Files
honey/source/ir/ir.hon
T

655 lines
23 KiB
Plaintext

import "@std/mem"
import "@std/arraylist"
import "@std/debug"
import "@source/diagnostics"
FunctionId :: distinct u32
GlobalId :: distinct u32
LocalId :: distinct u32
ValueId :: distinct u32
BlockId :: distinct u32
StringId :: distinct u32
ArrayId :: distinct u32
no_array :: maxval!(ArrayId)
no_value :: maxval!(ValueId)
Type :: enum {
invalid
int
float
bool
string
void
function
array
record
address
pointer
i8, i16, i32, isize
u8, u16, u32, u64, usize
}
aggregate proc(type Type) bool {
return type == .array or type == .record
}
#! integer storage widths for the supported 64-bit target; zero for noninteger types.
integer_bits proc(type Type) usize {
return match type {
.i8, .u8: 8
.i16, .u16: 16
.i32, .u32: 32
.int, .isize, .usize, .u64: 64
else: 0
}
}
unsigned_integer proc(type Type) bool {
return type == .u8 or type == .u16 or type == .u32 or type == .u64 or type == .usize
}
integer_max proc(type Type) u64 {
return match type {
.i8: 127
.i16: 32767
.i32: 2147483647
.int, .isize: u64(maxval!(i64))
.u8: 255
.u16: 65535
.u32: 4294967295
.u64, .usize: maxval!(u64)
else: unreachable
}
}
integer_min proc(type Type) i64 {
return match type {
.i8: -128
.i16: -32768
.i32: -2147483648
.int, .isize: minval!(i64)
.u8, .u16, .u32, .u64, .usize: 0
else: unreachable
}
}
ValueData :: union {
integer i64
# source pointers use run-wide handles; internal addresses use frame-local IDs below.
unsigned u64
real f64
boolean bool
string StringId
function FunctionId
elements []mut Value
address u32
}
Value :: struct {
type Type = .void
array_type ArrayId = no_array
raw bool = false
# interpreter poison survives copies; native storage uses LLVM poison directly.
uninitialized bool = false
data ValueData = ValueData{ integer = 0 }
}
RecordField :: struct {
type Type
array_type ArrayId = no_array
offset usize = 0
byte_offset usize = 0
tag Value = Value{}
}
#! fixed recursive aggregate shape; cells count interpreter slots, byte_size describes native layout.
#! unions retain overlapping byte cells; ordinary aggregates retain flattened scalar leaves.
ArrayType :: struct {
kind Type = .array
element Type = .invalid
element_array ArrayId = no_array
len usize = 0
cells usize = 0
mutable bool = false
fields []mut RecordField = &[]
is_union bool = false
tag_type Type = .void
payload_offset usize = 0
byte_size usize = 0
alignment usize = 1
}
#! maps a local slot or temporary to its preallocated, by-value frame segment.
ArrayStorage :: struct {
index u32
array_type ArrayId
offset usize
local bool
}
Op :: enum {
constant
undefined_value
load_local
store_local
assign_local
reset_local
load_global
array_literal
record_literal
union_literal
union_tag
field
index
address_local
address_global
index_address
field_address
load_address
store_address
pointer_from_address
pointer_address
pointer_offset
pointer_cast
string_pointer
string_length
slice_check
sentinel_check
optional_check
memory_copy, memory_set
negate
convert
logical_not
bit_not, bit_and, bit_or, bit_xor
shift_left, shift_right, shift_left_saturating
add, subtract
multiply, divide
call
equal, not_equal
less, less_equal
greater, greater_equal
}
Instruction :: struct {
op Op
type Type = .void
# pointer operations describe their pointee here, not aggregate result storage.
array_type ArrayId = no_array
pointee Type = .invalid
span diagnostics.Span = diagnostics.Span{ start = 0, end = 0 }
destination ValueId = no_value
left ValueId = no_value
right ValueId = no_value
extra ValueId = no_value
slot u32 = 0
constant Value = Value{}
arguments_start usize = 0
arguments_count usize = 0
}
TerminatorKind :: enum {
return_value,
trap,
jump,
branch,
unreachable,
}
Terminator :: struct {
kind TerminatorKind = .return_value
value ValueId = no_value
target BlockId = BlockId(0)
alternative BlockId = BlockId(0)
diagnostic diagnostics.DiagnosticId = diagnostics.no_diagnostic
span diagnostics.Span = diagnostics.Span{ start = 0, end = 0 }
}
Block :: struct {
instructions arraylist.ArrayList(Instruction)
arguments arraylist.ArrayList(ValueId)
terminator Terminator = Terminator{}
}
#! construction derives storage segments, aggregate totals, value counts, and address presence.
#! producers use add_local, add_parameter, and emit; derived metadata is read-only to callers.
Function :: struct {
parameters arraylist.ArrayList(Type)
# owned by the module allocator; empty for interpreted/native-defined functions.
external_name []u8 = ""
locals arraylist.ArrayList(Type)
result Type = .void
result_array_type ArrayId = no_array
result_fallible bool = false
array_storage arraylist.ArrayList(ArrayStorage)
aggregate_cells usize = 0
has_addresses bool = false
blocks arraylist.ArrayList(Block)
entry BlockId = BlockId(0)
value_count usize = 0
span diagnostics.Span = diagnostics.Span{ start = 0, end = 0 }
}
Global :: struct {
type Type
array_type ArrayId = no_array
initializer FunctionId
span diagnostics.Span
}
#! retains the original allocation for freeing while exposing only decoded bytes.
StringStorage :: struct {
allocation []mut u8
len usize
}
#! owns executable storage, including decoded strings; no AST or binding table is retained.
#! spans and diagnostic IDs refer to the caller's source and diagnostic store.
Module :: struct {
allocator mem.Allocator
functions arraylist.ArrayList(Function)
globals arraylist.ArrayList(Global)
strings arraylist.ArrayList(StringStorage)
arrays arraylist.ArrayList(ArrayType)
entry ?FunctionId = null
entry_diagnostic diagnostics.DiagnosticId = diagnostics.no_diagnostic
}
#! retains `allocator` for executable storage; release the returned module with deinit.
init proc(allocator mem.Allocator) Module {
return Module{
allocator = allocator,
functions = arraylist.init(allocator),
globals = arraylist.init(allocator),
strings = arraylist.init(allocator),
arrays = arraylist.init(allocator),
}
}
#! retains `allocator` in its lists; transfer the function to a module using the same allocator for cleanup with deinit.
init_function proc(allocator mem.Allocator) Function {
return Function{
parameters = arraylist.init(allocator),
locals = arraylist.init(allocator),
blocks = arraylist.init(allocator),
array_storage = arraylist.init(allocator),
}
}
#! retains `allocator` in its lists; transfer the block to a module function for cleanup with deinit.
init_block proc(allocator mem.Allocator) Block {
return Block{
instructions = arraylist.init(allocator),
arguments = arraylist.init(allocator),
}
}
#! adds a fixed shape and derives its flattened storage size; child shapes must already exist.
#! scalar elements use no_array; zero-leaf children retain their logical lengths.
add_array proc(
module @mut Module,
element Type,
element_array ArrayId,
len usize,
mutable bool,
) ArrayId ! (mem.AllocError | diagnostics.CapacityError) {
debug.assert(aggregate(element) == (element_array != no_array))
width :: if (aggregate(element)) module.arrays.items[usize(element_array)].cells else 1
if (width != 0 and len > divtrunc!(maxval!(usize), width)) return .storage_limit_reached
cells :: len * width
if (cells > divtrunc!(maxval!(usize), sizeof!(Value))) return .storage_limit_reached
if (module.arrays.items.len >= usize(no_array)) return .storage_limit_reached
stride :: storage_size(module, element, element_array)
if (stride != 0 and len > divtrunc!(maxval!(usize), stride)) return .storage_limit_reached
id :: ArrayId(module.arrays.items.len)
try arraylist.append(&module.arrays, ArrayType{
element = element,
element_array = element_array,
len = len,
cells = cells,
mutable = mutable,
byte_size = len * stride,
alignment = storage_alignment(module, element, element_array),
})
return id
}
#! copies declaration-order fields and derives their flattened offsets; child shapes must exist.
add_record proc(
module @mut Module,
fields []RecordField,
) ArrayId ! (mem.AllocError | diagnostics.CapacityError) {
if (module.arrays.items.len >= usize(no_array)) return .storage_limit_reached
owned :: try mem.alloc(RecordField, module.allocator, fields.len)
errdefer mem.free(module.allocator, owned)
cells usize := 0
bytes usize := 0
alignment usize := 1
for (fields) |field, index| {
debug.assert(aggregate(field.type) == (field.array_type != no_array))
width :: if (aggregate(field.type)) module.arrays.items[usize(field.array_type)].cells else 1
if (width > divtrunc!(maxval!(usize), sizeof!(Value)) - cells) return .storage_limit_reached
field_alignment :: storage_alignment(module, field.type, field.array_type)
if (field_alignment > alignment) alignment = field_alignment
if (bytes > maxval!(usize) - (field_alignment - 1)) return .storage_limit_reached
bytes = aligned_size(bytes, field_alignment)
size :: storage_size(module, field.type, field.array_type)
if (size > maxval!(usize) - bytes) return .storage_limit_reached
owned[index] = RecordField{
type = field.type, array_type = field.array_type, offset = cells,
byte_offset = bytes, tag = field.tag,
}
bytes += size
cells += width
}
id :: ArrayId(module.arrays.items.len)
if (bytes > maxval!(usize) - (alignment - 1)) return .storage_limit_reached
try arraylist.append(&module.arrays, ArrayType{
kind = .record, fields = owned, cells = cells,
byte_size = aligned_size(bytes, alignment), alignment = alignment,
})
return id
}
#! returns a borrowed child, including a raw view when projecting overlapping union storage.
aggregate_item proc(module @Module, value Value, index usize) Value {
shape :: module.arrays.items[usize(value.array_type)]
type := shape.element
child := shape.element_array
start usize := 0
width usize := 1
if (shape.kind == .record) {
field :: shape.fields[index]
type = field.type
child = field.array_type
start = field.offset
if (value.raw) start = field.byte_offset
if (shape.is_union) start = shape.payload_offset
} else {
if (value.raw) width = storage_size(module, type, child)
else if (aggregate(type)) width = module.arrays.items[usize(child)].cells
start = index * width
}
raw :: value.raw or shape.is_union
if (!aggregate(type)) {
if (raw) return read_storage(module, type, child, value.data.elements[start..], true)
if (value.data.elements[start].uninitialized) return Value{ type = type, uninitialized = true }
return value.data.elements[start]
}
width = if (raw) storage_size(module, type, child) else module.arrays.items[usize(child)].cells
return Value{
type = type, array_type = child, raw = raw,
data = ValueData{ elements = value.data.elements[start..start + width] },
}
}
#! copies variant descriptors; all payloads share one eight-byte-aligned storage region.
add_union proc(module @mut Module, fields []RecordField, tagged bool) ArrayId ! (mem.AllocError | diagnostics.CapacityError) {
if (module.arrays.items.len >= usize(no_array)) return .storage_limit_reached
owned :: try mem.alloc(RecordField, module.allocator, fields.len)
errdefer mem.free(module.allocator, owned)
size usize := 0
for (fields) |field, index| {
width :: storage_size(module, field.type, field.array_type)
if (width > size) size = width
owned[index] = field
owned[index].offset = if (tagged) 8 else 0
owned[index].byte_offset = owned[index].offset
}
prefix usize :: if (tagged) 8 else 0
if (size > divtrunc!(maxval!(usize), sizeof!(Value)) - 15) return .storage_limit_reached
size = aligned_size(size, 8) + prefix
id :: ArrayId(module.arrays.items.len)
tag_type :: if (tagged and fields.len != 0) fields[0].tag.type else Type.void
try arraylist.append(&module.arrays, ArrayType{
kind = .record, fields = owned, is_union = true,
tag_type = tag_type,
payload_offset = prefix, cells = size, byte_size = size, alignment = 8,
})
return id
}
@hide:file
aligned_size proc(size, alignment usize) usize {
return divtrunc!(size + alignment - 1, alignment) * alignment
}
storage_alignment proc(module @Module, type Type, shape ArrayId) usize {
if (aggregate(type)) return module.arrays.items[usize(shape)].alignment
bits :: integer_bits(type)
if (bits != 0) return divtrunc!(bits, 8)
return if (type == .float or type == .string or type == .function or type == .pointer) 8 else 1
}
storage_size proc(module @Module, type Type, shape ArrayId) usize {
if (aggregate(type)) return module.arrays.items[usize(shape)].byte_size
bits :: integer_bits(type)
if (bits != 0) return divtrunc!(bits, 8)
return match type {
.float, .function, .pointer: 8
.string: 16
.bool: 1
.void: 0
else: unreachable
}
}
#! loads a scalar or borrows an aggregate from byte cells without allocating.
read_storage proc(module @Module, type Type, shape ArrayId, cells []mut Value, raw bool) Value {
if (aggregate(type)) return Value{ type = type, array_type = shape, raw = raw, data = ValueData{ elements = cells[..storage_size(module, type, shape)] } }
bits u64 := 0
size :: storage_size(module, type, shape)
count :: if (size > 8) usize(8) else size
for (0..count) |i| {
if (cells[i].uninitialized) return Value{ type = type, uninitialized = true }
}
for (0..count) |i| bits += cells[i].data.unsigned << u64(i * 8)
data := ValueData{ unsigned = bits }
match type {
.i8: data = ValueData{ integer = i64(ptrcast!(@i8, &bits)^) }
.i16: data = ValueData{ integer = i64(ptrcast!(@i16, &bits)^) }
.i32: data = ValueData{ integer = i64(ptrcast!(@i32, &bits)^) }
.int, .isize: data = ValueData{ integer = ptrcast!(@i64, &bits)^ }
.float: data = ValueData{ real = ptrcast!(@f64, &bits)^ }
.bool: data = ValueData{ boolean = (bits & 1) != 0 }
.string: data = ValueData{ string = StringId(bits) }
.function: data = ValueData{ unsigned = bits }
.void: return Value{}
else: {}
}
return Value{ type = type, data = data }
}
#! stores a value in shared byte cells; recursive aggregates preserve their native field padding.
write_storage proc(module @Module, cells []mut Value, value Value) void {
if (aggregate(value.type)) {
shape :: module.arrays.items[usize(value.array_type)]
if (value.raw or shape.is_union) {
memcopy!(cells[..shape.byte_size], value.data.elements)
return
}
count :: if (shape.kind == .record) shape.fields.len else shape.len
for (0..count) |i| {
offset :: if (shape.kind == .record) shape.fields[i].byte_offset else i * storage_size(module, shape.element, shape.element_array)
write_storage(module, cells[offset..], aggregate_item(module, value, i))
}
return
}
bits u64 := 0
match value.type {
.float: bits = ptrcast!(@u64, &value.data.real)^
.bool: bits = if (value.data.boolean) 1 else 0
.string: bits = u64(value.data.string)
.function: bits = if (value.data.function == maxval!(FunctionId)) maxval!(u64) else u64(value.data.function)
.pointer: bits = value.data.unsigned
.void: return
else: bits = ptrcast!(@u64, &value.data.integer)^
}
size :: storage_size(module, value.type, value.array_type)
for (0..size) |i| {
byte u64 := 0
if (i < 8) byte = (bits >> u64(i * 8)) & 255
else byte = (u64(string_bytes(module, value.data.string).len) >> u64((i - 8) * 8)) & 255
cells[i] = Value{ type = .u8, uninitialized = value.uninitialized, data = ValueData{ unsigned = byte } }
}
}
#! converts raw aggregate projections into the caller's preallocated flattened segment.
copy_aggregate proc(module @Module, destination Value, source Value) void {
shape :: module.arrays.items[usize(source.array_type)]
if (!source.raw or shape.is_union) {
memcopy!(destination.data.elements, source.data.elements)
return
}
count :: if (shape.kind == .record) shape.fields.len else shape.len
for (0..count) |i| {
child :: aggregate_item(module, source, i)
if (aggregate(child.type)) copy_aggregate(module, aggregate_item(module, destination, i), child)
else {
offset :: if (shape.kind == .record) shape.fields[i].offset else i
destination.data.elements[offset] = child
}
}
}
union_tag proc(module @Module, value Value) Value {
shape :: module.arrays.items[usize(value.array_type)]
return read_storage(module, shape.tag_type, no_array, value.data.elements, true)
}
union_active proc(module @Module, value Value, field usize) bool {
shape :: module.arrays.items[usize(value.array_type)]
if (shape.tag_type == .void) return true
tag :: union_tag(module, value)
return tag.data.unsigned == shape.fields[field].tag.data.unsigned
}
@hide:file
prepare_storage proc(module @Module, function @mut Function, index u32, shape ArrayId, local bool) void ! (mem.AllocError | diagnostics.CapacityError) {
cells :: module.arrays.items[usize(shape)].cells
if (cells > divtrunc!(maxval!(usize), sizeof!(Value)) - function.aggregate_cells) return .storage_limit_reached
try arraylist.append(&function.array_storage, ArrayStorage{
index = index,
array_type = shape,
offset = function.aggregate_cells,
local = local,
})
function.aggregate_cells += cells
}
#! creates a local and its disjoint by-value backing together; scalar locals use no_array.
add_local proc(
module @mut Module,
function FunctionId,
type Type,
shape ArrayId,
) LocalId ! (mem.AllocError | diagnostics.CapacityError) {
debug.assert(aggregate(type) == (shape != no_array))
body :: &module.functions.items[usize(function)]
if (body.locals.items.len >= usize(maxval!(LocalId))) return .storage_limit_reached
id :: LocalId(body.locals.items.len)
try arraylist.append(&body.locals, type)
errdefer _ = arraylist.pop(&body.locals)
if (aggregate(type)) try prepare_storage(module, body, u32(id), shape, true)
return id
}
#! creates a parameter and its local backing; all parameters precede non-parameter locals.
add_parameter proc(
module @mut Module,
function FunctionId,
type Type,
shape ArrayId,
) LocalId ! (mem.AllocError | diagnostics.CapacityError) {
body :: &module.functions.items[usize(function)]
debug.assert(body.parameters.items.len == body.locals.items.len)
try arraylist.append(&body.parameters, type)
errdefer _ = arraylist.pop(&body.parameters)
return try add_local(module, function, type, shape)
}
#! appends an instruction and derives its result count, aggregate backing, and address presence.
#! no_value requests a fresh result; explicit result IDs support non-SSA definitions across blocks.
#! repeated aggregate results must retain their shape and reuse their existing segment.
#! failures leave instruction and storage lengths, totals, counts, and flags unchanged.
emit proc(
module @mut Module,
function FunctionId,
block BlockId,
instruction Instruction,
) ValueId ! (mem.AllocError | diagnostics.CapacityError) {
body :: &module.functions.items[usize(function)]
target :: &body.blocks.items[usize(block)]
operation := instruction
produces_value :: (
operation.op != .store_local
and operation.op != .assign_local
and operation.op != .reset_local
and operation.op != .store_address
and operation.op != .slice_check
and operation.op != .sentinel_check
and operation.op != .optional_check
and operation.op != .memory_copy
and operation.op != .memory_set
)
count := body.value_count
if (produces_value) {
if (operation.destination == no_value) {
if (count >= usize(no_value)) return .storage_limit_reached
operation.destination = ValueId(count)
}
if (usize(operation.destination) >= count) count = usize(operation.destination) + 1
} else {
debug.assert(operation.destination == no_value)
}
try arraylist.append(&target.instructions, operation)
errdefer _ = arraylist.pop(&target.instructions)
if (produces_value and aggregate(operation.type)) {
debug.assert(operation.array_type != no_array)
registered := false
if (usize(operation.destination) < body.value_count) {
for (body.array_storage.items) |storage| {
if (storage.local or storage.index != u32(operation.destination)) continue
debug.assert(storage.array_type == operation.array_type)
registered = true
break
}
}
if (!registered) try prepare_storage(module, body, u32(operation.destination), operation.array_type, false)
}
body.value_count = count
if (operation.type == .address) body.has_addresses = true
return operation.destination
}
#! resolves a module-local ID to bytes borrowed until module deinit.
string_bytes proc(module @Module, id StringId) []u8 {
string :: module.strings.items[usize(id)]
return string.allocation[..string.len]
}
#! releases all executable storage using the retained allocator.
deinit proc(module @mut Module) void {
for (0..(module.functions.items.len)) |i| {
function :: &module.functions.items[i]
for (0..(function.blocks.items.len)) |j| {
block :: &function.blocks.items[j]
arraylist.deinit(&block.instructions)
arraylist.deinit(&block.arguments)
}
arraylist.deinit(&function.parameters)
arraylist.deinit(&function.locals)
arraylist.deinit(&function.blocks)
arraylist.deinit(&function.array_storage)
if (function.external_name.len != 0) mem.free(module.allocator, function.external_name)
}
for (module.strings.items) |string|
mem.free(module.allocator, string.allocation)
for (module.arrays.items) |shape| {
if (shape.kind == .record) mem.free(module.allocator, shape.fields)
}
arraylist.deinit(&module.functions)
arraylist.deinit(&module.globals)
arraylist.deinit(&module.strings)
arraylist.deinit(&module.arrays)
}