tun: unwind summing loop in checksumNoFold()

$ benchstat old.txt new.txt
goos: linux
goarch: amd64
pkg: golang.zx2c4.com/wireguard/tun
cpu: 12th Gen Intel(R) Core(TM) i5-12400
                 │   old.txt    │               new.txt               │
                 │    sec/op    │   sec/op     vs base                │
Checksum/64-12     10.670n ± 2%   4.769n ± 0%  -55.30% (p=0.000 n=10)
Checksum/128-12    19.665n ± 2%   8.032n ± 0%  -59.16% (p=0.000 n=10)
Checksum/256-12     37.68n ± 1%   16.06n ± 0%  -57.37% (p=0.000 n=10)
Checksum/512-12     76.61n ± 3%   32.13n ± 0%  -58.06% (p=0.000 n=10)
Checksum/1024-12   160.55n ± 4%   64.25n ± 0%  -59.98% (p=0.000 n=10)
Checksum/1500-12   231.05n ± 7%   94.12n ± 0%  -59.26% (p=0.000 n=10)
Checksum/2048-12    309.5n ± 3%   128.5n ± 0%  -58.48% (p=0.000 n=10)
Checksum/4096-12    603.8n ± 4%   257.2n ± 0%  -57.41% (p=0.000 n=10)
Checksum/8192-12   1185.0n ± 3%   515.5n ± 0%  -56.50% (p=0.000 n=10)
Checksum/9000-12   1328.5n ± 5%   564.8n ± 0%  -57.49% (p=0.000 n=10)
Checksum/9001-12   1340.5n ± 3%   564.8n ± 0%  -57.87% (p=0.000 n=10)
geomean             185.3n        77.99n       -57.92%

Reviewed-by: Adrian Dewhurst <adrian@tailscale.com>
Signed-off-by: Jordan Whited <jordan@tailscale.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

1 files changed, 35 insertions, 0 deletions

diff --git a/tun/checksum_test.go b/tun/checksum_test.go
new file mode 100644
index 0000000..c1ccff5
--- /dev/null
+++ b/tun/checksum_test.go
@@ -0,0 +1,35 @@
+package tun
+
+import (
+	"fmt"
+	"math/rand"
+	"testing"
+)
+
+func BenchmarkChecksum(b *testing.B) {
+	lengths := []int{
+		64,
+		128,
+		256,
+		512,
+		1024,
+		1500,
+		2048,
+		4096,
+		8192,
+		9000,
+		9001,
+	}
+
+	for _, length := range lengths {
+		b.Run(fmt.Sprintf("%d", length), func(b *testing.B) {
+			buf := make([]byte, length)
+			rng := rand.New(rand.NewSource(1))
+			rng.Read(buf)
+			b.ResetTimer()
+			for i := 0; i < b.N; i++ {
+				checksum(buf, 0)
+			}
+		})
+	}
+}