Numeric helper call trees on f64; number-only leaves take converted arguments

crates/qjs-cli/hot-functions.order

@@ -13,7 +13,7 @@
 # budget 0x300 __RNvNtNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode10typed_loop7execute16boxed_truthiness
 # budget 0x300 __RNvNtNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode10typed_loop7execute14boxed_equality
 # budget 0x500 __RNvNtNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode10typed_loop7execute9get_named
-# pinned: typed-loop executor at 0x200, interpreter's at 0xc40 mod 4 KiB (python3 -m tools.benchmark.layout_pin), head 44
+# pinned: typed-loop executor at 0x200, interpreter's at 0xc40 mod 4 KiB (python3 -m tools.benchmark.layout_pin), head 49
 __RNvMsz_NtNtNtCs1OjIl8oxbrv_5alloc11collections5btree3mapINtB5_8IntoIteryNtNtNtCscUtGwbhD4WH_5gimli4read6abbrev12AbbreviationE10dying_nextCsg55jX0GwzBC_3std
 __RNvXs7_NtNtCsg55jX0GwzBC_3std2io5errorNtB5_5ErrorNtNtCsl8K0bEFm1U0_4core3fmt7Display3fmt
 __RINvNtNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode10typed_loop7execute3runNtNtB6_2vm2VmEB8_
@@ -27,7 +27,8 @@ __RINvNtNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode10typed_loop7execute18try_run_ty
 __RNvYINtNvNtCsg55jX0GwzBC_3std2io17default_write_fmt7AdapterINtNtCs1OjIl8oxbrv_5alloc3vec3VechEENtNtCsl8K0bEFm1U0_4core3fmt5Write10write_charB9_
 __RNvYNtNtNtNtCsg55jX0GwzBC_3std3sys5stdio4unix6StderrNtNtBa_2io5Write9write_allBa_
 __RNvNtNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode10typed_loop7execute16get_named_object
-__RNvNvNtCsg55jX0GwzBC_3std2fs4read5inner
+__RNvXso_NtNtCsg55jX0GwzBC_3std2io5stdioRNtB5_6StderrNtB7_5Write9write_fmt
+__RNvXse_NtNtCsg55jX0GwzBC_3std2io5stdioRNtB5_6StdoutNtB7_5Write9write_fmt
 __RNvMs4_NtNtCs9nYd1Hk1rek_11qjs_runtime5value5arrayNtB5_8ArrayRef24direct_dense_index_value
 __RNvMsn_NtCs1OjIl8oxbrv_5alloc4syncINtB5_3ArcINtNtNtCscUtGwbhD4WH_5gimli4read5dwarf5DwarfINtNtBL_12endian_slice11EndianSliceNtNtBN_9endianity12LittleEndianEEE9drop_slowCsg55jX0GwzBC_3std
 __RNvXs7_NtNtCsg55jX0GwzBC_3std2io5stdioNtB5_9StdinLockNtB7_7BufRead9read_line
@@ -36,26 +37,30 @@ __RNvYINtNtNtCscUtGwbhD4WH_5gimli4read12endian_slice11EndianSliceNtNtB9_9endiani
 __RNvNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode15vm_numeric_leaf21try_eval_numeric_leaf
 __RNvXNvNtCsg55jX0GwzBC_3std2io17default_write_fmtINtB2_7AdapterNtNtNtNtB6_3sys5stdio4unix6StderrENtNtCsl8K0bEFm1U0_4core3fmt5Write9write_strB6_
 __RNvMs3_NtNtCs9nYd1Hk1rek_11qjs_runtime5value5arrayNtB5_9ArrayData21has_property_at_index
-__RNvXso_NtNtCsg55jX0GwzBC_3std2io5stdioRNtB5_6StderrNtB7_5Write9write_fmt
-__RNvNtNtCsg55jX0GwzBC_3std2io5stdio7__eprint
-__RNvNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode15vm_numeric_leaf20direct_number_binary
-__RNvXse_NtNtCsg55jX0GwzBC_3std2io5stdioRNtB5_6StdoutNtB7_5Write9write_fmt
-__RNvNtNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode10typed_loop7execute22ordinary_data_property
 __RNvXs_NvNtCsg55jX0GwzBC_3std9panicking13panic_handlerNtB4_19FormatStringPayloadNtNtCsl8K0bEFm1U0_4core5panic12PanicPayload3get
+__RNvXNvNtCsg55jX0GwzBC_3std2io17default_write_fmtINtB2_7AdapterINtNtB4_6cursor6CursorQShEENtNtCsl8K0bEFm1U0_4core3fmt5Write9write_strB6_
 __RNvMs_NtNtNtCsg55jX0GwzBC_3std2io8buffered9bufwriterINtB4_9BufWriterNtNtB8_5stdio9StdoutRawE14write_all_coldBa_
+__RNvNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode15vm_numeric_leaf20direct_number_binary
+__RNvMsn_NtCs1OjIl8oxbrv_5alloc4syncINtB5_3ArcINtNtNtNtCsg55jX0GwzBC_3std4sync6poison5mutex5MutexINtNtB7_3vec3VechEEE9drop_slowBP_
+__RNvXs1g_NtCsl8K0bEFm1U0_4core3fmtRINtNtCs1OjIl8oxbrv_5alloc3vec3VechENtB6_5Debug3fmtCsg55jX0GwzBC_3std
+__RNvNtNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode10typed_loop7execute22ordinary_data_property
+__RNvNtNtCsg55jX0GwzBC_3std2io5stdio7__eprint
+__RNvNtNtCsg55jX0GwzBC_3std3sys9backtrace4lock
 __RNvMNtNtNtCs9nYd1Hk1rek_11qjs_runtime5value6object10slot_readsNtB4_9ObjectRef22own_data_property_read
 __RNvMs1_NtNtNtNtCsg55jX0GwzBC_3std3sys4sync6rwlock5queueNtB5_6RwLock21read_unlock_contended
 __RNvMs1_NtNtNtNtCsg55jX0GwzBC_3std3sys4sync6rwlock5queueNtB5_6RwLock16unlock_contended
 __RNvMs6_NtNtCs9nYd1Hk1rek_11qjs_runtime5value6objectNtB5_9ObjectRef32write_existing_own_data_property
 __RNvNtNtNtCsg55jX0GwzBC_3std12backtrace_rs9symbolize5gimli4mmap
 __RNvNtNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode10typed_loop7execute16boxed_truthiness
-__RNvNtNtNtNtCsg55jX0GwzBC_3std3sys2io5error4unix17decode_error_kind
-__RNvXNvNtCsg55jX0GwzBC_3std2io17default_write_fmtINtB2_7AdapterINtNtB4_6cursor6CursorQShEENtNtCsl8K0bEFm1U0_4core3fmt5Write9write_strB6_
+__RNvNtNtCsg55jX0GwzBC_3std3sys2fs8read_dir
+__RNvMsn_NtCs1OjIl8oxbrv_5alloc4syncINtB5_3ArcNtNtNtCsg55jX0GwzBC_3std6thread6thread5InnerNtNtBM_5alloc6SystemE9drop_slowBM_
 __RNvNtNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode10typed_loop7execute14boxed_equality
 __RNvMsn_NtCs1OjIl8oxbrv_5alloc4syncINtB5_3ArcNtNtNtNtCsg55jX0GwzBC_3std3sys2fs4unix12InnerReadDirE9drop_slowBO_
 __RNvYINtNvNtCsg55jX0GwzBC_3std2io17default_write_fmt7AdapterNtNtNtNtB9_3sys5stdio4unix6StderrENtNtCsl8K0bEFm1U0_4core3fmt5Write10write_charB9_
 __RNvNtNtNtCs9nYd1Hk1rek_11qjs_runtime8bytecode10typed_loop7execute9get_named
-__RNvNtNtCsg55jX0GwzBC_3std3sys2fs8read_dir
+__RNvNtNtCsg55jX0GwzBC_3std3sys2fs12canonicalize
+__RNvMs4_NtCs1OjIl8oxbrv_5alloc7raw_vecINtB5_11RawVecInnerNtNtCsg55jX0GwzBC_3std5alloc6SystemE14grow_amortizedBW_
+__RNvXs1i_NtCsl8K0bEFm1U0_4core3fmtRNtNtNtB8_5panic8location8LocationNtB6_7Display3fmtCsg55jX0GwzBC_3std
 __RNvXs1_NtCs9nYd1Hk1rek_11qjs_runtime5valueNtB5_5ValueNtNtCsl8K0bEFm1U0_4core5clone5Clone5clone
 __RINvNtCsl8K0bEFm1U0_4core3ptr13drop_in_placeNtNtCs9nYd1Hk1rek_11qjs_runtime5value5ValueEBK_
 __RNvNtNtCs9nYd1Hk1rek_11qjs_runtime8function4call25call_direct_leaf_function

crates/qjs-runtime/src/bytecode/typed_loop/execute.rs

@@ -981,13 +981,19 @@ fn boxed_truthiness(value: &Value) -> Typed {
     Typed::Boolean(crate::conversion::is_truthy(value))
 }
 
-fn typed_numbers(args: &[Typed]) -> Option<[f64; super::helper_graph::MAX_HELPER_ARITY]> {
+/// The arguments as numbers: each must be one unless `convert`, when a
+/// boolean or `undefined` takes its `ToNumber` value.
+fn typed_numbers(
+    args: &[Typed],
+    convert: bool,
+) -> Option<[f64; super::helper_graph::MAX_HELPER_ARITY]> {
     let mut numbers = [0.0; super::helper_graph::MAX_HELPER_ARITY];
     for (number, arg) in numbers.iter_mut().zip(args) {
-        let Typed::Number(value) = arg else {
-            return None;
+        *number = match arg {
+            Typed::Number(value) => *value,
+            other if convert => other.to_numeric().number()?,
+            _ => return None,
         };
-        *number = *value;
     }
     Some(numbers)
 }
@@ -1000,7 +1006,13 @@ fn call_number_only_leaf(
     bytecode: &crate::bytecode::Bytecode,
     args: &[Typed],
 ) -> Option<Value> {
-    let numbers = typed_numbers(args)?;
+    // `x[i + j]` past the end of a hash's input is `undefined`, which
+    // `safe_add` turns to NaN and then 0 like any number operator would;
+    // declining it deoptimized crypto-sha1's whole block loop.
+    let numbers = typed_numbers(
+        args,
+        super::super::vm_numeric_leaf::number_only_leaf_converts_arguments(bytecode),
+    )?;
     let value = super::super::vm_numeric_leaf::eval_number_only_leaf(
         bytecode,
         &function.params,

crates/qjs-runtime/src/bytecode/typed_loop/helper_graph.rs

@@ -178,8 +178,8 @@ impl HelperGraph {
             return None;
         }
         let program = self.programs.get(index as usize)?;
-        // A numeric body calls no other helper, so only the loop's own call
-        // (depth zero) can reach one; recursion skips the check. It is
+        // A numeric body runs its own calls on `f64` registers, so only the
+        // loop's own call (depth zero) enters one from here. It is
         // lowered with every parameter a number, so a call that leaves one
         // `undefined` -- or passes one past the parameters, which would land
         // in a local -- runs on the general path.
@@ -189,7 +189,7 @@ impl HelperGraph {
             && let Some(Some(numeric)) = self.numeric.get(index as usize)
             && let Some(numbers) = numbers(args)
         {
-            return numeric.run(&numbers[..arity]);
+            return numeric.run(&self.numeric, &numbers[..arity], 0);
         }
         // `Typed` is `Copy`, so the whole file is a stack array: a helper call
         // allocates nothing and its registers stay in the frame the compiler
@@ -356,6 +356,7 @@ impl Preparation {
             }
             preparation.prepare_callee(vm, &callee, site.arity, 0)?;
         }
+        numeric::NumProgram::settle(&mut preparation.graph.numeric);
         Some(preparation.graph)
     }