mirror of
https://github.com/golang/go
synced 2024-09-29 09:24:28 -06:00
c683ab8128
This CL optimizes math.Abs to an inline ABSD instruction on ARM. The benchmark results of src/math/ show big improvements. name old time/op new time/op delta Acos-4 181ns ± 0% 182ns ± 0% +0.30% (p=0.000 n=40+40) Acosh-4 202ns ± 0% 202ns ± 0% ~ (all equal) Asin-4 163ns ± 0% 163ns ± 0% ~ (all equal) Asinh-4 242ns ± 0% 242ns ± 0% ~ (all equal) Atan-4 120ns ± 0% 121ns ± 0% +0.83% (p=0.000 n=40+40) Atanh-4 202ns ± 0% 202ns ± 0% ~ (all equal) Atan2-4 173ns ± 0% 173ns ± 0% ~ (all equal) Cbrt-4 1.06µs ± 0% 1.06µs ± 0% +0.09% (p=0.000 n=39+37) Ceil-4 72.9ns ± 0% 72.8ns ± 0% ~ (p=0.237 n=40+40) Copysign-4 13.2ns ± 0% 13.2ns ± 0% ~ (all equal) Cos-4 193ns ± 0% 183ns ± 0% -5.18% (p=0.000 n=40+40) Cosh-4 254ns ± 0% 239ns ± 0% -5.91% (p=0.000 n=40+40) Erf-4 112ns ± 0% 112ns ± 0% ~ (all equal) Erfc-4 117ns ± 0% 117ns ± 0% ~ (all equal) Erfinv-4 127ns ± 0% 127ns ± 1% ~ (p=0.492 n=40+40) Erfcinv-4 128ns ± 0% 128ns ± 0% ~ (all equal) Exp-4 212ns ± 0% 206ns ± 0% -3.05% (p=0.000 n=40+40) ExpGo-4 216ns ± 0% 209ns ± 0% -3.24% (p=0.000 n=40+40) Expm1-4 142ns ± 0% 142ns ± 0% ~ (all equal) Exp2-4 191ns ± 0% 184ns ± 0% -3.45% (p=0.000 n=40+40) Exp2Go-4 194ns ± 0% 187ns ± 0% -3.61% (p=0.000 n=40+40) Abs-4 14.4ns ± 0% 6.3ns ± 0% -56.39% (p=0.000 n=38+39) Dim-4 12.6ns ± 0% 12.6ns ± 0% ~ (all equal) Floor-4 49.6ns ± 0% 49.6ns ± 0% ~ (all equal) Max-4 27.6ns ± 0% 27.6ns ± 0% ~ (all equal) Min-4 27.0ns ± 0% 27.0ns ± 0% ~ (all equal) Mod-4 349ns ± 0% 305ns ± 1% -12.55% (p=0.000 n=33+40) Frexp-4 54.0ns ± 0% 47.1ns ± 0% -12.78% (p=0.000 n=38+38) Gamma-4 242ns ± 0% 234ns ± 0% -3.16% (p=0.000 n=36+40) Hypot-4 84.8ns ± 0% 67.8ns ± 0% -20.05% (p=0.000 n=31+35) HypotGo-4 88.5ns ± 0% 71.6ns ± 0% -19.12% (p=0.000 n=40+38) Ilogb-4 45.8ns ± 0% 38.9ns ± 0% -15.12% (p=0.000 n=40+32) J0-4 821ns ± 0% 802ns ± 0% -2.33% (p=0.000 n=33+40) J1-4 816ns ± 0% 807ns ± 0% -1.05% (p=0.000 n=40+29) Jn-4 1.67µs ± 0% 1.65µs ± 0% -1.45% (p=0.000 n=40+39) Ldexp-4 61.5ns ± 0% 54.6ns ± 0% -11.27% (p=0.000 n=40+32) Lgamma-4 188ns ± 0% 188ns ± 0% ~ (all equal) Log-4 154ns ± 0% 147ns ± 0% -4.78% (p=0.000 n=40+40) Logb-4 50.9ns ± 0% 42.7ns ± 0% -16.11% (p=0.000 n=34+39) Log1p-4 160ns ± 0% 159ns ± 0% ~ (p=0.828 n=40+40) Log10-4 173ns ± 0% 166ns ± 0% -4.05% (p=0.000 n=40+40) Log2-4 65.3ns ± 0% 58.4ns ± 0% -10.57% (p=0.000 n=37+37) Modf-4 36.4ns ± 0% 36.4ns ± 0% ~ (all equal) Nextafter32-4 36.4ns ± 0% 36.4ns ± 0% ~ (all equal) Nextafter64-4 32.7ns ± 0% 32.6ns ± 0% ~ (p=0.375 n=40+40) PowInt-4 300ns ± 0% 277ns ± 0% -7.78% (p=0.000 n=40+40) PowFrac-4 676ns ± 0% 635ns ± 0% -6.00% (p=0.000 n=40+35) Pow10Pos-4 17.6ns ± 0% 17.6ns ± 0% ~ (all equal) Pow10Neg-4 22.0ns ± 0% 22.0ns ± 0% ~ (all equal) Round-4 30.1ns ± 0% 30.1ns ± 0% ~ (all equal) RoundToEven-4 38.9ns ± 0% 38.9ns ± 0% ~ (all equal) Remainder-4 291ns ± 0% 263ns ± 0% -9.62% (p=0.000 n=40+40) Signbit-4 11.3ns ± 0% 11.3ns ± 0% ~ (all equal) Sin-4 185ns ± 0% 185ns ± 0% ~ (all equal) Sincos-4 230ns ± 0% 230ns ± 0% ~ (all equal) Sinh-4 253ns ± 0% 246ns ± 0% -2.77% (p=0.000 n=39+39) SqrtIndirect-4 41.4ns ± 0% 41.4ns ± 0% ~ (all equal) SqrtLatency-4 13.8ns ± 0% 13.8ns ± 0% ~ (all equal) SqrtIndirectLatency-4 37.0ns ± 0% 37.0ns ± 0% ~ (p=0.632 n=40+40) SqrtGoLatency-4 911ns ± 0% 911ns ± 0% +0.08% (p=0.000 n=40+40) SqrtPrime-4 13.2µs ± 0% 13.2µs ± 0% +0.01% (p=0.038 n=38+40) Tan-4 205ns ± 0% 205ns ± 0% ~ (all equal) Tanh-4 264ns ± 0% 247ns ± 0% -6.44% (p=0.000 n=39+32) Trunc-4 45.2ns ± 0% 45.2ns ± 0% ~ (all equal) Y0-4 796ns ± 0% 792ns ± 0% -0.55% (p=0.000 n=35+40) Y1-4 804ns ± 0% 797ns ± 0% -0.82% (p=0.000 n=24+40) Yn-4 1.64µs ± 0% 1.62µs ± 0% -1.27% (p=0.000 n=40+39) Float64bits-4 8.16ns ± 0% 8.16ns ± 0% +0.04% (p=0.000 n=35+40) Float64frombits-4 10.7ns ± 0% 10.7ns ± 0% ~ (all equal) Float32bits-4 7.53ns ± 0% 7.53ns ± 0% ~ (p=0.760 n=40+40) Float32frombits-4 6.91ns ± 0% 6.91ns ± 0% -0.04% (p=0.002 n=32+38) [Geo mean] 111ns 106ns -3.98% Change-Id: I54f4fd7f5160db020b430b556bde59cc0fdb996d Reviewed-on: https://go-review.googlesource.com/c/go/+/188678 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com> |
||
---|---|---|
.. | ||
alias3.dir | ||
bench | ||
chan | ||
closure3.dir | ||
codegen | ||
ddd2.dir | ||
dwarf | ||
fixedbugs | ||
import2.dir | ||
import4.dir | ||
interface | ||
intrinsic.dir | ||
ken | ||
linkname.dir | ||
method4.dir | ||
oldescape_linkname.dir | ||
retjmp.dir | ||
runtime | ||
stress | ||
syntax | ||
uintptrescapes.dir | ||
64bit.go | ||
235.go | ||
alg.go | ||
alias1.go | ||
alias2.go | ||
alias3.go | ||
alias.go | ||
align.go | ||
append1.go | ||
append.go | ||
args.go | ||
armimm.go | ||
assign1.go | ||
assign.go | ||
atomicload.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 | ||
checkbce.go | ||
clearfat.go | ||
closedchan.go | ||
closure1.go | ||
closure2.go | ||
closure3.go | ||
closure4.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 | ||
convert2.go | ||
convert3.go | ||
convert.go | ||
convlit1.go | ||
convlit.go | ||
convT2X.go | ||
copy1.go | ||
copy.go | ||
crlf.go | ||
ddd1.go | ||
ddd2.go | ||
ddd.go | ||
decl.go | ||
declbad.go | ||
defer.go | ||
deferfin.go | ||
deferprint.go | ||
deferprint.out | ||
devirt.go | ||
divide.go | ||
divmod.go | ||
empty.go | ||
env.go | ||
eof1.go | ||
eof.go | ||
escape2.go | ||
escape2n.go | ||
escape3.go | ||
escape4.go | ||
escape5.go | ||
escape_array.go | ||
escape_because.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_runtime_atomic.go | ||
escape_selfassign.go | ||
escape_slice.go | ||
escape_struct_param1.go | ||
escape_struct_param2.go | ||
escape_struct_return.go | ||
escape_sync_atomic.go | ||
escape_unsafe.go | ||
escape.go | ||
fibo.go | ||
finprofiled.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 | ||
gcgort.go | ||
gcstring.go | ||
goprint.go | ||
goprint.out | ||
goto.go | ||
heapsampling.go | ||
helloworld.go | ||
helloworld.out | ||
if.go | ||
import1.go | ||
import2.go | ||
import4.go | ||
import5.go | ||
import6.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 | ||
initloop.go | ||
inline_big.go | ||
inline_caller.go | ||
inline_callers.go | ||
inline_literal.go | ||
inline_math_bits_rotate.go | ||
inline_sync.go | ||
inline_variadic.go | ||
inline.go | ||
int_lit.go | ||
intcvt.go | ||
intrinsic_atomic.go | ||
intrinsic.go | ||
iota.go | ||
label1.go | ||
label.go | ||
linkmain_run.go | ||
linkmain.go | ||
linkname.go | ||
linkobj.go | ||
linkx_run.go | ||
linkx.go | ||
literal2.go | ||
literal.go | ||
live1.go | ||
live2.go | ||
live_syscall.go | ||
live.go | ||
locklinear.go | ||
loopbce.go | ||
makechan.go | ||
makemap.go | ||
makenew.go | ||
mallocfin.go | ||
map1.go | ||
map.go | ||
mapclear.go | ||
maplinear.go | ||
mergemul.go | ||
method1.go | ||
method2.go | ||
method3.go | ||
method4.go | ||
method5.go | ||
method6.go | ||
method7.go | ||
method.go | ||
named1.go | ||
named.go | ||
nil.go | ||
nilcheck.go | ||
nilptr2.go | ||
nilptr3.go | ||
nilptr4.go | ||
nilptr5_aix.go | ||
nilptr5_wasm.go | ||
nilptr5.go | ||
nilptr_aix.go | ||
nilptr.go | ||
nosplit.go | ||
notinheap2.go | ||
notinheap3.go | ||
notinheap.go | ||
nowritebarrier.go | ||
nul1.go | ||
oldescape2.go | ||
oldescape2n.go | ||
oldescape5.go | ||
oldescape_calls.go | ||
oldescape_closure.go | ||
oldescape_field.go | ||
oldescape_iface.go | ||
oldescape_linkname.go | ||
oldescape_param.go | ||
oldescape_struct_return.go | ||
opt_branchlikely.go | ||
parentype.go | ||
peano.go | ||
phiopt.go | ||
print.go | ||
print.out | ||
printbig.go | ||
printbig.out | ||
prove.go | ||
range.go | ||
README.md | ||
recover1.go | ||
recover2.go | ||
recover3.go | ||
recover4.go | ||
recover5.go | ||
recover.go | ||
reflectmethod1.go | ||
reflectmethod2.go | ||
reflectmethod3.go | ||
reflectmethod4.go | ||
rename1.go | ||
rename.go | ||
reorder2.go | ||
reorder.go | ||
retjmp.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 | ||
stackobj2.go | ||
stackobj3.go | ||
stackobj.go | ||
strcopy.go | ||
strength.go | ||
string_lit.go | ||
stringrange.go | ||
struct0.go | ||
switch2.go | ||
switch3.go | ||
switch4.go | ||
switch5.go | ||
switch6.go | ||
switch7.go | ||
switch.go | ||
tinyfin.go | ||
torture.go | ||
turing.go | ||
typecheck.go | ||
typecheckloop.go | ||
typeswitch1.go | ||
typeswitch2.go | ||
typeswitch3.go | ||
typeswitch.go | ||
uintptrescapes2.go | ||
uintptrescapes.go | ||
undef.go | ||
utf.go | ||
varerr.go | ||
varinit.go | ||
writebarrier.go | ||
zerodivide.go |
The test directory contains tests of the Go tool chain and runtime. It includes black box tests, regression tests, and error output tests. They are run as part of all.bash.
To run just these tests, execute:
../bin/go run run.go
Standard library tests should be written as regular Go tests in the appropriate package.
The tool chain and runtime also have regular Go tests in their packages. The main reasons to add a new test to this directory are:
- it is most naturally expressed using the test runner; or
- it is also applicable to
gccgo
and other Go tool chains.