mirror of
https://github.com/golang/go
synced 2024-11-18 15:14:44 -07:00
8552047a32
The code generated for x = append(x, v) is roughly:
t := x
if len(t)+1 > cap(t) {
t = grow(t)
}
t[len(t)] = v
len(t)++
x = t
We used to generate this code as Go pseudocode during walk.
Generate it instead as actual instructions during gen.
Doing so lets us apply a few optimizations. The most important
is that when, as in the above example, the source slice and the
destination slice are the same, the code can instead do:
t := x
if len(t)+1 > cap(t) {
t = grow(t)
x = {base(t), len(t)+1, cap(t)}
} else {
len(x)++
}
t[len(t)] = v
That is, in the fast path that does not reallocate the array,
only the updated length needs to be written back to x,
not the array pointer and not the capacity. This is more like
what you'd write by hand in C. It's faster in general, since
the fast path elides two of the three stores, but it's especially
faster when the form of x is such that the base pointer write
would turn into a write barrier. No write, no barrier.
name old mean new mean delta
BinaryTree17 5.68s × (0.97,1.04) 5.81s × (0.98,1.03) +2.35% (p=0.023)
Fannkuch11 4.41s × (0.98,1.03) 4.35s × (1.00,1.00) ~ (p=0.090)
FmtFprintfEmpty 92.7ns × (0.91,1.16) 86.0ns × (0.94,1.11) -7.31% (p=0.038)
FmtFprintfString 281ns × (0.96,1.08) 276ns × (0.98,1.04) ~ (p=0.219)
FmtFprintfInt 288ns × (0.97,1.06) 274ns × (0.98,1.06) -4.94% (p=0.002)
FmtFprintfIntInt 493ns × (0.97,1.04) 506ns × (0.99,1.01) +2.65% (p=0.009)
FmtFprintfPrefixedInt 423ns × (0.97,1.04) 391ns × (0.99,1.01) -7.52% (p=0.000)
FmtFprintfFloat 598ns × (0.99,1.01) 566ns × (0.99,1.01) -5.27% (p=0.000)
FmtManyArgs 1.89µs × (0.98,1.05) 1.91µs × (0.99,1.01) ~ (p=0.231)
GobDecode 14.8ms × (0.98,1.03) 15.3ms × (0.99,1.02) +3.01% (p=0.000)
GobEncode 12.3ms × (0.98,1.01) 11.5ms × (0.97,1.03) -5.93% (p=0.000)
Gzip 656ms × (0.99,1.05) 645ms × (0.99,1.01) ~ (p=0.055)
Gunzip 142ms × (1.00,1.00) 142ms × (1.00,1.00) -0.32% (p=0.034)
HTTPClientServer 91.2µs × (0.97,1.04) 90.5µs × (0.97,1.04) ~ (p=0.468)
JSONEncode 32.6ms × (0.97,1.08) 32.0ms × (0.98,1.03) ~ (p=0.190)
JSONDecode 114ms × (0.97,1.05) 114ms × (0.99,1.01) ~ (p=0.887)
Mandelbrot200 6.11ms × (0.98,1.04) 6.04ms × (1.00,1.01) ~ (p=0.167)
GoParse 6.66ms × (0.97,1.04) 6.47ms × (0.97,1.05) -2.81% (p=0.014)
RegexpMatchEasy0_32 159ns × (0.99,1.00) 171ns × (0.93,1.07) +7.19% (p=0.002)
RegexpMatchEasy0_1K 538ns × (1.00,1.01) 550ns × (0.98,1.01) +2.30% (p=0.000)
RegexpMatchEasy1_32 138ns × (1.00,1.00) 135ns × (0.99,1.02) -1.60% (p=0.000)
RegexpMatchEasy1_1K 869ns × (0.99,1.01) 879ns × (1.00,1.01) +1.08% (p=0.000)
RegexpMatchMedium_32 252ns × (0.99,1.01) 243ns × (1.00,1.00) -3.71% (p=0.000)
RegexpMatchMedium_1K 72.7µs × (1.00,1.00) 70.3µs × (1.00,1.00) -3.34% (p=0.000)
RegexpMatchHard_32 3.85µs × (1.00,1.00) 3.82µs × (1.00,1.01) -0.81% (p=0.000)
RegexpMatchHard_1K 118µs × (1.00,1.00) 117µs × (1.00,1.00) -0.56% (p=0.000)
Revcomp 920ms × (0.97,1.07) 917ms × (0.97,1.04) ~ (p=0.808)
Template 129ms × (0.98,1.03) 114ms × (0.99,1.01) -12.06% (p=0.000)
TimeParse 619ns × (0.99,1.01) 622ns × (0.99,1.01) ~ (p=0.062)
TimeFormat 661ns × (0.98,1.04) 665ns × (0.99,1.01) ~ (p=0.524)
See next CL for combination with a similar optimization for slice.
The benchmarks that are slower in this CL are still faster overall
with the combination of the two.
Change-Id: I2a7421658091b2488c64741b4db15ab6c3b4cb7e
Reviewed-on: https://go-review.googlesource.com/9812
Reviewed-by: David Chase <drchase@google.com>
|
||
|---|---|---|
| .. | ||
| bench | ||
| bugs | ||
| chan | ||
| ddd2.dir | ||
| dwarf | ||
| fixedbugs | ||
| import2.dir | ||
| import4.dir | ||
| interface | ||
| ken | ||
| method4.dir | ||
| safe | ||
| stress | ||
| syntax | ||
| 64bit.go | ||
| 235.go | ||
| alias1.go | ||
| alias.go | ||
| append.go | ||
| args.go | ||
| assign1.go | ||
| assign.go | ||
| bigalg.go | ||
| bigmap.go | ||
| blank1.go | ||
| blank.go | ||
| bom.go | ||
| bombad.go | ||
| bounds.go | ||
| chancap.go | ||
| chanlinear.go | ||
| char_lit1.go | ||
| char_lit.go | ||
| clearfat.go | ||
| closedchan.go | ||
| closure1.go | ||
| closure2.go | ||
| closure.go | ||
| cmp6.go | ||
| cmp.go | ||
| cmplx.go | ||
| cmplxdivide1.go | ||
| cmplxdivide.c | ||
| cmplxdivide.go | ||
| complit1.go | ||
| complit.go | ||
| compos.go | ||
| const1.go | ||
| const2.go | ||
| const3.go | ||
| const4.go | ||
| const5.go | ||
| const6.go | ||
| const.go | ||
| convert1.go | ||
| convert3.go | ||
| convert.go | ||
| convlit1.go | ||
| convlit.go | ||
| convT2X.go | ||
| copy.go | ||
| crlf.go | ||
| ddd1.go | ||
| ddd2.go | ||
| ddd.go | ||
| decl.go | ||
| declbad.go | ||
| defer.go | ||
| deferfin.go | ||
| deferprint.go | ||
| deferprint.out | ||
| divide.go | ||
| divmod.go | ||
| empty.go | ||
| env.go | ||
| eof1.go | ||
| eof.go | ||
| errchk | ||
| escape2.go | ||
| escape2n.go | ||
| escape3.go | ||
| escape4.go | ||
| escape5.go | ||
| escape_array.go | ||
| escape_calls.go | ||
| escape_closure.go | ||
| escape_field.go | ||
| escape_iface.go | ||
| escape_indir.go | ||
| escape_level.go | ||
| escape_map.go | ||
| escape_param.go | ||
| escape_slice.go | ||
| escape_struct_param1.go | ||
| escape_struct_param2.go | ||
| escape_struct_return.go | ||
| escape.go | ||
| fibo.go | ||
| float_lit2.go | ||
| float_lit3.go | ||
| float_lit.go | ||
| floatcmp.go | ||
| for.go | ||
| func1.go | ||
| func2.go | ||
| func3.go | ||
| func4.go | ||
| func5.go | ||
| func6.go | ||
| func7.go | ||
| func8.go | ||
| func.go | ||
| funcdup2.go | ||
| funcdup.go | ||
| gc1.go | ||
| gc2.go | ||
| gc.go | ||
| gcstring.go | ||
| goprint.go | ||
| goprint.out | ||
| goto.go | ||
| helloworld.go | ||
| helloworld.out | ||
| if.go | ||
| import1.go | ||
| import2.go | ||
| import4.go | ||
| import5.go | ||
| import.go | ||
| index0.go | ||
| index1.go | ||
| index2.go | ||
| index.go | ||
| indirect1.go | ||
| indirect.go | ||
| init1.go | ||
| init.go | ||
| initcomma.go | ||
| initialize.go | ||
| initializerr.go | ||
| inline.go | ||
| int_lit.go | ||
| intcvt.go | ||
| iota.go | ||
| label1.go | ||
| label.go | ||
| linkx_run.go | ||
| linkx.go | ||
| literal.go | ||
| live1.go | ||
| live2.go | ||
| live.go | ||
| mallocfin.go | ||
| map1.go | ||
| map.go | ||
| maplinear.go | ||
| method1.go | ||
| method2.go | ||
| method3.go | ||
| method4.go | ||
| method5.go | ||
| method.go | ||
| named1.go | ||
| named.go | ||
| nil.go | ||
| nilcheck.go | ||
| nilptr2.go | ||
| nilptr3.go | ||
| nilptr4.go | ||
| nilptr.go | ||
| nosplit.go | ||
| nul1.go | ||
| parentype.go | ||
| peano.go | ||
| print.go | ||
| print.out | ||
| printbig.go | ||
| printbig.out | ||
| range.go | ||
| recover1.go | ||
| recover2.go | ||
| recover3.go | ||
| recover4.go | ||
| recover.go | ||
| rename1.go | ||
| rename.go | ||
| reorder2.go | ||
| reorder.go | ||
| return.go | ||
| rotate0.go | ||
| rotate1.go | ||
| rotate2.go | ||
| rotate3.go | ||
| rotate.go | ||
| run.go | ||
| rune.go | ||
| runtime.go | ||
| shift1.go | ||
| shift2.go | ||
| sieve.go | ||
| sigchld.go | ||
| sigchld.out | ||
| simassign.go | ||
| sinit_run.go | ||
| sinit.go | ||
| sizeof.go | ||
| slice3.go | ||
| slice3err.go | ||
| slicecap.go | ||
| sliceopt.go | ||
| solitaire.go | ||
| stack.go | ||
| string_lit.go | ||
| stringrange.go | ||
| struct0.go | ||
| switch3.go | ||
| switch4.go | ||
| switch.go | ||
| tinyfin.go | ||
| torture.go | ||
| turing.go | ||
| typecheck.go | ||
| typeswitch1.go | ||
| typeswitch2.go | ||
| typeswitch3.go | ||
| typeswitch.go | ||
| undef.go | ||
| utf.go | ||
| varerr.go | ||
| varinit.go | ||
| writebarrier.go | ||
| zerodivide.go | ||