hashtbl.add Parser.binop_precedence '+' 20;
+  Hashtbl.add Parser.binop_precedence '-' 20;
+  Hashtbl.add Parser.binop_precedence '*' 40;    (* highest. *)
+
+  (* Prime the first token. *)
+  print_string "ready> "; flush stdout;
+  let stream = Lexer.lex (Stream.of_channel stdin) in
+
+  (* Create the JIT. *)
+  let the_module_provider = ModuleProvider.create Codegen.the_module in
+  let the_execution_engine = ExecutionEngine.create the_module_provider in
+  let the_fpm = PassManager.create_function the_module_provider in
+
+  (* Set up the optimizer pipeline.  Start with registering info about how the
+   * target lays out data structures. *)
+  TargetData.add (ExecutionEngine.target_data the_execution_engine) the_fpm;
+
+  (* Do simple "peephole" optimizations and bit-twiddling optzn. *)
+  add_instruction_combining the_fpm;
+
+  (* reassociate expressions. *)
+  add_reassociation the_fpm;
+
+  (* Eliminate Common SubExpressions. *)
+  add_gvn the_fpm;
+
+  (* Simplify the control flow graph (deleting unreachable blocks, etc). *)
+  add_cfg_simplification the_fpm;
+
+  (* Run the main "interpreter loop" now. *)
+  Toplevel.main_loop the_fpm the_execution_engine stream;
+
+  (* Print out all the generated code. *)
+  dump_module Codegen.the_module
+;;
+
+main ()
+
+
+ +
bindings.c
+
+
+#include <stdio.h>
+
+/* putchard - putchar that takes a double and returns 0. */
+extern double putchard(double X) {
+  putchar((char)X);
+  return 0;
+}
+
+
+
+ +Next: Extending the language: user-defined +operators +
+ + +
+
+ Valid CSS! + Valid HTML 4.01! + + Chris Lattner
+ Erick Tryzelaar
+ The LLVM Compiler Infrastructure
+ Last modified: $Date: 2007-10-17 11:05:13 -0700 (Wed, 17 Oct 2007) $ +
+ + diff --git a/docs/tutorial/OCamlLangImpl6.html b/docs/tutorial/OCamlLangImpl6.html new file mode 100644 index 00000000000..780cab81914 --- /dev/null +++ b/docs/tutorial/OCamlLangImpl6.html @@ -0,0 +1,1569 @@ + + + + + Kaleidoscope: Extending the Language: User-defined Operators + + + + + + + + +
Kaleidoscope: Extending the Language: User-defined Operators
+ + + +
+

+ Written by Chris Lattner + and Erick Tryzelaar +

+
+ + +
Chapter 6 Introduction
+ + +
+ +

Welcome to Chapter 6 of the "Implementing a language +with LLVM" tutorial. At this point in our tutorial, we now have a fully +functional language that is fairly minimal, but also useful. There +is still one big problem with it, however. Our language doesn't have many +useful operators (like division, logical negation, or even any comparisons +besides less-than).

+ +

This chapter of the tutorial takes a wild digression into adding user-defined +operators to the simple and beautiful Kaleidoscope language. This digression now +gives us a simple and ugly language in some ways, but also a powerful one at the +same time. One of the great things about creating your own language is that you +get to decide what is good or bad. In this tutorial we'll assume that it is +okay to use this as a way to show some interesting parsing techniques.

+ +

At the end of this tutorial, we'll run through an example Kaleidoscope +application that renders the Mandelbrot set. This gives +an example of what you can build with Kaleidoscope and its feature set.

+ +
+ + +
User-defined Operators: the Idea
+ + +
+ +

+The "operator overloading" that we will add to Kaleidoscope is more general than +languages like C++. In C++, you are only allowed to redefine existing +operators: you can't programatically change the grammar, introduce new +operators, change precedence levels, etc. In this chapter, we will add this +capability to Kaleidoscope, which will let the user round out the set of +operators that are supported.

+ +

The point of going into user-defined operators in a tutorial like this is to +show the power and flexibility of using a hand-written parser. Thus far, the parser +we have been implementing uses recursive descent for most parts of the grammar and +operator precedence parsing for the expressions. See Chapter 2 for details. Without using operator +precedence parsing, it would be very difficult to allow the programmer to +introduce new operators into the grammar: the grammar is dynamically extensible +as the JIT runs.

+ +

The two specific features we'll add are programmable unary operators (right +now, Kaleidoscope has no unary operators at all) as well as binary operators. +An example of this is:

+ +
+
+# Logical unary not.
+def unary!(v)
+  if v then
+    0
+  else
+    1;
+
+# Define > with the same precedence as <.
+def binary> 10 (LHS RHS)
+  RHS < LHS;
+
+# Binary "logical or", (note that it does not "short circuit")
+def binary| 5 (LHS RHS)
+  if LHS then
+    1
+  else if RHS then
+    1
+  else
+    0;
+
+# Define = with slightly lower precedence than relationals.
+def binary= 9 (LHS RHS)
+  !(LHS < RHS | LHS > RHS);
+
+
+ +

Many languages aspire to being able to implement their standard runtime +library in the language itself. In Kaleidoscope, we can implement significant +parts of the language in the library!

+ +

We will break down implementation of these features into two parts: +implementing support for user-defined binary operators and adding unary +operators.

+ +
+ + +
User-defined Binary Operators
+ + +
+ +

Adding support for user-defined binary operators is pretty simple with our +current framework. We'll first add support for the unary/binary keywords:

+ +
+
+type token =
+  ...
+  (* operators *)
+  | Binary | Unary
+
+...
+
+and lex_ident buffer = parser
+  ...
+      | "for" -> [< 'Token.For; stream >]
+      | "in" -> [< 'Token.In; stream >]
+      | "binary" -> [< 'Token.Binary; stream >]
+      | "unary" -> [< 'Token.Unary; stream >]
+
+
+ +

This just adds lexer support for the unary and binary keywords, like we +did in previous chapters. One nice +thing about our current AST, is that we represent binary operators with full +generalisation by using their ASCII code as the opcode. For our extended +operators, we'll use this same representation, so we don't need any new AST or +parser support.

+ +

On the other hand, we have to be able to represent the definitions of these +new operators, in the "def binary| 5" part of the function definition. In our +grammar so far, the "name" for the function definition is parsed as the +"prototype" production and into the Ast.Prototype AST node. To +represent our new user-defined operators as prototypes, we have to extend +the Ast.Prototype AST node like this:

+ +
+
+(* proto - This type represents the "prototype" for a function, which captures
+ * its name, and its argument names (thus implicitly the number of arguments the
+ * function takes). *)
+type proto =
+  | Prototype of string * string array
+  | BinOpPrototype of string * string array * int
+
+
+ +

Basically, in addition to knowing a name for the prototype, we now keep track +of whether it was an operator, and if it was, what precedence level the operator +is at. The precedence is only used for binary operators (as you'll see below, +it just doesn't apply for unary operators). Now that we have a way to represent +the prototype for a user-defined operator, we need to parse it:

+ +
+
+(* prototype
+ *   ::= id '(' id* ')'
+ *   ::= binary LETTER number? (id, id)
+ *   ::= unary LETTER number? (id) *)
+let parse_prototype =
+  let rec parse_args accumulator = parser
+    | [< 'Token.Ident id; e=parse_args (id::accumulator) >] -> e
+    | [< >] -> accumulator
+  in
+  let parse_operator = parser
+    | [< 'Token.Unary >] -> "unary", 1
+    | [< 'Token.Binary >] -> "binary", 2
+  in
+  let parse_binary_precedence = parser
+    | [< 'Token.Number n >] -> int_of_float n
+    | [< >] -> 30
+  in
+  parser
+  | [< 'Token.Ident id;
+       'Token.Kwd '(' ?? "expected '(' in prototype";
+       args=parse_args [];
+       'Token.Kwd ')' ?? "expected ')' in prototype" >] ->
+      (* success. *)
+      Ast.Prototype (id, Array.of_list (List.rev args))
+  | [< (prefix, kind)=parse_operator;
+       'Token.Kwd op ?? "expected an operator";
+       (* Read the precedence if present. *)
+       binary_precedence=parse_binary_precedence;
+       'Token.Kwd '(' ?? "expected '(' in prototype";
+        args=parse_args [];
+       'Token.Kwd ')' ?? "expected ')' in prototype" >] ->
+      let name = prefix ^ (String.make 1 op) in
+      let args = Array.of_list (List.rev args) in
+
+      (* Verify right number of arguments for operator. *)
+      if Array.length args != kind
+      then raise (Stream.Error "invalid number of operands for operator")
+      else
+        if kind == 1 then
+          Ast.Prototype (name, args)
+        else
+          Ast.BinOpPrototype (name, args, binary_precedence)
+  | [< >] ->
+      raise (Stream.Error "expected function name in prototype")
+
+
+ +

This is all fairly straightforward parsing code, and we have already seen +a lot of similar code in the past. One interesting part about the code above is +the couple lines that set up name for binary operators. This builds +names like "binary@" for a newly defined "@" operator. This then takes +advantage of the fact that symbol names in the LLVM symbol table are allowed to +have any character in them, including embedded nul characters.

+ +

The next interesting thing to add, is codegen support for these binary +operators. Given our current structure, this is a simple addition of a default +case for our existing binary operator node:

+ +
+
+let codegen_expr = function
+  ...
+  | Ast.Binary (op, lhs, rhs) ->
+      let lhs_val = codegen_expr lhs in
+      let rhs_val = codegen_expr rhs in
+      begin
+        match op with
+        | '+' -> build_add lhs_val rhs_val "addtmp" builder
+        | '-' -> build_sub lhs_val rhs_val "subtmp" builder
+        | '*' -> build_mul lhs_val rhs_val "multmp" builder
+        | '<' ->
+            (* Convert bool 0/1 to double 0.0 or 1.0 *)
+            let i = build_fcmp Fcmp.Ult lhs_val rhs_val "cmptmp" builder in
+            build_uitofp i double_type "booltmp" builder
+        | _ ->
+            (* If it wasn't a builtin binary operator, it must be a user defined
+             * one. Emit a call to it. *)
+            let callee = "binary" ^ (String.make 1 op) in
+            let callee =
+              match lookup_function callee the_module with
+              | Some callee -> callee
+              | None -> raise (Error "binary operator not found!")
+            in
+            build_call callee [|lhs_val; rhs_val|] "binop" builder
+      end
+
+
+ +

As you can see above, the new code is actually really simple. It just does +a lookup for the appropriate operator in the symbol table and generates a +function call to it. Since user-defined operators are just built as normal +functions (because the "prototype" boils down to a function with the right +name) everything falls into place.

+ +

The final piece of code we are missing, is a bit of top level magic:

+ +
+
+let codegen_func the_fpm = function
+  | Ast.Function (proto, body) ->
+      Hashtbl.clear named_values;
+      let the_function = codegen_proto proto in
+
+      (* If this is an operator, install it. *)
+      begin match proto with
+      | Ast.BinOpPrototype (name, args, prec) ->
+          let op = name.[String.length name - 1] in
+          Hashtbl.add Parser.binop_precedence op prec;
+      | _ -> ()
+      end;
+
+      (* Create a new basic block to start insertion into. *)
+      let bb = append_block "entry" the_function in
+      position_at_end bb builder;
+      ...
+
+
+ +

Basically, before codegening a function, if it is a user-defined operator, we +register it in the precedence table. This allows the binary operator parsing +logic we already have in place to handle it. Since we are working on a +fully-general operator precedence parser, this is all we need to do to "extend +the grammar".

+ +

Now we have useful user-defined binary operators. This builds a lot +on the previous framework we built for other operators. Adding unary operators +is a bit more challenging, because we don't have any framework for it yet - lets +see what it takes.

+ +
+ + +
User-defined Unary Operators
+ + +
+ +

Since we don't currently support unary operators in the Kaleidoscope +language, we'll need to add everything to support them. Above, we added simple +support for the 'unary' keyword to the lexer. In addition to that, we need an +AST node:

+ +
+
+type expr =
+  ...
+  (* variant for a unary operator. *)
+  | Unary of char * expr
+  ...
+
+
+ +

This AST node is very simple and obvious by now. It directly mirrors the +binary operator AST node, except that it only has one child. With this, we +need to add the parsing logic. Parsing a unary operator is pretty simple: we'll +add a new function to do it:

+ +
+
+(* unary
+ *   ::= primary
+ *   ::= '!' unary *)
+and parse_unary = parser
+  (* If this is a unary operator, read it. *)
+  | [< 'Token.Kwd op when op != '(' && op != ')'; operand=parse_expr >] ->
+      Ast.Unary (op, operand)
+
+  (* If the current token is not an operator, it must be a primary expr. *)
+  | [< stream >] -> parse_primary stream
+
+
+ +

The grammar we add is pretty straightforward here. If we see a unary +operator when parsing a primary operator, we eat the operator as a prefix and +parse the remaining piece as another unary operator. This allows us to handle +multiple unary operators (e.g. "!!x"). Note that unary operators can't have +ambiguous parses like binary operators can, so there is no need for precedence +information.

+ +

The problem with this function, is that we need to call ParseUnary from +somewhere. To do this, we change previous callers of ParsePrimary to call +parse_unary instead:

+ +
+
+(* binoprhs
+ *   ::= ('+' primary)* *)
+and parse_bin_rhs expr_prec lhs stream =
+        ...
+        (* Parse the unary expression after the binary operator. *)
+        let rhs = parse_unary stream in
+        ...
+
+...
+
+(* expression
+ *   ::= primary binoprhs *)
+and parse_expr = parser
+  | [< lhs=parse_unary; stream >] -> parse_bin_rhs 0 lhs stream
+
+
+ +

With these two simple changes, we are now able to parse unary operators and build the +AST for them. Next up, we need to add parser support for prototypes, to parse +the unary operator prototype. We extend the binary operator code above +with:

+ +
+
+(* prototype
+ *   ::= id '(' id* ')'
+ *   ::= binary LETTER number? (id, id)
+ *   ::= unary LETTER number? (id) *)
+let parse_prototype =
+  let rec parse_args accumulator = parser
+    | [< 'Token.Ident id; e=parse_args (id::accumulator) >] -> e
+    | [< >] -> accumulator
+  in
+  let parse_operator = parser
+    | [< 'Token.Unary >] -> "unary", 1
+    | [< 'Token.Binary >] -> "binary", 2
+  in
+  let parse_binary_precedence = parser
+    | [< 'Token.Number n >] -> int_of_float n
+    | [< >] -> 30
+  in
+  parser
+  | [< 'Token.Ident id;
+       'Token.Kwd '(' ?? "expected '(' in prototype";
+       args=parse_args [];
+       'Token.Kwd ')' ?? "expected ')' in prototype" >] ->
+      (* success. *)
+      Ast.Prototype (id, Array.of_list (List.rev args))
+  | [< (prefix, kind)=parse_operator;
+       'Token.Kwd op ?? "expected an operator";
+       (* Read the precedence if present. *)
+       binary_precedence=parse_binary_precedence;
+       'Token.Kwd '(' ?? "expected '(' in prototype";
+        args=parse_args [];
+       'Token.Kwd ')' ?? "expected ')' in prototype" >] ->
+      let name = prefix ^ (String.make 1 op) in
+      let args = Array.of_list (List.rev args) in
+
+      (* Verify right number of arguments for operator. *)
+      if Array.length args != kind
+      then raise (Stream.Error "invalid number of operands for operator")
+      else
+        if kind == 1 then
+          Ast.Prototype (name, args)
+        else
+          Ast.BinOpPrototype (name, args, binary_precedence)
+  | [< >] ->
+      raise (Stream.Error "expected function name in prototype")
+
+
+ +

As with binary operators, we name unary operators with a name that includes +the operator character. This assists us at code generation time. Speaking of, +the final piece we need to add is codegen support for unary operators. It looks +like this:

+ +
+
+let rec codegen_expr = function
+  ...
+  | Ast.Unary (op, operand) ->
+      let operand = codegen_expr operand in
+      let callee = "unary" ^ (String.make 1 op) in
+      let callee =
+        match lookup_function callee the_module with
+        | Some callee -> callee
+        | None -> raise (Error "unknown unary operator")
+      in
+      build_call callee [|operand|] "unop" builder
+
+
+ +

This code is similar to, but simpler than, the code for binary operators. It +is simpler primarily because it doesn't need to handle any predefined operators. +

+ +
+ + +
Kicking the Tires
+ + +
+ +

It is somewhat hard to believe, but with a few simple extensions we've +covered in the last chapters, we have grown a real-ish language. With this, we +can do a lot of interesting things, including I/O, math, and a bunch of other +things. For example, we can now add a nice sequencing operator (printd is +defined to print out the specified value and a newline):

+ +
+
+ready> extern printd(x);
+Read extern: declare double @printd(double)
+ready> def binary : 1 (x y) 0;  # Low-precedence operator that ignores operands.
+..
+ready> printd(123) : printd(456) : printd(789);
+123.000000
+456.000000
+789.000000
+Evaluated to 0.000000
+
+
+ +

We can also define a bunch of other "primitive" operations, such as:

+ +
+
+# Logical unary not.
+def unary!(v)
+  if v then
+    0
+  else
+    1;
+
+# Unary negate.
+def unary-(v)
+  0-v;
+
+# Define > with the same precedence as >.
+def binary> 10 (LHS RHS)
+  RHS < LHS;
+
+# Binary logical or, which does not short circuit.
+def binary| 5 (LHS RHS)
+  if LHS then
+    1
+  else if RHS then
+    1
+  else
+    0;
+
+# Binary logical and, which does not short circuit.
+def binary& 6 (LHS RHS)
+  if !LHS then
+    0
+  else
+    !!RHS;
+
+# Define = with slightly lower precedence than relationals.
+def binary = 9 (LHS RHS)
+  !(LHS < RHS | LHS > RHS);
+
+
+
+ + +

Given the previous if/then/else support, we can also define interesting +functions for I/O. For example, the following prints out a character whose +"density" reflects the value passed in: the lower the value, the denser the +character:

+ +
+
+ready>
+
+extern putchard(char)
+def printdensity(d)
+  if d > 8 then
+    putchard(32)  # ' '
+  else if d > 4 then
+    putchard(46)  # '.'
+  else if d > 2 then
+    putchard(43)  # '+'
+  else
+    putchard(42); # '*'
+...
+ready> printdensity(1): printdensity(2): printdensity(3) :
+          printdensity(4): printdensity(5): printdensity(9): putchard(10);
+*++..
+Evaluated to 0.000000
+
+
+ +

Based on these simple primitive operations, we can start to define more +interesting things. For example, here's a little function that solves for the +number of iterations it takes a function in the complex plane to +converge:

+ +
+
+# determine whether the specific location diverges.
+# Solve for z = z^2 + c in the complex plane.
+def mandleconverger(real imag iters creal cimag)
+  if iters > 255 | (real*real + imag*imag > 4) then
+    iters
+  else
+    mandleconverger(real*real - imag*imag + creal,
+                    2*real*imag + cimag,
+                    iters+1, creal, cimag);
+
+# return the number of iterations required for the iteration to escape
+def mandleconverge(real imag)
+  mandleconverger(real, imag, 0, real, imag);
+
+
+ +

This "z = z2 + c" function is a beautiful little creature that is the basis +for computation of the Mandelbrot Set. Our +mandelconverge function returns the number of iterations that it takes +for a complex orbit to escape, saturating to 255. This is not a very useful +function by itself, but if you plot its value over a two-dimensional plane, +you can see the Mandelbrot set. Given that we are limited to using putchard +here, our amazing graphical output is limited, but we can whip together +something using the density plotter above:

+ +
+
+# compute and plot the mandlebrot set with the specified 2 dimensional range
+# info.
+def mandelhelp(xmin xmax xstep   ymin ymax ystep)
+  for y = ymin, y < ymax, ystep in (
+    (for x = xmin, x < xmax, xstep in
+       printdensity(mandleconverge(x,y)))
+    : putchard(10)
+  )
+
+# mandel - This is a convenient helper function for ploting the mandelbrot set
+# from the specified position with the specified Magnification.
+def mandel(realstart imagstart realmag imagmag)
+  mandelhelp(realstart, realstart+realmag*78, realmag,
+             imagstart, imagstart+imagmag*40, imagmag);
+
+
+ +

Given this, we can try plotting out the mandlebrot set! Lets try it out:

+ +
+
+ready> mandel(-2.3, -1.3, 0.05, 0.07);
+*******************************+++++++++++*************************************
+*************************+++++++++++++++++++++++*******************************
+**********************+++++++++++++++++++++++++++++****************************
+*******************+++++++++++++++++++++.. ...++++++++*************************
+*****************++++++++++++++++++++++.... ...+++++++++***********************
+***************+++++++++++++++++++++++.....   ...+++++++++*********************
+**************+++++++++++++++++++++++....     ....+++++++++********************
+*************++++++++++++++++++++++......      .....++++++++*******************
+************+++++++++++++++++++++.......       .......+++++++******************
+***********+++++++++++++++++++....                ... .+++++++*****************
+**********+++++++++++++++++.......                     .+++++++****************
+*********++++++++++++++...........                    ...+++++++***************
+********++++++++++++............                      ...++++++++**************
+********++++++++++... ..........                        .++++++++**************
+*******+++++++++.....                                   .+++++++++*************
+*******++++++++......                                  ..+++++++++*************
+*******++++++.......                                   ..+++++++++*************
+*******+++++......                                     ..+++++++++*************
+*******.... ....                                      ...+++++++++*************
+*******.... .                                         ...+++++++++*************
+*******+++++......                                    ...+++++++++*************
+*******++++++.......                                   ..+++++++++*************
+*******++++++++......                                   .+++++++++*************
+*******+++++++++.....                                  ..+++++++++*************
+********++++++++++... ..........                        .++++++++**************
+********++++++++++++............                      ...++++++++**************
+*********++++++++++++++..........                     ...+++++++***************
+**********++++++++++++++++........                     .+++++++****************
+**********++++++++++++++++++++....                ... ..+++++++****************
+***********++++++++++++++++++++++.......       .......++++++++*****************
+************+++++++++++++++++++++++......      ......++++++++******************
+**************+++++++++++++++++++++++....      ....++++++++********************
+***************+++++++++++++++++++++++.....   ...+++++++++*********************
+*****************++++++++++++++++++++++....  ...++++++++***********************
+*******************+++++++++++++++++++++......++++++++*************************
+*********************++++++++++++++++++++++.++++++++***************************
+*************************+++++++++++++++++++++++*******************************
+******************************+++++++++++++************************************
+*******************************************************************************
+*******************************************************************************
+*******************************************************************************
+Evaluated to 0.000000
+ready> mandel(-2, -1, 0.02, 0.04);
+**************************+++++++++++++++++++++++++++++++++++++++++++++++++++++
+***********************++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+*********************+++++++++++++++++++++++++++++++++++++++++++++++++++++++++.
+*******************+++++++++++++++++++++++++++++++++++++++++++++++++++++++++...
+*****************+++++++++++++++++++++++++++++++++++++++++++++++++++++++++.....
+***************++++++++++++++++++++++++++++++++++++++++++++++++++++++++........
+**************++++++++++++++++++++++++++++++++++++++++++++++++++++++...........
+************+++++++++++++++++++++++++++++++++++++++++++++++++++++..............
+***********++++++++++++++++++++++++++++++++++++++++++++++++++........        .
+**********++++++++++++++++++++++++++++++++++++++++++++++.............
+********+++++++++++++++++++++++++++++++++++++++++++..................
+*******+++++++++++++++++++++++++++++++++++++++.......................
+******+++++++++++++++++++++++++++++++++++...........................
+*****++++++++++++++++++++++++++++++++............................
+*****++++++++++++++++++++++++++++...............................
+****++++++++++++++++++++++++++......   .........................
+***++++++++++++++++++++++++.........     ......    ...........
+***++++++++++++++++++++++............
+**+++++++++++++++++++++..............
+**+++++++++++++++++++................
+*++++++++++++++++++.................
+*++++++++++++++++............ ...
+*++++++++++++++..............
+*+++....++++................
+*..........  ...........
+*
+*..........  ...........
+*+++....++++................
+*++++++++++++++..............
+*++++++++++++++++............ ...
+*++++++++++++++++++.................
+**+++++++++++++++++++................
+**+++++++++++++++++++++..............
+***++++++++++++++++++++++............
+***++++++++++++++++++++++++.........     ......    ...........
+****++++++++++++++++++++++++++......   .........................
+*****++++++++++++++++++++++++++++...............................
+*****++++++++++++++++++++++++++++++++............................
+******+++++++++++++++++++++++++++++++++++...........................
+*******+++++++++++++++++++++++++++++++++++++++.......................
+********+++++++++++++++++++++++++++++++++++++++++++..................
+Evaluated to 0.000000
+ready> mandel(-0.9, -1.4, 0.02, 0.03);
+*******************************************************************************
+*******************************************************************************
+*******************************************************************************
+**********+++++++++++++++++++++************************************************
+*+++++++++++++++++++++++++++++++++++++++***************************************
++++++++++++++++++++++++++++++++++++++++++++++**********************************
+++++++++++++++++++++++++++++++++++++++++++++++++++*****************************
+++++++++++++++++++++++++++++++++++++++++++++++++++++++*************************
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++**********************
++++++++++++++++++++++++++++++++++.........++++++++++++++++++*******************
++++++++++++++++++++++++++++++++....   ......+++++++++++++++++++****************
++++++++++++++++++++++++++++++.......  ........+++++++++++++++++++**************
+++++++++++++++++++++++++++++........   ........++++++++++++++++++++************
++++++++++++++++++++++++++++.........     ..  ...+++++++++++++++++++++**********
+++++++++++++++++++++++++++...........        ....++++++++++++++++++++++********
+++++++++++++++++++++++++.............       .......++++++++++++++++++++++******
++++++++++++++++++++++++.............        ........+++++++++++++++++++++++****
+++++++++++++++++++++++...........           ..........++++++++++++++++++++++***
+++++++++++++++++++++...........                .........++++++++++++++++++++++*
+++++++++++++++++++............                  ...........++++++++++++++++++++
+++++++++++++++++...............                 .............++++++++++++++++++
+++++++++++++++.................                 ...............++++++++++++++++
+++++++++++++..................                  .................++++++++++++++
++++++++++..................                      .................+++++++++++++
+++++++........        .                               .........  ..++++++++++++
+++............                                         ......    ....++++++++++
+..............                                                    ...++++++++++
+..............                                                    ....+++++++++
+..............                                                    .....++++++++
+.............                                                    ......++++++++
+...........                                                     .......++++++++
+.........                                                       ........+++++++
+.........                                                       ........+++++++
+.........                                                           ....+++++++
+........                                                             ...+++++++
+.......                                                              ...+++++++
+                                                                    ....+++++++
+                                                                   .....+++++++
+                                                                    ....+++++++
+                                                                    ....+++++++
+                                                                    ....+++++++
+Evaluated to 0.000000
+ready> ^D
+
+
+ +

At this point, you may be starting to realize that Kaleidoscope is a real +and powerful language. It may not be self-similar :), but it can be used to +plot things that are!

+ +

With this, we conclude the "adding user-defined operators" chapter of the +tutorial. We have successfully augmented our language, adding the ability to +extend the language in the library, and we have shown how this can be used to +build a simple but interesting end-user application in Kaleidoscope. At this +point, Kaleidoscope can build a variety of applications that are functional and +can call functions with side-effects, but it can't actually define and mutate a +variable itself.

+ +

Strikingly, variable mutation is an important feature of some +languages, and it is not at all obvious how to add +support for mutable variables without having to add an "SSA construction" +phase to your front-end. In the next chapter, we will describe how you can +add variable mutation without building SSA in your front-end.

+ +
+ + + +
Full Code Listing
+ + +
+ +

+Here is the complete code listing for our running example, enhanced with the +if/then/else and for expressions.. To build this example, use: +

+ +
+
+# Compile
+ocamlbuild toy.byte
+# Run
+./toy.byte
+
+
+ +

Here is the code:

+ +
+
_tags:
+
+
+<{lexer,parser}.ml>: use_camlp4, pp(camlp4of)
+<*.{byte,native}>: g++, use_llvm, use_llvm_analysis
+<*.{byte,native}>: use_llvm_executionengine, use_llvm_target
+<*.{byte,native}>: use_llvm_scalar_opts, use_bindings
+
+
+ +
myocamlbuild.ml:
+
+
+open Ocamlbuild_plugin;;
+
+ocaml_lib ~extern:true "llvm";;
+ocaml_lib ~extern:true "llvm_analysis";;
+ocaml_lib ~extern:true "llvm_executionengine";;
+ocaml_lib ~extern:true "llvm_target";;
+ocaml_lib ~extern:true "llvm_scalar_opts";;
+
+flag ["link"; "ocaml"; "g++"] (S[A"-cc"; A"g++"]);;
+dep ["link"; "ocaml"; "use_bindings"] ["bindings.o"];;
+
+
+ +
token.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Lexer Tokens
+ *===----------------------------------------------------------------------===*)
+
+(* The lexer returns these 'Kwd' if it is an unknown character, otherwise one of
+ * these others for known things. *)
+type token =
+  (* commands *)
+  | Def | Extern
+
+  (* primary *)
+  | Ident of string | Number of float
+
+  (* unknown *)
+  | Kwd of char
+
+  (* control *)
+  | If | Then | Else
+  | For | In
+
+  (* operators *)
+  | Binary | Unary
+
+
+ +
lexer.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Lexer
+ *===----------------------------------------------------------------------===*)
+
+let rec lex = parser
+  (* Skip any whitespace. *)
+  | [< ' (' ' | '\n' | '\r' | '\t'); stream >] -> lex stream
+
+  (* identifier: [a-zA-Z][a-zA-Z0-9] *)
+  | [< ' ('A' .. 'Z' | 'a' .. 'z' as c); stream >] ->
+      let buffer = Buffer.create 1 in
+      Buffer.add_char buffer c;
+      lex_ident buffer stream
+
+  (* number: [0-9.]+ *)
+  | [< ' ('0' .. '9' as c); stream >] ->
+      let buffer = Buffer.create 1 in
+      Buffer.add_char buffer c;
+      lex_number buffer stream
+
+  (* Comment until end of line. *)
+  | [< ' ('#'); stream >] ->
+      lex_comment stream
+
+  (* Otherwise, just return the character as its ascii value. *)
+  | [< 'c; stream >] ->
+      [< 'Token.Kwd c; lex stream >]
+
+  (* end of stream. *)
+  | [< >] -> [< >]
+
+and lex_number buffer = parser
+  | [< ' ('0' .. '9' | '.' as c); stream >] ->
+      Buffer.add_char buffer c;
+      lex_number buffer stream
+  | [< stream=lex >] ->
+      [< 'Token.Number (float_of_string (Buffer.contents buffer)); stream >]
+
+and lex_ident buffer = parser
+  | [< ' ('A' .. 'Z' | 'a' .. 'z' | '0' .. '9' as c); stream >] ->
+      Buffer.add_char buffer c;
+      lex_ident buffer stream
+  | [< stream=lex >] ->
+      match Buffer.contents buffer with
+      | "def" -> [< 'Token.Def; stream >]
+      | "extern" -> [< 'Token.Extern; stream >]
+      | "if" -> [< 'Token.If; stream >]
+      | "then" -> [< 'Token.Then; stream >]
+      | "else" -> [< 'Token.Else; stream >]
+      | "for" -> [< 'Token.For; stream >]
+      | "in" -> [< 'Token.In; stream >]
+      | "binary" -> [< 'Token.Binary; stream >]
+      | "unary" -> [< 'Token.Unary; stream >]
+      | id -> [< 'Token.Ident id; stream >]
+
+and lex_comment = parser
+  | [< ' ('\n'); stream=lex >] -> stream
+  | [< 'c; e=lex_comment >] -> e
+  | [< >] -> [< >]
+
+
+ +
ast.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Abstract Syntax Tree (aka Parse Tree)
+ *===----------------------------------------------------------------------===*)
+
+(* expr - Base type for all expression nodes. *)
+type expr =
+  (* variant for numeric literals like "1.0". *)
+  | Number of float
+
+  (* variant for referencing a variable, like "a". *)
+  | Variable of string
+
+  (* variant for a unary operator. *)
+  | Unary of char * expr
+
+  (* variant for a binary operator. *)
+  | Binary of char * expr * expr
+
+  (* variant for function calls. *)
+  | Call of string * expr array
+
+  (* variant for if/then/else. *)
+  | If of expr * expr * expr
+
+  (* variant for for/in. *)
+  | For of string * expr * expr * expr option * expr
+
+(* proto - This type represents the "prototype" for a function, which captures
+ * its name, and its argument names (thus implicitly the number of arguments the
+ * function takes). *)
+type proto =
+  | Prototype of string * string array
+  | BinOpPrototype of string * string array * int
+
+(* func - This type represents a function definition itself. *)
+type func = Function of proto * expr
+
+
+ +
parser.ml:
+
+
+(*===---------------------------------------------------------------------===
+ * Parser
+ *===---------------------------------------------------------------------===*)
+
+(* binop_precedence - This holds the precedence for each binary operator that is
+ * defined *)
+let binop_precedence:(char, int) Hashtbl.t = Hashtbl.create 10
+
+(* precedence - Get the precedence of the pending binary operator token. *)
+let precedence c = try Hashtbl.find binop_precedence c with Not_found -> -1
+
+(* primary
+ *   ::= identifier
+ *   ::= numberexpr
+ *   ::= parenexpr
+ *   ::= ifexpr
+ *   ::= forexpr *)
+let rec parse_primary = parser
+  (* numberexpr ::= number *)
+  | [< 'Token.Number n >] -> Ast.Number n
+
+  (* parenexpr ::= '(' expression ')' *)
+  | [< 'Token.Kwd '('; e=parse_expr; 'Token.Kwd ')' ?? "expected ')'" >] -> e
+
+  (* identifierexpr
+   *   ::= identifier
+   *   ::= identifier '(' argumentexpr ')' *)
+  | [< 'Token.Ident id; stream >] ->
+      let rec parse_args accumulator = parser
+        | [< e=parse_expr; stream >] ->
+            begin parser
+              | [< 'Token.Kwd ','; e=parse_args (e :: accumulator) >] -> e
+              | [< >] -> e :: accumulator
+            end stream
+        | [< >] -> accumulator
+      in
+      let rec parse_ident id = parser
+        (* Call. *)
+        | [< 'Token.Kwd '(';
+             args=parse_args [];
+             'Token.Kwd ')' ?? "expected ')'">] ->
+            Ast.Call (id, Array.of_list (List.rev args))
+
+        (* Simple variable ref. *)
+        | [< >] -> Ast.Variable id
+      in
+      parse_ident id stream
+
+  (* ifexpr ::= 'if' expr 'then' expr 'else' expr *)
+  | [< 'Token.If; c=parse_expr;
+       'Token.Then ?? "expected 'then'"; t=parse_expr;
+       'Token.Else ?? "expected 'else'"; e=parse_expr >] ->
+      Ast.If (c, t, e)
+
+  (* forexpr
+        ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression *)
+  | [< 'Token.For;
+       'Token.Ident id ?? "expected identifier after for";
+       'Token.Kwd '=' ?? "expected '=' after for";
+       stream >] ->
+      begin parser
+        | [<
+             start=parse_expr;
+             'Token.Kwd ',' ?? "expected ',' after for";
+             end_=parse_expr;
+             stream >] ->
+            let step =
+              begin parser
+              | [< 'Token.Kwd ','; step=parse_expr >] -> Some step
+              | [< >] -> None
+              end stream
+            in
+            begin parser
+            | [< 'Token.In; body=parse_expr >] ->
+                Ast.For (id, start, end_, step, body)
+            | [< >] ->
+                raise (Stream.Error "expected 'in' after for")
+            end stream
+        | [< >] ->
+            raise (Stream.Error "expected '=' after for")
+      end stream
+
+  | [< >] -> raise (Stream.Error "unknown token when expecting an expression.")
+
+(* unary
+ *   ::= primary
+ *   ::= '!' unary *)
+and parse_unary = parser
+  (* If this is a unary operator, read it. *)
+  | [< 'Token.Kwd op when op != '(' && op != ')'; operand=parse_expr >] ->
+      Ast.Unary (op, operand)
+
+  (* If the current token is not an operator, it must be a primary expr. *)
+  | [< stream >] -> parse_primary stream
+
+(* binoprhs
+ *   ::= ('+' primary)* *)
+and parse_bin_rhs expr_prec lhs stream =
+  match Stream.peek stream with
+  (* If this is a binop, find its precedence. *)
+  | Some (Token.Kwd c) when Hashtbl.mem binop_precedence c ->
+      let token_prec = precedence c in
+
+      (* If this is a binop that binds at least as tightly as the current binop,
+       * consume it, otherwise we are done. *)
+      if token_prec < expr_prec then lhs else begin
+        (* Eat the binop. *)
+        Stream.junk stream;
+
+        (* Parse the unary expression after the binary operator. *)
+        let rhs = parse_unary stream in
+
+        (* Okay, we know this is a binop. *)
+        let rhs =
+          match Stream.peek stream with
+          | Some (Token.Kwd c2) ->
+              (* If BinOp binds less tightly with rhs than the operator after
+               * rhs, let the pending operator take rhs as its lhs. *)
+              let next_prec = precedence c2 in
+              if token_prec < next_prec
+              then parse_bin_rhs (token_prec + 1) rhs stream
+              else rhs
+          | _ -> rhs
+        in
+
+        (* Merge lhs/rhs. *)
+        let lhs = Ast.Binary (c, lhs, rhs) in
+        parse_bin_rhs expr_prec lhs stream
+      end
+  | _ -> lhs
+
+(* expression
+ *   ::= primary binoprhs *)
+and parse_expr = parser
+  | [< lhs=parse_unary; stream >] -> parse_bin_rhs 0 lhs stream
+
+(* prototype
+ *   ::= id '(' id* ')'
+ *   ::= binary LETTER number? (id, id)
+ *   ::= unary LETTER number? (id) *)
+let parse_prototype =
+  let rec parse_args accumulator = parser
+    | [< 'Token.Ident id; e=parse_args (id::accumulator) >] -> e
+    | [< >] -> accumulator
+  in
+  let parse_operator = parser
+    | [< 'Token.Unary >] -> "unary", 1
+    | [< 'Token.Binary >] -> "binary", 2
+  in
+  let parse_binary_precedence = parser
+    | [< 'Token.Number n >] -> int_of_float n
+    | [< >] -> 30
+  in
+  parser
+  | [< 'Token.Ident id;
+       'Token.Kwd '(' ?? "expected '(' in prototype";
+       args=parse_args [];
+       'Token.Kwd ')' ?? "expected ')' in prototype" >] ->
+      (* success. *)
+      Ast.Prototype (id, Array.of_list (List.rev args))
+  | [< (prefix, kind)=parse_operator;
+       'Token.Kwd op ?? "expected an operator";
+       (* Read the precedence if present. *)
+       binary_precedence=parse_binary_precedence;
+       'Token.Kwd '(' ?? "expected '(' in prototype";
+        args=parse_args [];
+       'Token.Kwd ')' ?? "expected ')' in prototype" >] ->
+      let name = prefix ^ (String.make 1 op) in
+      let args = Array.of_list (List.rev args) in
+
+      (* Verify right number of arguments for operator. *)
+      if Array.length args != kind
+      then raise (Stream.Error "invalid number of operands for operator")
+      else
+        if kind == 1 then
+          Ast.Prototype (name, args)
+        else
+          Ast.BinOpPrototype (name, args, binary_precedence)
+  | [< >] ->
+      raise (Stream.Error "expected function name in prototype")
+
+(* definition ::= 'def' prototype expression *)
+let parse_definition = parser
+  | [< 'Token.Def; p=parse_prototype; e=parse_expr >] ->
+      Ast.Function (p, e)
+
+(* toplevelexpr ::= expression *)
+let parse_toplevel = parser
+  | [< e=parse_expr >] ->
+      (* Make an anonymous proto. *)
+      Ast.Function (Ast.Prototype ("", [||]), e)
+
+(*  external ::= 'extern' prototype *)
+let parse_extern = parser
+  | [< 'Token.Extern; e=parse_prototype >] -> e
+
+
+ +
codegen.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Code Generation
+ *===----------------------------------------------------------------------===*)
+
+open Llvm
+
+exception Error of string
+
+let the_module = create_module "my cool jit"
+let builder = builder ()
+let named_values:(string, llvalue) Hashtbl.t = Hashtbl.create 10
+
+let rec codegen_expr = function
+  | Ast.Number n -> const_float double_type n
+  | Ast.Variable name ->
+      (try Hashtbl.find named_values name with
+        | Not_found -> raise (Error "unknown variable name"))
+  | Ast.Unary (op, operand) ->
+      let operand = codegen_expr operand in
+      let callee = "unary" ^ (String.make 1 op) in
+      let callee =
+        match lookup_function callee the_module with
+        | Some callee -> callee
+        | None -> raise (Error "unknown unary operator")
+      in
+      build_call callee [|operand|] "unop" builder
+  | Ast.Binary (op, lhs, rhs) ->
+      let lhs_val = codegen_expr lhs in
+      let rhs_val = codegen_expr rhs in
+      begin
+        match op with
+        | '+' -> build_add lhs_val rhs_val "addtmp" builder
+        | '-' -> build_sub lhs_val rhs_val "subtmp" builder
+        | '*' -> build_mul lhs_val rhs_val "multmp" builder
+        | '<' ->
+            (* Convert bool 0/1 to double 0.0 or 1.0 *)
+            let i = build_fcmp Fcmp.Ult lhs_val rhs_val "cmptmp" builder in
+            build_uitofp i double_type "booltmp" builder
+        | _ ->
+            (* If it wasn't a builtin binary operator, it must be a user defined
+             * one. Emit a call to it. *)
+            let callee = "binary" ^ (String.make 1 op) in
+            let callee =
+              match lookup_function callee the_module with
+              | Some callee -> callee
+              | None -> raise (Error "binary operator not found!")
+            in
+            build_call callee [|lhs_val; rhs_val|] "binop" builder
+      end
+  | Ast.Call (callee, args) ->
+      (* Look up the name in the module table. *)
+      let callee =
+        match lookup_function callee the_module with
+        | Some callee -> callee
+        | None -> raise (Error "unknown function referenced")
+      in
+      let params = params callee in
+
+      (* If argument mismatch error. *)
+      if Array.length params == Array.length args then () else
+        raise (Error "incorrect # arguments passed");
+      let args = Array.map codegen_expr args in
+      build_call callee args "calltmp" builder
+  | Ast.If (cond, then_, else_) ->
+      let cond = codegen_expr cond in
+
+      (* Convert condition to a bool by comparing equal to 0.0 *)
+      let zero = const_float double_type 0.0 in
+      let cond_val = build_fcmp Fcmp.One cond zero "ifcond" builder in
+
+      (* Grab the first block so that we might later add the conditional branch
+       * to it at the end of the function. *)
+      let start_bb = insertion_block builder in
+      let the_function = block_parent start_bb in
+
+      let then_bb = append_block "then" the_function in
+
+      (* Emit 'then' value. *)
+      position_at_end then_bb builder;
+      let then_val = codegen_expr then_ in
+
+      (* Codegen of 'then' can change the current block, update then_bb for the
+       * phi. We create a new name because one is used for the phi node, and the
+       * other is used for the conditional branch. *)
+      let new_then_bb = insertion_block builder in
+
+      (* Emit 'else' value. *)
+      let else_bb = append_block "else" the_function in
+      position_at_end else_bb builder;
+      let else_val = codegen_expr else_ in
+
+      (* Codegen of 'else' can change the current block, update else_bb for the
+       * phi. *)
+      let new_else_bb = insertion_block builder in
+
+      (* Emit merge block. *)
+      let merge_bb = append_block "ifcont" the_function in
+      position_at_end merge_bb builder;
+      let incoming = [(then_val, new_then_bb); (else_val, new_else_bb)] in
+      let phi = build_phi incoming "iftmp" builder in
+
+      (* Return to the start block to add the conditional branch. *)
+      position_at_end start_bb builder;
+      ignore (build_cond_br cond_val then_bb else_bb builder);
+
+      (* Set a unconditional branch at the end of the 'then' block and the
+       * 'else' block to the 'merge' block. *)
+      position_at_end new_then_bb builder; ignore (build_br merge_bb builder);
+      position_at_end new_else_bb builder; ignore (build_br merge_bb builder);
+
+      (* Finally, set the builder to the end of the merge block. *)
+      position_at_end merge_bb builder;
+
+      phi
+  | Ast.For (var_name, start, end_, step, body) ->
+      (* Emit the start code first, without 'variable' in scope. *)
+      let start_val = codegen_expr start in
+
+      (* Make the new basic block for the loop header, inserting after current
+       * block. *)
+      let preheader_bb = insertion_block builder in
+      let the_function = block_parent preheader_bb in
+      let loop_bb = append_block "loop" the_function in
+
+      (* Insert an explicit fall through from the current block to the
+       * loop_bb. *)
+      ignore (build_br loop_bb builder);
+
+      (* Start insertion in loop_bb. *)
+      position_at_end loop_bb builder;
+
+      (* Start the PHI node with an entry for start. *)
+      let variable = build_phi [(start_val, preheader_bb)] var_name builder in
+
+      (* Within the loop, the variable is defined equal to the PHI node. If it
+       * shadows an existing variable, we have to restore it, so save it
+       * now. *)
+      let old_val =
+        try Some (Hashtbl.find named_values var_name) with Not_found -> None
+      in
+      Hashtbl.add named_values var_name variable;
+
+      (* Emit the body of the loop.  This, like any other expr, can change the
+       * current BB.  Note that we ignore the value computed by the body, but
+       * don't allow an error *)
+      ignore (codegen_expr body);
+
+      (* Emit the step value. *)
+      let step_val =
+        match step with
+        | Some step -> codegen_expr step
+        (* If not specified, use 1.0. *)
+        | None -> const_float double_type 1.0
+      in
+
+      let next_var = build_add variable step_val "nextvar" builder in
+
+      (* Compute the end condition. *)
+      let end_cond = codegen_expr end_ in
+
+      (* Convert condition to a bool by comparing equal to 0.0. *)
+      let zero = const_float double_type 0.0 in
+      let end_cond = build_fcmp Fcmp.One end_cond zero "loopcond" builder in
+
+      (* Create the "after loop" block and insert it. *)
+      let loop_end_bb = insertion_block builder in
+      let after_bb = append_block "afterloop" the_function in
+
+      (* Insert the conditional branch into the end of loop_end_bb. *)
+      ignore (build_cond_br end_cond loop_bb after_bb builder);
+
+      (* Any new code will be inserted in after_bb. *)
+      position_at_end after_bb builder;
+
+      (* Add a new entry to the PHI node for the backedge. *)
+      add_incoming (next_var, loop_end_bb) variable;
+
+      (* Restore the unshadowed variable. *)
+      begin match old_val with
+      | Some old_val -> Hashtbl.add named_values var_name old_val
+      | None -> ()
+      end;
+
+      (* for expr always returns 0.0. *)
+      const_null double_type
+
+let codegen_proto = function
+  | Ast.Prototype (name, args) | Ast.BinOpPrototype (name, args, _) ->
+      (* Make the function type: double(double,double) etc. *)
+      let doubles = Array.make (Array.length args) double_type in
+      let ft = function_type double_type doubles in
+      let f =
+        match lookup_function name the_module with
+        | None -> declare_function name ft the_module
+
+        (* If 'f' conflicted, there was already something named 'name'. If it
+         * has a body, don't allow redefinition or reextern. *)
+        | Some f ->
+            (* If 'f' already has a body, reject this. *)
+            if block_begin f <> At_end f then
+              raise (Error "redefinition of function");
+
+            (* If 'f' took a different number of arguments, reject. *)
+            if element_type (type_of f) <> ft then
+              raise (Error "redefinition of function with different # args");
+            f
+      in
+
+      (* Set names for all arguments. *)
+      Array.iteri (fun i a ->
+        let n = args.(i) in
+        set_value_name n a;
+        Hashtbl.add named_values n a;
+      ) (params f);
+      f
+
+let codegen_func the_fpm = function
+  | Ast.Function (proto, body) ->
+      Hashtbl.clear named_values;
+      let the_function = codegen_proto proto in
+
+      (* If this is an operator, install it. *)
+      begin match proto with
+      | Ast.BinOpPrototype (name, args, prec) ->
+          let op = name.[String.length name - 1] in
+          Hashtbl.add Parser.binop_precedence op prec;
+      | _ -> ()
+      end;
+
+      (* Create a new basic block to start insertion into. *)
+      let bb = append_block "entry" the_function in
+      position_at_end bb builder;
+
+      try
+        let ret_val = codegen_expr body in
+
+        (* Finish off the function. *)
+        let _ = build_ret ret_val builder in
+
+        (* Validate the generated code, checking for consistency. *)
+        Llvm_analysis.assert_valid_function the_function;
+
+        (* Optimize the function. *)
+        let _ = PassManager.run_function the_function the_fpm in
+
+        the_function
+      with e ->
+        delete_function the_function;
+        raise e
+
+
+ +
toplevel.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Top-Level parsing and JIT Driver
+ *===----------------------------------------------------------------------===*)
+
+open Llvm
+open Llvm_executionengine
+
+(* top ::= definition | external | expression | ';' *)
+let rec main_loop the_fpm the_execution_engine stream =
+  match Stream.peek stream with
+  | None -> ()
+
+  (* ignore top-level semicolons. *)
+  | Some (Token.Kwd ';') ->
+      Stream.junk stream;
+      main_loop the_fpm the_execution_engine stream
+
+  | Some token ->
+      begin
+        try match token with
+        | Token.Def ->
+            let e = Parser.parse_definition stream in
+            print_endline "parsed a function definition.";
+            dump_value (Codegen.codegen_func the_fpm e);
+        | Token.Extern ->
+            let e = Parser.parse_extern stream in
+            print_endline "parsed an extern.";
+            dump_value (Codegen.codegen_proto e);
+        | _ ->
+            (* Evaluate a top-level expression into an anonymous function. *)
+            let e = Parser.parse_toplevel stream in
+            print_endline "parsed a top-level expr";
+            let the_function = Codegen.codegen_func the_fpm e in
+            dump_value the_function;
+
+            (* JIT the function, returning a function pointer. *)
+            let result = ExecutionEngine.run_function the_function [||]
+              the_execution_engine in
+
+            print_string "Evaluated to ";
+            print_float (GenericValue.as_float double_type result);
+            print_newline ();
+        with Stream.Error s | Codegen.Error s ->
+          (* Skip token for error recovery. *)
+          Stream.junk stream;
+          print_endline s;
+      end;
+      print_string "ready> "; flush stdout;
+      main_loop the_fpm the_execution_engine stream
+
+
+ +
toy.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Main driver code.
+ *===----------------------------------------------------------------------===*)
+
+open Llvm
+open Llvm_executionengine
+open Llvm_target
+open Llvm_scalar_opts
+
+let main () =
+  (* Install standard binary operators.
+   * 1 is the lowest precedence. *)
+  Hashtbl.add Parser.binop_precedence '<' 10;
+  Hashtbl.add Parser.binop_precedence '+' 20;
+  Hashtbl.add Parser.binop_precedence '-' 20;
+  Hashtbl.add Parser.binop_precedence '*' 40;    (* highest. *)
+
+  (* Prime the first token. *)
+  print_string "ready> "; flush stdout;
+  let stream = Lexer.lex (Stream.of_channel stdin) in
+
+  (* Create the JIT. *)
+  let the_module_provider = ModuleProvider.create Codegen.the_module in
+  let the_execution_engine = ExecutionEngine.create the_module_provider in
+  let the_fpm = PassManager.create_function the_module_provider in
+
+  (* Set up the optimizer pipeline.  Start with registering info about how the
+   * target lays out data structures. *)
+  TargetData.add (ExecutionEngine.target_data the_execution_engine) the_fpm;
+
+  (* Do simple "peephole" optimizations and bit-twiddling optzn. *)
+  add_instruction_combining the_fpm;
+
+  (* reassociate expressions. *)
+  add_reassociation the_fpm;
+
+  (* Eliminate Common SubExpressions. *)
+  add_gvn the_fpm;
+
+  (* Simplify the control flow graph (deleting unreachable blocks, etc). *)
+  add_cfg_simplification the_fpm;
+
+  (* Run the main "interpreter loop" now. *)
+  Toplevel.main_loop the_fpm the_execution_engine stream;
+
+  (* Print out all the generated code. *)
+  dump_module Codegen.the_module
+;;
+
+main ()
+
+
+ +
bindings.c
+
+
+#include <stdio.h>
+
+/* putchard - putchar that takes a double and returns 0. */
+extern double putchard(double X) {
+  putchar((char)X);
+  return 0;
+}
+
+/* printd - printf that takes a double prints it as "%f\n", returning 0. */
+extern double printd(double X) {
+  printf("%f\n", X);
+  return 0;
+}
+
+
+
+ +Next: Extending the language: mutable variables / +SSA construction +
+ + +
+
+ Valid CSS! + Valid HTML 4.01! + + Chris Lattner
+ Erick Tryzelaar
+ The LLVM Compiler Infrastructure
+ Last modified: $Date: 2007-10-17 11:05:13 -0700 (Wed, 17 Oct 2007) $ +
+ + diff --git a/docs/tutorial/OCamlLangImpl7.html b/docs/tutorial/OCamlLangImpl7.html new file mode 100644 index 00000000000..abda44011ca --- /dev/null +++ b/docs/tutorial/OCamlLangImpl7.html @@ -0,0 +1,1902 @@ + + + + + Kaleidoscope: Extending the Language: Mutable Variables / SSA + construction + + + + + + + + +
Kaleidoscope: Extending the Language: Mutable Variables
+ + + +
+

+ Written by Chris Lattner + and Erick Tryzelaar +

+
+ + +
Chapter 7 Introduction
+ + +
+ +

Welcome to Chapter 7 of the "Implementing a language +with LLVM" tutorial. In chapters 1 through 6, we've built a very +respectable, albeit simple, functional +programming language. In our journey, we learned some parsing techniques, +how to build and represent an AST, how to build LLVM IR, and how to optimize +the resultant code as well as JIT compile it.

+ +

While Kaleidoscope is interesting as a functional language, the fact that it +is functional makes it "too easy" to generate LLVM IR for it. In particular, a +functional language makes it very easy to build LLVM IR directly in SSA form. +Since LLVM requires that the input code be in SSA form, this is a very nice +property and it is often unclear to newcomers how to generate code for an +imperative language with mutable variables.

+ +

The short (and happy) summary of this chapter is that there is no need for +your front-end to build SSA form: LLVM provides highly tuned and well tested +support for this, though the way it works is a bit unexpected for some.

+ +
+ + +
Why is this a hard problem?
+ + +
+ +

+To understand why mutable variables cause complexities in SSA construction, +consider this extremely simple C example: +

+ +
+
+int G, H;
+int test(_Bool Condition) {
+  int X;
+  if (Condition)
+    X = G;
+  else
+    X = H;
+  return X;
+}
+
+
+ +

In this case, we have the variable "X", whose value depends on the path +executed in the program. Because there are two different possible values for X +before the return instruction, a PHI node is inserted to merge the two values. +The LLVM IR that we want for this example looks like this:

+ +
+
+@G = weak global i32 0   ; type of @G is i32*
+@H = weak global i32 0   ; type of @H is i32*
+
+define i32 @test(i1 %Condition) {
+entry:
+  br i1 %Condition, label %cond_true, label %cond_false
+
+cond_true:
+  %X.0 = load i32* @G
+  br label %cond_next
+
+cond_false:
+  %X.1 = load i32* @H
+  br label %cond_next
+
+cond_next:
+  %X.2 = phi i32 [ %X.1, %cond_false ], [ %X.0, %cond_true ]
+  ret i32 %X.2
+}
+
+
+ +

In this example, the loads from the G and H global variables are explicit in +the LLVM IR, and they live in the then/else branches of the if statement +(cond_true/cond_false). In order to merge the incoming values, the X.2 phi node +in the cond_next block selects the right value to use based on where control +flow is coming from: if control flow comes from the cond_false block, X.2 gets +the value of X.1. Alternatively, if control flow comes from cond_true, it gets +the value of X.0. The intent of this chapter is not to explain the details of +SSA form. For more information, see one of the many online +references.

+ +

The question for this article is "who places the phi nodes when lowering +assignments to mutable variables?". The issue here is that LLVM +requires that its IR be in SSA form: there is no "non-ssa" mode for it. +However, SSA construction requires non-trivial algorithms and data structures, +so it is inconvenient and wasteful for every front-end to have to reproduce this +logic.

+ +
+ + +
Memory in LLVM
+ + +
+ +

The 'trick' here is that while LLVM does require all register values to be +in SSA form, it does not require (or permit) memory objects to be in SSA form. +In the example above, note that the loads from G and H are direct accesses to +G and H: they are not renamed or versioned. This differs from some other +compiler systems, which do try to version memory objects. In LLVM, instead of +encoding dataflow analysis of memory into the LLVM IR, it is handled with Analysis Passes which are computed on +demand.

+ +

+With this in mind, the high-level idea is that we want to make a stack variable +(which lives in memory, because it is on the stack) for each mutable object in +a function. To take advantage of this trick, we need to talk about how LLVM +represents stack variables. +

+ +

In LLVM, all memory accesses are explicit with load/store instructions, and +it is carefully designed not to have (or need) an "address-of" operator. Notice +how the type of the @G/@H global variables is actually "i32*" even though the +variable is defined as "i32". What this means is that @G defines space +for an i32 in the global data area, but its name actually refers to the +address for that space. Stack variables work the same way, except that instead of +being declared with global variable definitions, they are declared with the +LLVM alloca instruction:

+ +
+
+define i32 @example() {
+entry:
+  %X = alloca i32           ; type of %X is i32*.
+  ...
+  %tmp = load i32* %X       ; load the stack value %X from the stack.
+  %tmp2 = add i32 %tmp, 1   ; increment it
+  store i32 %tmp2, i32* %X  ; store it back
+  ...
+
+
+ +

This code shows an example of how you can declare and manipulate a stack +variable in the LLVM IR. Stack memory allocated with the alloca instruction is +fully general: you can pass the address of the stack slot to functions, you can +store it in other variables, etc. In our example above, we could rewrite the +example to use the alloca technique to avoid using a PHI node:

+ +
+
+@G = weak global i32 0   ; type of @G is i32*
+@H = weak global i32 0   ; type of @H is i32*
+
+define i32 @test(i1 %Condition) {
+entry:
+  %X = alloca i32           ; type of %X is i32*.
+  br i1 %Condition, label %cond_true, label %cond_false
+
+cond_true:
+  %X.0 = load i32* @G
+        store i32 %X.0, i32* %X   ; Update X
+  br label %cond_next
+
+cond_false:
+  %X.1 = load i32* @H
+        store i32 %X.1, i32* %X   ; Update X
+  br label %cond_next
+
+cond_next:
+  %X.2 = load i32* %X       ; Read X
+  ret i32 %X.2
+}
+
+
+ +

With this, we have discovered a way to handle arbitrary mutable variables +without the need to create Phi nodes at all:

+ +
    +
  1. Each mutable variable becomes a stack allocation.
    2. +
  2. Each read of the variable becomes a load from the stack.
    3. +
  3. Each update of the variable becomes a store to the stack.
    4. +
  4. Taking the address of a variable just uses the stack address directly.
    5. +
+ +

While this solution has solved our immediate problem, it introduced another +one: we have now apparently introduced a lot of stack traffic for very simple +and common operations, a major performance problem. Fortunately for us, the +LLVM optimizer has a highly-tuned optimization pass named "mem2reg" that handles +this case, promoting allocas like this into SSA registers, inserting Phi nodes +as appropriate. If you run this example through the pass, for example, you'll +get:

+ +
+
+$ llvm-as < example.ll | opt -mem2reg | llvm-dis
+@G = weak global i32 0
+@H = weak global i32 0
+
+define i32 @test(i1 %Condition) {
+entry:
+  br i1 %Condition, label %cond_true, label %cond_false
+
+cond_true:
+  %X.0 = load i32* @G
+  br label %cond_next
+
+cond_false:
+  %X.1 = load i32* @H
+  br label %cond_next
+
+cond_next:
+  %X.01 = phi i32 [ %X.1, %cond_false ], [ %X.0, %cond_true ]
+  ret i32 %X.01
+}
+
+
+ +

The mem2reg pass implements the standard "iterated dominance frontier" +algorithm for constructing SSA form and has a number of optimizations that speed +up (very common) degenerate cases. The mem2reg optimization pass is the answer +to dealing with mutable variables, and we highly recommend that you depend on +it. Note that mem2reg only works on variables in certain circumstances:

+ +
    +
  1. mem2reg is alloca-driven: it looks for allocas and if it can handle them, it +promotes them. It does not apply to global variables or heap allocations.
    2. + +
  2. mem2reg only looks for alloca instructions in the entry block of the +function. Being in the entry block guarantees that the alloca is only executed +once, which makes analysis simpler.
    3. + +
  3. mem2reg only promotes allocas whose uses are direct loads and stores. If +the address of the stack object is passed to a function, or if any funny pointer +arithmetic is involved, the alloca will not be promoted.
    4. + +
  4. mem2reg only works on allocas of first class +values (such as pointers, scalars and vectors), and only if the array size +of the allocation is 1 (or missing in the .ll file). mem2reg is not capable of +promoting structs or arrays to registers. Note that the "scalarrepl" pass is +more powerful and can promote structs, "unions", and arrays in many cases.
    5. + +
+ +

+All of these properties are easy to satisfy for most imperative languages, and +we'll illustrate it below with Kaleidoscope. The final question you may be +asking is: should I bother with this nonsense for my front-end? Wouldn't it be +better if I just did SSA construction directly, avoiding use of the mem2reg +optimization pass? In short, we strongly recommend that you use this technique +for building SSA form, unless there is an extremely good reason not to. Using +this technique is:

+ +
    +
  • Proven and well tested: llvm-gcc and clang both use this technique for local +mutable variables. As such, the most common clients of LLVM are using this to +handle a bulk of their variables. You can be sure that bugs are found fast and +fixed early.
    • + +
  • Extremely Fast: mem2reg has a number of special cases that make it fast in +common cases as well as fully general. For example, it has fast-paths for +variables that are only used in a single block, variables that only have one +assignment point, good heuristics to avoid insertion of unneeded phi nodes, etc. +
    • + +
  • Needed for debug info generation: +Debug information in LLVM relies on having the address of the variable +exposed so that debug info can be attached to it. This technique dovetails +very naturally with this style of debug info.
    • +
+ +

If nothing else, this makes it much easier to get your front-end up and +running, and is very simple to implement. Lets extend Kaleidoscope with mutable +variables now! +

+ +
+ + +
Mutable Variables in +Kaleidoscope
+ + +
+ +

Now that we know the sort of problem we want to tackle, lets see what this +looks like in the context of our little Kaleidoscope language. We're going to +add two features:

+ +
    +
  1. The ability to mutate variables with the '=' operator.
    2. +
  2. The ability to define new variables.
    3. +
+ +

While the first item is really what this is about, we only have variables +for incoming arguments as well as for induction variables, and redefining those only +goes so far :). Also, the ability to define new variables is a +useful thing regardless of whether you will be mutating them. Here's a +motivating example that shows how we could use these:

+ +
+
+# Define ':' for sequencing: as a low-precedence operator that ignores operands
+# and just returns the RHS.
+def binary : 1 (x y) y;
+
+# Recursive fib, we could do this before.
+def fib(x)
+  if (x < 3) then
+    1
+  else
+    fib(x-1)+fib(x-2);
+
+# Iterative fib.
+def fibi(x)
+  var a = 1, b = 1, c in
+  (for i = 3, i < x in
+     c = a + b :
+     a = b :
+     b = c) :
+  b;
+
+# Call it.
+fibi(10);
+
+
+ +

+In order to mutate variables, we have to change our existing variables to use +the "alloca trick". Once we have that, we'll add our new operator, then extend +Kaleidoscope to support new variable definitions. +

+ +
+ + +
Adjusting Existing Variables for +Mutation
+ + +
+ +

+The symbol table in Kaleidoscope is managed at code generation time by the +'named_values' map. This map currently keeps track of the LLVM +"Value*" that holds the double value for the named variable. In order to +support mutation, we need to change this slightly, so that it +named_values holds the memory location of the variable in +question. Note that this change is a refactoring: it changes the structure of +the code, but does not (by itself) change the behavior of the compiler. All of +these changes are isolated in the Kaleidoscope code generator.

+ +

+At this point in Kaleidoscope's development, it only supports variables for two +things: incoming arguments to functions and the induction variable of 'for' +loops. For consistency, we'll allow mutation of these variables in addition to +other user-defined variables. This means that these will both need memory +locations. +

+ +

To start our transformation of Kaleidoscope, we'll change the +named_values map so that it maps to AllocaInst* instead of Value*. +Once we do this, the C++ compiler will tell us what parts of the code we need to +update:

+ +

Note: the ocaml bindings currently model both Value*s and +AllocInst*s as Llvm.llvalues, but this may change in the +future to be more type safe.

+ +
+
+let named_values:(string, llvalue) Hashtbl.t = Hashtbl.create 10
+
+
+ +

Also, since we will need to create these alloca's, we'll use a helper +function that ensures that the allocas are created in the entry block of the +function:

+ +
+
+(* Create an alloca instruction in the entry block of the function. This
+ * is used for mutable variables etc. *)
+let create_entry_block_alloca the_function var_name =
+  let builder = builder_at (instr_begin (entry_block the_function)) in
+  build_alloca double_type var_name builder
+
+
+ +

This funny looking code creates an Llvm.llbuilder object that is +pointing at the first instruction of the entry block. It then creates an alloca +with the expected name and returns it. Because all values in Kaleidoscope are +doubles, there is no need to pass in a type to use.

+ +

With this in place, the first functionality change we want to make is to +variable references. In our new scheme, variables live on the stack, so code +generating a reference to them actually needs to produce a load from the stack +slot:

+ +
+
+let rec codegen_expr = function
+  ...
+  | Ast.Variable name ->
+      let v = try Hashtbl.find named_values name with
+        | Not_found -> raise (Error "unknown variable name")
+      in
+      (* Load the value. *)
+      build_load v name builder
+
+
+ +

As you can see, this is pretty straightforward. Now we need to update the +things that define the variables to set up the alloca. We'll start with +codegen_expr Ast.For ... (see the full code listing +for the unabridged code):

+ +
+
+  | Ast.For (var_name, start, end_, step, body) ->
+      let the_function = block_parent (insertion_block builder) in
+
+      (* Create an alloca for the variable in the entry block. *)
+      let alloca = create_entry_block_alloca the_function var_name in
+
+      (* Emit the start code first, without 'variable' in scope. *)
+      let start_val = codegen_expr start in
+
+      (* Store the value into the alloca. *)
+      ignore(build_store start_val alloca builder);
+
+      ...
+
+      (* Within the loop, the variable is defined equal to the PHI node. If it
+       * shadows an existing variable, we have to restore it, so save it
+       * now. *)
+      let old_val =
+        try Some (Hashtbl.find named_values var_name) with Not_found -> None
+      in
+      Hashtbl.add named_values var_name alloca;
+
+      ...
+
+      (* Compute the end condition. *)
+      let end_cond = codegen_expr end_ in
+
+      (* Reload, increment, and restore the alloca. This handles the case where
+       * the body of the loop mutates the variable. *)
+      let cur_var = build_load alloca var_name builder in
+      let next_var = build_add cur_var step_val "nextvar" builder in
+      ignore(build_store next_var alloca builder);
+      ...
+
+
+ +

This code is virtually identical to the code before we allowed mutable variables. +The big difference is that we no longer have to construct a PHI node, and we use +load/store to access the variable as needed.

+ +

To support mutable argument variables, we need to also make allocas for them. +The code for this is also pretty simple:

+ +
+
+(* Create an alloca for each argument and register the argument in the symbol
+ * table so that references to it will succeed. *)
+let create_argument_allocas the_function proto =
+  let args = match proto with
+    | Ast.Prototype (_, args) | Ast.BinOpPrototype (_, args, _) -> args
+  in
+  Array.iteri (fun i ai ->
+    let var_name = args.(i) in
+    (* Create an alloca for this variable. *)
+    let alloca = create_entry_block_alloca the_function var_name in
+
+    (* Store the initial value into the alloca. *)
+    ignore(build_store ai alloca builder);
+
+    (* Add arguments to variable symbol table. *)
+    Hashtbl.add named_values var_name alloca;
+  ) (params the_function)
+
+
+ +

For each argument, we make an alloca, store the input value to the function +into the alloca, and register the alloca as the memory location for the +argument. This method gets invoked by Codegen.codegen_func right after +it sets up the entry block for the function.

+ +

The final missing piece is adding the mem2reg pass, which allows us to get +good codegen once again:

+ +
+
+let main () =
+  ...
+  let the_fpm = PassManager.create_function the_module_provider in
+
+  (* Set up the optimizer pipeline.  Start with registering info about how the
+   * target lays out data structures. *)
+  TargetData.add (ExecutionEngine.target_data the_execution_engine) the_fpm;
+
+  (* Promote allocas to registers. *)
+  add_memory_to_register_promotion the_fpm;
+
+  (* Do simple "peephole" optimizations and bit-twiddling optzn. *)
+  add_instruction_combining the_fpm;
+
+  (* reassociate expressions. *)
+  add_reassociation the_fpm;
+
+
+ +

It is interesting to see what the code looks like before and after the +mem2reg optimization runs. For example, this is the before/after code for our +recursive fib function. Before the optimization:

+ +
+
+define double @fib(double %x) {
+entry:
+  %x1 = alloca double
+  store double %x, double* %x1
+  %x2 = load double* %x1
+  %cmptmp = fcmp ult double %x2, 3.000000e+00
+  %booltmp = uitofp i1 %cmptmp to double
+  %ifcond = fcmp one double %booltmp, 0.000000e+00
+  br i1 %ifcond, label %then, label %else
+
+then:    ; preds = %entry
+  br label %ifcont
+
+else:    ; preds = %entry
+  %x3 = load double* %x1
+  %subtmp = sub double %x3, 1.000000e+00
+  %calltmp = call double @fib( double %subtmp )
+  %x4 = load double* %x1
+  %subtmp5 = sub double %x4, 2.000000e+00
+  %calltmp6 = call double @fib( double %subtmp5 )
+  %addtmp = add double %calltmp, %calltmp6
+  br label %ifcont
+
+ifcont:    ; preds = %else, %then
+  %iftmp = phi double [ 1.000000e+00, %then ], [ %addtmp, %else ]
+  ret double %iftmp
+}
+
+
+ +

Here there is only one variable (x, the input argument) but you can still +see the extremely simple-minded code generation strategy we are using. In the +entry block, an alloca is created, and the initial input value is stored into +it. Each reference to the variable does a reload from the stack. Also, note +that we didn't modify the if/then/else expression, so it still inserts a PHI +node. While we could make an alloca for it, it is actually easier to create a +PHI node for it, so we still just make the PHI.

+ +

Here is the code after the mem2reg pass runs:

+ +
+
+define double @fib(double %x) {
+entry:
+  %cmptmp = fcmp ult double %x, 3.000000e+00
+  %booltmp = uitofp i1 %cmptmp to double
+  %ifcond = fcmp one double %booltmp, 0.000000e+00
+  br i1 %ifcond, label %then, label %else
+
+then:
+  br label %ifcont
+
+else:
+  %subtmp = sub double %x, 1.000000e+00
+  %calltmp = call double @fib( double %subtmp )
+  %subtmp5 = sub double %x, 2.000000e+00
+  %calltmp6 = call double @fib( double %subtmp5 )
+  %addtmp = add double %calltmp, %calltmp6
+  br label %ifcont
+
+ifcont:    ; preds = %else, %then
+  %iftmp = phi double [ 1.000000e+00, %then ], [ %addtmp, %else ]
+  ret double %iftmp
+}
+
+
+ +

This is a trivial case for mem2reg, since there are no redefinitions of the +variable. The point of showing this is to calm your tension about inserting +such blatent inefficiencies :).

+ +

After the rest of the optimizers run, we get:

+ +
+
+define double @fib(double %x) {
+entry:
+  %cmptmp = fcmp ult double %x, 3.000000e+00
+  %booltmp = uitofp i1 %cmptmp to double
+  %ifcond = fcmp ueq double %booltmp, 0.000000e+00
+  br i1 %ifcond, label %else, label %ifcont
+
+else:
+  %subtmp = sub double %x, 1.000000e+00
+  %calltmp = call double @fib( double %subtmp )
+  %subtmp5 = sub double %x, 2.000000e+00
+  %calltmp6 = call double @fib( double %subtmp5 )
+  %addtmp = add double %calltmp, %calltmp6
+  ret double %addtmp
+
+ifcont:
+  ret double 1.000000e+00
+}
+
+
+ +

Here we see that the simplifycfg pass decided to clone the return instruction +into the end of the 'else' block. This allowed it to eliminate some branches +and the PHI node.

+ +

Now that all symbol table references are updated to use stack variables, +we'll add the assignment operator.

+ +
+ + +
New Assignment Operator
+ + +
+ +

With our current framework, adding a new assignment operator is really +simple. We will parse it just like any other binary operator, but handle it +internally (instead of allowing the user to define it). The first step is to +set a precedence:

+ +
+
+let main () =
+  (* Install standard binary operators.
+   * 1 is the lowest precedence. *)
+  Hashtbl.add Parser.binop_precedence '=' 2;
+  Hashtbl.add Parser.binop_precedence '<' 10;
+  Hashtbl.add Parser.binop_precedence '+' 20;
+  Hashtbl.add Parser.binop_precedence '-' 20;
+  ...
+
+
+ +

Now that the parser knows the precedence of the binary operator, it takes +care of all the parsing and AST generation. We just need to implement codegen +for the assignment operator. This looks like:

+ +
+
+let rec codegen_expr = function
+      begin match op with
+      | '=' ->
+          (* Special case '=' because we don't want to emit the LHS as an
+           * expression. *)
+          let name =
+            match lhs with
+            | Ast.Variable name -> name
+            | _ -> raise (Error "destination of '=' must be a variable")
+          in
+
+
+ +

Unlike the rest of the binary operators, our assignment operator doesn't +follow the "emit LHS, emit RHS, do computation" model. As such, it is handled +as a special case before the other binary operators are handled. The other +strange thing is that it requires the LHS to be a variable. It is invalid to +have "(x+1) = expr" - only things like "x = expr" are allowed. +

+ + +
+
+          (* Codegen the rhs. *)
+          let val_ = codegen_expr rhs in
+
+          (* Lookup the name. *)
+          let variable = try Hashtbl.find named_values name with
+          | Not_found -> raise (Error "unknown variable name")
+          in
+          ignore(build_store val_ variable builder);
+          val_
+      | _ ->
+			...
+
+
+ +

Once we have the variable, codegen'ing the assignment is straightforward: +we emit the RHS of the assignment, create a store, and return the computed +value. Returning a value allows for chained assignments like "X = (Y = Z)".

+ +

Now that we have an assignment operator, we can mutate loop variables and +arguments. For example, we can now run code like this:

+ +
+
+# Function to print a double.
+extern printd(x);
+
+# Define ':' for sequencing: as a low-precedence operator that ignores operands
+# and just returns the RHS.
+def binary : 1 (x y) y;
+
+def test(x)
+  printd(x) :
+  x = 4 :
+  printd(x);
+
+test(123);
+
+
+ +

When run, this example prints "123" and then "4", showing that we did +actually mutate the value! Okay, we have now officially implemented our goal: +getting this to work requires SSA construction in the general case. However, +to be really useful, we want the ability to define our own local variables, lets +add this next! +

+ +
+ + +
User-defined Local +Variables
+ + +
+ +

Adding var/in is just like any other other extensions we made to +Kaleidoscope: we extend the lexer, the parser, the AST and the code generator. +The first step for adding our new 'var/in' construct is to extend the lexer. +As before, this is pretty trivial, the code looks like this:

+ +
+
+type token =
+  ...
+  (* var definition *)
+  | Var
+
+...
+
+and lex_ident buffer = parser
+      ...
+      | "in" -> [< 'Token.In; stream >]
+      | "binary" -> [< 'Token.Binary; stream >]
+      | "unary" -> [< 'Token.Unary; stream >]
+      | "var" -> [< 'Token.Var; stream >]
+      ...
+
+
+ +

The next step is to define the AST node that we will construct. For var/in, +it looks like this:

+ +
+
+type expr =
+  ...
+  (* variant for var/in. *)
+  | Var of (string * expr option) array * expr
+  ...
+
+
+ +

var/in allows a list of names to be defined all at once, and each name can +optionally have an initializer value. As such, we capture this information in +the VarNames vector. Also, var/in has a body, this body is allowed to access +the variables defined by the var/in.

+ +

With this in place, we can define the parser pieces. The first thing we do +is add it as a primary expression:

+ +
+
+(* primary
+ *   ::= identifier
+ *   ::= numberexpr
+ *   ::= parenexpr
+ *   ::= ifexpr
+ *   ::= forexpr
+ *   ::= varexpr *)
+let rec parse_primary = parser
+  ...
+  (* varexpr
+   *   ::= 'var' identifier ('=' expression?
+   *             (',' identifier ('=' expression)?)* 'in' expression *)
+  | [< 'Token.Var;
+       (* At least one variable name is required. *)
+       'Token.Ident id ?? "expected identifier after var";
+       init=parse_var_init;
+       var_names=parse_var_names [(id, init)];
+       (* At this point, we have to have 'in'. *)
+       'Token.In ?? "expected 'in' keyword after 'var'";
+       body=parse_expr >] ->
+      Ast.Var (Array.of_list (List.rev var_names), body)
+
+...
+
+and parse_var_init = parser
+  (* read in the optional initializer. *)
+  | [< 'Token.Kwd '='; e=parse_expr >] -> Some e
+  | [< >] -> None
+
+and parse_var_names accumulator = parser
+  | [< 'Token.Kwd ',';
+       'Token.Ident id ?? "expected identifier list after var";
+       init=parse_var_init;
+       e=parse_var_names ((id, init) :: accumulator) >] -> e
+  | [< >] -> accumulator
+
+
+ +

Now that we can parse and represent the code, we need to support emission of +LLVM IR for it. This code starts out with:

+ +
+
+let rec codegen_expr = function
+  ...
+  | Ast.Var (var_names, body)
+      let old_bindings = ref [] in
+
+      let the_function = block_parent (insertion_block builder) in
+
+      (* Register all variables and emit their initializer. *)
+      Array.iter (fun (var_name, init) ->
+
+
+ +

Basically it loops over all the variables, installing them one at a time. +For each variable we put into the symbol table, we remember the previous value +that we replace in OldBindings.

+ +
+
+        (* Emit the initializer before adding the variable to scope, this
+         * prevents the initializer from referencing the variable itself, and
+         * permits stuff like this:
+         *   var a = 1 in
+         *     var a = a in ...   # refers to outer 'a'. *)
+        let init_val =
+          match init with
+          | Some init -> codegen_expr init
+          (* If not specified, use 0.0. *)
+          | None -> const_float double_type 0.0
+        in
+
+        let alloca = create_entry_block_alloca the_function var_name in
+        ignore(build_store init_val alloca builder);
+
+        (* Remember the old variable binding so that we can restore the binding
+         * when we unrecurse. *)
+
+        begin
+          try
+            let old_value = Hashtbl.find named_values var_name in
+            old_bindings := (var_name, old_value) :: !old_bindings;
+          with Not_found > ()
+        end;
+
+        (* Remember this binding. *)
+        Hashtbl.add named_values var_name alloca;
+      ) var_names;
+
+
+ +

There are more comments here than code. The basic idea is that we emit the +initializer, create the alloca, then update the symbol table to point to it. +Once all the variables are installed in the symbol table, we evaluate the body +of the var/in expression:

+ +
+
+      (* Codegen the body, now that all vars are in scope. *)
+      let body_val = codegen_expr body in
+
+
+ +

Finally, before returning, we restore the previous variable bindings:

+ +
+
+      (* Pop all our variables from scope. *)
+      List.iter (fun (var_name, old_value) ->
+        Hashtbl.add named_values var_name old_value
+      ) !old_bindings;
+
+      (* Return the body computation. *)
+      body_val
+
+
+ +

The end result of all of this is that we get properly scoped variable +definitions, and we even (trivially) allow mutation of them :).

+ +

With this, we completed what we set out to do. Our nice iterative fib +example from the intro compiles and runs just fine. The mem2reg pass optimizes +all of our stack variables into SSA registers, inserting PHI nodes where needed, +and our front-end remains simple: no "iterated dominance frontier" computation +anywhere in sight.

+ +
+ + +
Full Code Listing
+ + +
+ +

+Here is the complete code listing for our running example, enhanced with mutable +variables and var/in support. To build this example, use: +

+ +
+
+# Compile
+ocamlbuild toy.byte
+# Run
+./toy.byte
+
+
+ +

Here is the code:

+ +
+
_tags:
+
+
+<{lexer,parser}.ml>: use_camlp4, pp(camlp4of)
+<*.{byte,native}>: g++, use_llvm, use_llvm_analysis
+<*.{byte,native}>: use_llvm_executionengine, use_llvm_target
+<*.{byte,native}>: use_llvm_scalar_opts, use_bindings
+
+
+ +
myocamlbuild.ml:
+
+
+open Ocamlbuild_plugin;;
+
+ocaml_lib ~extern:true "llvm";;
+ocaml_lib ~extern:true "llvm_analysis";;
+ocaml_lib ~extern:true "llvm_executionengine";;
+ocaml_lib ~extern:true "llvm_target";;
+ocaml_lib ~extern:true "llvm_scalar_opts";;
+
+flag ["link"; "ocaml"; "g++"] (S[A"-cc"; A"g++"]);;
+dep ["link"; "ocaml"; "use_bindings"] ["bindings.o"];;
+
+
+ +
token.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Lexer Tokens
+ *===----------------------------------------------------------------------===*)
+
+(* The lexer returns these 'Kwd' if it is an unknown character, otherwise one of
+ * these others for known things. *)
+type token =
+  (* commands *)
+  | Def | Extern
+
+  (* primary *)
+  | Ident of string | Number of float
+
+  (* unknown *)
+  | Kwd of char
+
+  (* control *)
+  | If | Then | Else
+  | For | In
+
+  (* operators *)
+  | Binary | Unary
+
+  (* var definition *)
+  | Var
+
+
+ +
lexer.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Lexer
+ *===----------------------------------------------------------------------===*)
+
+let rec lex = parser
+  (* Skip any whitespace. *)
+  | [< ' (' ' | '\n' | '\r' | '\t'); stream >] -> lex stream
+
+  (* identifier: [a-zA-Z][a-zA-Z0-9] *)
+  | [< ' ('A' .. 'Z' | 'a' .. 'z' as c); stream >] ->
+      let buffer = Buffer.create 1 in
+      Buffer.add_char buffer c;
+      lex_ident buffer stream
+
+  (* number: [0-9.]+ *)
+  | [< ' ('0' .. '9' as c); stream >] ->
+      let buffer = Buffer.create 1 in
+      Buffer.add_char buffer c;
+      lex_number buffer stream
+
+  (* Comment until end of line. *)
+  | [< ' ('#'); stream >] ->
+      lex_comment stream
+
+  (* Otherwise, just return the character as its ascii value. *)
+  | [< 'c; stream >] ->
+      [< 'Token.Kwd c; lex stream >]
+
+  (* end of stream. *)
+  | [< >] -> [< >]
+
+and lex_number buffer = parser
+  | [< ' ('0' .. '9' | '.' as c); stream >] ->
+      Buffer.add_char buffer c;
+      lex_number buffer stream
+  | [< stream=lex >] ->
+      [< 'Token.Number (float_of_string (Buffer.contents buffer)); stream >]
+
+and lex_ident buffer = parser
+  | [< ' ('A' .. 'Z' | 'a' .. 'z' | '0' .. '9' as c); stream >] ->
+      Buffer.add_char buffer c;
+      lex_ident buffer stream
+  | [< stream=lex >] ->
+      match Buffer.contents buffer with
+      | "def" -> [< 'Token.Def; stream >]
+      | "extern" -> [< 'Token.Extern; stream >]
+      | "if" -> [< 'Token.If; stream >]
+      | "then" -> [< 'Token.Then; stream >]
+      | "else" -> [< 'Token.Else; stream >]
+      | "for" -> [< 'Token.For; stream >]
+      | "in" -> [< 'Token.In; stream >]
+      | "binary" -> [< 'Token.Binary; stream >]
+      | "unary" -> [< 'Token.Unary; stream >]
+      | "var" -> [< 'Token.Var; stream >]
+      | id -> [< 'Token.Ident id; stream >]
+
+and lex_comment = parser
+  | [< ' ('\n'); stream=lex >] -> stream
+  | [< 'c; e=lex_comment >] -> e
+  | [< >] -> [< >]
+
+
+ +
ast.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Abstract Syntax Tree (aka Parse Tree)
+ *===----------------------------------------------------------------------===*)
+
+(* expr - Base type for all expression nodes. *)
+type expr =
+  (* variant for numeric literals like "1.0". *)
+  | Number of float
+
+  (* variant for referencing a variable, like "a". *)
+  | Variable of string
+
+  (* variant for a unary operator. *)
+  | Unary of char * expr
+
+  (* variant for a binary operator. *)
+  | Binary of char * expr * expr
+
+  (* variant for function calls. *)
+  | Call of string * expr array
+
+  (* variant for if/then/else. *)
+  | If of expr * expr * expr
+
+  (* variant for for/in. *)
+  | For of string * expr * expr * expr option * expr
+
+  (* variant for var/in. *)
+  | Var of (string * expr option) array * expr
+
+(* proto - This type represents the "prototype" for a function, which captures
+ * its name, and its argument names (thus implicitly the number of arguments the
+ * function takes). *)
+type proto =
+  | Prototype of string * string array
+  | BinOpPrototype of string * string array * int
+
+(* func - This type represents a function definition itself. *)
+type func = Function of proto * expr
+
+
+ +
parser.ml:
+
+
+(*===---------------------------------------------------------------------===
+ * Parser
+ *===---------------------------------------------------------------------===*)
+
+(* binop_precedence - This holds the precedence for each binary operator that is
+ * defined *)
+let binop_precedence:(char, int) Hashtbl.t = Hashtbl.create 10
+
+(* precedence - Get the precedence of the pending binary operator token. *)
+let precedence c = try Hashtbl.find binop_precedence c with Not_found -> -1
+
+(* primary
+ *   ::= identifier
+ *   ::= numberexpr
+ *   ::= parenexpr
+ *   ::= ifexpr
+ *   ::= forexpr
+ *   ::= varexpr *)
+let rec parse_primary = parser
+  (* numberexpr ::= number *)
+  | [< 'Token.Number n >] -> Ast.Number n
+
+  (* parenexpr ::= '(' expression ')' *)
+  | [< 'Token.Kwd '('; e=parse_expr; 'Token.Kwd ')' ?? "expected ')'" >] -> e
+
+  (* identifierexpr
+   *   ::= identifier
+   *   ::= identifier '(' argumentexpr ')' *)
+  | [< 'Token.Ident id; stream >] ->
+      let rec parse_args accumulator = parser
+        | [< e=parse_expr; stream >] ->
+            begin parser
+              | [< 'Token.Kwd ','; e=parse_args (e :: accumulator) >] -> e
+              | [< >] -> e :: accumulator
+            end stream
+        | [< >] -> accumulator
+      in
+      let rec parse_ident id = parser
+        (* Call. *)
+        | [< 'Token.Kwd '(';
+             args=parse_args [];
+             'Token.Kwd ')' ?? "expected ')'">] ->
+            Ast.Call (id, Array.of_list (List.rev args))
+
+        (* Simple variable ref. *)
+        | [< >] -> Ast.Variable id
+      in
+      parse_ident id stream
+
+  (* ifexpr ::= 'if' expr 'then' expr 'else' expr *)
+  | [< 'Token.If; c=parse_expr;
+       'Token.Then ?? "expected 'then'"; t=parse_expr;
+       'Token.Else ?? "expected 'else'"; e=parse_expr >] ->
+      Ast.If (c, t, e)
+
+  (* forexpr
+        ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression *)
+  | [< 'Token.For;
+       'Token.Ident id ?? "expected identifier after for";
+       'Token.Kwd '=' ?? "expected '=' after for";
+       stream >] ->
+      begin parser
+        | [<
+             start=parse_expr;
+             'Token.Kwd ',' ?? "expected ',' after for";
+             end_=parse_expr;
+             stream >] ->
+            let step =
+              begin parser
+              | [< 'Token.Kwd ','; step=parse_expr >] -> Some step
+              | [< >] -> None
+              end stream
+            in
+            begin parser
+            | [< 'Token.In; body=parse_expr >] ->
+                Ast.For (id, start, end_, step, body)
+            | [< >] ->
+                raise (Stream.Error "expected 'in' after for")
+            end stream
+        | [< >] ->
+            raise (Stream.Error "expected '=' after for")
+      end stream
+
+  (* varexpr
+   *   ::= 'var' identifier ('=' expression?
+   *             (',' identifier ('=' expression)?)* 'in' expression *)
+  | [< 'Token.Var;
+       (* At least one variable name is required. *)
+       'Token.Ident id ?? "expected identifier after var";
+       init=parse_var_init;
+       var_names=parse_var_names [(id, init)];
+       (* At this point, we have to have 'in'. *)
+       'Token.In ?? "expected 'in' keyword after 'var'";
+       body=parse_expr >] ->
+      Ast.Var (Array.of_list (List.rev var_names), body)
+
+  | [< >] -> raise (Stream.Error "unknown token when expecting an expression.")
+
+(* unary
+ *   ::= primary
+ *   ::= '!' unary *)
+and parse_unary = parser
+  (* If this is a unary operator, read it. *)
+  | [< 'Token.Kwd op when op != '(' && op != ')'; operand=parse_expr >] ->
+      Ast.Unary (op, operand)
+
+  (* If the current token is not an operator, it must be a primary expr. *)
+  | [< stream >] -> parse_primary stream
+
+(* binoprhs
+ *   ::= ('+' primary)* *)
+and parse_bin_rhs expr_prec lhs stream =
+  match Stream.peek stream with
+  (* If this is a binop, find its precedence. *)
+  | Some (Token.Kwd c) when Hashtbl.mem binop_precedence c ->
+      let token_prec = precedence c in
+
+      (* If this is a binop that binds at least as tightly as the current binop,
+       * consume it, otherwise we are done. *)
+      if token_prec < expr_prec then lhs else begin
+        (* Eat the binop. *)
+        Stream.junk stream;
+
+        (* Parse the primary expression after the binary operator. *)
+        let rhs = parse_unary stream in
+
+        (* Okay, we know this is a binop. *)
+        let rhs =
+          match Stream.peek stream with
+          | Some (Token.Kwd c2) ->
+              (* If BinOp binds less tightly with rhs than the operator after
+               * rhs, let the pending operator take rhs as its lhs. *)
+              let next_prec = precedence c2 in
+              if token_prec < next_prec
+              then parse_bin_rhs (token_prec + 1) rhs stream
+              else rhs
+          | _ -> rhs
+        in
+
+        (* Merge lhs/rhs. *)
+        let lhs = Ast.Binary (c, lhs, rhs) in
+        parse_bin_rhs expr_prec lhs stream
+      end
+  | _ -> lhs
+
+and parse_var_init = parser
+  (* read in the optional initializer. *)
+  | [< 'Token.Kwd '='; e=parse_expr >] -> Some e
+  | [< >] -> None
+
+and parse_var_names accumulator = parser
+  | [< 'Token.Kwd ',';
+       'Token.Ident id ?? "expected identifier list after var";
+       init=parse_var_init;
+       e=parse_var_names ((id, init) :: accumulator) >] -> e
+  | [< >] -> accumulator
+
+(* expression
+ *   ::= primary binoprhs *)
+and parse_expr = parser
+  | [< lhs=parse_unary; stream >] -> parse_bin_rhs 0 lhs stream
+
+(* prototype
+ *   ::= id '(' id* ')'
+ *   ::= binary LETTER number? (id, id)
+ *   ::= unary LETTER number? (id) *)
+let parse_prototype =
+  let rec parse_args accumulator = parser
+    | [< 'Token.Ident id; e=parse_args (id::accumulator) >] -> e
+    | [< >] -> accumulator
+  in
+  let parse_operator = parser
+    | [< 'Token.Unary >] -> "unary", 1
+    | [< 'Token.Binary >] -> "binary", 2
+  in
+  let parse_binary_precedence = parser
+    | [< 'Token.Number n >] -> int_of_float n
+    | [< >] -> 30
+  in
+  parser
+  | [< 'Token.Ident id;
+       'Token.Kwd '(' ?? "expected '(' in prototype";
+       args=parse_args [];
+       'Token.Kwd ')' ?? "expected ')' in prototype" >] ->
+      (* success. *)
+      Ast.Prototype (id, Array.of_list (List.rev args))
+  | [< (prefix, kind)=parse_operator;
+       'Token.Kwd op ?? "expected an operator";
+       (* Read the precedence if present. *)
+       binary_precedence=parse_binary_precedence;
+       'Token.Kwd '(' ?? "expected '(' in prototype";
+        args=parse_args [];
+       'Token.Kwd ')' ?? "expected ')' in prototype" >] ->
+      let name = prefix ^ (String.make 1 op) in
+      let args = Array.of_list (List.rev args) in
+
+      (* Verify right number of arguments for operator. *)
+      if Array.length args != kind
+      then raise (Stream.Error "invalid number of operands for operator")
+      else
+        if kind == 1 then
+          Ast.Prototype (name, args)
+        else
+          Ast.BinOpPrototype (name, args, binary_precedence)
+  | [< >] ->
+      raise (Stream.Error "expected function name in prototype")
+
+(* definition ::= 'def' prototype expression *)
+let parse_definition = parser
+  | [< 'Token.Def; p=parse_prototype; e=parse_expr >] ->
+      Ast.Function (p, e)
+
+(* toplevelexpr ::= expression *)
+let parse_toplevel = parser
+  | [< e=parse_expr >] ->
+      (* Make an anonymous proto. *)
+      Ast.Function (Ast.Prototype ("", [||]), e)
+
+(*  external ::= 'extern' prototype *)
+let parse_extern = parser
+  | [< 'Token.Extern; e=parse_prototype >] -> e
+
+
+ +
codegen.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Code Generation
+ *===----------------------------------------------------------------------===*)
+
+open Llvm
+
+exception Error of string
+
+let the_module = create_module "my cool jit"
+let builder = builder ()
+let named_values:(string, llvalue) Hashtbl.t = Hashtbl.create 10
+
+(* Create an alloca instruction in the entry block of the function. This
+ * is used for mutable variables etc. *)
+let create_entry_block_alloca the_function var_name =
+  let builder = builder_at (instr_begin (entry_block the_function)) in
+  build_alloca double_type var_name builder
+
+let rec codegen_expr = function
+  | Ast.Number n -> const_float double_type n
+  | Ast.Variable name ->
+      let v = try Hashtbl.find named_values name with
+        | Not_found -> raise (Error "unknown variable name")
+      in
+      (* Load the value. *)
+      build_load v name builder
+  | Ast.Unary (op, operand) ->
+      let operand = codegen_expr operand in
+      let callee = "unary" ^ (String.make 1 op) in
+      let callee =
+        match lookup_function callee the_module with
+        | Some callee -> callee
+        | None -> raise (Error "unknown unary operator")
+      in
+      build_call callee [|operand|] "unop" builder
+  | Ast.Binary (op, lhs, rhs) ->
+      begin match op with
+      | '=' ->
+          (* Special case '=' because we don't want to emit the LHS as an
+           * expression. *)
+          let name =
+            match lhs with
+            | Ast.Variable name -> name
+            | _ -> raise (Error "destination of '=' must be a variable")
+          in
+
+          (* Codegen the rhs. *)
+          let val_ = codegen_expr rhs in
+
+          (* Lookup the name. *)
+          let variable = try Hashtbl.find named_values name with
+          | Not_found -> raise (Error "unknown variable name")
+          in
+          ignore(build_store val_ variable builder);
+          val_
+      | _ ->
+          let lhs_val = codegen_expr lhs in
+          let rhs_val = codegen_expr rhs in
+          begin
+            match op with
+            | '+' -> build_add lhs_val rhs_val "addtmp" builder
+            | '-' -> build_sub lhs_val rhs_val "subtmp" builder
+            | '*' -> build_mul lhs_val rhs_val "multmp" builder
+            | '<' ->
+                (* Convert bool 0/1 to double 0.0 or 1.0 *)
+                let i = build_fcmp Fcmp.Ult lhs_val rhs_val "cmptmp" builder in
+                build_uitofp i double_type "booltmp" builder
+            | _ ->
+                (* If it wasn't a builtin binary operator, it must be a user defined
+                 * one. Emit a call to it. *)
+                let callee = "binary" ^ (String.make 1 op) in
+                let callee =
+                  match lookup_function callee the_module with
+                  | Some callee -> callee
+                  | None -> raise (Error "binary operator not found!")
+                in
+                build_call callee [|lhs_val; rhs_val|] "binop" builder
+          end
+      end
+  | Ast.Call (callee, args) ->
+      (* Look up the name in the module table. *)
+      let callee =
+        match lookup_function callee the_module with
+        | Some callee -> callee
+        | None -> raise (Error "unknown function referenced")
+      in
+      let params = params callee in
+
+      (* If argument mismatch error. *)
+      if Array.length params == Array.length args then () else
+        raise (Error "incorrect # arguments passed");
+      let args = Array.map codegen_expr args in
+      build_call callee args "calltmp" builder
+  | Ast.If (cond, then_, else_) ->
+      let cond = codegen_expr cond in
+
+      (* Convert condition to a bool by comparing equal to 0.0 *)
+      let zero = const_float double_type 0.0 in
+      let cond_val = build_fcmp Fcmp.One cond zero "ifcond" builder in
+
+      (* Grab the first block so that we might later add the conditional branch
+       * to it at the end of the function. *)
+      let start_bb = insertion_block builder in
+      let the_function = block_parent start_bb in
+
+      let then_bb = append_block "then" the_function in
+
+      (* Emit 'then' value. *)
+      position_at_end then_bb builder;
+      let then_val = codegen_expr then_ in
+
+      (* Codegen of 'then' can change the current block, update then_bb for the
+       * phi. We create a new name because one is used for the phi node, and the
+       * other is used for the conditional branch. *)
+      let new_then_bb = insertion_block builder in
+
+      (* Emit 'else' value. *)
+      let else_bb = append_block "else" the_function in
+      position_at_end else_bb builder;
+      let else_val = codegen_expr else_ in
+
+      (* Codegen of 'else' can change the current block, update else_bb for the
+       * phi. *)
+      let new_else_bb = insertion_block builder in
+
+      (* Emit merge block. *)
+      let merge_bb = append_block "ifcont" the_function in
+      position_at_end merge_bb builder;
+      let incoming = [(then_val, new_then_bb); (else_val, new_else_bb)] in
+      let phi = build_phi incoming "iftmp" builder in
+
+      (* Return to the start block to add the conditional branch. *)
+      position_at_end start_bb builder;
+      ignore (build_cond_br cond_val then_bb else_bb builder);
+
+      (* Set a unconditional branch at the end of the 'then' block and the
+       * 'else' block to the 'merge' block. *)
+      position_at_end new_then_bb builder; ignore (build_br merge_bb builder);
+      position_at_end new_else_bb builder; ignore (build_br merge_bb builder);
+
+      (* Finally, set the builder to the end of the merge block. *)
+      position_at_end merge_bb builder;
+
+      phi
+  | Ast.For (var_name, start, end_, step, body) ->
+      (* Output this as:
+       *   var = alloca double
+       *   ...
+       *   start = startexpr
+       *   store start -> var
+       *   goto loop
+       * loop:
+       *   ...
+       *   bodyexpr
+       *   ...
+       * loopend:
+       *   step = stepexpr
+       *   endcond = endexpr
+       *
+       *   curvar = load var
+       *   nextvar = curvar + step
+       *   store nextvar -> var
+       *   br endcond, loop, endloop
+       * outloop: *)
+
+      let the_function = block_parent (insertion_block builder) in
+
+      (* Create an alloca for the variable in the entry block. *)
+      let alloca = create_entry_block_alloca the_function var_name in
+
+      (* Emit the start code first, without 'variable' in scope. *)
+      let start_val = codegen_expr start in
+
+      (* Store the value into the alloca. *)
+      ignore(build_store start_val alloca builder);
+
+      (* Make the new basic block for the loop header, inserting after current
+       * block. *)
+      let loop_bb = append_block "loop" the_function in
+
+      (* Insert an explicit fall through from the current block to the
+       * loop_bb. *)
+      ignore (build_br loop_bb builder);
+
+      (* Start insertion in loop_bb. *)
+      position_at_end loop_bb builder;
+
+      (* Within the loop, the variable is defined equal to the PHI node. If it
+       * shadows an existing variable, we have to restore it, so save it
+       * now. *)
+      let old_val =
+        try Some (Hashtbl.find named_values var_name) with Not_found -> None
+      in
+      Hashtbl.add named_values var_name alloca;
+
+      (* Emit the body of the loop.  This, like any other expr, can change the
+       * current BB.  Note that we ignore the value computed by the body, but
+       * don't allow an error *)
+      ignore (codegen_expr body);
+
+      (* Emit the step value. *)
+      let step_val =
+        match step with
+        | Some step -> codegen_expr step
+        (* If not specified, use 1.0. *)
+        | None -> const_float double_type 1.0
+      in
+
+      (* Compute the end condition. *)
+      let end_cond = codegen_expr end_ in
+
+      (* Reload, increment, and restore the alloca. This handles the case where
+       * the body of the loop mutates the variable. *)
+      let cur_var = build_load alloca var_name builder in
+      let next_var = build_add cur_var step_val "nextvar" builder in
+      ignore(build_store next_var alloca builder);
+
+      (* Convert condition to a bool by comparing equal to 0.0. *)
+      let zero = const_float double_type 0.0 in
+      let end_cond = build_fcmp Fcmp.One end_cond zero "loopcond" builder in
+
+      (* Create the "after loop" block and insert it. *)
+      let after_bb = append_block "afterloop" the_function in
+
+      (* Insert the conditional branch into the end of loop_end_bb. *)
+      ignore (build_cond_br end_cond loop_bb after_bb builder);
+
+      (* Any new code will be inserted in after_bb. *)
+      position_at_end after_bb builder;
+
+      (* Restore the unshadowed variable. *)
+      begin match old_val with
+      | Some old_val -> Hashtbl.add named_values var_name old_val
+      | None -> ()
+      end;
+
+      (* for expr always returns 0.0. *)
+      const_null double_type
+  | Ast.Var (var_names, body) ->
+      let old_bindings = ref [] in
+
+      let the_function = block_parent (insertion_block builder) in
+
+      (* Register all variables and emit their initializer. *)
+      Array.iter (fun (var_name, init) ->
+        (* Emit the initializer before adding the variable to scope, this
+         * prevents the initializer from referencing the variable itself, and
+         * permits stuff like this:
+         *   var a = 1 in
+         *     var a = a in ...   # refers to outer 'a'. *)
+        let init_val =
+          match init with
+          | Some init -> codegen_expr init
+          (* If not specified, use 0.0. *)
+          | None -> const_float double_type 0.0
+        in
+
+        let alloca = create_entry_block_alloca the_function var_name in
+        ignore(build_store init_val alloca builder);
+
+        (* Remember the old variable binding so that we can restore the binding
+         * when we unrecurse. *)
+        begin
+          try
+            let old_value = Hashtbl.find named_values var_name in
+            old_bindings := (var_name, old_value) :: !old_bindings;
+          with Not_found -> ()
+        end;
+
+        (* Remember this binding. *)
+        Hashtbl.add named_values var_name alloca;
+      ) var_names;
+
+      (* Codegen the body, now that all vars are in scope. *)
+      let body_val = codegen_expr body in
+
+      (* Pop all our variables from scope. *)
+      List.iter (fun (var_name, old_value) ->
+        Hashtbl.add named_values var_name old_value
+      ) !old_bindings;
+
+      (* Return the body computation. *)
+      body_val
+
+let codegen_proto = function
+  | Ast.Prototype (name, args) | Ast.BinOpPrototype (name, args, _) ->
+      (* Make the function type: double(double,double) etc. *)
+      let doubles = Array.make (Array.length args) double_type in
+      let ft = function_type double_type doubles in
+      let f =
+        match lookup_function name the_module with
+        | None -> declare_function name ft the_module
+
+        (* If 'f' conflicted, there was already something named 'name'. If it
+         * has a body, don't allow redefinition or reextern. *)
+        | Some f ->
+            (* If 'f' already has a body, reject this. *)
+            if block_begin f <> At_end f then
+              raise (Error "redefinition of function");
+
+            (* If 'f' took a different number of arguments, reject. *)
+            if element_type (type_of f) <> ft then
+              raise (Error "redefinition of function with different # args");
+            f
+      in
+
+      (* Set names for all arguments. *)
+      Array.iteri (fun i a ->
+        let n = args.(i) in
+        set_value_name n a;
+        Hashtbl.add named_values n a;
+      ) (params f);
+      f
+
+(* Create an alloca for each argument and register the argument in the symbol
+ * table so that references to it will succeed. *)
+let create_argument_allocas the_function proto =
+  let args = match proto with
+    | Ast.Prototype (_, args) | Ast.BinOpPrototype (_, args, _) -> args
+  in
+  Array.iteri (fun i ai ->
+    let var_name = args.(i) in
+    (* Create an alloca for this variable. *)
+    let alloca = create_entry_block_alloca the_function var_name in
+
+    (* Store the initial value into the alloca. *)
+    ignore(build_store ai alloca builder);
+
+    (* Add arguments to variable symbol table. *)
+    Hashtbl.add named_values var_name alloca;
+  ) (params the_function)
+
+let codegen_func the_fpm = function
+  | Ast.Function (proto, body) ->
+      Hashtbl.clear named_values;
+      let the_function = codegen_proto proto in
+
+      (* If this is an operator, install it. *)
+      begin match proto with
+      | Ast.BinOpPrototype (name, args, prec) ->
+          let op = name.[String.length name - 1] in
+          Hashtbl.add Parser.binop_precedence op prec;
+      | _ -> ()
+      end;
+
+      (* Create a new basic block to start insertion into. *)
+      let bb = append_block "entry" the_function in
+      position_at_end bb builder;
+
+      try
+        (* Add all arguments to the symbol table and create their allocas. *)
+        create_argument_allocas the_function proto;
+
+        let ret_val = codegen_expr body in
+
+        (* Finish off the function. *)
+        let _ = build_ret ret_val builder in
+
+        (* Validate the generated code, checking for consistency. *)
+        Llvm_analysis.assert_valid_function the_function;
+
+        (* Optimize the function. *)
+        let _ = PassManager.run_function the_function the_fpm in
+
+        the_function
+      with e ->
+        delete_function the_function;
+        raise e
+
+
+ +
toplevel.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Top-Level parsing and JIT Driver
+ *===----------------------------------------------------------------------===*)
+
+open Llvm
+open Llvm_executionengine
+
+(* top ::= definition | external | expression | ';' *)
+let rec main_loop the_fpm the_execution_engine stream =
+  match Stream.peek stream with
+  | None -> ()
+
+  (* ignore top-level semicolons. *)
+  | Some (Token.Kwd ';') ->
+      Stream.junk stream;
+      main_loop the_fpm the_execution_engine stream
+
+  | Some token ->
+      begin
+        try match token with
+        | Token.Def ->
+            let e = Parser.parse_definition stream in
+            print_endline "parsed a function definition.";
+            dump_value (Codegen.codegen_func the_fpm e);
+        | Token.Extern ->
+            let e = Parser.parse_extern stream in
+            print_endline "parsed an extern.";
+            dump_value (Codegen.codegen_proto e);
+        | _ ->
+            (* Evaluate a top-level expression into an anonymous function. *)
+            let e = Parser.parse_toplevel stream in
+            print_endline "parsed a top-level expr";
+            let the_function = Codegen.codegen_func the_fpm e in
+            dump_value the_function;
+
+            (* JIT the function, returning a function pointer. *)
+            let result = ExecutionEngine.run_function the_function [||]
+              the_execution_engine in
+
+            print_string "Evaluated to ";
+            print_float (GenericValue.as_float double_type result);
+            print_newline ();
+        with Stream.Error s | Codegen.Error s ->
+          (* Skip token for error recovery. *)
+          Stream.junk stream;
+          print_endline s;
+      end;
+      print_string "ready> "; flush stdout;
+      main_loop the_fpm the_execution_engine stream
+
+
+ +
toy.ml:
+
+
+(*===----------------------------------------------------------------------===
+ * Main driver code.
+ *===----------------------------------------------------------------------===*)
+
+open Llvm
+open Llvm_executionengine
+open Llvm_target
+open Llvm_scalar_opts
+
+let main () =
+  (* Install standard binary operators.
+   * 1 is the lowest precedence. *)
+  Hashtbl.add Parser.binop_precedence '=' 2;
+  Hashtbl.add Parser.binop_precedence '<' 10;
+  Hashtbl.add Parser.binop_precedence '+' 20;
+  Hashtbl.add Parser.binop_precedence '-' 20;
+  Hashtbl.add Parser.binop_precedence '*' 40;    (* highest. *)
+
+  (* Prime the first token. *)
+  print_string "ready> "; flush stdout;
+  let stream = Lexer.lex (Stream.of_channel stdin) in
+
+  (* Create the JIT. *)
+  let the_module_provider = ModuleProvider.create Codegen.the_module in
+  let the_execution_engine = ExecutionEngine.create the_module_provider in
+  let the_fpm = PassManager.create_function the_module_provider in
+
+  (* Set up the optimizer pipeline.  Start with registering info about how the
+   * target lays out data structures. *)
+  TargetData.add (ExecutionEngine.target_data the_execution_engine) the_fpm;
+
+  (* Promote allocas to registers. *)
+  add_memory_to_register_promotion the_fpm;
+
+  (* Do simple "peephole" optimizations and bit-twiddling optzn. *)
+  add_instruction_combining the_fpm;
+
+  (* reassociate expressions. *)
+  add_reassociation the_fpm;
+
+  (* Eliminate Common SubExpressions. *)
+  add_gvn the_fpm;
+
+  (* Simplify the control flow graph (deleting unreachable blocks, etc). *)
+  add_cfg_simplification the_fpm;
+
+  (* Run the main "interpreter loop" now. *)
+  Toplevel.main_loop the_fpm the_execution_engine stream;
+
+  (* Print out all the generated code. *)
+  dump_module Codegen.the_module
+;;
+
+main ()
+
+
+ +
bindings.c
+
+
+#include <stdio.h>
+
+/* putchard - putchar that takes a double and returns 0. */
+extern double putchard(double X) {
+  putchar((char)X);
+  return 0;
+}
+
+/* printd - printf that takes a double prints it as "%f\n", returning 0. */
+extern double printd(double X) {
+  printf("%f\n", X);
+  return 0;
+}
+
+
+
+ +Next: Conclusion and other useful LLVM tidbits +
+ + +
+
+ Valid CSS! + Valid HTML 4.01! + + Chris Lattner
+ The LLVM Compiler Infrastructure
+ Erick Tryzelaar
+ Last modified: $Date: 2007-10-17 11:05:13 -0700 (Wed, 17 Oct 2007) $ +
+ +