mirror of
https://github.com/golang/go
synced 2024-11-23 04:40:09 -07:00
43d5f213e2
amd64 can shift in bits from another register instead of filling with 0/1. This pattern is helpful when implementing 128 bit shifts or arbitrary length shifts. In the standard library, it shows up in pure Go math/big. Benchmarks results on amd64 with -tags=math_big_pure_go. name old time/op new time/op delta NonZeroShifts/1/shrVU-8 4.45ns ± 3% 4.39ns ± 1% -1.28% (p=0.000 n=30+27) NonZeroShifts/1/shlVU-8 4.13ns ± 4% 4.10ns ± 2% ~ (p=0.254 n=29+28) NonZeroShifts/2/shrVU-8 5.55ns ± 1% 5.63ns ± 2% +1.42% (p=0.000 n=28+29) NonZeroShifts/2/shlVU-8 5.70ns ± 2% 5.14ns ± 1% -9.82% (p=0.000 n=29+28) NonZeroShifts/3/shrVU-8 6.79ns ± 2% 6.35ns ± 2% -6.46% (p=0.000 n=28+29) NonZeroShifts/3/shlVU-8 6.69ns ± 1% 6.25ns ± 1% -6.60% (p=0.000 n=28+27) NonZeroShifts/4/shrVU-8 7.79ns ± 2% 7.06ns ± 2% -9.48% (p=0.000 n=30+30) NonZeroShifts/4/shlVU-8 7.82ns ± 1% 7.24ns ± 1% -7.37% (p=0.000 n=28+29) NonZeroShifts/5/shrVU-8 8.90ns ± 3% 7.93ns ± 1% -10.84% (p=0.000 n=29+26) NonZeroShifts/5/shlVU-8 8.68ns ± 1% 7.92ns ± 1% -8.76% (p=0.000 n=29+29) NonZeroShifts/10/shrVU-8 14.4ns ± 1% 12.3ns ± 2% -14.79% (p=0.000 n=28+29) NonZeroShifts/10/shlVU-8 14.1ns ± 1% 11.9ns ± 2% -15.55% (p=0.000 n=28+27) NonZeroShifts/100/shrVU-8 118ns ± 1% 96ns ± 3% -18.82% (p=0.000 n=30+29) NonZeroShifts/100/shlVU-8 120ns ± 2% 98ns ± 2% -18.46% (p=0.000 n=29+28) NonZeroShifts/1000/shrVU-8 1.10µs ± 1% 0.88µs ± 2% -19.63% (p=0.000 n=29+30) NonZeroShifts/1000/shlVU-8 1.10µs ± 2% 0.88µs ± 2% -20.28% (p=0.000 n=29+28) NonZeroShifts/10000/shrVU-8 10.9µs ± 1% 8.7µs ± 1% -19.78% (p=0.000 n=28+27) NonZeroShifts/10000/shlVU-8 10.9µs ± 2% 8.7µs ± 1% -19.64% (p=0.000 n=29+27) NonZeroShifts/100000/shrVU-8 111µs ± 2% 90µs ± 2% -19.39% (p=0.000 n=28+29) NonZeroShifts/100000/shlVU-8 113µs ± 2% 90µs ± 2% -20.43% (p=0.000 n=30+27) The assembly version is still faster, unfortunately, but the gap is narrowing. Speedup from pure Go to assembly: name old time/op new time/op delta NonZeroShifts/1/shrVU-8 4.39ns ± 1% 3.45ns ± 2% -21.36% (p=0.000 n=27+29) NonZeroShifts/1/shlVU-8 4.10ns ± 2% 3.47ns ± 3% -15.42% (p=0.000 n=28+30) NonZeroShifts/2/shrVU-8 5.63ns ± 2% 3.97ns ± 0% -29.40% (p=0.000 n=29+25) NonZeroShifts/2/shlVU-8 5.14ns ± 1% 3.77ns ± 2% -26.65% (p=0.000 n=28+26) NonZeroShifts/3/shrVU-8 6.35ns ± 2% 4.79ns ± 2% -24.52% (p=0.000 n=29+29) NonZeroShifts/3/shlVU-8 6.25ns ± 1% 4.42ns ± 1% -29.29% (p=0.000 n=27+26) NonZeroShifts/4/shrVU-8 7.06ns ± 2% 5.64ns ± 1% -20.05% (p=0.000 n=30+29) NonZeroShifts/4/shlVU-8 7.24ns ± 1% 5.34ns ± 2% -26.23% (p=0.000 n=29+29) NonZeroShifts/5/shrVU-8 7.93ns ± 1% 6.56ns ± 2% -17.26% (p=0.000 n=26+30) NonZeroShifts/5/shlVU-8 7.92ns ± 1% 6.27ns ± 1% -20.79% (p=0.000 n=29+25) NonZeroShifts/10/shrVU-8 12.3ns ± 2% 10.2ns ± 2% -17.21% (p=0.000 n=29+29) NonZeroShifts/10/shlVU-8 11.9ns ± 2% 10.5ns ± 2% -12.45% (p=0.000 n=27+29) NonZeroShifts/100/shrVU-8 95.9ns ± 3% 77.7ns ± 1% -19.00% (p=0.000 n=29+30) NonZeroShifts/100/shlVU-8 97.5ns ± 2% 66.8ns ± 2% -31.47% (p=0.000 n=28+30) NonZeroShifts/1000/shrVU-8 884ns ± 2% 705ns ± 1% -20.17% (p=0.000 n=30+28) NonZeroShifts/1000/shlVU-8 880ns ± 2% 590ns ± 1% -32.96% (p=0.000 n=28+25) NonZeroShifts/10000/shrVU-8 8.74µs ± 1% 7.34µs ± 3% -15.94% (p=0.000 n=27+30) NonZeroShifts/10000/shlVU-8 8.73µs ± 1% 6.00µs ± 1% -31.25% (p=0.000 n=27+28) NonZeroShifts/100000/shrVU-8 89.6µs ± 2% 75.5µs ± 2% -15.80% (p=0.000 n=29+29) NonZeroShifts/100000/shlVU-8 89.6µs ± 2% 68.0µs ± 3% -24.09% (p=0.000 n=27+30) Change-Id: I18f58d8f5513d737d9cdf09b8f9d14011ffe3958 Reviewed-on: https://go-review.googlesource.com/c/go/+/297050 Trust: Josh Bleecher Snyder <josharian@gmail.com> Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> |
||
---|---|---|
.. | ||
abi | ||
alias3.dir | ||
bench | ||
chan | ||
closure3.dir | ||
closure5.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 | ||
typeparam | ||
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 | ||
cannotassign.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 | ||
closure5.go | ||
closure6.go | ||
closure7.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 | ||
const7.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 | ||
defererrcheck.go | ||
deferfin.go | ||
defernil.go | ||
deferprint.go | ||
deferprint.out | ||
devirt.go | ||
directive.go | ||
divide.go | ||
divmod.go | ||
embedfunc.go | ||
embedvers.go | ||
empty.go | ||
env.go | ||
eof1.go | ||
eof.go | ||
escape2.go | ||
escape2n.go | ||
escape3.go | ||
escape4.go | ||
escape5.go | ||
escape_array.go | ||
escape_calls.go | ||
escape_closure.go | ||
escape_field.go | ||
escape_goto.go | ||
escape_hash_maphash.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 | ||
initempty.go | ||
initexp.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 | ||
linkname2.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 | ||
mainsig.go | ||
makechan.go | ||
makemap.go | ||
makenew.go | ||
makeslice.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 | ||
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 | ||
reflectmethod5.go | ||
reflectmethod6.go | ||
reflectmethod7.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 | ||
typeswitch2b.go | ||
typeswitch3.go | ||
typeswitch.go | ||
uintptrescapes2.go | ||
uintptrescapes3.go | ||
uintptrescapes.go | ||
undef.go | ||
used.go | ||
utf.go | ||
varerr.go | ||
varinit.go | ||
winbatch.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
To run just tests from specified files in this directory, execute:
../bin/go run run.go -- file1.go file2.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.