Added regex-dna-parallel.go, a pretty trivial parallelization.

R=rsc, r
CC=golang-dev
https://golang.org/cl/972046

diff --git a/test/bench/regex-dna-parallel.go b/test/bench/regex-dna-parallel.go
new file mode 100644 (file)
index 0000000..d33f246
--- /dev/null
+++ b/test/bench/regex-dna-parallel.go
@@ -0,0 +1,124 @@
+/*
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright
+    notice, this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+    notice, this list of conditions and the following disclaimer in the
+    documentation and/or other materials provided with the distribution.
+
+    * Neither the name of "The Computer Language Benchmarks Game" nor the
+    name of "The Computer Language Shootout Benchmarks" nor the names of
+    its contributors may be used to endorse or promote products derived
+    from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+*/
+
+/* The Computer Language Benchmarks Game
+ * http://shootout.alioth.debian.org/
+ *
+ * contributed by The Go Authors.
+ */
+
+package main
+
+import (
+       "fmt"
+       "io/ioutil"
+       "os"
+       "runtime"
+       "regexp"
+)
+
+var variants = []string{
+       "agggtaaa|tttaccct",
+       "[cgt]gggtaaa|tttaccc[acg]",
+       "a[act]ggtaaa|tttacc[agt]t",
+       "ag[act]gtaaa|tttac[agt]ct",
+       "agg[act]taaa|ttta[agt]cct",
+       "aggg[acg]aaa|ttt[cgt]ccct",
+       "agggt[cgt]aa|tt[acg]accct",
+       "agggta[cgt]a|t[acg]taccct",
+       "agggtaa[cgt]|[acg]ttaccct",
+}
+
+type Subst struct {
+       pat, repl string
+}
+
+var substs = []Subst{
+       Subst{"B", "(c|g|t)"},
+       Subst{"D", "(a|g|t)"},
+       Subst{"H", "(a|c|t)"},
+       Subst{"K", "(g|t)"},
+       Subst{"M", "(a|c)"},
+       Subst{"N", "(a|c|g|t)"},
+       Subst{"R", "(a|g)"},
+       Subst{"S", "(c|g)"},
+       Subst{"V", "(a|c|g)"},
+       Subst{"W", "(a|t)"},
+       Subst{"Y", "(c|t)"},
+}
+
+func countMatches(pat string, bytes []byte) int {
+       re := regexp.MustCompile(pat)
+       n := 0
+       for {
+               e := re.Execute(bytes)
+               if len(e) == 0 {
+                       break
+               }
+               n++
+               bytes = bytes[e[1]:]
+       }
+       return n
+}
+
+func main() {
+       runtime.GOMAXPROCS(4)
+       bytes, err := ioutil.ReadFile("/dev/stdin")
+       if err != nil {
+               fmt.Fprintf(os.Stderr, "can't read input: %s\n", err)
+               os.Exit(2)
+       }
+       ilen := len(bytes)
+       // Delete the comment lines and newlines
+       bytes = regexp.MustCompile("(>[^\n]+)?\n").ReplaceAll(bytes, []byte{})
+       clen := len(bytes)
+
+       mresults := make([]chan int, len(variants))
+       for i, s := range variants {
+               ch := make(chan int)
+               mresults[i] = ch
+               go func(ss string) {
+                       ch <- countMatches(ss, bytes)
+               }(s)
+       }
+
+       lenresult := make(chan int)
+       bb := bytes
+       go func() {
+               for _, sub := range substs {
+                       bb = regexp.MustCompile(sub.pat).ReplaceAll(bb, []byte(sub.repl))
+               }
+               lenresult <- len(bb)
+       }()
+
+       for i, s := range variants {
+               fmt.Printf("%s %d\n", s, <-mresults[i])
+       }
+       fmt.Printf("\n%d\n%d\n%d\n", ilen, clen, <-lenresult)
+}

diff --git a/test/bench/regex-dna-parallel.txt b/test/bench/regex-dna-parallel.txt
new file mode 100644 (file)
index 0000000..e23e71f
--- /dev/null
+++ b/test/bench/regex-dna-parallel.txt
@@ -0,0 +1,13 @@
+agggtaaa|tttaccct 1
+[cgt]gggtaaa|tttaccc[acg] 0
+a[act]ggtaaa|tttacc[agt]t 0
+ag[act]gtaaa|tttac[agt]ct 0
+agg[act]taaa|ttta[agt]cct 1
+aggg[acg]aaa|ttt[cgt]ccct 0
+agggt[cgt]aa|tt[acg]accct 0
+agggta[cgt]a|t[acg]taccct 0
+agggtaa[cgt]|[acg]ttaccct 2
+
+10245
+10000
+13348

diff --git a/test/bench/timing.sh b/test/bench/timing.sh
index 83ffd2494c8157b6db06d7044479b4693d3d0589..5cd82dfd964eb9771b76687b0b78cabea202a2eb 100755 (executable)
--- a/test/bench/timing.sh
+++ b/test/bench/timing.sh
@@ -119,6 +119,7 @@ regexdna() {
        run 'gcc -O2 regex-dna.c -lpcre' a.out <x
 #      run 'gccgo -O2 regex-dna.go' a.out <x   # pages badly; don't run
        run 'gc regex-dna' $O.out <x
+       run 'gc regex-dna-parallel' $O.out <x
        run 'gc_B regex-dna' $O.out <x
        rm x
 }