util/deephash: optimize CPU a bit by by avoiding fmt in more places

name              old time/op    new time/op    delta
Hash-6               179µs ± 5%     173µs ± 4%   -3.12%  (p=0.004 n=10+10)
HashMapAcyclic-6     115µs ± 3%     101µs ± 5%  -11.51%  (p=0.000 n=9+9)
TailcfgNode-6       30.8µs ± 4%    29.4µs ± 2%   -4.51%  (p=0.000 n=10+8)

name              old alloc/op   new alloc/op   delta
Hash-6              3.60kB ± 0%    3.60kB ± 0%     ~     (p=0.445 n=9+10)
HashMapAcyclic-6    2.53kB ± 0%    2.53kB ± 0%     ~     (p=0.065 n=9+10)
TailcfgNode-6         528B ± 0%      528B ± 0%     ~     (all equal)

name              old allocs/op  new allocs/op  delta
Hash-6                84.0 ± 0%      84.0 ± 0%     ~     (all equal)
HashMapAcyclic-6       202 ± 0%       202 ± 0%     ~     (all equal)
TailcfgNode-6         11.0 ± 0%      11.0 ± 0%     ~     (all equal)

Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>

util/deephash/deephash.go

@@ -15,6 +15,7 @@ import (
 	"encoding/hex"
 	"fmt"
 	"hash"
+	"math"
 	"reflect"
 	"strconv"
 	"sync"
@@ -159,14 +160,15 @@ func print(w *bufio.Writer, v reflect.Value, visited map[uintptr]bool, scratch [
 	case reflect.String:
 		w.WriteString(v.String())
 	case reflect.Bool:
-		fmt.Fprintf(w, "%v", v.Bool())
+		w.Write(strconv.AppendBool(scratch[:0], v.Bool()))
 	case reflect.Int, reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64:
-		fmt.Fprintf(w, "%v", v.Int())
+		w.Write(strconv.AppendInt(scratch[:0], v.Int(), 10))
 	case reflect.Uint, reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64, reflect.Uintptr:
 		scratch = strconv.AppendUint(scratch[:0], v.Uint(), 10)
 		w.Write(scratch)
 	case reflect.Float32, reflect.Float64:
-		fmt.Fprintf(w, "%v", v.Float())
+		scratch = strconv.AppendUint(scratch[:0], math.Float64bits(v.Float()), 10)
+		w.Write(scratch)
 	case reflect.Complex64, reflect.Complex128:
 		fmt.Fprintf(w, "%v", v.Complex())
 	}