cmd/compile: parallelize one more bit of rulegen

'go tool trace' pointed at an obvious inefficiency; roughly the first
fifth of the program's life was CPU-heavy and making use of only one CPU
core at a time.

This was due to genOp being run before genLower. We did make genLower
use goroutines to parallelize the work between architectures, but we
didn't make genOp run in parallel too.

Do that. To avoid having two layers of goroutines, simply fire off all
goroutines from the main function, and inline genLower, since it now
becomes just two lines of code.

Overall, this shaves another ~300ms from 'go run *.go' on my laptop.

	name     old time/op         new time/op         delta
	Rulegen          2.04s ± 2%          1.76s ± 2%  -13.93%  (p=0.008 n=5+5)

	name     old user-time/op    new user-time/op    delta
	Rulegen          9.04s ± 1%          9.25s ± 1%   +2.37%  (p=0.008 n=5+5)

	name     old sys-time/op     new sys-time/op     delta
	Rulegen          235ms ±14%          245ms ±16%     ~     (p=0.690 n=5+5)

	name     old peak-RSS-bytes  new peak-RSS-bytes  delta
	Rulegen          179MB ± 1%          190MB ± 2%   +6.21%  (p=0.008 n=5+5)

Change-Id: I057e074c592afe06c831b03ca447fba12005e6f6
Reviewed-on: https://go-review.googlesource.com/c/go/+/196177
Run-TryBot: Daniel Martí <mvdan@mvdan.cc>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>

diff --git a/src/cmd/compile/internal/ssa/gen/main.go b/src/cmd/compile/internal/ssa/gen/main.go
index db400577439ba1ce11f4b434d5ac4c521bdfd0aa..253af9047adb5d10ed3d4949a1405560ba324904 100644 (file)
--- a/src/cmd/compile/internal/ssa/gen/main.go
+++ b/src/cmd/compile/internal/ssa/gen/main.go
@@ -114,8 +114,37 @@ func main() {
                defer pprof.StopCPUProfile()
        }
        sort.Sort(ArchsByName(archs))
-       genOp()
-       genLower()
+
+       // The generate tasks are run concurrently, since they are CPU-intensive
+       // that can easily make use of many cores on a machine.
+       //
+       // Note that there is no limit on the concurrency at the moment. On a
+       // four-core laptop at the time of writing, peak RSS usually reaches
+       // ~200MiB, which seems doable by practically any machine nowadays. If
+       // that stops being the case, we can cap this func to a fixed number of
+       // architectures being generated at once.
+
+       tasks := []func(){
+               genOp,
+       }
+       for _, a := range archs {
+               a := a // the funcs are ran concurrently at a later time
+               tasks = append(tasks, func() {
+                       genRules(a)
+                       genSplitLoadRules(a)
+               })
+       }
+       var wg sync.WaitGroup
+       for _, task := range tasks {
+               task := task
+               wg.Add(1)
+               go func() {
+                       task()
+                       wg.Done()
+               }()
+       }
+       wg.Wait()
+
        if *memprofile != "" {
                f, err := os.Create(*memprofile)
                if err != nil {
@@ -385,8 +414,7 @@ func genOp() {
                panic(err)
        }
 
-       err = ioutil.WriteFile("../opGen.go", b, 0666)
-       if err != nil {
+       if err := ioutil.WriteFile("../opGen.go", b, 0666); err != nil {
                log.Fatalf("can't write output: %v\n", err)
        }
 
@@ -432,28 +460,6 @@ func (a arch) Name() string {
        return s
 }
 
-// genLower generates all arch-specific rewrite Go source files. The files are
-// generated and written concurrently, since it's a CPU-intensive task that can
-// easily make use of many cores on a machine.
-//
-// Note that there is no limit on the concurrency at the moment. On a four-core
-// laptop at the time of writing, peak RSS usually reached ~230MiB, which seems
-// doable by practically any machine nowadays. If that stops being the case, we
-// can cap this func to a fixed number of architectures being generated at once.
-func genLower() {
-       var wg sync.WaitGroup
-       for _, a := range archs {
-               a := a
-               wg.Add(1)
-               go func() {
-                       genRules(a)
-                       genSplitLoadRules(a)
-                       wg.Done()
-               }()
-       }
-       wg.Wait()
-}
-
 // countRegs returns the number of set bits in the register mask.
 func countRegs(r regMask) int {
        n := 0