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.
2026-06-14 19:11:04 +00:00 · 2025-02-25 16:47:01 +01:00
parent 7ffe64ed7c
commit a07968205b
32 changed files with 1444 additions and 655 deletions
@@ -4,10 +4,206 @@ use inkwell::types::BasicType;

 use crate::polkavm::context::address_space::AddressSpace;
 use crate::polkavm::context::code_type::CodeType;
-use crate::polkavm::context::function::runtime;
 use crate::polkavm::context::pointer::Pointer;
+use crate::polkavm::context::runtime::RuntimeFunction;
 use crate::polkavm::context::Context;
 use crate::polkavm::Dependency;
+use crate::polkavm::WriteLLVM;
+
+/// A function for requesting the immutable data from the runtime.
+/// This is a special function that is only used by the front-end generated code.
+///
+/// The runtime API is called lazily and subsequent calls are no-ops.
+///
+/// The bytes written is asserted to match the expected length.
+/// This should never fail; the length is known.
+/// However, this is a one time assertion, hence worth it.
+pub struct Load;
+
+impl<D> RuntimeFunction<D> for Load
+where
+    D: Dependency + Clone,
+{
+    const NAME: &'static str = "__revive_load_immutable_data";
+
+    fn r#type<'ctx>(context: &Context<'ctx, D>) -> inkwell::types::FunctionType<'ctx> {
+        context.void_type().fn_type(Default::default(), false)
+    }
+
+    fn emit_body<'ctx>(
+        &self,
+        context: &mut Context<'ctx, D>,
+    ) -> anyhow::Result<Option<inkwell::values::BasicValueEnum<'ctx>>> {
+        let immutable_data_size_pointer = context
+            .get_global(revive_runtime_api::immutable_data::GLOBAL_IMMUTABLE_DATA_SIZE)?
+            .value
+            .as_pointer_value();
+        let immutable_data_size = context.build_load(
+            Pointer::new(
+                context.xlen_type(),
+                AddressSpace::Stack,
+                immutable_data_size_pointer,
+            ),
+            "immutable_data_size_load",
+        )?;
+
+        let load_immutable_data_block = context.append_basic_block("load_immutables_block");
+        let return_block = context.current_function().borrow().return_block();
+        let immutable_data_size_is_zero = context.builder().build_int_compare(
+            inkwell::IntPredicate::EQ,
+            context.xlen_type().const_zero(),
+            immutable_data_size.into_int_value(),
+            "immutable_data_size_is_zero",
+        )?;
+        context.build_conditional_branch(
+            immutable_data_size_is_zero,
+            return_block,
+            load_immutable_data_block,
+        )?;
+
+        context.set_basic_block(load_immutable_data_block);
+        let output_pointer = context
+            .get_global(revive_runtime_api::immutable_data::GLOBAL_IMMUTABLE_DATA_POINTER)?
+            .value
+            .as_pointer_value();
+        context.build_runtime_call(
+            revive_runtime_api::polkavm_imports::GET_IMMUTABLE_DATA,
+            &[
+                context
+                    .builder()
+                    .build_ptr_to_int(output_pointer, context.xlen_type(), "ptr_to_xlen")?
+                    .into(),
+                context
+                    .builder()
+                    .build_ptr_to_int(
+                        immutable_data_size_pointer,
+                        context.xlen_type(),
+                        "ptr_to_xlen",
+                    )?
+                    .into(),
+            ],
+        );
+        let bytes_written = context.builder().build_load(
+            context.xlen_type(),
+            immutable_data_size_pointer,
+            "bytes_written",
+        )?;
+        context.builder().build_store(
+            immutable_data_size_pointer,
+            context.xlen_type().const_zero(),
+        )?;
+        let overflow_block = context.append_basic_block("immutable_data_overflow");
+        let is_overflow = context.builder().build_int_compare(
+            inkwell::IntPredicate::UGT,
+            immutable_data_size.into_int_value(),
+            bytes_written.into_int_value(),
+            "is_overflow",
+        )?;
+        context.build_conditional_branch(is_overflow, overflow_block, return_block)?;
+
+        context.set_basic_block(overflow_block);
+        context.build_call(context.intrinsics().trap, &[], "invalid_trap");
+        context.build_unreachable();
+
+        Ok(None)
+    }
+}
+
+impl<D> WriteLLVM<D> for Load
+where
+    D: Dependency + Clone,
+{
+    fn declare(&mut self, context: &mut Context<D>) -> anyhow::Result<()> {
+        <Self as RuntimeFunction<_>>::declare(self, context)
+    }
+
+    fn into_llvm(self, context: &mut Context<D>) -> anyhow::Result<()> {
+        <Self as RuntimeFunction<_>>::emit(&self, context)
+    }
+}
+
+/// Store the immutable data from the constructor code.
+pub struct Store;
+
+impl<D> RuntimeFunction<D> for Store
+where
+    D: Dependency + Clone,
+{
+    const NAME: &'static str = "__revive_store_immutable_data";
+
+    fn r#type<'ctx>(context: &Context<'ctx, D>) -> inkwell::types::FunctionType<'ctx> {
+        context.void_type().fn_type(Default::default(), false)
+    }
+
+    fn emit_body<'ctx>(
+        &self,
+        context: &mut Context<'ctx, D>,
+    ) -> anyhow::Result<Option<inkwell::values::BasicValueEnum<'ctx>>> {
+        let immutable_data_size_pointer = context
+            .get_global(revive_runtime_api::immutable_data::GLOBAL_IMMUTABLE_DATA_SIZE)?
+            .value
+            .as_pointer_value();
+        let immutable_data_size = context.build_load(
+            Pointer::new(
+                context.xlen_type(),
+                AddressSpace::Stack,
+                immutable_data_size_pointer,
+            ),
+            "immutable_data_size_load",
+        )?;
+
+        let write_immutable_data_block = context.append_basic_block("write_immutables_block");
+        let join_return_block = context.append_basic_block("join_return_block");
+        let immutable_data_size_is_zero = context.builder().build_int_compare(
+            inkwell::IntPredicate::EQ,
+            context.xlen_type().const_zero(),
+            immutable_data_size.into_int_value(),
+            "immutable_data_size_is_zero",
+        )?;
+        context.build_conditional_branch(
+            immutable_data_size_is_zero,
+            join_return_block,
+            write_immutable_data_block,
+        )?;
+
+        context.set_basic_block(write_immutable_data_block);
+        let immutable_data_pointer = context
+            .get_global(revive_runtime_api::immutable_data::GLOBAL_IMMUTABLE_DATA_POINTER)?
+            .value
+            .as_pointer_value();
+        context.build_runtime_call(
+            revive_runtime_api::polkavm_imports::SET_IMMUTABLE_DATA,
+            &[
+                context
+                    .builder()
+                    .build_ptr_to_int(
+                        immutable_data_pointer,
+                        context.xlen_type(),
+                        "immutable_data_pointer_to_xlen",
+                    )?
+                    .into(),
+                immutable_data_size,
+            ],
+        );
+        context.build_unconditional_branch(join_return_block);
+
+        context.set_basic_block(join_return_block);
+        Ok(None)
+    }
+}
+
+impl<D> WriteLLVM<D> for Store
+where
+    D: Dependency + Clone,
+{
+    fn declare(&mut self, context: &mut Context<D>) -> anyhow::Result<()> {
+        <Self as RuntimeFunction<_>>::declare(self, context)
+    }
+
+    fn into_llvm(self, context: &mut Context<D>) -> anyhow::Result<()> {
+        <Self as RuntimeFunction<_>>::emit(&self, context)
+    }
+}

 /// Translates the contract immutable load.
 ///
@@ -27,14 +223,15 @@ where
        }
        Some(CodeType::Deploy) => load_from_memory(context, index),
        Some(CodeType::Runtime) => {
+            let name = <Load as RuntimeFunction<D>>::NAME;
            context.build_call(
                context
-                    .get_function(runtime::FUNCTION_LOAD_IMMUTABLE_DATA)
+                    .get_function(name)
                    .expect("is always declared for runtime code")
                    .borrow()
                    .declaration(),
                &[],
-                runtime::FUNCTION_LOAD_IMMUTABLE_DATA,
+                name,
            );
            load_from_memory(context, index)
        }