gitback/zig
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'simd2' of https://github.com/shawnl/zig into shawnl-simd2

Browse Source
This commit is contained in:
Andrew Kelley 2019-06-23 17:10:33 -04:00
commit b2cbc59e4c
No known key found for this signature in database
GPG Key ID: 7C5F548F728501A9
13 changed files with 1014 additions and 133 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
CMakeLists.txt
View File

@ -389,6 +389,8 @@ set(EMBEDDED_SOFTFLOAT_SOURCES
"${CMAKE_SOURCE_DIR}/deps/SoftFloat-3e/source/s_subMagsF32.c"
"${CMAKE_SOURCE_DIR}/deps/SoftFloat-3e/source/s_subMagsF64.c"
"${CMAKE_SOURCE_DIR}/deps/SoftFloat-3e/source/s_tryPropagateNaNF128M.c"
"${CMAKE_SOURCE_DIR}/deps/SoftFloat-3e/source/f16_mulAdd.c"
"${CMAKE_SOURCE_DIR}/deps/SoftFloat-3e/source/f128M_mulAdd.c"
"${CMAKE_SOURCE_DIR}/deps/SoftFloat-3e/source/softfloat_state.c"
"${CMAKE_SOURCE_DIR}/deps/SoftFloat-3e/source/ui32_to_f128M.c"
"${CMAKE_SOURCE_DIR}/deps/SoftFloat-3e/source/ui64_to_f128M.c"

92
doc/langref.html.in
View File

@ -6259,6 +6259,13 @@ comptime {
This function is only valid within function scope.
</p>
{#header_close#}
{#header_open|@mulAdd#}
<pre>{#syntax#}@mulAdd(comptime T: type, a: T, b: T, c: T) T{#endsyntax#}</pre>
<p>
Fused multiply add (for floats), similar to {#syntax#}(a * b) + c{#endsyntax#}, except
only rounds once, and is thus more accurate.
</p>
{#header_close#}
{#header_open|@byteSwap#}
@ -7347,10 +7354,91 @@ test "@setRuntimeSafety" {
<pre>{#syntax#}@sqrt(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Performs the square root of a floating point number. Uses a dedicated hardware instruction
when available. Currently only supports f32 and f64 at runtime. f128 at runtime is TODO.
when available. Supports f16, f32, f64, and f128, as well as vectors.
</p>
{#header_close#}
{#header_open|@sin#}
<pre>{#syntax#}@sin(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
This is a low-level intrinsic. Most code can use {#syntax#}std.math.sqrt{#endsyntax#} instead.
Sine trigometric function on a floating point number. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}
{#header_open|@cos#}
<pre>{#syntax#}@cos(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Cosine trigometric function on a floating point number. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}
{#header_open|@exp#}
<pre>{#syntax#}@exp(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Base-e exponential function on a floating point number. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}
{#header_open|@exp2#}
<pre>{#syntax#}@exp2(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Base-2 exponential function on a floating point number. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}
{#header_open|@ln#}
<pre>{#syntax#}@ln(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Returns the natural logarithm of a floating point number. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}
{#header_open|@log2#}
<pre>{#syntax#}@log2(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Returns the logarithm to the base 2 of a floating point number. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}
{#header_open|@log10#}
<pre>{#syntax#}@log10(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Returns the logarithm to the base 10 of a floating point number. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}
{#header_open|@fabs#}
<pre>{#syntax#}@fabs(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Returns the absolute value of a floating point number. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}
{#header_open|@floor#}
<pre>{#syntax#}@floor(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Returns the largest integral value not greater than the given floating point number. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}
{#header_open|@ceil#}
<pre>{#syntax#}@ceil(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Returns the largest integral value not less than the given floating point number. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}
{#header_open|@trunc#}
<pre>{#syntax#}@trunc(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Rounds the given floating point number to an integer, towards zero. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}
{#header_open|@round#}
<pre>{#syntax#}@round(comptime T: type, value: T) T{#endsyntax#}</pre>
<p>
Rounds the given floating point number to an integer, away from zero. Uses a dedicated hardware instruction
when available. Currently supports f32 and f64.
</p>
{#header_close#}

39
src/all_types.hpp
View File

@ -1406,6 +1406,7 @@ enum BuiltinFnId {
BuiltinFnIdSubWithOverflow,
BuiltinFnIdMulWithOverflow,
BuiltinFnIdShlWithOverflow,
BuiltinFnIdMulAdd,
BuiltinFnIdCInclude,
BuiltinFnIdCDefine,
BuiltinFnIdCUndef,
@ -1433,6 +1434,19 @@ enum BuiltinFnId {
BuiltinFnIdRem,
BuiltinFnIdMod,
BuiltinFnIdSqrt,
BuiltinFnIdSin,
BuiltinFnIdCos,
BuiltinFnIdExp,
BuiltinFnIdExp2,
BuiltinFnIdLn,
BuiltinFnIdLog2,
BuiltinFnIdLog10,
BuiltinFnIdFabs,
BuiltinFnIdFloor,
BuiltinFnIdCeil,
BuiltinFnIdTrunc,
BuiltinFnIdNearbyInt,
BuiltinFnIdRound,
BuiltinFnIdTruncate,
BuiltinFnIdIntCast,
BuiltinFnIdFloatCast,
@ -1554,9 +1568,8 @@ enum ZigLLVMFnId {
ZigLLVMFnIdClz,
ZigLLVMFnIdPopCount,
ZigLLVMFnIdOverflowArithmetic,
ZigLLVMFnIdFloor,
ZigLLVMFnIdCeil,
ZigLLVMFnIdSqrt,
ZigLLVMFnIdFMA,
ZigLLVMFnIdFloatOp,
ZigLLVMFnIdBswap,
ZigLLVMFnIdBitReverse,
};
@ -1583,7 +1596,9 @@ struct ZigLLVMFnKey {
uint32_t bit_count;
} pop_count;
struct {
BuiltinFnId op;
uint32_t bit_count;
uint32_t vector_len; // 0 means not a vector
} floating;
struct {
AddSubMul add_sub_mul;
@ -2235,6 +2250,8 @@ enum IrInstructionId {
IrInstructionIdHandle,
IrInstructionIdAlignOf,
IrInstructionIdOverflowOp,
IrInstructionIdMulAdd,
IrInstructionIdFloatOp,
IrInstructionIdTestErr,
IrInstructionIdUnwrapErrCode,
IrInstructionIdUnwrapErrPayload,
@ -2296,7 +2313,6 @@ enum IrInstructionId {
IrInstructionIdAddImplicitReturnType,
IrInstructionIdMergeErrRetTraces,
IrInstructionIdMarkErrRetTracePtr,
IrInstructionIdSqrt,
IrInstructionIdErrSetCast,
IrInstructionIdToBytes,
IrInstructionIdFromBytes,
@ -3038,6 +3054,15 @@ struct IrInstructionOverflowOp {
ZigType *result_ptr_type;
};
struct IrInstructionMulAdd {
IrInstruction base;
IrInstruction *type_value;
IrInstruction *op1;
IrInstruction *op2;
IrInstruction *op3;
};
struct IrInstructionAlignOf {
IrInstruction base;
@ -3461,11 +3486,13 @@ struct IrInstructionMarkErrRetTracePtr {
IrInstruction *err_ret_trace_ptr;
};
struct IrInstructionSqrt {
// For float ops which take a single argument
struct IrInstructionFloatOp {
IrInstruction base;
BuiltinFnId op;
IrInstruction *type;
IrInstruction *op;
IrInstruction *op1;
};
struct IrInstructionCheckRuntimeScope {

24
src/analyze.cpp
View File

@ -5736,12 +5736,13 @@ uint32_t zig_llvm_fn_key_hash(ZigLLVMFnKey x) {
return (uint32_t)(x.data.clz.bit_count) * (uint32_t)2428952817;
case ZigLLVMFnIdPopCount:
return (uint32_t)(x.data.clz.bit_count) * (uint32_t)101195049;
case ZigLLVMFnIdFloor:
return (uint32_t)(x.data.floating.bit_count) * (uint32_t)1899859168;
case ZigLLVMFnIdCeil:
return (uint32_t)(x.data.floating.bit_count) * (uint32_t)1953839089;
case ZigLLVMFnIdSqrt:
return (uint32_t)(x.data.floating.bit_count) * (uint32_t)2225366385;
case ZigLLVMFnIdFloatOp:
return (uint32_t)(x.data.floating.bit_count) * ((uint32_t)x.id + 1025) +
(uint32_t)(x.data.floating.vector_len) * (((uint32_t)x.id << 5) + 1025) +
(uint32_t)(x.data.floating.op) * (uint32_t)43789879;
case ZigLLVMFnIdFMA:
return (uint32_t)(x.data.floating.bit_count) * ((uint32_t)x.id + 1025) +
(uint32_t)(x.data.floating.vector_len) * (((uint32_t)x.id << 5) + 1025);
case ZigLLVMFnIdBswap:
return (uint32_t)(x.data.bswap.bit_count) * (uint32_t)3661994335;
case ZigLLVMFnIdBitReverse:
@ -5769,10 +5770,13 @@ bool zig_llvm_fn_key_eql(ZigLLVMFnKey a, ZigLLVMFnKey b) {
return a.data.bswap.bit_count == b.data.bswap.bit_count;
case ZigLLVMFnIdBitReverse:
return a.data.bit_reverse.bit_count == b.data.bit_reverse.bit_count;
case ZigLLVMFnIdFloor:
case ZigLLVMFnIdCeil:
case ZigLLVMFnIdSqrt:
return a.data.floating.bit_count == b.data.floating.bit_count;
case ZigLLVMFnIdFloatOp:
return a.data.floating.bit_count == b.data.floating.bit_count &&
a.data.floating.vector_len == b.data.floating.vector_len &&
a.data.floating.op == b.data.floating.op;
case ZigLLVMFnIdFMA:
return a.data.floating.bit_count == b.data.floating.bit_count &&
a.data.floating.vector_len == b.data.floating.vector_len;
case ZigLLVMFnIdOverflowArithmetic:
return (a.data.overflow_arithmetic.bit_count == b.data.overflow_arithmetic.bit_count) &&
(a.data.overflow_arithmetic.add_sub_mul == b.data.overflow_arithmetic.add_sub_mul) &&

104
src/codegen.cpp
View File

@ -806,32 +806,47 @@ static LLVMValueRef get_int_overflow_fn(CodeGen *g, ZigType *operand_type, AddSu
return fn_val;
}
static LLVMValueRef get_float_fn(CodeGen *g, ZigType *type_entry, ZigLLVMFnId fn_id) {
assert(type_entry->id == ZigTypeIdFloat);
static LLVMValueRef get_float_fn(CodeGen *g, ZigType *type_entry, ZigLLVMFnId fn_id, BuiltinFnId op) {
assert(type_entry->id == ZigTypeIdFloat ||
type_entry->id == ZigTypeIdVector);
bool is_vector = (type_entry->id == ZigTypeIdVector);
ZigType *float_type = is_vector ? type_entry->data.vector.elem_type : type_entry;
ZigLLVMFnKey key = {};
key.id = fn_id;
key.data.floating.bit_count = (uint32_t)type_entry->data.floating.bit_count;
key.data.floating.bit_count = (uint32_t)float_type->data.floating.bit_count;
key.data.floating.vector_len = is_vector ? (uint32_t)type_entry->data.vector.len : 0;
key.data.floating.op = op;
auto existing_entry = g->llvm_fn_table.maybe_get(key);
if (existing_entry)
return existing_entry->value;
const char *name;
if (fn_id == ZigLLVMFnIdFloor) {
name = "floor";
} else if (fn_id == ZigLLVMFnIdCeil) {
name = "ceil";
} else if (fn_id == ZigLLVMFnIdSqrt) {
name = "sqrt";
uint32_t num_args;
if (fn_id == ZigLLVMFnIdFMA) {
name = "fma";
num_args = 3;
} else if (fn_id == ZigLLVMFnIdFloatOp) {
name = float_op_to_name(op, true);
num_args = 1;
} else {
zig_unreachable();
}
char fn_name[64];
sprintf(fn_name, "llvm.%s.f%" ZIG_PRI_usize "", name, type_entry->data.floating.bit_count);
if (is_vector)
sprintf(fn_name, "llvm.%s.v%" PRIu32 "f%" PRIu32, name, key.data.floating.vector_len, key.data.floating.bit_count);
else
sprintf(fn_name, "llvm.%s.f%" PRIu32, name, key.data.floating.bit_count);
LLVMTypeRef float_type_ref = get_llvm_type(g, type_entry);
LLVMTypeRef fn_type = LLVMFunctionType(float_type_ref, &float_type_ref, 1, false);
LLVMTypeRef return_elem_types[3] = {
float_type_ref,
float_type_ref,
float_type_ref,
};
LLVMTypeRef fn_type = LLVMFunctionType(float_type_ref, return_elem_types, num_args, false);
LLVMValueRef fn_val = LLVMAddFunction(g->module, fn_name, fn_type);
assert(LLVMGetIntrinsicID(fn_val));
@ -2460,22 +2475,17 @@ static LLVMValueRef gen_overflow_shr_op(CodeGen *g, ZigType *type_entry,
return result;
}
static LLVMValueRef gen_floor(CodeGen *g, LLVMValueRef val, ZigType *type_entry) {
if (type_entry->id == ZigTypeIdInt)
static LLVMValueRef gen_float_op(CodeGen *g, LLVMValueRef val, ZigType *type_entry, BuiltinFnId op) {
if ((op == BuiltinFnIdCeil ||
op == BuiltinFnIdFloor) &&
type_entry->id == ZigTypeIdInt)
return val;
assert(type_entry->id == ZigTypeIdFloat);
LLVMValueRef floor_fn = get_float_fn(g, type_entry, ZigLLVMFnIdFloor);
LLVMValueRef floor_fn = get_float_fn(g, type_entry, ZigLLVMFnIdFloatOp, op);
return LLVMBuildCall(g->builder, floor_fn, &val, 1, "");
}
static LLVMValueRef gen_ceil(CodeGen *g, LLVMValueRef val, ZigType *type_entry) {
if (type_entry->id == ZigTypeIdInt)
return val;
LLVMValueRef ceil_fn = get_float_fn(g, type_entry, ZigLLVMFnIdCeil);
return LLVMBuildCall(g->builder, ceil_fn, &val, 1, "");
}
enum DivKind {
DivKindFloat,
DivKindTrunc,
@ -2551,7 +2561,7 @@ static LLVMValueRef gen_div(CodeGen *g, bool want_runtime_safety, bool want_fast
return result;
case DivKindExact:
if (want_runtime_safety) {
LLVMValueRef floored = gen_floor(g, result, type_entry);
LLVMValueRef floored = gen_float_op(g, result, type_entry, BuiltinFnIdFloor);
LLVMBasicBlockRef ok_block = LLVMAppendBasicBlock(g->cur_fn_val, "DivExactOk");
LLVMBasicBlockRef fail_block = LLVMAppendBasicBlock(g->cur_fn_val, "DivExactFail");
LLVMValueRef ok_bit = LLVMBuildFCmp(g->builder, LLVMRealOEQ, floored, result, "");
@ -2573,12 +2583,12 @@ static LLVMValueRef gen_div(CodeGen *g, bool want_runtime_safety, bool want_fast
LLVMBuildCondBr(g->builder, ltz, ltz_block, gez_block);
LLVMPositionBuilderAtEnd(g->builder, ltz_block);
LLVMValueRef ceiled = gen_ceil(g, result, type_entry);
LLVMValueRef ceiled = gen_float_op(g, result, type_entry, BuiltinFnIdCeil);
LLVMBasicBlockRef ceiled_end_block = LLVMGetInsertBlock(g->builder);
LLVMBuildBr(g->builder, end_block);
LLVMPositionBuilderAtEnd(g->builder, gez_block);
LLVMValueRef floored = gen_floor(g, result, type_entry);
LLVMValueRef floored = gen_float_op(g, result, type_entry, BuiltinFnIdFloor);
LLVMBasicBlockRef floored_end_block = LLVMGetInsertBlock(g->builder);
LLVMBuildBr(g->builder, end_block);
@ -2590,7 +2600,7 @@ static LLVMValueRef gen_div(CodeGen *g, bool want_runtime_safety, bool want_fast
return phi;
}
case DivKindFloor:
return gen_floor(g, result, type_entry);
return gen_float_op(g, result, type_entry, BuiltinFnIdFloor);
}
zig_unreachable();
}
@ -5430,13 +5440,28 @@ static LLVMValueRef ir_render_mark_err_ret_trace_ptr(CodeGen *g, IrExecutable *e
return nullptr;
}
static LLVMValueRef ir_render_sqrt(CodeGen *g, IrExecutable *executable, IrInstructionSqrt *instruction) {
LLVMValueRef op = ir_llvm_value(g, instruction->op);
static LLVMValueRef ir_render_float_op(CodeGen *g, IrExecutable *executable, IrInstructionFloatOp *instruction) {
LLVMValueRef op = ir_llvm_value(g, instruction->op1);
assert(instruction->base.value.type->id == ZigTypeIdFloat);
LLVMValueRef fn_val = get_float_fn(g, instruction->base.value.type, ZigLLVMFnIdSqrt);
LLVMValueRef fn_val = get_float_fn(g, instruction->base.value.type, ZigLLVMFnIdFloatOp, instruction->op);
return LLVMBuildCall(g->builder, fn_val, &op, 1, "");
}
static LLVMValueRef ir_render_mul_add(CodeGen *g, IrExecutable *executable, IrInstructionMulAdd *instruction) {
LLVMValueRef op1 = ir_llvm_value(g, instruction->op1);
LLVMValueRef op2 = ir_llvm_value(g, instruction->op2);
LLVMValueRef op3 = ir_llvm_value(g, instruction->op3);
assert(instruction->base.value.type->id == ZigTypeIdFloat ||
instruction->base.value.type->id == ZigTypeIdVector);
LLVMValueRef fn_val = get_float_fn(g, instruction->base.value.type, ZigLLVMFnIdFMA, BuiltinFnIdMulAdd);
LLVMValueRef args[3] = {
op1,
op2,
op3,
};
return LLVMBuildCall(g->builder, fn_val, args, 3, "");
}
static LLVMValueRef ir_render_bswap(CodeGen *g, IrExecutable *executable, IrInstructionBswap *instruction) {
LLVMValueRef op = ir_llvm_value(g, instruction->op);
ZigType *int_type = instruction->base.value.type;
@ -5779,8 +5804,10 @@ static LLVMValueRef ir_render_instruction(CodeGen *g, IrExecutable *executable,
return ir_render_merge_err_ret_traces(g, executable, (IrInstructionMergeErrRetTraces *)instruction);
case IrInstructionIdMarkErrRetTracePtr:
return ir_render_mark_err_ret_trace_ptr(g, executable, (IrInstructionMarkErrRetTracePtr *)instruction);
case IrInstructionIdSqrt:
return ir_render_sqrt(g, executable, (IrInstructionSqrt *)instruction);
case IrInstructionIdFloatOp:
return ir_render_float_op(g, executable, (IrInstructionFloatOp *)instruction);
case IrInstructionIdMulAdd:
return ir_render_mul_add(g, executable, (IrInstructionMulAdd *)instruction);
case IrInstructionIdArrayToVector:
return ir_render_array_to_vector(g, executable, (IrInstructionArrayToVector *)instruction);
case IrInstructionIdVectorToArray:
@ -7398,6 +7425,21 @@ static void define_builtin_fns(CodeGen *g) {
create_builtin_fn(g, BuiltinFnIdRem, "rem", 2);
create_builtin_fn(g, BuiltinFnIdMod, "mod", 2);
create_builtin_fn(g, BuiltinFnIdSqrt, "sqrt", 2);
create_builtin_fn(g, BuiltinFnIdSin, "sin", 2);
create_builtin_fn(g, BuiltinFnIdCos, "cos", 2);
create_builtin_fn(g, BuiltinFnIdExp, "exp", 2);
create_builtin_fn(g, BuiltinFnIdExp2, "exp2", 2);
create_builtin_fn(g, BuiltinFnIdLn, "ln", 2);
create_builtin_fn(g, BuiltinFnIdLog2, "log2", 2);
create_builtin_fn(g, BuiltinFnIdLog10, "log10", 2);
create_builtin_fn(g, BuiltinFnIdFabs, "fabs", 2);
create_builtin_fn(g, BuiltinFnIdFloor, "floor", 2);
create_builtin_fn(g, BuiltinFnIdCeil, "ceil", 2);
create_builtin_fn(g, BuiltinFnIdTrunc, "trunc", 2);
//Needs library support on Windows
//create_builtin_fn(g, BuiltinFnIdNearbyInt, "nearbyInt", 2);
create_builtin_fn(g, BuiltinFnIdRound, "round", 2);
create_builtin_fn(g, BuiltinFnIdMulAdd, "mulAdd", 4);
create_builtin_fn(g, BuiltinFnIdInlineCall, "inlineCall", SIZE_MAX);
create_builtin_fn(g, BuiltinFnIdNoInlineCall, "noInlineCall", SIZE_MAX);
create_builtin_fn(g, BuiltinFnIdNewStackCall, "newStackCall", SIZE_MAX);

536
src/ir.cpp
View File

@ -747,6 +747,10 @@ static constexpr IrInstructionId ir_instruction_id(IrInstructionTestErr *) {
return IrInstructionIdTestErr;
}
static constexpr IrInstructionId ir_instruction_id(IrInstructionMulAdd *) {
return IrInstructionIdMulAdd;
}
static constexpr IrInstructionId ir_instruction_id(IrInstructionUnwrapErrCode *) {
return IrInstructionIdUnwrapErrCode;
}
@ -987,8 +991,8 @@ static constexpr IrInstructionId ir_instruction_id(IrInstructionMarkErrRetTraceP
return IrInstructionIdMarkErrRetTracePtr;
}
static constexpr IrInstructionId ir_instruction_id(IrInstructionSqrt *) {
return IrInstructionIdSqrt;
static constexpr IrInstructionId ir_instruction_id(IrInstructionFloatOp *) {
return IrInstructionIdFloatOp;
}
static constexpr IrInstructionId ir_instruction_id(IrInstructionCheckRuntimeScope *) {
@ -2308,6 +2312,75 @@ static IrInstruction *ir_build_overflow_op(IrBuilder *irb, Scope *scope, AstNode
return &instruction->base;
}
//TODO Powi, Pow, minnum, maxnum, maximum, minimum, copysign,
// lround, llround, lrint, llrint
// So far this is only non-complicated type functions.
const char *float_op_to_name(BuiltinFnId op, bool llvm_name) {
const bool b = llvm_name;
switch (op) {
case BuiltinFnIdSqrt:
return "sqrt";
case BuiltinFnIdSin:
return "sin";
case BuiltinFnIdCos:
return "cos";
case BuiltinFnIdExp:
return "exp";
case BuiltinFnIdExp2:
return "exp2";
case BuiltinFnIdLn:
return b ? "log" : "ln";
case BuiltinFnIdLog10:
return "log10";
case BuiltinFnIdLog2:
return "log2";
case BuiltinFnIdFabs:
return "fabs";
case BuiltinFnIdFloor:
return "floor";
case BuiltinFnIdCeil:
return "ceil";
case BuiltinFnIdTrunc:
return "trunc";
case BuiltinFnIdNearbyInt:
return b ? "nearbyint" : "nearbyInt";
case BuiltinFnIdRound:
return "round";
default:
zig_unreachable();
}
}
static IrInstruction *ir_build_float_op(IrBuilder *irb, Scope *scope, AstNode *source_node, IrInstruction *type, IrInstruction *op1, BuiltinFnId op) {
IrInstructionFloatOp *instruction = ir_build_instruction<IrInstructionFloatOp>(irb, scope, source_node);
instruction->type = type;
instruction->op1 = op1;
instruction->op = op;
if (type != nullptr) ir_ref_instruction(type, irb->current_basic_block);
ir_ref_instruction(op1, irb->current_basic_block);
return &instruction->base;
}
static IrInstruction *ir_build_mul_add(IrBuilder *irb, Scope *scope, AstNode *source_node,
IrInstruction *type_value, IrInstruction *op1, IrInstruction *op2, IrInstruction *op3) {
IrInstructionMulAdd *instruction = ir_build_instruction<IrInstructionMulAdd>(irb, scope, source_node);
instruction->type_value = type_value;
instruction->op1 = op1;
instruction->op2 = op2;
instruction->op3 = op3;
ir_ref_instruction(type_value, irb->current_basic_block);
ir_ref_instruction(op1, irb->current_basic_block);
ir_ref_instruction(op2, irb->current_basic_block);
ir_ref_instruction(op3, irb->current_basic_block);
return &instruction->base;
}
static IrInstruction *ir_build_align_of(IrBuilder *irb, Scope *scope, AstNode *source_node, IrInstruction *type_value) {
IrInstructionAlignOf *instruction = ir_build_instruction<IrInstructionAlignOf>(irb, scope, source_node);
instruction->type_value = type_value;
@ -3013,17 +3086,6 @@ static IrInstruction *ir_build_mark_err_ret_trace_ptr(IrBuilder *irb, Scope *sco
return &instruction->base;
}
static IrInstruction *ir_build_sqrt(IrBuilder *irb, Scope *scope, AstNode *source_node, IrInstruction *type, IrInstruction *op) {
IrInstructionSqrt *instruction = ir_build_instruction<IrInstructionSqrt>(irb, scope, source_node);
instruction->type = type;
instruction->op = op;
if (type != nullptr) ir_ref_instruction(type, irb->current_basic_block);
ir_ref_instruction(op, irb->current_basic_block);
return &instruction->base;
}
static IrInstruction *ir_build_has_decl(IrBuilder *irb, Scope *scope, AstNode *source_node,
IrInstruction *container, IrInstruction *name)
{
@ -4028,6 +4090,33 @@ static IrInstruction *ir_gen_overflow_op(IrBuilder *irb, Scope *scope, AstNode *
return ir_build_overflow_op(irb, scope, node, op, type_value, op1, op2, result_ptr, nullptr);
}
static IrInstruction *ir_gen_mul_add(IrBuilder *irb, Scope *scope, AstNode *node) {
assert(node->type == NodeTypeFnCallExpr);
AstNode *type_node = node->data.fn_call_expr.params.at(0);
AstNode *op1_node = node->data.fn_call_expr.params.at(1);
AstNode *op2_node = node->data.fn_call_expr.params.at(2);
AstNode *op3_node = node->data.fn_call_expr.params.at(3);
IrInstruction *type_value = ir_gen_node(irb, type_node, scope);
if (type_value == irb->codegen->invalid_instruction)
return irb->codegen->invalid_instruction;
IrInstruction *op1 = ir_gen_node(irb, op1_node, scope);
if (op1 == irb->codegen->invalid_instruction)
return irb->codegen->invalid_instruction;
IrInstruction *op2 = ir_gen_node(irb, op2_node, scope);
if (op2 == irb->codegen->invalid_instruction)
return irb->codegen->invalid_instruction;
IrInstruction *op3 = ir_gen_node(irb, op3_node, scope);
if (op3 == irb->codegen->invalid_instruction)
return irb->codegen->invalid_instruction;
return ir_build_mul_add(irb, scope, node, type_value, op1, op2, op3);
}
static IrInstruction *ir_gen_this(IrBuilder *irb, Scope *orig_scope, AstNode *node) {
for (Scope *it_scope = orig_scope; it_scope != nullptr; it_scope = it_scope->parent) {
if (it_scope->id == ScopeIdDecls) {
@ -4353,6 +4442,19 @@ static IrInstruction *ir_gen_builtin_fn_call(IrBuilder *irb, Scope *scope, AstNo
return ir_lval_wrap(irb, scope, bin_op, lval);
}
case BuiltinFnIdSqrt:
case BuiltinFnIdSin:
case BuiltinFnIdCos:
case BuiltinFnIdExp:
case BuiltinFnIdExp2:
case BuiltinFnIdLn:
case BuiltinFnIdLog2:
case BuiltinFnIdLog10:
case BuiltinFnIdFabs:
case BuiltinFnIdFloor:
case BuiltinFnIdCeil:
case BuiltinFnIdTrunc:
case BuiltinFnIdNearbyInt:
case BuiltinFnIdRound:
{
AstNode *arg0_node = node->data.fn_call_expr.params.at(0);
IrInstruction *arg0_value = ir_gen_node(irb, arg0_node, scope);
@ -4364,7 +4466,7 @@ static IrInstruction *ir_gen_builtin_fn_call(IrBuilder *irb, Scope *scope, AstNo
if (arg1_value == irb->codegen->invalid_instruction)
return arg1_value;
IrInstruction *ir_sqrt = ir_build_sqrt(irb, scope, node, arg0_value, arg1_value);
IrInstruction *ir_sqrt = ir_build_float_op(irb, scope, node, arg0_value, arg1_value, builtin_fn->id);
return ir_lval_wrap(irb, scope, ir_sqrt, lval);
}
case BuiltinFnIdTruncate:
@ -4687,6 +4789,8 @@ static IrInstruction *ir_gen_builtin_fn_call(IrBuilder *irb, Scope *scope, AstNo
return ir_lval_wrap(irb, scope, ir_gen_overflow_op(irb, scope, node, IrOverflowOpMul), lval);
case BuiltinFnIdShlWithOverflow:
return ir_lval_wrap(irb, scope, ir_gen_overflow_op(irb, scope, node, IrOverflowOpShl), lval);
case BuiltinFnIdMulAdd:
return ir_lval_wrap(irb, scope, ir_gen_mul_add(irb, scope, node), lval);
case BuiltinFnIdTypeName:
{
AstNode *arg0_node = node->data.fn_call_expr.params.at(0);
@ -21187,6 +21291,125 @@ static IrInstruction *ir_analyze_instruction_overflow_op(IrAnalyze *ira, IrInstr
return result;
}
static void ir_eval_mul_add(IrAnalyze *ira, IrInstructionMulAdd *source_instr, ZigType *float_type,
ConstExprValue *op1, ConstExprValue *op2, ConstExprValue *op3, ConstExprValue *out_val) {
if (float_type->id == ZigTypeIdComptimeFloat) {
f128M_mulAdd(&out_val->data.x_bigfloat.value, &op1->data.x_bigfloat.value, &op2->data.x_bigfloat.value,
&op3->data.x_bigfloat.value);
} else if (float_type->id == ZigTypeIdFloat) {
switch (float_type->data.floating.bit_count) {
case 16:
out_val->data.x_f16 = f16_mulAdd(op1->data.x_f16, op2->data.x_f16, op3->data.x_f16);
break;
case 32:
out_val->data.x_f32 = fmaf(op1->data.x_f32, op2->data.x_f32, op3->data.x_f32);
break;
case 64:
out_val->data.x_f64 = fma(op1->data.x_f64, op2->data.x_f64, op3->data.x_f64);
break;
case 128:
f128M_mulAdd(&op1->data.x_f128, &op2->data.x_f128, &op3->data.x_f128, &out_val->data.x_f128);
break;
default:
zig_unreachable();
}
} else {
zig_unreachable();
}
}
static IrInstruction *ir_analyze_instruction_mul_add(IrAnalyze *ira, IrInstructionMulAdd *instruction) {
IrInstruction *type_value = instruction->type_value->child;
if (type_is_invalid(type_value->value.type))
return ira->codegen->invalid_instruction;
ZigType *expr_type = ir_resolve_type(ira, type_value);
if (type_is_invalid(expr_type))
return ira->codegen->invalid_instruction;
// Only allow float types, and vectors of floats.
ZigType *float_type = (expr_type->id == ZigTypeIdVector) ? expr_type->data.vector.elem_type : expr_type;
if (float_type->id != ZigTypeIdFloat) {
ir_add_error(ira, type_value,
buf_sprintf("expected float or vector of float type, found '%s'", buf_ptr(&float_type->name)));
return ira->codegen->invalid_instruction;
}
IrInstruction *op1 = instruction->op1->child;
if (type_is_invalid(op1->value.type))
return ira->codegen->invalid_instruction;
IrInstruction *casted_op1 = ir_implicit_cast(ira, op1, expr_type);
if (type_is_invalid(casted_op1->value.type))
return ira->codegen->invalid_instruction;
IrInstruction *op2 = instruction->op2->child;
if (type_is_invalid(op2->value.type))
return ira->codegen->invalid_instruction;
IrInstruction *casted_op2 = ir_implicit_cast(ira, op2, expr_type);
if (type_is_invalid(casted_op2->value.type))
return ira->codegen->invalid_instruction;
IrInstruction *op3 = instruction->op3->child;
if (type_is_invalid(op3->value.type))
return ira->codegen->invalid_instruction;
IrInstruction *casted_op3 = ir_implicit_cast(ira, op3, expr_type);
if (type_is_invalid(casted_op3->value.type))
return ira->codegen->invalid_instruction;
if (instr_is_comptime(casted_op1) &&
instr_is_comptime(casted_op2) &&
instr_is_comptime(casted_op3)) {
ConstExprValue *op1_const = ir_resolve_const(ira, casted_op1, UndefBad);
if (!op1_const)
return ira->codegen->invalid_instruction;
ConstExprValue *op2_const = ir_resolve_const(ira, casted_op2, UndefBad);
if (!op2_const)
return ira->codegen->invalid_instruction;
ConstExprValue *op3_const = ir_resolve_const(ira, casted_op3, UndefBad);
if (!op3_const)
return ira->codegen->invalid_instruction;
IrInstruction *result = ir_const(ira, &instruction->base, expr_type);
ConstExprValue *out_val = &result->value;
if (expr_type->id == ZigTypeIdVector) {
expand_undef_array(ira->codegen, op1_const);
expand_undef_array(ira->codegen, op2_const);
expand_undef_array(ira->codegen, op3_const);
out_val->special = ConstValSpecialUndef;
expand_undef_array(ira->codegen, out_val);
size_t len = expr_type->data.vector.len;
for (size_t i = 0; i < len; i += 1) {
ConstExprValue *float_operand_op1 = &op1_const->data.x_array.data.s_none.elements[i];
ConstExprValue *float_operand_op2 = &op2_const->data.x_array.data.s_none.elements[i];
ConstExprValue *float_operand_op3 = &op3_const->data.x_array.data.s_none.elements[i];
ConstExprValue *float_out_val = &out_val->data.x_array.data.s_none.elements[i];
assert(float_operand_op1->type == float_type);
assert(float_operand_op2->type == float_type);
assert(float_operand_op3->type == float_type);
assert(float_out_val->type == float_type);
ir_eval_mul_add(ira, instruction, float_type,
op1_const, op2_const, op3_const, float_out_val);
float_out_val->type = float_type;
}
out_val->type = expr_type;
out_val->special = ConstValSpecialStatic;
} else {
ir_eval_mul_add(ira, instruction, float_type, op1_const, op2_const, op3_const, out_val);
}
return result;
}
IrInstruction *result = ir_build_mul_add(&ira->new_irb,
instruction->base.scope, instruction->base.source_node,
type_value, casted_op1, casted_op2, casted_op3);
result->value.type = expr_type;
return result;
}
static IrInstruction *ir_analyze_instruction_test_err(IrAnalyze *ira, IrInstructionTestErr *instruction) {
IrInstruction *value = instruction->value->child;
if (type_is_invalid(value->value.type))
@ -23048,70 +23271,248 @@ static IrInstruction *ir_analyze_instruction_mark_err_ret_trace_ptr(IrAnalyze *i
return result;
}
static IrInstruction *ir_analyze_instruction_sqrt(IrAnalyze *ira, IrInstructionSqrt *instruction) {
ZigType *float_type = ir_resolve_type(ira, instruction->type->child);
if (type_is_invalid(float_type))
static void ir_eval_float_op(IrAnalyze *ira, IrInstructionFloatOp *source_instr, ZigType *float_type,
ConstExprValue *op, ConstExprValue *out_val) {
assert(ira && source_instr && float_type && out_val && op);
assert(float_type->id == ZigTypeIdFloat ||
float_type->id == ZigTypeIdComptimeFloat);
BuiltinFnId fop = source_instr->op;
unsigned bits;
if (float_type->id == ZigTypeIdComptimeFloat) {
bits = 128;
} else if (float_type->id == ZigTypeIdFloat)
bits = float_type->data.floating.bit_count;
switch (bits) {
case 16: {
switch (fop) {
case BuiltinFnIdSqrt:
out_val->data.x_f16 = f16_sqrt(op->data.x_f16);
break;
case BuiltinFnIdSin:
case BuiltinFnIdCos:
case BuiltinFnIdExp:
case BuiltinFnIdExp2:
case BuiltinFnIdLn:
case BuiltinFnIdLog10:
case BuiltinFnIdLog2:
case BuiltinFnIdFabs:
case BuiltinFnIdFloor:
case BuiltinFnIdCeil:
case BuiltinFnIdTrunc:
case BuiltinFnIdNearbyInt:
case BuiltinFnIdRound:
zig_panic("unimplemented f16 builtin");
default:
zig_unreachable();
};
break;
};
case 32: {
switch (fop) {
case BuiltinFnIdSqrt:
out_val->data.x_f32 = sqrtf(op->data.x_f32);
break;
case BuiltinFnIdSin:
out_val->data.x_f32 = sinf(op->data.x_f32);
break;
case BuiltinFnIdCos:
out_val->data.x_f32 = cosf(op->data.x_f32);
break;
case BuiltinFnIdExp:
out_val->data.x_f32 = expf(op->data.x_f32);
break;
case BuiltinFnIdExp2:
out_val->data.x_f32 = exp2f(op->data.x_f32);
break;
case BuiltinFnIdLn:
out_val->data.x_f32 = logf(op->data.x_f32);
break;
case BuiltinFnIdLog10:
out_val->data.x_f32 = log10f(op->data.x_f32);
break;
case BuiltinFnIdLog2:
out_val->data.x_f32 = log2f(op->data.x_f32);
break;
case BuiltinFnIdFabs:
out_val->data.x_f32 = fabsf(op->data.x_f32);
break;
case BuiltinFnIdFloor:
out_val->data.x_f32 = floorf(op->data.x_f32);
break;
case BuiltinFnIdCeil:
out_val->data.x_f32 = ceilf(op->data.x_f32);
break;
case BuiltinFnIdTrunc:
out_val->data.x_f32 = truncf(op->data.x_f32);
break;
case BuiltinFnIdNearbyInt:
out_val->data.x_f32 = nearbyintf(op->data.x_f32);
break;
case BuiltinFnIdRound:
out_val->data.x_f32 = roundf(op->data.x_f32);
break;
default:
zig_unreachable();
};
break;
};
case 64: {
switch (fop) {
case BuiltinFnIdSqrt:
out_val->data.x_f64 = sqrt(op->data.x_f64);
break;
case BuiltinFnIdSin:
out_val->data.x_f64 = sin(op->data.x_f64);
break;
case BuiltinFnIdCos:
out_val->data.x_f64 = cos(op->data.x_f64);
break;
case BuiltinFnIdExp:
out_val->data.x_f64 = exp(op->data.x_f64);
break;
case BuiltinFnIdExp2:
out_val->data.x_f64 = exp2(op->data.x_f64);
break;
case BuiltinFnIdLn:
out_val->data.x_f64 = log(op->data.x_f64);
break;
case BuiltinFnIdLog10:
out_val->data.x_f64 = log10(op->data.x_f64);
break;
case BuiltinFnIdLog2:
out_val->data.x_f64 = log2(op->data.x_f64);
break;
case BuiltinFnIdFabs:
out_val->data.x_f64 = fabs(op->data.x_f64);
break;
case BuiltinFnIdFloor:
out_val->data.x_f64 = floor(op->data.x_f64);
break;
case BuiltinFnIdCeil:
out_val->data.x_f64 = ceil(op->data.x_f64);
break;
case BuiltinFnIdTrunc:
out_val->data.x_f64 = trunc(op->data.x_f64);
break;
case BuiltinFnIdNearbyInt:
out_val->data.x_f64 = nearbyint(op->data.x_f64);
break;
case BuiltinFnIdRound:
out_val->data.x_f64 = round(op->data.x_f64);
break;
default:
zig_unreachable();
}
break;
};
case 128: {
float128_t *out, *in;
if (float_type->id == ZigTypeIdComptimeFloat) {
out = &out_val->data.x_bigfloat.value;
in = &op->data.x_bigfloat.value;
} else {
out = &out_val->data.x_f128;
in = &op->data.x_f128;
}
switch (fop) {
case BuiltinFnIdSqrt:
f128M_sqrt(in, out);
break;
case BuiltinFnIdNearbyInt:
case BuiltinFnIdSin:
case BuiltinFnIdCos:
case BuiltinFnIdExp:
case BuiltinFnIdExp2:
case BuiltinFnIdLn:
case BuiltinFnIdLog10:
case BuiltinFnIdLog2:
case BuiltinFnIdFabs:
case BuiltinFnIdFloor:
case BuiltinFnIdCeil:
case BuiltinFnIdTrunc:
case BuiltinFnIdRound:
zig_panic("unimplemented f128 builtin");
default:
zig_unreachable();
}
break;
};
default:
zig_unreachable();
}
}
static IrInstruction *ir_analyze_instruction_float_op(IrAnalyze *ira, IrInstructionFloatOp *instruction) {
IrInstruction *type = instruction->type->child;
if (type_is_invalid(type->value.type))
return ira->codegen->invalid_instruction;
ZigType *expr_type = ir_resolve_type(ira, type);
if (type_is_invalid(expr_type))
return ira->codegen->invalid_instruction;
IrInstruction *op = instruction->op->child;
if (type_is_invalid(op->value.type))
return ira->codegen->invalid_instruction;
bool ok_type = float_type->id == ZigTypeIdComptimeFloat || float_type->id == ZigTypeIdFloat;
if (!ok_type) {
ir_add_error(ira, instruction->type, buf_sprintf("@sqrt does not support type '%s'", buf_ptr(&float_type->name)));
// Only allow float types, and vectors of floats.
ZigType *float_type = (expr_type->id == ZigTypeIdVector) ? expr_type->data.vector.elem_type : expr_type;
if (float_type->id != ZigTypeIdFloat && float_type->id != ZigTypeIdComptimeFloat) {
ir_add_error(ira, instruction->type, buf_sprintf("@%s does not support type '%s'", float_op_to_name(instruction->op, false), buf_ptr(&float_type->name)));
return ira->codegen->invalid_instruction;
}
IrInstruction *casted_op = ir_implicit_cast(ira, op, float_type);
if (type_is_invalid(casted_op->value.type))
IrInstruction *op1 = instruction->op1->child;
if (type_is_invalid(op1->value.type))
return ira->codegen->invalid_instruction;
if (instr_is_comptime(casted_op)) {
ConstExprValue *val = ir_resolve_const(ira, casted_op, UndefBad);
if (!val)
IrInstruction *casted_op1 = ir_implicit_cast(ira, op1, float_type);
if (type_is_invalid(casted_op1->value.type))
return ira->codegen->invalid_instruction;
if (instr_is_comptime(casted_op1)) {
// Our comptime 16-bit and 128-bit support is quite limited.
if ((float_type->id == ZigTypeIdComptimeFloat ||
float_type->data.floating.bit_count == 16 ||
float_type->data.floating.bit_count == 128) &&
instruction->op != BuiltinFnIdSqrt) {
ir_add_error(ira, instruction->type, buf_sprintf("@%s does not support type '%s'", float_op_to_name(instruction->op, false), buf_ptr(&float_type->name)));
return ira->codegen->invalid_instruction;
IrInstruction *result = ir_const(ira, &instruction->base, float_type);
ConstExprValue *out_val = &result->value;
if (float_type->id == ZigTypeIdComptimeFloat) {
bigfloat_sqrt(&out_val->data.x_bigfloat, &val->data.x_bigfloat);
} else if (float_type->id == ZigTypeIdFloat) {
switch (float_type->data.floating.bit_count) {
case 16:
out_val->data.x_f16 = f16_sqrt(val->data.x_f16);
break;
case 32:
out_val->data.x_f32 = sqrtf(val->data.x_f32);
break;
case 64:
out_val->data.x_f64 = sqrt(val->data.x_f64);
break;
case 128:
f128M_sqrt(&val->data.x_f128, &out_val->data.x_f128);
break;
default:
zig_unreachable();
}
} else {
zig_unreachable();
}
ConstExprValue *op1_const = ir_resolve_const(ira, casted_op1, UndefBad);
if (!op1_const)
return ira->codegen->invalid_instruction;
IrInstruction *result = ir_const(ira, &instruction->base, expr_type);
ConstExprValue *out_val = &result->value;
if (expr_type->id == ZigTypeIdVector) {
expand_undef_array(ira->codegen, op1_const);
out_val->special = ConstValSpecialUndef;
expand_undef_array(ira->codegen, out_val);
size_t len = expr_type->data.vector.len;
for (size_t i = 0; i < len; i += 1) {
ConstExprValue *float_operand_op1 = &op1_const->data.x_array.data.s_none.elements[i];
ConstExprValue *float_out_val = &out_val->data.x_array.data.s_none.elements[i];
assert(float_operand_op1->type == float_type);
assert(float_out_val->type == float_type);
ir_eval_float_op(ira, instruction, float_type,
op1_const, float_out_val);
float_out_val->type = float_type;
}
out_val->type = expr_type;
out_val->special = ConstValSpecialStatic;
} else {
ir_eval_float_op(ira, instruction, float_type, op1_const, out_val);
}
return result;
}
ir_assert(float_type->id == ZigTypeIdFloat, &instruction->base);
if (float_type->data.floating.bit_count != 16 &&
float_type->data.floating.bit_count != 32 &&
float_type->data.floating.bit_count != 64) {
ir_add_error(ira, instruction->type, buf_sprintf("compiler TODO: add implementation of sqrt for '%s'", buf_ptr(&float_type->name)));
return ira->codegen->invalid_instruction;
}
IrInstruction *result = ir_build_sqrt(&ira->new_irb, instruction->base.scope,
instruction->base.source_node, nullptr, casted_op);
result->value.type = float_type;
IrInstruction *result = ir_build_float_op(&ira->new_irb, instruction->base.scope,
instruction->base.source_node, nullptr, casted_op1, instruction->op);
result->value.type = expr_type;
return result;
}
@ -23596,8 +23997,10 @@ static IrInstruction *ir_analyze_instruction_nocast(IrAnalyze *ira, IrInstructio
return ir_analyze_instruction_merge_err_ret_traces(ira, (IrInstructionMergeErrRetTraces *)instruction);
case IrInstructionIdMarkErrRetTracePtr:
return ir_analyze_instruction_mark_err_ret_trace_ptr(ira, (IrInstructionMarkErrRetTracePtr *)instruction);
case IrInstructionIdSqrt:
return ir_analyze_instruction_sqrt(ira, (IrInstructionSqrt *)instruction);
case IrInstructionIdFloatOp:
return ir_analyze_instruction_float_op(ira, (IrInstructionFloatOp *)instruction);
case IrInstructionIdMulAdd:
return ir_analyze_instruction_mul_add(ira, (IrInstructionMulAdd *)instruction);
case IrInstructionIdIntToErr:
return ir_analyze_instruction_int_to_err(ira, (IrInstructionIntToErr *)instruction);
case IrInstructionIdErrToInt:
@ -23836,7 +24239,8 @@ bool ir_has_side_effects(IrInstruction *instruction) {
case IrInstructionIdCoroFree:
case IrInstructionIdCoroPromise:
case IrInstructionIdPromiseResultType:
case IrInstructionIdSqrt:
case IrInstructionIdFloatOp:
case IrInstructionIdMulAdd:
case IrInstructionIdAtomicLoad:
case IrInstructionIdIntCast:
case IrInstructionIdFloatCast:

1
src/ir.hpp
View File

@ -26,5 +26,6 @@ bool ir_has_side_effects(IrInstruction *instruction);
struct IrAnalyze;
ConstExprValue *const_ptr_pointee(IrAnalyze *ira, CodeGen *codegen, ConstExprValue *const_val,
AstNode *source_node);
const char *float_op_to_name(BuiltinFnId op, bool llvm_name);
#endif

30
src/ir_print.cpp
View File

@ -1427,15 +1427,32 @@ static void ir_print_mark_err_ret_trace_ptr(IrPrint *irp, IrInstructionMarkErrRe
fprintf(irp->f, ")");
}
static void ir_print_sqrt(IrPrint *irp, IrInstructionSqrt *instruction) {
fprintf(irp->f, "@sqrt(");
static void ir_print_float_op(IrPrint *irp, IrInstructionFloatOp *instruction) {
fprintf(irp->f, "@%s(", float_op_to_name(instruction->op, false));
if (instruction->type != nullptr) {
ir_print_other_instruction(irp, instruction->type);
} else {
fprintf(irp->f, "null");
}
fprintf(irp->f, ",");
ir_print_other_instruction(irp, instruction->op);
ir_print_other_instruction(irp, instruction->op1);
fprintf(irp->f, ")");
}
static void ir_print_mul_add(IrPrint *irp, IrInstructionMulAdd *instruction) {
fprintf(irp->f, "@mulAdd(");
if (instruction->type_value != nullptr) {
ir_print_other_instruction(irp, instruction->type_value);
} else {
fprintf(irp->f, "null");
}
fprintf(irp->f, ",");
ir_print_other_instruction(irp, instruction->op1);
fprintf(irp->f, ",");
ir_print_other_instruction(irp, instruction->op2);
fprintf(irp->f, ",");
ir_print_other_instruction(irp, instruction->op3);
fprintf(irp->f, ")");
}
@ -1902,8 +1919,11 @@ static void ir_print_instruction(IrPrint *irp, IrInstruction *instruction) {
case IrInstructionIdMarkErrRetTracePtr:
ir_print_mark_err_ret_trace_ptr(irp, (IrInstructionMarkErrRetTracePtr *)instruction);
break;
case IrInstructionIdSqrt:
ir_print_sqrt(irp, (IrInstructionSqrt *)instruction);
case IrInstructionIdFloatOp:
ir_print_float_op(irp, (IrInstructionFloatOp *)instruction);
break;
case IrInstructionIdMulAdd:
ir_print_mul_add(irp, (IrInstructionMulAdd *)instruction);
break;
case IrInstructionIdAtomicLoad:
ir_print_atomic_load(irp, (IrInstructionAtomicLoad *)instruction);

1
src/util.cpp
View File

@ -13,6 +13,7 @@
#include "userland.h"
void zig_panic(const char *format, ...) {
abort();
va_list ap;
va_start(ap, format);
vfprintf(stderr, format, ap);

39
std/special/c.zig
View File

@ -254,19 +254,32 @@ export fn fmod(x: f64, y: f64) f64 {
// TODO add intrinsics for these (and probably the double version too)
// and have the math stuff use the intrinsic. same as @mod and @rem
export fn floorf(x: f32) f32 {
return math.floor(x);
}
export fn ceilf(x: f32) f32 {
return math.ceil(x);
}
export fn floor(x: f64) f64 {
return math.floor(x);
}
export fn ceil(x: f64) f64 {
return math.ceil(x);
}
export fn floorf(x: f32) f32 {return math.floor(x);}
export fn ceilf(x: f32) f32 {return math.ceil(x);}
export fn floor(x: f64) f64 {return math.floor(x);}
export fn ceil(x: f64) f64 {return math.ceil(x);}
export fn fma(a: f64, b: f64, c: f64) f64 {return math.fma(f64, a, b, c);}
export fn fmaf(a: f32, b: f32, c: f32) f32 {return math.fma(f32, a, b, c);}
export fn sin(a: f64) f64 {return math.sin(a);}
export fn sinf(a: f32) f32 {return math.sin(a);}
export fn cos(a: f64) f64 {return math.cos(a);}
export fn cosf(a: f32) f32 {return math.cos(a);}
export fn exp(a: f64) f64 {return math.exp(a);}
export fn expf(a: f32) f32 {return math.exp(a);}
export fn exp2(a: f64) f64 {return math.exp2(a);}
export fn exp2f(a: f32) f32 {return math.exp2(a);}
export fn log(a: f64) f64 {return math.ln(a);}
export fn logf(a: f32) f32 {return math.ln(a);}
export fn log2(a: f64) f64 {return math.log2(a);}
export fn log2f(a: f32) f32 {return math.log2(a);}
export fn log10(a: f64) f64 {return math.log10(a);}
export fn log10f(a: f32) f32 {return math.log10(a);}
export fn fabs(a: f64) f64 {return math.fabs(a);}
export fn fabsf(a: f32) f32 {return math.fabs(a);}
export fn trunc(a: f64) f64 {return math.trunc(a);}
export fn truncf(a: f32) f32 {return math.trunc(a);}
export fn round(a: f64) f64 {return math.round(a);}
export fn roundf(a: f32) f32 {return math.round(a);}
fn generic_fmod(comptime T: type, x: T, y: T) T {
@setRuntimeSafety(false);

2
test/stage1/behavior.zig
View File

@ -69,6 +69,8 @@ comptime {
_ = @import("behavior/optional.zig");
_ = @import("behavior/pointers.zig");
_ = @import("behavior/popcount.zig");
_ = @import("behavior/muladd.zig");
_ = @import("behavior/floatop.zig");
_ = @import("behavior/ptrcast.zig");
_ = @import("behavior/pub_enum.zig");
_ = @import("behavior/ref_var_in_if_after_if_2nd_switch_prong.zig");

243
test/stage1/behavior/floatop.zig Normal file
View File

@ -0,0 +1,243 @@
const expect = @import("std").testing.expect;
const pi = @import("std").math.pi;
const e = @import("std").math.e;
test "@sqrt" {
comptime testSqrt();
testSqrt();
}
fn testSqrt() void {
{
var a: f16 = 4;
expect(@sqrt(f16, a) == 2);
}
{
var a: f32 = 9;
expect(@sqrt(f32, a) == 3);
}
{
var a: f64 = 25;
expect(@sqrt(f64, a) == 5);
}
{
const a: comptime_float = 25.0;
expect(@sqrt(comptime_float, a) == 5.0);
}
// Waiting on a c.zig implementation
//{
// var a: f128 = 49;
// expect(@sqrt(f128, a) == 7);
//}
}
test "@sin" {
comptime testSin();
testSin();
}
fn testSin() void {
// TODO - this is actually useful and should be implemented
// (all the trig functions for f16)
// but will probably wait till self-hosted
//{
// var a: f16 = pi;
// expect(@sin(f16, a/2) == 1);
//}
{
var a: f32 = 0;
expect(@sin(f32, a) == 0);
}
{
var a: f64 = 0;
expect(@sin(f64, a) == 0);
}
// TODO
//{
// var a: f16 = pi;
// expect(@sqrt(f128, a/2) == 1);
//}
}
test "@cos" {
comptime testCos();
testCos();
}
fn testCos() void {
{
var a: f32 = 0;
expect(@cos(f32, a) == 1);
}
{
var a: f64 = 0;
expect(@cos(f64, a) == 1);
}
}
test "@exp" {
comptime testExp();
testExp();
}
fn testExp() void {
{
var a: f32 = 0;
expect(@exp(f32, a) == 1);
}
{
var a: f64 = 0;
expect(@exp(f64, a) == 1);
}
}
test "@exp2" {
comptime testExp2();
testExp2();
}
fn testExp2() void {
{
var a: f32 = 2;
expect(@exp2(f32, a) == 4);
}
{
var a: f64 = 2;
expect(@exp2(f64, a) == 4);
}
}
test "@ln" {
// Old musl (and glibc?), and our current math.ln implementation do not return 1
// so also accept those values.
comptime testLn();
testLn();
}
fn testLn() void {
{
var a: f32 = e;
expect(@ln(f32, a) == 1 or @ln(f32, a) == @bitCast(f32, u32(0x3f7fffff)));
}
{
var a: f64 = e;
expect(@ln(f64, a) == 1 or @ln(f64, a) == @bitCast(f64, u64(0x3ff0000000000000)));
}
}
test "@log2" {
comptime testLog2();
testLog2();
}
fn testLog2() void {
{
var a: f32 = 4;
expect(@log2(f32, a) == 2);
}
{
var a: f64 = 4;
expect(@log2(f64, a) == 2);
}
}
test "@log10" {
comptime testLog10();
testLog10();
}
fn testLog10() void {
{
var a: f32 = 100;
expect(@log10(f32, a) == 2);
}
{
var a: f64 = 1000;
expect(@log10(f64, a) == 3);
}
}
test "@fabs" {
comptime testFabs();
testFabs();
}
fn testFabs() void {
{
var a: f32 = -2.5;
var b: f32 = 2.5;
expect(@fabs(f32, a) == 2.5);
expect(@fabs(f32, b) == 2.5);
}
{
var a: f64 = -2.5;
var b: f64 = 2.5;
expect(@fabs(f64, a) == 2.5);
expect(@fabs(f64, b) == 2.5);
}
}
test "@floor" {
comptime testFloor();
testFloor();
}
fn testFloor() void {
{
var a: f32 = 2.1;
expect(@floor(f32, a) == 2);
}
{
var a: f64 = 3.5;
expect(@floor(f64, a) == 3);
}
}
test "@ceil" {
comptime testCeil();
testCeil();
}
fn testCeil() void {
{
var a: f32 = 2.1;
expect(@ceil(f32, a) == 3);
}
{
var a: f64 = 3.5;
expect(@ceil(f64, a) == 4);
}
}
test "@trunc" {
comptime testTrunc();
testTrunc();
}
fn testTrunc() void {
{
var a: f32 = 2.1;
expect(@trunc(f32, a) == 2);
}
{
var a: f64 = -3.5;
expect(@trunc(f64, a) == -3);
}
}
// This is waiting on library support for the Windows build (not sure why the other's don't need it)
//test "@nearbyInt" {
// comptime testNearbyInt();
// testNearbyInt();
//}
//fn testNearbyInt() void {
// {
// var a: f32 = 2.1;
// expect(@nearbyInt(f32, a) == 2);
// }
// {
// var a: f64 = -3.75;
// expect(@nearbyInt(f64, a) == -4);
// }
//}

34
test/stage1/behavior/muladd.zig Normal file
View File

@ -0,0 +1,34 @@
const expect = @import("std").testing.expect;
test "@mulAdd" {
comptime testMulAdd();
testMulAdd();
}
fn testMulAdd() void {
{
var a: f16 = 5.5;
var b: f16 = 2.5;
var c: f16 = 6.25;
expect(@mulAdd(f16, a, b, c) == 20);
}
{
var a: f32 = 5.5;
var b: f32 = 2.5;
var c: f32 = 6.25;
expect(@mulAdd(f32, a, b, c) == 20);
}
{
var a: f64 = 5.5;
var b: f64 = 2.5;
var c: f64 = 6.25;
expect(@mulAdd(f64, a, b, c) == 20);
}
// Awaits implementation in libm.zig
//{
// var a: f16 = 5.5;
// var b: f128 = 2.5;
// var c: f128 = 6.25;
// expect(@mulAdd(f128, a, b, c) == 20);
//}
}