Cherry Zhang 6464e5dc4b cmd/compile: do not fold offset into load/store for args on ARM64 ... Args may be not at 8-byte aligned offset to SP. When the stack frame is large, folding the offset of args may cause large unaligned offsets that does not fit in a machine instruction on ARM64. Therefore disable folding offsets for args. This has small performance impact (see below). A better fix would be letting the assembler backend fix up the offset by loading it into a register if it doesn't fit into an instruction. And the compiler can simply generate large load/stores with offset. Since in most of the cases the offset is aligned or the stack frame is small, it can fit in an instruction and no fixup is needed. But this is too complicated for Go 1.8. name old time/op new time/op delta BinaryTree17-8 8.30s ± 0% 8.31s ± 0% ~ (p=0.579 n=10+10) Fannkuch11-8 6.14s ± 0% 6.18s ± 0% +0.53% (p=0.000 n=9+10) FmtFprintfEmpty-8 117ns ± 0% 117ns ± 0% ~ (all equal) FmtFprintfString-8 196ns ± 0% 197ns ± 0% +0.72% (p=0.000 n=10+10) FmtFprintfInt-8 204ns ± 0% 205ns ± 0% +0.49% (p=0.000 n=9+10) FmtFprintfIntInt-8 302ns ± 0% 307ns ± 1% +1.46% (p=0.000 n=10+10) FmtFprintfPrefixedInt-8 329ns ± 2% 326ns ± 0% ~ (p=0.083 n=10+10) FmtFprintfFloat-8 540ns ± 0% 542ns ± 0% +0.46% (p=0.000 n=8+7) FmtManyArgs-8 1.20µs ± 1% 1.19µs ± 1% -1.02% (p=0.000 n=10+10) GobDecode-8 17.3ms ± 1% 17.8ms ± 0% +2.75% (p=0.000 n=10+7) GobEncode-8 15.3ms ± 1% 15.4ms ± 0% +0.57% (p=0.004 n=9+10) Gzip-8 789ms ± 0% 803ms ± 0% +1.78% (p=0.000 n=9+10) Gunzip-8 128ms ± 0% 130ms ± 0% +1.73% (p=0.000 n=10+9) HTTPClientServer-8 202µs ± 6% 201µs ±10% ~ (p=0.739 n=10+10) JSONEncode-8 42.0ms ± 0% 42.1ms ± 0% +0.19% (p=0.028 n=10+9) JSONDecode-8 159ms ± 0% 161ms ± 0% +1.05% (p=0.000 n=9+10) Mandelbrot200-8 10.1ms ± 0% 10.1ms ± 0% -0.07% (p=0.000 n=10+9) GoParse-8 8.46ms ± 1% 8.61ms ± 1% +1.77% (p=0.000 n=10+10) RegexpMatchEasy0_32-8 227ns ± 1% 226ns ± 0% -0.35% (p=0.001 n=10+9) RegexpMatchEasy0_1K-8 1.63µs ± 0% 1.63µs ± 0% -0.13% (p=0.000 n=10+9) RegexpMatchEasy1_32-8 250ns ± 0% 249ns ± 0% -0.40% (p=0.001 n=8+9) RegexpMatchEasy1_1K-8 2.07µs ± 0% 2.08µs ± 0% +0.05% (p=0.027 n=9+9) RegexpMatchMedium_32-8 350ns ± 0% 350ns ± 0% ~ (p=0.412 n=9+8) RegexpMatchMedium_1K-8 104µs ± 0% 104µs ± 0% +0.31% (p=0.000 n=10+7) RegexpMatchHard_32-8 5.82µs ± 0% 5.82µs ± 0% ~ (p=0.937 n=9+9) RegexpMatchHard_1K-8 176µs ± 0% 176µs ± 0% +0.03% (p=0.000 n=9+8) Revcomp-8 1.36s ± 1% 1.37s ± 1% ~ (p=0.218 n=10+10) Template-8 151ms ± 1% 156ms ± 1% +3.21% (p=0.000 n=10+10) TimeParse-8 737ns ± 0% 758ns ± 2% +2.74% (p=0.000 n=10+10) TimeFormat-8 801ns ± 2% 789ns ± 1% -1.51% (p=0.000 n=10+10) [Geo mean] 142µs 143µs +0.50% Fixes #19137. Change-Id: Ib8a21ea98c0ffb2d282a586535b213cc163e1b67 Reviewed-on: https://go-review.googlesource.com/37251 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>		2017-02-21 19:39:08 +00:00
..
alias3.dir	[dev.typealias] cmd/compile: export/import test cases for type aliases	2017-01-20 05:55:53 +00:00
bench	test/bench/go1: reduce fasta data size for mips{,64}	2016-12-13 22:04:23 +00:00
chan
ddd2.dir
dwarf
fixedbugs	cmd/compile: do not fold offset into load/store for args on ARM64	2017-02-21 19:39:08 +00:00
import2.dir
import4.dir
interface	cmd/compile: do more type conversion inline	2016-11-02 21:33:03 +00:00
intrinsic.dir	cmd/compile: intrinsify Ctz, Bswap on ARM	2016-09-12 19:26:31 +00:00
ken
linkname.dir	cmd/compile: include linknames in export data	2017-02-08 20:59:45 +00:00
method4.dir
safe
stress
syntax	cmd/compile/internal/syntax: generalize error about var decls in init clauses	2017-02-13 23:15:32 +00:00
uintptrescapes.dir	cmd/compile, syscall: add //go:uintptrescapes comment, and use it	2016-07-06 20:48:41 +00:00
64bit.go
235.go
alg.go
alias1.go
alias2.go	[dev.typealias] cmd/compile: declare methods after resolving receiver type	2017-01-25 08:04:17 +00:00
alias3.go	[dev.typealias] cmd/compile: export/import test cases for type aliases	2017-01-20 05:55:53 +00:00
alias.go
append.go
args.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	cmd/compile: use len(s)<=cap(s) to remove more bounds checks	2017-02-02 17:45:58 +00:00
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	cmd/compile: fix compiler bug for constant equality comparison	2016-09-17 01:12:24 +00:00
convert1.go
convert2.go	cmd/compile: ignore struct tags when converting structs	2016-10-04 17:10:47 +00:00
convert3.go
convert.go
convlit1.go
convlit.go
convT2X.go
copy.go
crlf.go
ddd1.go	cmd/compile: improve not enough / too many arguments errors	2016-10-28 21:53:07 +00:00
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	cmd/vet: make checking example names in _test packages more robust	2016-06-28 22:09:00 +00:00
escape2.go
escape2n.go
escape3.go
escape4.go
escape5.go
escape_array.go
escape_because.go	cmd/compile: add explicit 'where' to EscStep data for explanations	2016-10-26 18:46:59 +00:00
escape_calls.go
escape_closure.go	cmd/compile/internal/syntax: establish principled position information	2017-02-15 01:33:03 +00:00
escape_field.go
escape_iface.go	cmd/compile: avoid leak of dottype expression on double assignment form	2016-10-10 12:09:16 +00:00
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
finprofiled.go
float_lit2.go	test/float_lit2: fix expressions in comment	2016-09-14 16:39:47 +00:00
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
heapsampling.go
helloworld.go
helloworld.out
if.go
import1.go
import2.go
import4.go
import5.go	cmd/compile/internal/syntax: removed gcCompat code needed to pass orig. tests	2017-02-10 01:22:30 +00:00
import6.go	cmd/compile/internal/syntax: removed gcCompat code needed to pass orig. tests	2017-02-10 01:22:30 +00:00
import.go
index0.go
index1.go
index2.go
index.go
indirect1.go
indirect.go
init1.go
init.go	cmd/compile: improve error message if init is directly invoked	2017-02-02 05:55:03 +00:00
initcomma.go
initialize.go
initializerr.go
initloop.go
inline_variadic.go	cmd/compile: generate code that type checks when inlining variadic functions	2016-11-30 19:46:00 +00:00
inline.go
int_lit.go
intcvt.go
intrinsic_atomic.go	cmd/compile: intrinsify Ctz, Bswap on ARM	2016-09-12 19:26:31 +00:00
intrinsic.go	cmd/compile: intrinsify Ctz{32,64} and Bswap{32,64} on s390x	2016-09-19 19:03:01 +00:00
iota.go
label1.go
label.go
linkmain_run.go
linkmain.go
linkname.go	cmd/compile: include linknames in export data	2017-02-08 20:59:45 +00:00
linkobj.go
linkx_run.go
linkx.go
literal.go
live1.go
live2.go	cmd/compile: mark temps with new AutoTemp flag, and use it.	2016-10-31 19:38:50 +00:00
live_syscall.go	cmd/compile: mark temps with new AutoTemp flag, and use it.	2016-10-31 19:38:50 +00:00
live.go	cmd/compile/internal/syntax: removed gcCompat code needed to pass orig. tests	2017-02-10 01:22:30 +00:00
locklinear.go	runtime: use balanced tree for addr lookup in semaphore implementation	2017-02-16 17:52:15 +00:00
loopbce.go
mallocfin.go
map1.go
map.go
maplinear.go
method1.go
method2.go	test: avoid matching file names in errcheck	2016-10-18 05:32:37 +00:00
method3.go
method4.go
method5.go
method.go
named1.go
named.go
nil.go
nilcheck.go
nilptr2.go
nilptr3.go	cmd/compile: re-enable nilcheck removal in same block	2017-02-17 19:19:59 +00:00
nilptr4.go
nilptr.go
nosplit.go	test: add mipsx case to nosplit.go	2016-12-15 22:43:28 +00:00
notinheap2.go	cmd/compile: add go:notinheap type pragma	2016-10-15 17:58:14 +00:00
notinheap.go	cmd/compile/internal/gc: inline typedcl0 and typedcl1	2017-02-01 22:52:32 +00:00
nowritebarrier.go	cmd/compile, runtime: add go:yeswritebarrierrec pragma	2016-10-15 17:58:11 +00:00
nul1.go	cmd/compile/internal/gc: enable new parser by default	2016-10-25 22:28:40 +00:00
opt_branchlikely.go	cmd/compile: insert scheduling checks on loop backedges	2017-01-09 21:01:29 +00:00
parentype.go
peano.go
phiopt.go	test: re-enable phi optimization test	2016-09-13 20:06:13 +00:00
print.go
print.out
printbig.go
printbig.out
prove.go	cmd/compile: use len(s)<=cap(s) to remove more bounds checks	2017-02-02 17:45:58 +00:00
range.go	cmd/compile: move stringtoslicebytetmp to the backend	2016-10-28 07:58:47 +00:00
recover1.go
recover2.go
recover3.go
recover4.go
recover.go
reflectmethod1.go
reflectmethod2.go
reflectmethod3.go
reflectmethod4.go
rename1.go
rename.go
reorder2.go
reorder.go	cmd/compile: Ensure left-to-right assignment	2017-02-11 21:46:21 +00:00
return.go
rotate0.go
rotate1.go
rotate2.go
rotate3.go
rotate.go
run.go	cmd/compile: insert scheduling checks on loop backedges	2017-01-09 21:01:29 +00:00
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	cmd/compile: use masks instead of branches for slicing	2016-10-27 20:22:49 +00:00
solitaire.go
stack.go
strength.go
string_lit.go
stringrange.go
struct0.go
switch2.go	cmd/compile/internal/syntax: match old parser errors and line numbers	2016-08-19 01:10:21 +00:00
switch3.go
switch4.go
switch5.go	cmd/compile/internal/syntax: removed gcCompat code needed to pass orig. tests	2017-02-10 01:22:30 +00:00
switch6.go	cmd/compile: improve error for wrong type in switch	2017-02-02 17:36:43 +00:00
switch.go
tinyfin.go
torture.go
turing.go
typecheck.go
typecheckloop.go
typeswitch1.go
typeswitch2.go	cmd/compile/internal/syntax: removed gcCompat code needed to pass orig. tests	2017-02-10 01:22:30 +00:00
typeswitch3.go
typeswitch.go
uintptrescapes2.go	cmd/compile: mark temps with new AutoTemp flag, and use it.	2016-10-31 19:38:50 +00:00
uintptrescapes.go	cmd/compile, syscall: add //go:uintptrescapes comment, and use it	2016-07-06 20:48:41 +00:00
undef.go
utf.go
varerr.go
varinit.go
writebarrier.go	cmd/compile: do not use "oaslit" for global	2017-02-07 17:23:23 +00:00
zerodivide.go	test: lock in test for _ assignment evaluation/zerodivide panic	2016-12-23 17:35:24 +00:00