github/esphome
2
0
Fork 0
mirror of https://github.com/esphome/esphome.git synced 2026-10-01 17:00:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

[api] Keep the decode loop register resident and inline the varint fast path

Browse Source 
CodSpeed showed the single virtual costing 7 to 18 percent on the
decode benchmarks. The x86-64 disassembly pointed at the call, not the
switch: passing the field number and wire type alongside the tag plus
a 16 byte union payload kept five values live across the call, so the
compiler spilled this, the end pointer and half of the payload to the
stack and reloaded them for every field.

decode_field() now takes only the tag, the payload pointer (already
the loop cursor) and one scalar that holds the varint or fixed32 value
or the payload length. The generated override wraps them in a
ProtoFieldValue that never exists in memory. On the host the switch
key is the field number derived with one shift and the guard compares
the whole tag against the constant the case declares, which is the
same two instructions the old per wire type dispatch cost.

The loop also handles single byte varints inline instead of going
through the parse result struct, which drops the materialized consumed
count and its add on every tag and small value.
This commit is contained in:
J. Nick Koston
2026-09-07 15:57:13 +02:00
parent b0ce7f58f3
commit bcf812d62b
6 changed files with 578 additions and 528 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/unit_tests/components/api/test_api_protobuf_generator.py
+7 -4
View File
@@ -226,7 +226,9 @@ def test_decode_cases_carry_field_number_and_wire_type(
assert len(cases) == 1, cases
lines = cases[0].splitlines()
assert lines[0] == f"case PROTO_DECODE_CASE({number}, {wire_type}):", cases[0]
assert lines[1].strip() == f"PROTO_DECODE_GUARD(wire_type, {wire_type});", cases[0]
assert lines[1].strip() == f"PROTO_DECODE_GUARD(tag, {number}, {wire_type});", (
cases[0]
)
assert accessor in cases[0], cases[0]
@@ -237,15 +239,16 @@ def test_message_gets_a_single_decode_field_override() -> None:
desc.field.add(name="count", number=2, type=UINT32_T)
desc.field.add(name="level", number=3, type=FLOAT)
header, cpp, _ = build_message_type(desc, {}, {"Mixed": SOURCE_CLIENT})
decl = "bool decode_field(uint32_t tag, uint32_t field_id, uint32_t wire_type, ProtoFieldValue value) override;"
decl = "bool decode_field(uint32_t tag, const uint8_t *data, proto_varint_value_t scalar) override;"
assert header.count(decl) == 1
assert "decode_varint" not in header and "decode_length" not in header
assert (
cpp.count(
"bool Mixed::decode_field(uint32_t tag, uint32_t field_id, uint32_t wire_type, ProtoFieldValue value) {"
"bool Mixed::decode_field(uint32_t tag, const uint8_t *data, proto_varint_value_t scalar) {"
)
== 1
)
assert "switch (PROTO_DECODE_KEY(tag, field_id)) {" in cpp
assert "switch (PROTO_DECODE_KEY(tag)) {" in cpp
assert "const ProtoFieldValue value(data, scalar);" in cpp
for number, wire_type in ((1, 2), (2, 0), (3, 5)):
assert f"case PROTO_DECODE_CASE({number}, {wire_type}):" in cpp, cpp