Instantiate compiler for garbage collection

This commit is contained in:
Danila Fedorin 2020-01-27 14:52:25 -08:00
parent b5694b92bc
commit 0bc9ae320b
33 changed files with 2277 additions and 0 deletions

42
09/CMakeLists.txt Normal file
View File

@ -0,0 +1,42 @@
cmake_minimum_required(VERSION 3.1)
project(compiler)
# Find all the required packages
find_package(BISON)
find_package(FLEX)
find_package(LLVM REQUIRED CONFIG)
# Set up the flex and bison targets
bison_target(parser
${CMAKE_CURRENT_SOURCE_DIR}/parser.y
${CMAKE_CURRENT_BINARY_DIR}/parser.cpp
COMPILE_FLAGS "-d")
flex_target(scanner
${CMAKE_CURRENT_SOURCE_DIR}/scanner.l
${CMAKE_CURRENT_BINARY_DIR}/scanner.cpp)
add_flex_bison_dependency(scanner parser)
# Find all the relevant LLVM components
llvm_map_components_to_libnames(LLVM_LIBS core x86asmparser x86codegen)
# Create compiler executable
add_executable(compiler
ast.cpp ast.hpp definition.cpp
llvm_context.cpp llvm_context.hpp
type_env.cpp type_env.hpp
env.cpp env.hpp
type.cpp type.hpp
error.cpp error.hpp
binop.cpp binop.hpp
instruction.cpp instruction.hpp
${BISON_parser_OUTPUTS}
${FLEX_scanner_OUTPUTS}
main.cpp
)
# Configure compiler executable
target_include_directories(compiler PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
target_include_directories(compiler PUBLIC ${CMAKE_CURRENT_BINARY_DIR})
target_include_directories(compiler PUBLIC ${LLVM_INCLUDE_DIRS})
target_compile_definitions(compiler PUBLIC ${LLVM_DEFINITIONS})
target_link_libraries(compiler ${LLVM_LIBS})

264
09/ast.cpp Normal file
View File

@ -0,0 +1,264 @@
#include "ast.hpp"
#include <ostream>
#include "binop.hpp"
#include "error.hpp"
static void print_indent(int n, std::ostream& to) {
while(n--) to << " ";
}
type_ptr ast::typecheck_common(type_mgr& mgr, const type_env& env) {
node_type = typecheck(mgr, env);
return node_type;
}
void ast::resolve_common(const type_mgr& mgr) {
type_var* var;
type_ptr resolved_type = mgr.resolve(node_type, var);
if(var) throw type_error("ambiguously typed program");
resolve(mgr);
node_type = std::move(resolved_type);
}
void ast_int::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "INT: " << value << std::endl;
}
type_ptr ast_int::typecheck(type_mgr& mgr, const type_env& env) const {
return type_ptr(new type_base("Int"));
}
void ast_int::resolve(const type_mgr& mgr) const {
}
void ast_int::compile(const env_ptr& env, std::vector<instruction_ptr>& into) const {
into.push_back(instruction_ptr(new instruction_pushint(value)));
}
void ast_lid::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "LID: " << id << std::endl;
}
type_ptr ast_lid::typecheck(type_mgr& mgr, const type_env& env) const {
return env.lookup(id);
}
void ast_lid::resolve(const type_mgr& mgr) const {
}
void ast_lid::compile(const env_ptr& env, std::vector<instruction_ptr>& into) const {
into.push_back(instruction_ptr(
env->has_variable(id) ?
(instruction*) new instruction_push(env->get_offset(id)) :
(instruction*) new instruction_pushglobal(id)));
}
void ast_uid::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "UID: " << id << std::endl;
}
type_ptr ast_uid::typecheck(type_mgr& mgr, const type_env& env) const {
return env.lookup(id);
}
void ast_uid::resolve(const type_mgr& mgr) const {
}
void ast_uid::compile(const env_ptr& env, std::vector<instruction_ptr>& into) const {
into.push_back(instruction_ptr(new instruction_pushglobal(id)));
}
void ast_binop::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "BINOP: " << op_name(op) << std::endl;
left->print(indent + 1, to);
right->print(indent + 1, to);
}
type_ptr ast_binop::typecheck(type_mgr& mgr, const type_env& env) const {
type_ptr ltype = left->typecheck_common(mgr, env);
type_ptr rtype = right->typecheck_common(mgr, env);
type_ptr ftype = env.lookup(op_name(op));
if(!ftype) throw type_error(std::string("unknown binary operator ") + op_name(op));
type_ptr return_type = mgr.new_type();
type_ptr arrow_one = type_ptr(new type_arr(rtype, return_type));
type_ptr arrow_two = type_ptr(new type_arr(ltype, arrow_one));
mgr.unify(arrow_two, ftype);
return return_type;
}
void ast_binop::resolve(const type_mgr& mgr) const {
left->resolve_common(mgr);
right->resolve_common(mgr);
}
void ast_binop::compile(const env_ptr& env, std::vector<instruction_ptr>& into) const {
right->compile(env, into);
left->compile(env_ptr(new env_offset(1, env)), into);
into.push_back(instruction_ptr(new instruction_pushglobal(op_action(op))));
into.push_back(instruction_ptr(new instruction_mkapp()));
into.push_back(instruction_ptr(new instruction_mkapp()));
}
void ast_app::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "APP:" << std::endl;
left->print(indent + 1, to);
right->print(indent + 1, to);
}
type_ptr ast_app::typecheck(type_mgr& mgr, const type_env& env) const {
type_ptr ltype = left->typecheck_common(mgr, env);
type_ptr rtype = right->typecheck_common(mgr, env);
type_ptr return_type = mgr.new_type();
type_ptr arrow = type_ptr(new type_arr(rtype, return_type));
mgr.unify(arrow, ltype);
return return_type;
}
void ast_app::resolve(const type_mgr& mgr) const {
left->resolve_common(mgr);
right->resolve_common(mgr);
}
void ast_app::compile(const env_ptr& env, std::vector<instruction_ptr>& into) const {
right->compile(env, into);
left->compile(env_ptr(new env_offset(1, env)), into);
into.push_back(instruction_ptr(new instruction_mkapp()));
}
void ast_case::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "CASE: " << std::endl;
for(auto& branch : branches) {
print_indent(indent + 1, to);
branch->pat->print(to);
to << std::endl;
branch->expr->print(indent + 2, to);
}
}
type_ptr ast_case::typecheck(type_mgr& mgr, const type_env& env) const {
type_var* var;
type_ptr case_type = mgr.resolve(of->typecheck_common(mgr, env), var);
type_ptr branch_type = mgr.new_type();
for(auto& branch : branches) {
type_env new_env = env.scope();
branch->pat->match(case_type, mgr, new_env);
type_ptr curr_branch_type = branch->expr->typecheck_common(mgr, new_env);
mgr.unify(branch_type, curr_branch_type);
}
case_type = mgr.resolve(case_type, var);
if(!dynamic_cast<type_data*>(case_type.get())) {
throw type_error("attempting case analysis of non-data type");
}
return branch_type;
}
void ast_case::resolve(const type_mgr& mgr) const {
of->resolve_common(mgr);
for(auto& branch : branches) {
branch->expr->resolve_common(mgr);
}
}
void ast_case::compile(const env_ptr& env, std::vector<instruction_ptr>& into) const {
type_data* type = dynamic_cast<type_data*>(of->node_type.get());
of->compile(env, into);
into.push_back(instruction_ptr(new instruction_eval()));
instruction_jump* jump_instruction = new instruction_jump();
into.push_back(instruction_ptr(jump_instruction));
for(auto& branch : branches) {
std::vector<instruction_ptr> branch_instructions;
pattern_var* vpat;
pattern_constr* cpat;
if((vpat = dynamic_cast<pattern_var*>(branch->pat.get()))) {
branch->expr->compile(env_ptr(new env_offset(1, env)), branch_instructions);
for(auto& constr_pair : type->constructors) {
if(jump_instruction->tag_mappings.find(constr_pair.second.tag) !=
jump_instruction->tag_mappings.end())
break;
jump_instruction->tag_mappings[constr_pair.second.tag] =
jump_instruction->branches.size();
}
jump_instruction->branches.push_back(std::move(branch_instructions));
} else if((cpat = dynamic_cast<pattern_constr*>(branch->pat.get()))) {
env_ptr new_env = env;
for(auto it = cpat->params.rbegin(); it != cpat->params.rend(); it++) {
new_env = env_ptr(new env_var(*it, new_env));
}
branch_instructions.push_back(instruction_ptr(new instruction_split(
cpat->params.size())));
branch->expr->compile(new_env, branch_instructions);
branch_instructions.push_back(instruction_ptr(new instruction_slide(
cpat->params.size())));
int new_tag = type->constructors[cpat->constr].tag;
if(jump_instruction->tag_mappings.find(new_tag) !=
jump_instruction->tag_mappings.end())
throw type_error("technically not a type error: duplicate pattern");
jump_instruction->tag_mappings[new_tag] =
jump_instruction->branches.size();
jump_instruction->branches.push_back(std::move(branch_instructions));
}
}
for(auto& constr_pair : type->constructors) {
if(jump_instruction->tag_mappings.find(constr_pair.second.tag) ==
jump_instruction->tag_mappings.end())
throw type_error("non-total pattern");
}
}
void pattern_var::print(std::ostream& to) const {
to << var;
}
void pattern_var::match(type_ptr t, type_mgr& mgr, type_env& env) const {
env.bind(var, t);
}
void pattern_constr::print(std::ostream& to) const {
to << constr;
for(auto& param : params) {
to << " " << param;
}
}
void pattern_constr::match(type_ptr t, type_mgr& mgr, type_env& env) const {
type_ptr constructor_type = env.lookup(constr);
if(!constructor_type) {
throw type_error(std::string("pattern using unknown constructor ") + constr);
}
for(int i = 0; i < params.size(); i++) {
type_arr* arr = dynamic_cast<type_arr*>(constructor_type.get());
if(!arr) throw type_error("too many parameters in constructor pattern");
env.bind(params[i], arr->left);
constructor_type = arr->right;
}
mgr.unify(t, constructor_type);
}

141
09/ast.hpp Normal file
View File

@ -0,0 +1,141 @@
#pragma once
#include <memory>
#include <vector>
#include "type.hpp"
#include "type_env.hpp"
#include "binop.hpp"
#include "instruction.hpp"
#include "env.hpp"
struct ast {
type_ptr node_type;
virtual ~ast() = default;
virtual void print(int indent, std::ostream& to) const = 0;
virtual type_ptr typecheck(type_mgr& mgr, const type_env& env) const = 0;
virtual void resolve(const type_mgr& mgr) const = 0;
virtual void compile(const env_ptr& env,
std::vector<instruction_ptr>& into) const = 0;
type_ptr typecheck_common(type_mgr& mgr, const type_env& env);
void resolve_common(const type_mgr& mgr);
};
using ast_ptr = std::unique_ptr<ast>;
struct pattern {
virtual ~pattern() = default;
virtual void print(std::ostream& to) const = 0;
virtual void match(type_ptr t, type_mgr& mgr, type_env& env) const = 0;
};
using pattern_ptr = std::unique_ptr<pattern>;
struct branch {
pattern_ptr pat;
ast_ptr expr;
branch(pattern_ptr p, ast_ptr a)
: pat(std::move(p)), expr(std::move(a)) {}
};
using branch_ptr = std::unique_ptr<branch>;
struct ast_int : public ast {
int value;
explicit ast_int(int v)
: value(v) {}
void print(int indent, std::ostream& to) const;
type_ptr typecheck(type_mgr& mgr, const type_env& env) const;
void resolve(const type_mgr& mgr) const;
void compile(const env_ptr& env, std::vector<instruction_ptr>& into) const;
};
struct ast_lid : public ast {
std::string id;
explicit ast_lid(std::string i)
: id(std::move(i)) {}
void print(int indent, std::ostream& to) const;
type_ptr typecheck(type_mgr& mgr, const type_env& env) const;
void resolve(const type_mgr& mgr) const;
void compile(const env_ptr& env, std::vector<instruction_ptr>& into) const;
};
struct ast_uid : public ast {
std::string id;
explicit ast_uid(std::string i)
: id(std::move(i)) {}
void print(int indent, std::ostream& to) const;
type_ptr typecheck(type_mgr& mgr, const type_env& env) const;
void resolve(const type_mgr& mgr) const;
void compile(const env_ptr& env, std::vector<instruction_ptr>& into) const;
};
struct ast_binop : public ast {
binop op;
ast_ptr left;
ast_ptr right;
ast_binop(binop o, ast_ptr l, ast_ptr r)
: op(o), left(std::move(l)), right(std::move(r)) {}
void print(int indent, std::ostream& to) const;
type_ptr typecheck(type_mgr& mgr, const type_env& env) const;
void resolve(const type_mgr& mgr) const;
void compile(const env_ptr& env, std::vector<instruction_ptr>& into) const;
};
struct ast_app : public ast {
ast_ptr left;
ast_ptr right;
ast_app(ast_ptr l, ast_ptr r)
: left(std::move(l)), right(std::move(r)) {}
void print(int indent, std::ostream& to) const;
type_ptr typecheck(type_mgr& mgr, const type_env& env) const;
void resolve(const type_mgr& mgr) const;
void compile(const env_ptr& env, std::vector<instruction_ptr>& into) const;
};
struct ast_case : public ast {
ast_ptr of;
std::vector<branch_ptr> branches;
ast_case(ast_ptr o, std::vector<branch_ptr> b)
: of(std::move(o)), branches(std::move(b)) {}
void print(int indent, std::ostream& to) const;
type_ptr typecheck(type_mgr& mgr, const type_env& env) const;
void resolve(const type_mgr& mgr) const;
void compile(const env_ptr& env, std::vector<instruction_ptr>& into) const;
};
struct pattern_var : public pattern {
std::string var;
pattern_var(std::string v)
: var(std::move(v)) {}
void print(std::ostream &to) const;
void match(type_ptr t, type_mgr& mgr, type_env& env) const;
};
struct pattern_constr : public pattern {
std::string constr;
std::vector<std::string> params;
pattern_constr(std::string c, std::vector<std::string> p)
: constr(std::move(c)), params(std::move(p)) {}
void print(std::ostream &to) const;
void match(type_ptr t, type_mgr&, type_env& env) const;
};

21
09/binop.cpp Normal file
View File

@ -0,0 +1,21 @@
#include "binop.hpp"
std::string op_name(binop op) {
switch(op) {
case PLUS: return "+";
case MINUS: return "-";
case TIMES: return "*";
case DIVIDE: return "/";
}
return "??";
}
std::string op_action(binop op) {
switch(op) {
case PLUS: return "plus";
case MINUS: return "minus";
case TIMES: return "times";
case DIVIDE: return "divide";
}
return "??";
}

12
09/binop.hpp Normal file
View File

@ -0,0 +1,12 @@
#pragma once
#include <string>
enum binop {
PLUS,
MINUS,
TIMES,
DIVIDE
};
std::string op_name(binop op);
std::string op_action(binop op);

116
09/definition.cpp Normal file
View File

@ -0,0 +1,116 @@
#include "definition.hpp"
#include "error.hpp"
#include "ast.hpp"
#include "llvm_context.hpp"
#include <llvm/IR/DerivedTypes.h>
#include <llvm/IR/Function.h>
#include <llvm/IR/Type.h>
void definition_defn::typecheck_first(type_mgr& mgr, type_env& env) {
return_type = mgr.new_type();
type_ptr full_type = return_type;
for(auto it = params.rbegin(); it != params.rend(); it++) {
type_ptr param_type = mgr.new_type();
full_type = type_ptr(new type_arr(param_type, full_type));
param_types.push_back(param_type);
}
env.bind(name, full_type);
}
void definition_defn::typecheck_second(type_mgr& mgr, const type_env& env) const {
type_env new_env = env.scope();
auto param_it = params.begin();
auto type_it = param_types.rbegin();
while(param_it != params.end() && type_it != param_types.rend()) {
new_env.bind(*param_it, *type_it);
param_it++;
type_it++;
}
type_ptr body_type = body->typecheck_common(mgr, new_env);
mgr.unify(return_type, body_type);
}
void definition_defn::resolve(const type_mgr& mgr) {
type_var* var;
body->resolve_common(mgr);
return_type = mgr.resolve(return_type, var);
if(var) throw type_error("ambiguously typed program");
for(auto& param_type : param_types) {
param_type = mgr.resolve(param_type, var);
if(var) throw type_error("ambiguously typed program");
}
}
void definition_defn::compile() {
env_ptr new_env = env_ptr(new env_offset(0, nullptr));
for(auto it = params.rbegin(); it != params.rend(); it++) {
new_env = env_ptr(new env_var(*it, new_env));
}
body->compile(new_env, instructions);
instructions.push_back(instruction_ptr(new instruction_update(params.size())));
instructions.push_back(instruction_ptr(new instruction_pop(params.size())));
}
void definition_defn::gen_llvm_first(llvm_context& ctx) {
generated_function = ctx.create_custom_function(name, params.size());
}
void definition_defn::gen_llvm_second(llvm_context& ctx) {
ctx.builder.SetInsertPoint(&generated_function->getEntryBlock());
for(auto& instruction : instructions) {
instruction->gen_llvm(ctx, generated_function);
}
ctx.builder.CreateRetVoid();
}
void definition_data::typecheck_first(type_mgr& mgr, type_env& env) {
type_data* this_type = new type_data(name);
type_ptr return_type = type_ptr(this_type);
int next_tag = 0;
for(auto& constructor : constructors) {
constructor->tag = next_tag;
this_type->constructors[constructor->name] = { next_tag++ };
type_ptr full_type = return_type;
for(auto it = constructor->types.rbegin(); it != constructor->types.rend(); it++) {
type_ptr type = type_ptr(new type_base(*it));
full_type = type_ptr(new type_arr(type, full_type));
}
env.bind(constructor->name, full_type);
}
}
void definition_data::typecheck_second(type_mgr& mgr, const type_env& env) const {
// Nothing
}
void definition_data::resolve(const type_mgr& mgr) {
// Nothing
}
void definition_data::compile() {
}
void definition_data::gen_llvm_first(llvm_context& ctx) {
for(auto& constructor : constructors) {
auto new_function =
ctx.create_custom_function(constructor->name, constructor->types.size());
ctx.builder.SetInsertPoint(&new_function->getEntryBlock());
ctx.create_pack(new_function,
ctx.create_size(constructor->types.size()),
ctx.create_i8(constructor->tag)
);
ctx.builder.CreateRetVoid();
}
}
void definition_data::gen_llvm_second(llvm_context& ctx) {
// Nothing
}

73
09/definition.hpp Normal file
View File

@ -0,0 +1,73 @@
#pragma once
#include <memory>
#include <vector>
#include "instruction.hpp"
#include "llvm_context.hpp"
#include "type_env.hpp"
struct ast;
using ast_ptr = std::unique_ptr<ast>;
struct definition {
virtual ~definition() = default;
virtual void typecheck_first(type_mgr& mgr, type_env& env) = 0;
virtual void typecheck_second(type_mgr& mgr, const type_env& env) const = 0;
virtual void resolve(const type_mgr& mgr) = 0;
virtual void compile() = 0;
virtual void gen_llvm_first(llvm_context& ctx) = 0;
virtual void gen_llvm_second(llvm_context& ctx) = 0;
};
using definition_ptr = std::unique_ptr<definition>;
struct constructor {
std::string name;
std::vector<std::string> types;
int8_t tag;
constructor(std::string n, std::vector<std::string> ts)
: name(std::move(n)), types(std::move(ts)) {}
};
using constructor_ptr = std::unique_ptr<constructor>;
struct definition_defn : public definition {
std::string name;
std::vector<std::string> params;
ast_ptr body;
type_ptr return_type;
std::vector<type_ptr> param_types;
std::vector<instruction_ptr> instructions;
llvm::Function* generated_function;
definition_defn(std::string n, std::vector<std::string> p, ast_ptr b)
: name(std::move(n)), params(std::move(p)), body(std::move(b)) {
}
void typecheck_first(type_mgr& mgr, type_env& env);
void typecheck_second(type_mgr& mgr, const type_env& env) const;
void resolve(const type_mgr& mgr);
void compile();
void gen_llvm_first(llvm_context& ctx);
void gen_llvm_second(llvm_context& ctx);
};
struct definition_data : public definition {
std::string name;
std::vector<constructor_ptr> constructors;
definition_data(std::string n, std::vector<constructor_ptr> cs)
: name(std::move(n)), constructors(std::move(cs)) {}
void typecheck_first(type_mgr& mgr, type_env& env);
void typecheck_second(type_mgr& mgr, const type_env& env) const;
void resolve(const type_mgr& mgr);
void compile();
void gen_llvm_first(llvm_context& ctx);
void gen_llvm_second(llvm_context& ctx);
};

23
09/env.cpp Normal file
View File

@ -0,0 +1,23 @@
#include "env.hpp"
int env_var::get_offset(const std::string& name) const {
if(name == this->name) return 0;
if(parent) return parent->get_offset(name) + 1;
throw 0;
}
bool env_var::has_variable(const std::string& name) const {
if(name == this->name) return true;
if(parent) return parent->has_variable(name);
return false;
}
int env_offset::get_offset(const std::string& name) const {
if(parent) return parent->get_offset(name) + offset;
throw 0;
}
bool env_offset::has_variable(const std::string& name) const {
if(parent) return parent->has_variable(name);
return false;
}

34
09/env.hpp Normal file
View File

@ -0,0 +1,34 @@
#pragma once
#include <memory>
#include <string>
struct env {
virtual ~env() = default;
virtual int get_offset(const std::string& name) const = 0;
virtual bool has_variable(const std::string& name) const = 0;
};
using env_ptr = std::shared_ptr<env>;
struct env_var : public env {
std::string name;
env_ptr parent;
env_var(std::string& n, env_ptr p)
: name(std::move(n)), parent(std::move(p)) {}
int get_offset(const std::string& name) const;
bool has_variable(const std::string& name) const;
};
struct env_offset : public env {
int offset;
env_ptr parent;
env_offset(int o, env_ptr p)
: offset(o), parent(std::move(p)) {}
int get_offset(const std::string& name) const;
bool has_variable(const std::string& name) const;
};

5
09/error.cpp Normal file
View File

@ -0,0 +1,5 @@
#include "error.hpp"
const char* type_error::what() const noexcept {
return "an error occured while checking the types of the program";
}

21
09/error.hpp Normal file
View File

@ -0,0 +1,21 @@
#pragma once
#include <exception>
#include "type.hpp"
struct type_error : std::exception {
std::string description;
type_error(std::string d)
: description(std::move(d)) {}
const char* what() const noexcept override;
};
struct unification_error : public type_error {
type_ptr left;
type_ptr right;
unification_error(type_ptr l, type_ptr r)
: left(std::move(l)), right(std::move(r)),
type_error("failed to unify types") {}
};

2
09/examples/bad1.txt Normal file
View File

@ -0,0 +1,2 @@
data Bool = { True, False }
defn main = { 3 + True }

1
09/examples/bad2.txt Normal file
View File

@ -0,0 +1 @@
defn main = { 1 2 3 4 5 }

8
09/examples/bad3.txt Normal file
View File

@ -0,0 +1,8 @@
data List = { Nil, Cons Int List }
defn head l = {
case l of {
Nil -> { 0 }
Cons x y z -> { x }
}
}

31
09/examples/runtime1.c Normal file
View File

@ -0,0 +1,31 @@
#include "../runtime.h"
void f_add(struct stack* s) {
struct node_num* left = (struct node_num*) eval(stack_peek(s, 0));
struct node_num* right = (struct node_num*) eval(stack_peek(s, 1));
stack_push(s, (struct node_base*) alloc_num(left->value + right->value));
}
void f_main(struct stack* s) {
// PushInt 320
stack_push(s, (struct node_base*) alloc_num(320));
// PushInt 6
stack_push(s, (struct node_base*) alloc_num(6));
// PushGlobal f_add (the function for +)
stack_push(s, (struct node_base*) alloc_global(f_add, 2));
struct node_base* left;
struct node_base* right;
// MkApp
left = stack_pop(s);
right = stack_pop(s);
stack_push(s, (struct node_base*) alloc_app(left, right));
// MkApp
left = stack_pop(s);
right = stack_pop(s);
stack_push(s, (struct node_base*) alloc_app(left, right));
}

3
09/examples/works1.txt Normal file
View File

@ -0,0 +1,3 @@
defn main = { sum 320 6 }
defn sum x y = { x + y }

3
09/examples/works2.txt Normal file
View File

@ -0,0 +1,3 @@
defn add x y = { x + y }
defn double x = { add x x }
defn main = { double 163 }

8
09/examples/works3.txt Normal file
View File

@ -0,0 +1,8 @@
data List = { Nil, Cons Int List }
defn length l = {
case l of {
Nil -> { 0 }
Cons x xs -> { 1 + length xs }
}
}
defn main = { length (Cons 1 (Cons 2 (Cons 3 Nil))) }

16
09/examples/works4.txt Normal file
View File

@ -0,0 +1,16 @@
data List = { Nil, Cons Int List }
defn add x y = { x + y }
defn mul x y = { x * y }
defn foldr f b l = {
case l of {
Nil -> { b }
Cons x xs -> { f x (foldr f b xs) }
}
}
defn main = {
foldr add 0 (Cons 1 (Cons 2 (Cons 3 (Cons 4 Nil)))) +
foldr mul 1 (Cons 1 (Cons 2 (Cons 3 (Cons 4 Nil))))
}

17
09/examples/works5.txt Normal file
View File

@ -0,0 +1,17 @@
data List = { Nil, Cons Int List }
defn sumZip l m = {
case l of {
Nil -> { 0 }
Cons x xs -> {
case m of {
Nil -> { 0 }
Cons y ys -> { x + y + sumZip xs ys }
}
}
}
}
defn ones = { Cons 1 ones }
defn main = { sumZip ones (Cons 1 (Cons 2 (Cons 3 Nil))) }

177
09/instruction.cpp Normal file
View File

@ -0,0 +1,177 @@
#include "instruction.hpp"
#include "llvm_context.hpp"
#include <llvm/IR/BasicBlock.h>
#include <llvm/IR/Function.h>
using namespace llvm;
static void print_indent(int n, std::ostream& to) {
while(n--) to << " ";
}
void instruction_pushint::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "PushInt(" << value << ")" << std::endl;
}
void instruction_pushint::gen_llvm(llvm_context& ctx, Function* f) const {
ctx.create_push(f, ctx.create_num(ctx.create_i32(value)));
}
void instruction_pushglobal::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "PushGlobal(" << name << ")" << std::endl;
}
void instruction_pushglobal::gen_llvm(llvm_context& ctx, Function* f) const {
auto& global_f = ctx.custom_functions.at("f_" + name);
auto arity = ctx.create_i32(global_f->arity);
ctx.create_push(f, ctx.create_global(global_f->function, arity));
}
void instruction_push::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "Push(" << offset << ")" << std::endl;
}
void instruction_push::gen_llvm(llvm_context& ctx, Function* f) const {
ctx.create_push(f, ctx.create_peek(f, ctx.create_size(offset)));
}
void instruction_pop::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "Pop(" << count << ")" << std::endl;
}
void instruction_pop::gen_llvm(llvm_context& ctx, Function* f) const {
ctx.create_popn(f, ctx.create_size(count));
}
void instruction_mkapp::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "MkApp()" << std::endl;
}
void instruction_mkapp::gen_llvm(llvm_context& ctx, Function* f) const {
auto left = ctx.create_pop(f);
auto right = ctx.create_pop(f);
ctx.create_push(f, ctx.create_app(left, right));
}
void instruction_update::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "Update(" << offset << ")" << std::endl;
}
void instruction_update::gen_llvm(llvm_context& ctx, Function* f) const {
ctx.create_update(f, ctx.create_size(offset));
}
void instruction_pack::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "Pack(" << tag << ", " << size << ")" << std::endl;
}
void instruction_pack::gen_llvm(llvm_context& ctx, Function* f) const {
ctx.create_pack(f, ctx.create_size(size), ctx.create_i8(tag));
}
void instruction_split::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "Split()" << std::endl;
}
void instruction_split::gen_llvm(llvm_context& ctx, Function* f) const {
ctx.create_split(f, ctx.create_size(size));
}
void instruction_jump::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "Jump(" << std::endl;
for(auto& instruction_set : branches) {
for(auto& instruction : instruction_set) {
instruction->print(indent + 2, to);
}
to << std::endl;
}
print_indent(indent, to);
to << ")" << std::endl;
}
void instruction_jump::gen_llvm(llvm_context& ctx, Function* f) const {
auto top_node = ctx.create_peek(f, ctx.create_size(0));
auto tag = ctx.unwrap_data_tag(top_node);
auto safety_block = BasicBlock::Create(ctx.ctx, "safety", f);
auto switch_op = ctx.builder.CreateSwitch(tag, safety_block, tag_mappings.size());
std::vector<BasicBlock*> blocks;
for(auto& branch : branches) {
auto branch_block = BasicBlock::Create(ctx.ctx, "branch", f);
ctx.builder.SetInsertPoint(branch_block);
for(auto& instruction : branch) {
instruction->gen_llvm(ctx, f);
}
ctx.builder.CreateBr(safety_block);
blocks.push_back(branch_block);
}
for(auto& mapping : tag_mappings) {
switch_op->addCase(ctx.create_i8(mapping.first), blocks[mapping.second]);
}
ctx.builder.SetInsertPoint(safety_block);
}
void instruction_slide::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "Slide(" << offset << ")" << std::endl;
}
void instruction_slide::gen_llvm(llvm_context& ctx, Function* f) const {
ctx.create_slide(f, ctx.create_size(offset));
}
void instruction_binop::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "BinOp(" << op_action(op) << ")" << std::endl;
}
void instruction_binop::gen_llvm(llvm_context& ctx, Function* f) const {
auto left_int = ctx.unwrap_num(ctx.create_pop(f));
auto right_int = ctx.unwrap_num(ctx.create_pop(f));
llvm::Value* result;
switch(op) {
case PLUS: result = ctx.builder.CreateAdd(left_int, right_int); break;
case MINUS: result = ctx.builder.CreateSub(left_int, right_int); break;
case TIMES: result = ctx.builder.CreateMul(left_int, right_int); break;
case DIVIDE: result = ctx.builder.CreateSDiv(left_int, right_int); break;
}
ctx.create_push(f, ctx.create_num(result));
}
void instruction_eval::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "Eval()" << std::endl;
}
void instruction_eval::gen_llvm(llvm_context& ctx, Function* f) const {
ctx.create_push(f, ctx.create_eval(ctx.create_pop(f)));
}
void instruction_alloc::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "Alloc(" << amount << ")" << std::endl;
}
void instruction_alloc::gen_llvm(llvm_context& ctx, Function* f) const {
ctx.create_alloc(f, ctx.create_size(amount));
}
void instruction_unwind::print(int indent, std::ostream& to) const {
print_indent(indent, to);
to << "Unwind()" << std::endl;
}
void instruction_unwind::gen_llvm(llvm_context& ctx, Function* f) const {
// Nothing
}

142
09/instruction.hpp Normal file
View File

@ -0,0 +1,142 @@
#pragma once
#include <llvm/IR/Function.h>
#include <string>
#include <memory>
#include <vector>
#include <map>
#include <ostream>
#include "binop.hpp"
#include "llvm_context.hpp"
struct instruction {
virtual ~instruction() = default;
virtual void print(int indent, std::ostream& to) const = 0;
virtual void gen_llvm(llvm_context& ctx, llvm::Function* f) const = 0;
};
using instruction_ptr = std::unique_ptr<instruction>;
struct instruction_pushint : public instruction {
int value;
instruction_pushint(int v)
: value(v) {}
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_pushglobal : public instruction {
std::string name;
instruction_pushglobal(std::string n)
: name(std::move(n)) {}
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_push : public instruction {
int offset;
instruction_push(int o)
: offset(o) {}
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_pop : public instruction {
int count;
instruction_pop(int c)
: count(c) {}
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_mkapp : public instruction {
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_update : public instruction {
int offset;
instruction_update(int o)
: offset(o) {}
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_pack : public instruction {
int tag;
int size;
instruction_pack(int t, int s)
: tag(t), size(s) {}
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_split : public instruction {
int size;
instruction_split(int s)
: size(s) {}
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_jump : public instruction {
std::vector<std::vector<instruction_ptr>> branches;
std::map<int, int> tag_mappings;
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_slide : public instruction {
int offset;
instruction_slide(int o)
: offset(o) {}
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_binop : public instruction {
binop op;
instruction_binop(binop o)
: op(o) {}
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_eval : public instruction {
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_alloc : public instruction {
int amount;
instruction_alloc(int a)
: amount(a) {}
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};
struct instruction_unwind : public instruction {
void print(int indent, std::ostream& to) const;
void gen_llvm(llvm_context& ctx, llvm::Function* f) const;
};

252
09/llvm_context.cpp Normal file
View File

@ -0,0 +1,252 @@
#include "llvm_context.hpp"
#include <llvm/IR/DerivedTypes.h>
using namespace llvm;
void llvm_context::create_types() {
stack_type = StructType::create(ctx, "stack");
stack_ptr_type = PointerType::getUnqual(stack_type);
tag_type = IntegerType::getInt8Ty(ctx);
struct_types["node_base"] = StructType::create(ctx, "node_base");
struct_types["node_app"] = StructType::create(ctx, "node_app");
struct_types["node_num"] = StructType::create(ctx, "node_num");
struct_types["node_global"] = StructType::create(ctx, "node_global");
struct_types["node_ind"] = StructType::create(ctx, "node_ind");
struct_types["node_data"] = StructType::create(ctx, "node_data");
node_ptr_type = PointerType::getUnqual(struct_types.at("node_base"));
function_type = FunctionType::get(Type::getVoidTy(ctx), { stack_ptr_type }, false);
struct_types.at("node_base")->setBody(
IntegerType::getInt32Ty(ctx)
);
struct_types.at("node_app")->setBody(
struct_types.at("node_base"),
node_ptr_type,
node_ptr_type
);
struct_types.at("node_num")->setBody(
struct_types.at("node_base"),
IntegerType::getInt32Ty(ctx)
);
struct_types.at("node_global")->setBody(
struct_types.at("node_base"),
FunctionType::get(Type::getVoidTy(ctx), { stack_ptr_type }, false)
);
struct_types.at("node_ind")->setBody(
struct_types.at("node_base"),
node_ptr_type
);
struct_types.at("node_data")->setBody(
struct_types.at("node_base"),
IntegerType::getInt8Ty(ctx),
PointerType::getUnqual(node_ptr_type)
);
}
void llvm_context::create_functions() {
auto void_type = Type::getVoidTy(ctx);
auto sizet_type = IntegerType::get(ctx, sizeof(size_t) * 8);
functions["stack_init"] = Function::Create(
FunctionType::get(void_type, { stack_ptr_type }, false),
Function::LinkageTypes::ExternalLinkage,
"stack_init",
&module
);
functions["stack_free"] = Function::Create(
FunctionType::get(void_type, { stack_ptr_type }, false),
Function::LinkageTypes::ExternalLinkage,
"stack_free",
&module
);
functions["stack_push"] = Function::Create(
FunctionType::get(void_type, { stack_ptr_type, node_ptr_type }, false),
Function::LinkageTypes::ExternalLinkage,
"stack_push",
&module
);
functions["stack_pop"] = Function::Create(
FunctionType::get(node_ptr_type, { stack_ptr_type }, false),
Function::LinkageTypes::ExternalLinkage,
"stack_pop",
&module
);
functions["stack_peek"] = Function::Create(
FunctionType::get(node_ptr_type, { stack_ptr_type, sizet_type }, false),
Function::LinkageTypes::ExternalLinkage,
"stack_peek",
&module
);
functions["stack_popn"] = Function::Create(
FunctionType::get(void_type, { stack_ptr_type, sizet_type }, false),
Function::LinkageTypes::ExternalLinkage,
"stack_popn",
&module
);
functions["stack_slide"] = Function::Create(
FunctionType::get(void_type, { stack_ptr_type, sizet_type }, false),
Function::LinkageTypes::ExternalLinkage,
"stack_slide",
&module
);
functions["stack_update"] = Function::Create(
FunctionType::get(void_type, { stack_ptr_type, sizet_type }, false),
Function::LinkageTypes::ExternalLinkage,
"stack_update",
&module
);
functions["stack_alloc"] = Function::Create(
FunctionType::get(void_type, { stack_ptr_type, sizet_type }, false),
Function::LinkageTypes::ExternalLinkage,
"stack_alloc",
&module
);
functions["stack_pack"] = Function::Create(
FunctionType::get(void_type, { stack_ptr_type, sizet_type, tag_type }, false),
Function::LinkageTypes::ExternalLinkage,
"stack_pack",
&module
);
functions["stack_split"] = Function::Create(
FunctionType::get(node_ptr_type, { stack_ptr_type, sizet_type }, false),
Function::LinkageTypes::ExternalLinkage,
"stack_split",
&module
);
auto int32_type = IntegerType::getInt32Ty(ctx);
functions["alloc_app"] = Function::Create(
FunctionType::get(node_ptr_type, { node_ptr_type, node_ptr_type }, false),
Function::LinkageTypes::ExternalLinkage,
"alloc_app",
&module
);
functions["alloc_num"] = Function::Create(
FunctionType::get(node_ptr_type, { int32_type }, false),
Function::LinkageTypes::ExternalLinkage,
"alloc_num",
&module
);
functions["alloc_global"] = Function::Create(
FunctionType::get(node_ptr_type, { function_type, int32_type }, false),
Function::LinkageTypes::ExternalLinkage,
"alloc_global",
&module
);
functions["alloc_ind"] = Function::Create(
FunctionType::get(node_ptr_type, { node_ptr_type }, false),
Function::LinkageTypes::ExternalLinkage,
"alloc_ind",
&module
);
functions["eval"] = Function::Create(
FunctionType::get(node_ptr_type, { node_ptr_type }, false),
Function::LinkageTypes::ExternalLinkage,
"eval",
&module
);
}
ConstantInt* llvm_context::create_i8(int8_t i) {
return ConstantInt::get(ctx, APInt(8, i));
}
ConstantInt* llvm_context::create_i32(int32_t i) {
return ConstantInt::get(ctx, APInt(32, i));
}
ConstantInt* llvm_context::create_size(size_t i) {
return ConstantInt::get(ctx, APInt(sizeof(size_t) * 8, i