call memset for read after write dependences at distance 1

On a benchmark using zlib to decompress a PNG image this change shows a 20%
speedup.  It makes sense to special case distance = 1 of read after write
dependences because it is possible to replace the loop kernel with a memset
which is usually implemented in assembly in the libc, and because of the
frequency at which distance = 1 appears during the PNG decompression:

Distance	Frequency
1		1009001
6		64500
9		29000
3		25500
144		14500
12		10000
15		3500
7		2000
24		1000
21		1000
18		1000
87		500
22		500
192		500

diff --git a/inffast.c b/inffast.c
index 2e510801019352afd26ac5967e090a7bacd42c8d..1d4048defa78565afbfcd261287e596f5e19d202 100644 (file)
--- a/inffast.c
+++ b/inffast.c
@@ -244,16 +244,21 @@ void ZLIB_INTERNAL inflate_fast(z_stream *strm, unsigned long start) {
                     }
                 } else {
                     from = out - dist;          /* copy direct from output */
-                    do {                        /* minimum length is three */
-                        *out++ = *from++;
-                        *out++ = *from++;
-                        *out++ = *from++;
-                        len -= 3;
-                    } while (len > 2);
-                    if (len) {
-                        *out++ = *from++;
-                        if (len > 1)
+                    if (dist == 1) {
+                        memset (out, *from, len);
+                        out += len;
+                    } else {
+                        do {                        /* minimum length is three */
+                            *out++ = *from++;
+                            *out++ = *from++;
                             *out++ = *from++;
+                            len -= 3;
+                        } while (len > 2);
+                        if (len) {
+                            *out++ = *from++;
+                            if (len > 1)
+                                *out++ = *from++;
+                        }
                     }
                 }
             } else if ((op & 64) == 0) {          /* 2nd level distance code */