runtime: replace needwb() with writeBarrierEnabled

Reduce the write barrier check to a single load and compare
so that it can be inlined into write barrier use sites.
Makes the standard write barrier a little faster too.

name                                       old                     new          delta
BenchmarkBinaryTree17              17.9s × (0.99,1.01)     17.9s × (1.00,1.01)  ~
BenchmarkFannkuch11                4.35s × (1.00,1.00)     4.43s × (1.00,1.00)  +1.81%
BenchmarkFmtFprintfEmpty           120ns × (0.93,1.06)     110ns × (1.00,1.06)  -7.92%
BenchmarkFmtFprintfString          479ns × (0.99,1.00)     487ns × (0.99,1.00)  +1.67%
BenchmarkFmtFprintfInt             452ns × (0.99,1.02)     450ns × (0.99,1.00)  ~
BenchmarkFmtFprintfIntInt          766ns × (0.99,1.01)     762ns × (1.00,1.00)  ~
BenchmarkFmtFprintfPrefixedInt     576ns × (0.98,1.01)     584ns × (0.99,1.01)  ~
BenchmarkFmtFprintfFloat           730ns × (1.00,1.01)     738ns × (1.00,1.00)  +1.16%
BenchmarkFmtManyArgs              2.84µs × (0.99,1.00)    2.80µs × (1.00,1.01)  -1.22%
BenchmarkGobDecode                39.3ms × (0.98,1.01)    39.0ms × (0.99,1.00)  ~
BenchmarkGobEncode                39.5ms × (0.99,1.01)    37.8ms × (0.98,1.01)  -4.33%
BenchmarkGzip                      663ms × (1.00,1.01)     661ms × (0.99,1.01)  ~
BenchmarkGunzip                    143ms × (1.00,1.00)     142ms × (1.00,1.00)  ~
BenchmarkHTTPClientServer          132µs × (0.99,1.01)     132µs × (0.99,1.01)  ~
BenchmarkJSONEncode               57.4ms × (0.99,1.01)    56.3ms × (0.99,1.01)  -1.96%
BenchmarkJSONDecode                139ms × (0.99,1.00)     138ms × (0.99,1.01)  ~
BenchmarkMandelbrot200            6.03ms × (1.00,1.00)    6.01ms × (1.00,1.00)  ~
BenchmarkGoParse                  10.3ms × (0.89,1.14)    10.2ms × (0.87,1.05)  ~
BenchmarkRegexpMatchEasy0_32       209ns × (1.00,1.00)     208ns × (1.00,1.00)  ~
BenchmarkRegexpMatchEasy0_1K       591ns × (0.99,1.00)     588ns × (1.00,1.00)  ~
BenchmarkRegexpMatchEasy1_32       184ns × (0.99,1.02)     182ns × (0.99,1.01)  ~
BenchmarkRegexpMatchEasy1_1K      1.01µs × (1.00,1.00)    0.99µs × (1.00,1.01)  -2.33%
BenchmarkRegexpMatchMedium_32      330ns × (1.00,1.00)     323ns × (1.00,1.01)  -2.12%
BenchmarkRegexpMatchMedium_1K     92.6µs × (1.00,1.00)    89.9µs × (1.00,1.00)  -2.92%
BenchmarkRegexpMatchHard_32       4.80µs × (0.95,1.00)    4.72µs × (0.95,1.01)  ~
BenchmarkRegexpMatchHard_1K        136µs × (1.00,1.00)     133µs × (1.00,1.01)  -1.86%
BenchmarkRevcomp                   900ms × (0.99,1.04)     900ms × (1.00,1.05)  ~
BenchmarkTemplate                  172ms × (1.00,1.00)     168ms × (0.99,1.01)  -2.07%
BenchmarkTimeParse                 637ns × (1.00,1.00)     637ns × (1.00,1.00)  ~
BenchmarkTimeFormat                744ns × (1.00,1.01)     738ns × (1.00,1.00)  -0.67%

Change-Id: I4ecc925805da1f5ee264377f1f7574f54ee575e7
Reviewed-on: https://go-review.googlesource.com/9321
Reviewed-by: Austin Clements <austin@google.com>
This commit is contained in:
Russ Cox 2015-04-24 14:00:55 -04:00
parent 2050f57141
commit 32d6fbcb4f
4 changed files with 40 additions and 38 deletions

View file

@ -84,7 +84,7 @@ func growslice(t *slicetype, old slice, n int) slice {
memclr(add(p, lenmem), capmem-lenmem)
} else {
// Note: can't use rawmem (which avoids zeroing of memory), because then GC can scan unitialized memory.
// TODO(rsc): Use memmove when !needwb().
// TODO(rsc): Use memmove when !writeBarrierEnabled.
p = newarray(et, uintptr(newcap))
for i := 0; i < old.len; i++ {
typedmemmove(et, add(p, uintptr(i)*et.size), add(old.array, uintptr(i)*et.size))