Skip to content

Add support for arbitrary large integers #74

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
smarr merged 13 commits into from
Aug 16, 2025
Merged

Add support for arbitrary large integers #74

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
0c0d3a7
Started adding support for BigIntegers
smarr May 21, 2025
fc72183
Added InfInt.h from github.com/sercantutar/infint
smarr Aug 15, 2025
a911962
Apply lint/tidy fixes to InfInt.h
smarr Aug 15, 2025
8a85c0f
Update Xcode
smarr Aug 15, 2025
42352fa
Fix leftShift
smarr Aug 15, 2025
8d9a6f5
Fix comparsions primtives
smarr Aug 15, 2025
727d969
Remove unused code, and make less ambiguous InfInt.h
smarr Aug 16, 2025
4fb4ca8
Add support for #& with big int and smal int
smarr Aug 15, 2025
a2e0efb
Added basic unit test
smarr Aug 16, 2025
ecfcc0f
Add isZero method
smarr Aug 16, 2025
0d7c1d0
Resolve clang-tidy issues
smarr Aug 16, 2025
5784722
Use compiler builtin instead of countl_zero
smarr Aug 16, 2025
a21314f
Add retries to apt-get since apt.llvm.org is flaky
smarr Aug 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion .github/workflows/ci.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,10 @@ jobs:
wget -O - https://apt.llvm.org/llvm-snapshot.gpg.key | sudo apt-key add -
sudo add-apt-repository "deb http://apt.llvm.org/noble/ llvm-toolchain-noble-20 main"
sudo apt-get update
sudo apt-get install -y clang-20 clang-tidy-20
for i in 1 2 3; do
sudo apt-get install -y clang-20 clang-tidy-20 && break
sleep 17
done
if: matrix.compiler == 'clang'

- name: Install Clang Format
Expand Down
28 changes: 27 additions & 1 deletion SOM.xcodeproj/project.pbxproj
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,6 +142,9 @@
0AB80AD42C392B78006B6419 /* Print.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 0AB80AD12C392B78006B6419 /* Print.cpp */; };
0AB80AD82C394806006B6419 /* Globals.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 0AB80AD72C394806006B6419 /* Globals.cpp */; };
0AB80AD92C394806006B6419 /* Globals.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 0AB80AD72C394806006B6419 /* Globals.cpp */; };
0ACA17172E509E6100FAC36B /* InfIntTests.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 0ACA17162E509E6100FAC36B /* InfIntTests.cpp */; };
0AF394592D7CA9860036FDEF /* VMBigInteger.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 0AF394582D7CA9860036FDEF /* VMBigInteger.cpp */; };
0AF3945A2D7CA9860036FDEF /* VMBigInteger.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 0AF394582D7CA9860036FDEF /* VMBigInteger.cpp */; };
/* End PBXBuildFile section */

/* Begin PBXCopyFilesBuildPhase section */
Expand Down Expand Up @@ -252,6 +255,12 @@
0AB80AD62C3947F7006B6419 /* Globals.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = Globals.h; sourceTree = "<group>"; };
0AB80AD72C394806006B6419 /* Globals.cpp */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.cpp.cpp; path = Globals.cpp; sourceTree = "<group>"; };
0AB80ADA2C39AC27006B6419 /* InterpreterLoop.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = InterpreterLoop.h; sourceTree = "<group>"; };
0ACA17152E509E6100FAC36B /* InfIntTests.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; name = InfIntTests.h; path = unitTests/InfIntTests.h; sourceTree = "<group>"; };
0ACA17162E509E6100FAC36B /* InfIntTests.cpp */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.cpp.cpp; name = InfIntTests.cpp; path = unitTests/InfIntTests.cpp; sourceTree = "<group>"; };
0AF394542D7B91990036FDEF /* TaggingTests.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; name = TaggingTests.h; path = unitTests/TaggingTests.h; sourceTree = "<group>"; };
0AF394572D7CA9860036FDEF /* VMBigInteger.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = VMBigInteger.h; sourceTree = "<group>"; };
0AF394582D7CA9860036FDEF /* VMBigInteger.cpp */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.cpp.cpp; path = VMBigInteger.cpp; sourceTree = "<group>"; };
0AF3945C2D7CAAF80036FDEF /* InfInt.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = InfInt.h; sourceTree = "<group>"; };
3F5202F10FA6624C00E75857 /* BytecodeGenerator.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = BytecodeGenerator.cpp; sourceTree = "<group>"; };
3F5202F20FA6624C00E75857 /* BytecodeGenerator.h */ = {isa = PBXFileReference; fileEncoding = 4; indentWidth = 4; lastKnownFileType = sourcecode.c.h; path = BytecodeGenerator.h; sourceTree = "<group>"; tabWidth = 4; };
3F5202F30FA6624C00E75857 /* ClassGenerationContext.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = ClassGenerationContext.cpp; sourceTree = "<group>"; };
Expand Down Expand Up @@ -448,13 +457,16 @@
0A67EA7A19ACD44000830E3B /* unittests */ = {
isa = PBXGroup;
children = (
0AF394542D7B91990036FDEF /* TaggingTests.h */,
0A3FABE724F4670D002D4D69 /* BasicInterpreterTests.h */,
0A67EA7019ACD43A00830E3B /* CloneObjectsTest.cpp */,
0A67EA7119ACD43A00830E3B /* main.cpp */,
0ACA17152E509E6100FAC36B /* InfIntTests.h */,
0ACA17162E509E6100FAC36B /* InfIntTests.cpp */,
0A67EAA319ACE09700830E3B /* CloneObjectsTest.h */,
0A67EAA519ACE09700830E3B /* WalkObjectsTest.h */,
0A67EAA619ACE09700830E3B /* WriteBarrierTest.h */,
0A67EA7319ACD43A00830E3B /* WalkObjectsTest.cpp */,
0A67EAA619ACE09700830E3B /* WriteBarrierTest.h */,
0A67EA7419ACD43A00830E3B /* WriteBarrierTest.cpp */,
0A1C98562C3DD87300735850 /* unitTests/BytecodeGenerationTest.h */,
0A1C98572C3DD88500735850 /* unitTests/BytecodeGenerationTest.cpp */,
Expand All @@ -466,6 +478,14 @@
name = unittests;
sourceTree = "<group>";
};
0AF3945D2D7CAAF80036FDEF /* lib */ = {
isa = PBXGroup;
children = (
0AF3945C2D7CAAF80036FDEF /* InfInt.h */,
);
path = lib;
sourceTree = "<group>";
};
3F5202720FA661D900E75857 = {
isa = PBXGroup;
children = (
Expand All @@ -487,6 +507,7 @@
3F5202EF0FA6624C00E75857 /* src */ = {
isa = PBXGroup;
children = (
0AF3945D2D7CAAF80036FDEF /* lib */,
0A67EA7A19ACD44000830E3B /* unittests */,
3F5202F00FA6624C00E75857 /* compiler */,
3F5203000FA6624C00E75857 /* interpreter */,
Expand Down Expand Up @@ -656,6 +677,8 @@
3F5203380FA6624C00E75857 /* Signature.h */,
3F52033B0FA6624C00E75857 /* VMArray.cpp */,
3F52033C0FA6624C00E75857 /* VMArray.h */,
0AF394572D7CA9860036FDEF /* VMBigInteger.h */,
0AF394582D7CA9860036FDEF /* VMBigInteger.cpp */,
3F52033F0FA6624C00E75857 /* VMBlock.cpp */,
3F5203400FA6624C00E75857 /* VMBlock.h */,
3F5203410FA6624C00E75857 /* VMClass.cpp */,
Expand Down Expand Up @@ -907,6 +930,7 @@
0A1887351832C10E00A2CBCA /* MarkSweepCollector.cpp in Sources */,
0A5A7E912C5D45A00011C783 /* VMSafePrimitive.cpp in Sources */,
0A1886FB1832BCF500A2CBCA /* VMBlock.cpp in Sources */,
0AF3945A2D7CA9860036FDEF /* VMBigInteger.cpp in Sources */,
0A1887391832C12E00A2CBCA /* Timer.cpp in Sources */,
0A1887021832BCFA00A2CBCA /* VMMethod.cpp in Sources */,
0AB80AD32C392B78006B6419 /* Print.cpp in Sources */,
Expand Down Expand Up @@ -962,6 +986,7 @@
0A67EA9019ACD83200830E3B /* Lexer.cpp in Sources */,
0AB80AD92C394806006B6419 /* Globals.cpp in Sources */,
0A5A7E9D2C617EE00011C783 /* TestWithParsing.cpp in Sources */,
0AF394592D7CA9860036FDEF /* VMBigInteger.cpp in Sources */,
0A3A3CA71A5D546D004CB03B /* Object.cpp in Sources */,
0A3A3CB21A5D5476004CB03B /* PrimitiveContainer.cpp in Sources */,
0A1C98582C3DD88500735850 /* unitTests/BytecodeGenerationTest.cpp in Sources */,
Expand Down Expand Up @@ -996,6 +1021,7 @@
0AB80AD02C392811006B6419 /* IsValidObject.cpp in Sources */,
0A67EA9519ACD83900830E3B /* Interpreter.cpp in Sources */,
0A67EA8A19ACD74800830E3B /* VMSymbol.cpp in Sources */,
0ACA17172E509E6100FAC36B /* InfIntTests.cpp in Sources */,
0A67EA7C19ACD74800830E3B /* AbstractObject.cpp in Sources */,
0A67EA8E19ACD83200830E3B /* ClassGenerationContext.cpp in Sources */,
0A3A3CB31A5D5476004CB03B /* PrimitiveLoader.cpp in Sources */,
Expand Down
4 changes: 2 additions & 2 deletions src/compiler/BytecodeGenerator.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,11 +164,11 @@ void EmitPUSHCONSTANT(MethodGenerationContext& mgenc, const Parser& parser,
// we also make sure that we don't miss anything in the else
// branch of the class check
if (CLASS_OF(cst) == load_ptr(integerClass)) {
if (INT_VAL(cst) == 0LL) {
if (SMALL_INT_VAL(cst) == 0LL) {
Emit1(mgenc, BC_PUSH_0, 1);
return;
}
if (INT_VAL(cst) == 1LL) {
if (SMALL_INT_VAL(cst) == 1LL) {
Emit1(mgenc, BC_PUSH_1, 1);
return;
}
Expand Down
7 changes: 5 additions & 2 deletions src/compiler/Disassembler.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@
#include "../vm/Universe.h"
#include "../vmobjects/ObjectFormats.h"
#include "../vmobjects/Signature.h"
#include "../vmobjects/VMBigInteger.h"
#include "../vmobjects/VMClass.h"
#include "../vmobjects/VMDouble.h"
#include "../vmobjects/VMFrame.h"
Expand Down Expand Up @@ -66,15 +67,17 @@ void Disassembler::dispatch(vm_oop_t o) {
DebugPrint("{Block Class object}");
} else if (o == Universe::GetGlobal(SymbolFor("system"))) {
DebugPrint("{System}");
} else if (IS_SMALL_INT(o)) {
DebugPrint("%lld", SMALL_INT_VAL(o));
} else if (IS_BIG_INT(o)) {
DebugPrint("%s", AS_BIG_INT(o)->embeddedInteger.toString().c_str());
} else {
VMClass* c = CLASS_OF(o);
if (c == load_ptr(stringClass)) {
DebugPrint("\"%s\"",
static_cast<VMString*>(o)->GetStdString().c_str());
} else if (c == load_ptr(doubleClass)) {
DebugPrint("%g", static_cast<VMDouble*>(o)->GetEmbeddedDouble());
} else if (c == load_ptr(integerClass)) {
DebugPrint("%lld", INT_VAL(o));
} else if (c == load_ptr(symbolClass)) {
DebugPrint("#%s",
static_cast<VMSymbol*>(o)->GetStdString().c_str());
Expand Down
1 change: 1 addition & 0 deletions src/compiler/MethodGenerationContext.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@
#include "../vm/Print.h"
#include "../vm/Universe.h"
#include "../vmobjects/ObjectFormats.h"
#include "../vmobjects/VMBigInteger.h" // NOLINT(misc-include-cleaner)
#include "../vmobjects/VMMethod.h"
#include "../vmobjects/VMPrimitive.h"
#include "../vmobjects/VMSymbol.h"
Expand Down
3 changes: 2 additions & 1 deletion src/compiler/Parser.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,7 @@
#include "../vm/Symbols.h"
#include "../vm/Universe.h"
#include "../vmobjects/ObjectFormats.h"
#include "../vmobjects/VMBigInteger.h" // NOLINT(misc-include-cleaner)
#include "../vmobjects/VMClass.h"
#include "../vmobjects/VMDouble.h" // NOLINT(misc-include-cleaner) it's required to make the types complete
#include "../vmobjects/VMMethod.h"
Expand Down Expand Up @@ -782,7 +783,7 @@ vm_oop_t Parser::negativeDecimal() {
}

vm_oop_t Parser::literalInteger(bool negateValue) {
vm_oop_t i = ParseInteger(text.c_str(), 10, negateValue);
vm_oop_t i = ParseInteger(text.c_str(), negateValue);
expect(Integer);
return i;
}
Expand Down
28 changes: 13 additions & 15 deletions src/interpreter/Interpreter.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,7 @@
#include "../vmobjects/ObjectFormats.h"
#include "../vmobjects/Signature.h"
#include "../vmobjects/VMArray.h"
#include "../vmobjects/VMBigInteger.h" // NOLINT(misc-include-cleaner)
#include "../vmobjects/VMBlock.h"
#include "../vmobjects/VMClass.h"
#include "../vmobjects/VMDouble.h"
Expand Down Expand Up @@ -1077,8 +1078,8 @@ void Interpreter::doReturnNonLocal() {
void Interpreter::doInc() {
vm_oop_t val = GetFrame()->Top();

if (IS_TAGGED(val) || CLASS_OF(val) == load_ptr(integerClass)) {
int64_t const result = (int64_t)INT_VAL(val) + 1;
if (IS_SMALL_INT(val)) {
int64_t const result = SMALL_INT_VAL(val) + 1;
val = NEW_INT(result);
} else if (CLASS_OF(val) == load_ptr(doubleClass)) {
double const d = static_cast<VMDouble*>(val)->GetEmbeddedDouble();
Expand All @@ -1093,8 +1094,8 @@ void Interpreter::doInc() {
void Interpreter::doDec() {
vm_oop_t val = GetFrame()->Top();

if (IS_TAGGED(val) || CLASS_OF(val) == load_ptr(integerClass)) {
int64_t const result = (int64_t)INT_VAL(val) - 1;
if (IS_SMALL_INT(val)) {
int64_t const result = SMALL_INT_VAL(val) - 1;
val = NEW_INT(result);
} else if (CLASS_OF(val) == load_ptr(doubleClass)) {
double const d = static_cast<VMDouble*>(val)->GetEmbeddedDouble();
Expand All @@ -1117,8 +1118,8 @@ void Interpreter::doIncField(uint8_t fieldIndex) {

vm_oop_t val = selfObj->GetField(fieldIndex);

if (IS_TAGGED(val) || CLASS_OF(val) == load_ptr(integerClass)) {
int64_t const result = (int64_t)INT_VAL(val) + 1;
if (IS_SMALL_INT(val)) {
int64_t const result = SMALL_INT_VAL(val) + 1;
val = NEW_INT(result);
} else if (CLASS_OF(val) == load_ptr(doubleClass)) {
double const d = static_cast<VMDouble*>(val)->GetEmbeddedDouble();
Expand All @@ -1141,8 +1142,8 @@ void Interpreter::doIncFieldPush(uint8_t fieldIndex) {

vm_oop_t val = selfObj->GetField(fieldIndex);

if (IS_TAGGED(val) || CLASS_OF(val) == load_ptr(integerClass)) {
int64_t const result = (int64_t)INT_VAL(val) + 1;
if (IS_SMALL_INT(val)) {
int64_t const result = SMALL_INT_VAL(val) + 1;
val = NEW_INT(result);
} else if (CLASS_OF(val) == load_ptr(doubleClass)) {
double const d = static_cast<VMDouble*>(val)->GetEmbeddedDouble();
Expand All @@ -1159,14 +1160,11 @@ bool Interpreter::checkIsGreater() {
vm_oop_t top = GetFrame()->Top();
vm_oop_t top2 = GetFrame()->Top2();

if ((IS_TAGGED(top) || CLASS_OF(top) == load_ptr(integerClass)) &&
(IS_TAGGED(top2) || CLASS_OF(top2) == load_ptr(integerClass))) {
return INT_VAL(top) > INT_VAL(top2);
if (IS_SMALL_INT(top) && IS_SMALL_INT(top2)) {
return SMALL_INT_VAL(top) > SMALL_INT_VAL(top2);
}
if ((CLASS_OF(top) == load_ptr(doubleClass)) &&
(CLASS_OF(top2) == load_ptr(doubleClass))) {
return static_cast<VMDouble*>(top)->GetEmbeddedDouble() >
static_cast<VMDouble*>(top2)->GetEmbeddedDouble();
if (IS_DOUBLE(top) && IS_DOUBLE(top2)) {
return AS_DOUBLE(top) > AS_DOUBLE(top2);
}

return false;
Expand Down
Loading