Add UPB_FORCEINLINE for varint32 decoding.
This speeds up the decoder by >20% and also reduces code size slightly!
name old time/op new time/op delta
ArenaOneAlloc 20.4ns ± 0% 20.2ns ± 0% -1.10% (p=0.000 n=12+11)
ArenaInitialBlockOneAlloc 5.25ns ± 0% 5.25ns ± 0% ~ (p=0.786 n=11+12)
ParseDescriptorNoHeap 17.1µs ± 0% 13.1µs ± 0% -23.29% (p=0.000 n=11+12)
ParseDescriptor 17.4µs ± 1% 13.5µs ± 1% -22.51% (p=0.000 n=12+12)
SerializeDescriptor 10.7µs ± 0% 10.9µs ± 0% +1.95% (p=0.000 n=12+12)
FILE SIZE VM SIZE
-------------- --------------
+2.7% +16 +2.7% +16 [LOAD #2 [RX]]
+0.5% +16 [ = ] 0 [Unmapped]
-1.4% -72 -0.7% -32 upb/decode.c
+3.1% +98 +3.1% +98 decode_msg
[DEL] -170 [DEL] -130 decode_varint32
-0.0% -40 -0.0% -16 TOTAL
diff --git a/benchmark.py b/benchmark.py
index 4a6e9f8..b75dd4d 100755
--- a/benchmark.py
+++ b/benchmark.py
@@ -15,7 +15,7 @@
@contextlib.contextmanager
def GitWorktree(commit):
tmpdir = tempfile.mkdtemp()
- subprocess.run(['git', 'worktree', 'add', '-q', tmpdir, commit], check=True)
+ subprocess.run(['git', 'worktree', 'add', '-q', '-d', tmpdir, commit], check=True)
cwd = os.getcwd()
os.chdir(tmpdir)
try: