diff options
Diffstat (limited to 'examples/OCaml-Kaleidoscope/Chapter3')
| -rw-r--r-- | examples/OCaml-Kaleidoscope/Chapter3/Makefile | 24 | ||||
| -rw-r--r-- | examples/OCaml-Kaleidoscope/Chapter3/_tags | 2 | ||||
| -rw-r--r-- | examples/OCaml-Kaleidoscope/Chapter3/ast.ml | 25 | ||||
| -rw-r--r-- | examples/OCaml-Kaleidoscope/Chapter3/codegen.ml | 100 | ||||
| -rw-r--r-- | examples/OCaml-Kaleidoscope/Chapter3/lexer.ml | 52 | ||||
| -rw-r--r-- | examples/OCaml-Kaleidoscope/Chapter3/myocamlbuild.ml | 6 | ||||
| -rw-r--r-- | examples/OCaml-Kaleidoscope/Chapter3/parser.ml | 122 | ||||
| -rw-r--r-- | examples/OCaml-Kaleidoscope/Chapter3/token.ml | 15 | ||||
| -rw-r--r-- | examples/OCaml-Kaleidoscope/Chapter3/toplevel.ml | 39 | ||||
| -rw-r--r-- | examples/OCaml-Kaleidoscope/Chapter3/toy.ml | 26 |
10 files changed, 411 insertions, 0 deletions
diff --git a/examples/OCaml-Kaleidoscope/Chapter3/Makefile b/examples/OCaml-Kaleidoscope/Chapter3/Makefile new file mode 100644 index 0000000..fdbcd51 --- /dev/null +++ b/examples/OCaml-Kaleidoscope/Chapter3/Makefile @@ -0,0 +1,24 @@ +##===- examples/OCaml-Kaleidoscope/Chapter3/Makefile -------*- Makefile -*-===## +# +# The LLVM Compiler Infrastructure +# +# This file is distributed under the University of Illinois Open Source +# License. See LICENSE.TXT for details. +# +##===----------------------------------------------------------------------===## +# +# This is the makefile for the Objective Caml kaleidoscope tutorial, chapter 3. +# +##===----------------------------------------------------------------------===## + +LEVEL := ../../.. +TOOLNAME := OCaml-Kaleidoscope-Ch3 +EXAMPLE_TOOL := 1 +UsedComponents := core +UsedOcamLibs := llvm llvm_analysis + +OCAMLCFLAGS += -pp camlp4of + +ExcludeSources = $(PROJ_SRC_DIR)/myocamlbuild.ml + +include $(LEVEL)/bindings/ocaml/Makefile.ocaml diff --git a/examples/OCaml-Kaleidoscope/Chapter3/_tags b/examples/OCaml-Kaleidoscope/Chapter3/_tags new file mode 100644 index 0000000..990490a --- /dev/null +++ b/examples/OCaml-Kaleidoscope/Chapter3/_tags @@ -0,0 +1,2 @@ +<{lexer,parser}.ml>: use_camlp4, pp(camlp4of) +<*.{byte,native}>: g++, use_llvm, use_llvm_analysis diff --git a/examples/OCaml-Kaleidoscope/Chapter3/ast.ml b/examples/OCaml-Kaleidoscope/Chapter3/ast.ml new file mode 100644 index 0000000..4cc2dea --- /dev/null +++ b/examples/OCaml-Kaleidoscope/Chapter3/ast.ml @@ -0,0 +1,25 @@ +(*===----------------------------------------------------------------------=== + * 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 + +(* 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 diff --git a/examples/OCaml-Kaleidoscope/Chapter3/codegen.ml b/examples/OCaml-Kaleidoscope/Chapter3/codegen.ml new file mode 100644 index 0000000..275cd0b --- /dev/null +++ b/examples/OCaml-Kaleidoscope/Chapter3/codegen.ml @@ -0,0 +1,100 @@ +(*===----------------------------------------------------------------------=== + * Code Generation + *===----------------------------------------------------------------------===*) + +open Llvm + +exception Error of string + +let context = global_context () +let the_module = create_module context "my cool jit" +let builder = builder context +let named_values:(string, llvalue) Hashtbl.t = Hashtbl.create 10 +let double_type = double_type context + +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 + +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 = 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 context "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; + + the_function + with e -> + delete_function the_function; + raise e diff --git a/examples/OCaml-Kaleidoscope/Chapter3/lexer.ml b/examples/OCaml-Kaleidoscope/Chapter3/lexer.ml new file mode 100644 index 0000000..22a9155 --- /dev/null +++ b/examples/OCaml-Kaleidoscope/Chapter3/lexer.ml @@ -0,0 +1,52 @@ +(*===----------------------------------------------------------------------=== + * 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 >] + | id -> [< 'Token.Ident id; stream >] + +and lex_comment = parser + | [< ' ('\n'); stream=lex >] -> stream + | [< 'c; e=lex_comment >] -> e + | [< >] -> [< >] diff --git a/examples/OCaml-Kaleidoscope/Chapter3/myocamlbuild.ml b/examples/OCaml-Kaleidoscope/Chapter3/myocamlbuild.ml new file mode 100644 index 0000000..b71f5d7 --- /dev/null +++ b/examples/OCaml-Kaleidoscope/Chapter3/myocamlbuild.ml @@ -0,0 +1,6 @@ +open Ocamlbuild_plugin;; + +ocaml_lib ~extern:true "llvm";; +ocaml_lib ~extern:true "llvm_analysis";; + +flag ["link"; "ocaml"; "g++"] (S[A"-cc"; A"g++"]);; diff --git a/examples/OCaml-Kaleidoscope/Chapter3/parser.ml b/examples/OCaml-Kaleidoscope/Chapter3/parser.ml new file mode 100644 index 0000000..83d9874 --- /dev/null +++ b/examples/OCaml-Kaleidoscope/Chapter3/parser.ml @@ -0,0 +1,122 @@ +(*===---------------------------------------------------------------------=== + * 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 *) +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 + + | [< >] -> 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 diff --git a/examples/OCaml-Kaleidoscope/Chapter3/token.ml b/examples/OCaml-Kaleidoscope/Chapter3/token.ml new file mode 100644 index 0000000..2ca782e --- /dev/null +++ b/examples/OCaml-Kaleidoscope/Chapter3/token.ml @@ -0,0 +1,15 @@ +(*===----------------------------------------------------------------------=== + * 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 diff --git a/examples/OCaml-Kaleidoscope/Chapter3/toplevel.ml b/examples/OCaml-Kaleidoscope/Chapter3/toplevel.ml new file mode 100644 index 0000000..d1bf5d4 --- /dev/null +++ b/examples/OCaml-Kaleidoscope/Chapter3/toplevel.ml @@ -0,0 +1,39 @@ +(*===----------------------------------------------------------------------=== + * Top-Level parsing and JIT Driver + *===----------------------------------------------------------------------===*) + +open Llvm + +(* top ::= definition | external | expression | ';' *) +let rec main_loop stream = + match Stream.peek stream with + | None -> () + + (* ignore top-level semicolons. *) + | Some (Token.Kwd ';') -> + Stream.junk stream; + main_loop 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 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"; + dump_value (Codegen.codegen_func e); + 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 stream diff --git a/examples/OCaml-Kaleidoscope/Chapter3/toy.ml b/examples/OCaml-Kaleidoscope/Chapter3/toy.ml new file mode 100644 index 0000000..73c1a1e --- /dev/null +++ b/examples/OCaml-Kaleidoscope/Chapter3/toy.ml @@ -0,0 +1,26 @@ +(*===----------------------------------------------------------------------=== + * Main driver code. + *===----------------------------------------------------------------------===*) + +open Llvm + +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 + + (* Run the main "interpreter loop" now. *) + Toplevel.main_loop stream; + + (* Print out all the generated code. *) + dump_module Codegen.the_module +;; + +main () |