llvm-context: modularize compiler builtin functions (#234)

- Add the revive runtime function interface to minimize boiler plate
code.
- Outline heavily repeated code into dedicated functions to bring down
code size.
- The code size tests builds optimized for size.
- Function attributes are passed as slices.

This significantly brings down the code size for all OpenZeppelin wizard
contracts (using all possible features) compiled against OpenZeppelin
`v5.0.0` with size optimizations.

|contract|| `-Oz` main | `-Oz` PR || `-O3` main | `-O3` PR |
|-|-|-|-|-|-|-|
|erc1155.sol||100K|67K||114K|147K|
|erc20.sol||120K|90K||160K|191K|
|erc721.sol||128K|101K||178K|214K|
|governor.sol||226K|165K||293K|349K|
|rwa.sol||116K|85K||154K|185K|
|stable.sol||116K|86K||155K|192K|

On the flip side this introduces a heavy penalty for cycle optimized
builds. Setting the no-inline attributes for cycle optimized builds
helps a lot but heavily penalizes runtime speed (LLVM does not yet
inline everything properly - to be investigated later on).

Next steps:
- Modularize more functions
- Refactor the YUL function arguments to use pointers instead of values
- Afterwards check if LLVM still has trouble inline-ing properly on O3
or set the no-inline attribute if it does not penalize runtime
performance too bad.

crates/solidity/src/yul/parser/statement/expression/function_call/mod.rs

@@ -672,7 +672,7 @@ impl FunctionCall {
                     context,
                     arguments[0].into_int_value(),
                     arguments[1].into_int_value(),
-                    vec![],
+                    [],
                 )
                 .map(|_| None)
             }
@@ -682,10 +682,7 @@ impl FunctionCall {
                     context,
                     arguments[0].into_int_value(),
                     arguments[1].into_int_value(),
-                    arguments[2..]
-                        .iter()
-                        .map(|argument| argument.into_int_value())
-                        .collect(),
+                    [arguments[2]],
                 )
                 .map(|_| None)
             }
@@ -695,10 +692,7 @@ impl FunctionCall {
                     context,
                     arguments[0].into_int_value(),
                     arguments[1].into_int_value(),
-                    arguments[2..]
-                        .iter()
-                        .map(|argument| argument.into_int_value())
-                        .collect(),
+                    [arguments[2], arguments[3]],
                 )
                 .map(|_| None)
             }
@@ -708,10 +702,7 @@ impl FunctionCall {
                     context,
                     arguments[0].into_int_value(),
                     arguments[1].into_int_value(),
-                    arguments[2..]
-                        .iter()
-                        .map(|argument| argument.into_int_value())
-                        .collect(),
+                    [arguments[2], arguments[3], arguments[4]],
                 )
                 .map(|_| None)
             }
@@ -721,10 +712,7 @@ impl FunctionCall {
                     context,
                     arguments[0].into_int_value(),
                     arguments[1].into_int_value(),
-                    arguments[2..]
-                        .iter()
-                        .map(|argument| argument.into_int_value())
-                        .collect(),
+                    [arguments[2], arguments[3], arguments[4], arguments[5]],
                 )
                 .map(|_| None)
             }

crates/solidity/src/yul/parser/statement/function_definition.rs

@@ -216,7 +216,7 @@ where
         revive_llvm_context::PolkaVMFunction::set_attributes(
             context.llvm(),
             function.borrow().declaration(),
-            self.attributes.clone().into_iter().collect(),
+            &self.attributes.clone().into_iter().collect::<Vec<_>>(),
             true,
         );
         function

crates/solidity/src/yul/parser/statement/object.rs

@@ -185,7 +185,28 @@ where
         &mut self,
         context: &mut revive_llvm_context::PolkaVMContext<D>,
     ) -> anyhow::Result<()> {
-        revive_llvm_context::PolkaVMImmutableDataLoadFunction.declare(context)?;
+        revive_llvm_context::PolkaVMLoadImmutableDataFunction.declare(context)?;
+        revive_llvm_context::PolkaVMStoreImmutableDataFunction.declare(context)?;
+
+        revive_llvm_context::PolkaVMLoadHeapWordFunction.declare(context)?;
+        revive_llvm_context::PolkaVMStoreHeapWordFunction.declare(context)?;
+        revive_llvm_context::PolkaVMLoadStorageWordFunction.declare(context)?;
+        revive_llvm_context::PolkaVMStoreStorageWordFunction.declare(context)?;
+
+        revive_llvm_context::PolkaVMWordToPointerFunction.declare(context)?;
+        revive_llvm_context::PolkaVMExitFunction.declare(context)?;
+
+        revive_llvm_context::PolkaVMEventLogFunction::<0>.declare(context)?;
+        revive_llvm_context::PolkaVMEventLogFunction::<1>.declare(context)?;
+        revive_llvm_context::PolkaVMEventLogFunction::<2>.declare(context)?;
+        revive_llvm_context::PolkaVMEventLogFunction::<3>.declare(context)?;
+        revive_llvm_context::PolkaVMEventLogFunction::<4>.declare(context)?;
+
+        revive_llvm_context::PolkaVMDivisionFunction.declare(context)?;
+        revive_llvm_context::PolkaVMSignedDivisionFunction.declare(context)?;
+        revive_llvm_context::PolkaVMRemainderFunction.declare(context)?;
+        revive_llvm_context::PolkaVMSignedRemainderFunction.declare(context)?;
+
         let mut entry = revive_llvm_context::PolkaVMEntryFunction::default();
         entry.declare(context)?;
 
@@ -202,7 +223,6 @@ where
             revive_llvm_context::PolkaVMFunctionDeployCode,
             revive_llvm_context::PolkaVMFunctionRuntimeCode,
             revive_llvm_context::PolkaVMFunctionEntry,
-            revive_llvm_context::PolkaVMFunctionImmutableDataLoad,
         ]
         .into_iter()
         {
@@ -215,6 +235,28 @@ where
 
         entry.into_llvm(context)?;
 
+        revive_llvm_context::PolkaVMLoadImmutableDataFunction.into_llvm(context)?;
+        revive_llvm_context::PolkaVMStoreImmutableDataFunction.into_llvm(context)?;
+
+        revive_llvm_context::PolkaVMLoadHeapWordFunction.into_llvm(context)?;
+        revive_llvm_context::PolkaVMStoreHeapWordFunction.into_llvm(context)?;
+        revive_llvm_context::PolkaVMLoadStorageWordFunction.into_llvm(context)?;
+        revive_llvm_context::PolkaVMStoreStorageWordFunction.into_llvm(context)?;
+
+        revive_llvm_context::PolkaVMWordToPointerFunction.into_llvm(context)?;
+        revive_llvm_context::PolkaVMExitFunction.into_llvm(context)?;
+
+        revive_llvm_context::PolkaVMEventLogFunction::<0>.into_llvm(context)?;
+        revive_llvm_context::PolkaVMEventLogFunction::<1>.into_llvm(context)?;
+        revive_llvm_context::PolkaVMEventLogFunction::<2>.into_llvm(context)?;
+        revive_llvm_context::PolkaVMEventLogFunction::<3>.into_llvm(context)?;
+        revive_llvm_context::PolkaVMEventLogFunction::<4>.into_llvm(context)?;
+
+        revive_llvm_context::PolkaVMDivisionFunction.into_llvm(context)?;
+        revive_llvm_context::PolkaVMSignedDivisionFunction.into_llvm(context)?;
+        revive_llvm_context::PolkaVMRemainderFunction.into_llvm(context)?;
+        revive_llvm_context::PolkaVMSignedRemainderFunction.into_llvm(context)?;
+
         Ok(())
     }
 
@@ -230,7 +272,6 @@ where
         }
 
         if self.identifier.ends_with("_deployed") {
-            revive_llvm_context::PolkaVMImmutableDataLoadFunction.into_llvm(context)?;
             revive_llvm_context::PolkaVMRuntimeCodeFunction::new(self.code).into_llvm(context)?;
         } else {
             revive_llvm_context::PolkaVMDeployCodeFunction::new(self.code).into_llvm(context)?;