• Ben Shi's avatar
    cmd/compile: optimize AMD64's bit wise operation · c6bf9a81
    Ben Shi authored
    Currently "arr[idx] |= 0x80" is compiled to MOVLload->BTSL->MOVLstore.
    And this CL optimizes it to a single BTSLconstmodify. Other bit wise
    operations with a direct memory operand are also implemented.
    
    1. The size of the executable bin/go decreases about 4KB, and the total size
    of pkg/linux_amd64 (excluding cmd/compile) decreases about 0.6KB.
    
    2. There a little improvement in the go1 benchmark test (excluding noise).
    name                     old time/op    new time/op    delta
    BinaryTree17-4              2.66s ± 4%     2.66s ± 3%    ~     (p=0.596 n=49+49)
    Fannkuch11-4                2.38s ± 2%     2.32s ± 2%  -2.69%  (p=0.000 n=50+50)
    FmtFprintfEmpty-4          42.7ns ± 4%    43.2ns ± 7%  +1.31%  (p=0.009 n=50+50)
    FmtFprintfString-4         71.0ns ± 5%    72.0ns ± 3%  +1.33%  (p=0.000 n=50+50)
    FmtFprintfInt-4            80.7ns ± 4%    80.6ns ± 3%    ~     (p=0.931 n=50+50)
    FmtFprintfIntInt-4          125ns ± 3%     126ns ± 4%    ~     (p=0.051 n=50+50)
    FmtFprintfPrefixedInt-4     158ns ± 1%     142ns ± 3%  -9.84%  (p=0.000 n=36+50)
    FmtFprintfFloat-4           215ns ± 4%     212ns ± 4%  -1.23%  (p=0.002 n=50+50)
    FmtManyArgs-4               519ns ± 3%     510ns ± 3%  -1.77%  (p=0.000 n=50+50)
    GobDecode-4                6.49ms ± 6%    6.52ms ± 5%    ~     (p=0.866 n=50+50)
    GobEncode-4                5.93ms ± 8%    6.01ms ± 7%    ~     (p=0.076 n=50+50)
    Gzip-4                      222ms ± 4%     224ms ± 8%  +0.80%  (p=0.001 n=50+50)
    Gunzip-4                   36.6ms ± 5%    36.4ms ± 4%    ~     (p=0.093 n=50+50)
    HTTPClientServer-4         59.1µs ± 1%    58.9µs ± 2%  -0.24%  (p=0.039 n=49+48)
    JSONEncode-4               9.23ms ± 4%    9.21ms ± 5%    ~     (p=0.244 n=50+50)
    JSONDecode-4               48.8ms ± 4%    48.7ms ± 4%    ~     (p=0.653 n=50+50)
    Mandelbrot200-4            3.81ms ± 4%    3.80ms ± 3%    ~     (p=0.834 n=50+50)
    GoParse-4                  3.20ms ± 5%    3.19ms ± 5%    ~     (p=0.494 n=50+50)
    RegexpMatchEasy0_32-4      78.1ns ± 2%    77.4ns ± 3%  -0.86%  (p=0.005 n=50+50)
    RegexpMatchEasy0_1K-4       233ns ± 3%     233ns ± 3%    ~     (p=0.074 n=50+50)
    RegexpMatchEasy1_32-4      74.2ns ± 3%    73.4ns ± 3%  -1.06%  (p=0.000 n=50+50)
    RegexpMatchEasy1_1K-4       369ns ± 2%     364ns ± 4%  -1.41%  (p=0.000 n=36+50)
    RegexpMatchMedium_32-4      109ns ± 4%     107ns ± 3%  -2.06%  (p=0.001 n=50+50)
    RegexpMatchMedium_1K-4     31.5µs ± 3%    30.8µs ± 3%  -2.20%  (p=0.000 n=50+50)
    RegexpMatchHard_32-4       1.57µs ± 3%    1.56µs ± 2%  -0.57%  (p=0.016 n=50+50)
    RegexpMatchHard_1K-4       47.4µs ± 4%    47.0µs ± 3%  -0.82%  (p=0.008 n=50+50)
    Revcomp-4                   414ms ± 7%     412ms ± 7%    ~     (p=0.285 n=50+50)
    Template-4                 64.3ms ± 4%    62.7ms ± 3%  -2.44%  (p=0.000 n=50+50)
    TimeParse-4                 316ns ± 3%     313ns ± 3%    ~     (p=0.122 n=50+50)
    TimeFormat-4                291ns ± 3%     293ns ± 3%  +0.80%  (p=0.001 n=50+50)
    [Geo mean]                 46.5µs         46.2µs       -0.81%
    
    name                     old speed      new speed      delta
    GobDecode-4               118MB/s ± 6%   118MB/s ± 5%    ~     (p=0.863 n=50+50)
    GobEncode-4               130MB/s ± 9%   128MB/s ± 8%    ~     (p=0.076 n=50+50)
    Gzip-4                   87.4MB/s ± 4%  86.8MB/s ± 7%  -0.78%  (p=0.002 n=50+50)
    Gunzip-4                  531MB/s ± 5%   533MB/s ± 4%    ~     (p=0.093 n=50+50)
    JSONEncode-4              210MB/s ± 4%   211MB/s ± 5%    ~     (p=0.247 n=50+50)
    JSONDecode-4             39.8MB/s ± 4%  39.9MB/s ± 4%    ~     (p=0.654 n=50+50)
    GoParse-4                18.1MB/s ± 5%  18.2MB/s ± 5%    ~     (p=0.493 n=50+50)
    RegexpMatchEasy0_32-4     410MB/s ± 2%   413MB/s ± 3%  +0.86%  (p=0.004 n=50+50)
    RegexpMatchEasy0_1K-4    4.39GB/s ± 3%  4.38GB/s ± 3%    ~     (p=0.063 n=50+50)
    RegexpMatchEasy1_32-4     432MB/s ± 3%   436MB/s ± 3%  +1.07%  (p=0.000 n=50+50)
    RegexpMatchEasy1_1K-4    2.77GB/s ± 2%  2.81GB/s ± 4%  +1.46%  (p=0.000 n=36+50)
    RegexpMatchMedium_32-4   9.16MB/s ± 3%  9.35MB/s ± 4%  +2.09%  (p=0.001 n=50+50)
    RegexpMatchMedium_1K-4   32.5MB/s ± 3%  33.2MB/s ± 3%  +2.25%  (p=0.000 n=50+50)
    RegexpMatchHard_32-4     20.4MB/s ± 3%  20.5MB/s ± 2%  +0.56%  (p=0.017 n=50+50)
    RegexpMatchHard_1K-4     21.6MB/s ± 4%  21.8MB/s ± 3%  +0.83%  (p=0.008 n=50+50)
    Revcomp-4                 613MB/s ± 4%   618MB/s ± 7%    ~     (p=0.152 n=48+50)
    Template-4               30.2MB/s ± 4%  30.9MB/s ± 3%  +2.49%  (p=0.000 n=50+50)
    [Geo mean]                127MB/s        128MB/s       +0.64%
    
    Change-Id: If405198283855d75697f66cf894b2bef458f620e
    Reviewed-on: https://go-review.googlesource.com/135422Reviewed-by: 's avatarKeith Randall <khr@golang.org>
    c6bf9a81
Name
Last commit
Last update
..
alias3.dir Loading commit data...
bench Loading commit data...
chan Loading commit data...
closure3.dir Loading commit data...
codegen Loading commit data...
ddd2.dir Loading commit data...
dwarf Loading commit data...
fixedbugs Loading commit data...
import2.dir Loading commit data...
import4.dir Loading commit data...
interface Loading commit data...
intrinsic.dir Loading commit data...
ken Loading commit data...
linkname.dir Loading commit data...
method4.dir Loading commit data...
retjmp.dir Loading commit data...
stress Loading commit data...
syntax Loading commit data...
uintptrescapes.dir Loading commit data...
235.go Loading commit data...
64bit.go Loading commit data...
README.md Loading commit data...
alg.go Loading commit data...
alias.go Loading commit data...
alias1.go Loading commit data...
alias2.go Loading commit data...
alias3.go Loading commit data...
align.go Loading commit data...
append.go Loading commit data...
append1.go Loading commit data...
args.go Loading commit data...
armimm.go Loading commit data...
assign.go Loading commit data...
assign1.go Loading commit data...
atomicload.go Loading commit data...
bigalg.go Loading commit data...
bigmap.go Loading commit data...
blank.go Loading commit data...
blank1.go Loading commit data...
bom.go Loading commit data...
bombad.go Loading commit data...
bounds.go Loading commit data...
chancap.go Loading commit data...
chanlinear.go Loading commit data...
char_lit.go Loading commit data...
char_lit1.go Loading commit data...
checkbce.go Loading commit data...
clearfat.go Loading commit data...
closedchan.go Loading commit data...
closure.go Loading commit data...
closure1.go Loading commit data...
closure2.go Loading commit data...
closure3.go Loading commit data...
closure4.go Loading commit data...
cmp.go Loading commit data...
cmp6.go Loading commit data...
cmplx.go Loading commit data...
cmplxdivide.c Loading commit data...
cmplxdivide.go Loading commit data...
cmplxdivide1.go Loading commit data...
complit.go Loading commit data...
complit1.go Loading commit data...
compos.go Loading commit data...
const.go Loading commit data...
const1.go Loading commit data...
const2.go Loading commit data...
const3.go Loading commit data...
const4.go Loading commit data...
const5.go Loading commit data...
const6.go Loading commit data...
convT2X.go Loading commit data...
convert.go Loading commit data...
convert1.go Loading commit data...
convert2.go Loading commit data...
convert3.go Loading commit data...
convlit.go Loading commit data...
convlit1.go Loading commit data...
copy.go Loading commit data...
copy1.go Loading commit data...
crlf.go Loading commit data...
ddd.go Loading commit data...
ddd1.go Loading commit data...
ddd2.go Loading commit data...
decl.go Loading commit data...
declbad.go Loading commit data...
defer.go Loading commit data...
deferfin.go Loading commit data...
deferprint.go Loading commit data...
deferprint.out Loading commit data...
devirt.go Loading commit data...
divide.go Loading commit data...
divmod.go Loading commit data...
empty.go Loading commit data...
env.go Loading commit data...
eof.go Loading commit data...
eof1.go Loading commit data...
escape.go Loading commit data...
escape2.go Loading commit data...
escape2n.go Loading commit data...
escape3.go Loading commit data...
escape4.go Loading commit data...
escape5.go Loading commit data...
escape_array.go Loading commit data...
escape_because.go Loading commit data...
escape_calls.go Loading commit data...
escape_closure.go Loading commit data...
escape_field.go Loading commit data...
escape_iface.go Loading commit data...
escape_indir.go Loading commit data...
escape_level.go Loading commit data...
escape_map.go Loading commit data...
escape_param.go Loading commit data...
escape_slice.go Loading commit data...
escape_struct_param1.go Loading commit data...
escape_struct_param2.go Loading commit data...
escape_struct_return.go Loading commit data...
fibo.go Loading commit data...
finprofiled.go Loading commit data...
float_lit.go Loading commit data...
float_lit2.go Loading commit data...
float_lit3.go Loading commit data...
floatcmp.go Loading commit data...
for.go Loading commit data...
func.go Loading commit data...
func1.go Loading commit data...
func2.go Loading commit data...
func3.go Loading commit data...
func4.go Loading commit data...
func5.go Loading commit data...
func6.go Loading commit data...
func7.go Loading commit data...
func8.go Loading commit data...
funcdup.go Loading commit data...
funcdup2.go Loading commit data...
gc.go Loading commit data...
gc1.go Loading commit data...
gc2.go Loading commit data...
gcgort.go Loading commit data...
gcstring.go Loading commit data...
goprint.go Loading commit data...
goprint.out Loading commit data...
goto.go Loading commit data...
heapsampling.go Loading commit data...
helloworld.go Loading commit data...
helloworld.out Loading commit data...
if.go Loading commit data...
import.go Loading commit data...
import1.go Loading commit data...
import2.go Loading commit data...
import4.go Loading commit data...
import5.go Loading commit data...
import6.go Loading commit data...
index.go Loading commit data...
index0.go Loading commit data...
index1.go Loading commit data...
index2.go Loading commit data...
indirect.go Loading commit data...
indirect1.go Loading commit data...
init.go Loading commit data...
init1.go Loading commit data...
initcomma.go Loading commit data...
initialize.go Loading commit data...
initializerr.go Loading commit data...
initloop.go Loading commit data...
inline.go Loading commit data...
inline_big.go Loading commit data...
inline_caller.go Loading commit data...
inline_callers.go Loading commit data...
inline_literal.go Loading commit data...
inline_math_bits_rotate.go Loading commit data...
inline_variadic.go Loading commit data...
int_lit.go Loading commit data...
intcvt.go Loading commit data...
intrinsic.go Loading commit data...
intrinsic_atomic.go Loading commit data...
iota.go Loading commit data...
label.go Loading commit data...
label1.go Loading commit data...
linkmain.go Loading commit data...
linkmain_run.go Loading commit data...
linkname.go Loading commit data...
linkobj.go Loading commit data...
linkx.go Loading commit data...
linkx_run.go Loading commit data...
literal.go Loading commit data...
live.go Loading commit data...
live1.go Loading commit data...
live2.go Loading commit data...
live_syscall.go Loading commit data...
locklinear.go Loading commit data...
loopbce.go Loading commit data...
makechan.go Loading commit data...
makemap.go Loading commit data...
makenew.go Loading commit data...
mallocfin.go Loading commit data...
map.go Loading commit data...
map1.go Loading commit data...
mapclear.go Loading commit data...
maplinear.go Loading commit data...
mergemul.go Loading commit data...
method.go Loading commit data...
method1.go Loading commit data...
method2.go Loading commit data...
method3.go Loading commit data...
method4.go Loading commit data...
method5.go Loading commit data...
method6.go Loading commit data...
method7.go Loading commit data...
named.go Loading commit data...
named1.go Loading commit data...
nil.go Loading commit data...
nilcheck.go Loading commit data...
nilptr.go Loading commit data...
nilptr2.go Loading commit data...
nilptr3.go Loading commit data...
nilptr3_wasm.go Loading commit data...
nilptr4.go Loading commit data...
nosplit.go Loading commit data...
notinheap.go Loading commit data...
notinheap2.go Loading commit data...
notinheap3.go Loading commit data...
nowritebarrier.go Loading commit data...
nul1.go Loading commit data...
opt_branchlikely.go Loading commit data...
parentype.go Loading commit data...
peano.go Loading commit data...
phiopt.go Loading commit data...
print.go Loading commit data...
print.out Loading commit data...
printbig.go Loading commit data...
printbig.out Loading commit data...
prove.go Loading commit data...
range.go Loading commit data...
recover.go Loading commit data...
recover1.go Loading commit data...
recover2.go Loading commit data...
recover3.go Loading commit data...
recover4.go Loading commit data...
recover5.go Loading commit data...
reflectmethod1.go Loading commit data...
reflectmethod2.go Loading commit data...
reflectmethod3.go Loading commit data...
reflectmethod4.go Loading commit data...
rename.go Loading commit data...
rename1.go Loading commit data...
reorder.go Loading commit data...
reorder2.go Loading commit data...
retjmp.go Loading commit data...
return.go Loading commit data...
rotate.go Loading commit data...
rotate0.go Loading commit data...
rotate1.go Loading commit data...
rotate2.go Loading commit data...
rotate3.go Loading commit data...
run.go Loading commit data...
rune.go Loading commit data...
runtime.go Loading commit data...
shift1.go Loading commit data...
shift2.go Loading commit data...
sieve.go Loading commit data...
sigchld.go Loading commit data...
sigchld.out Loading commit data...
simassign.go Loading commit data...
sinit.go Loading commit data...
sinit_run.go Loading commit data...
sizeof.go Loading commit data...
slice3.go Loading commit data...
slice3err.go Loading commit data...
slicecap.go Loading commit data...
sliceopt.go Loading commit data...
solitaire.go Loading commit data...
stack.go Loading commit data...
strcopy.go Loading commit data...
strength.go Loading commit data...
string_lit.go Loading commit data...
stringrange.go Loading commit data...
struct0.go Loading commit data...
switch.go Loading commit data...
switch2.go Loading commit data...
switch3.go Loading commit data...
switch4.go Loading commit data...
switch5.go Loading commit data...
switch6.go Loading commit data...
switch7.go Loading commit data...
tinyfin.go Loading commit data...
torture.go Loading commit data...
turing.go Loading commit data...
typecheck.go Loading commit data...
typecheckloop.go Loading commit data...
typeswitch.go Loading commit data...
typeswitch1.go Loading commit data...
typeswitch2.go Loading commit data...
typeswitch3.go Loading commit data...
uintptrescapes.go Loading commit data...
uintptrescapes2.go Loading commit data...
undef.go Loading commit data...
unsafereject1.go Loading commit data...
unsafereject2.go Loading commit data...
utf.go Loading commit data...
varerr.go Loading commit data...
varinit.go Loading commit data...
writebarrier.go Loading commit data...
zerodivide.go Loading commit data...