mirror of https://github.com/golang/go.git
dd91269b7c
Arm64 has a 32-bit CLZ instruction CLZW, which can be used for intrinsic Len32.
Function LeadingZeros32 calls Len32, with this change, the assembly code of
LeadingZeros32 becomes more concise.
Go code:
func f32(x uint32) { z = bits.LeadingZeros32(x) }
Before:
"".f32 STEXT size=32 args=0x8 locals=0x0 leaf
0x0000 00000 (test.go:7) TEXT "".f32(SB), LEAF|NOFRAME|ABIInternal, $0-8
0x0004 00004 (test.go:7) MOVWU "".x(FP), R0
0x0008 00008 ($GOROOT/src/math/bits/bits.go:30) CLZ R0, R0
0x000c 00012 ($GOROOT/src/math/bits/bits.go:30) SUB $32, R0, R0
0x0010 00016 (test.go:7) MOVD R0, "".z(SB)
0x001c 00028 (test.go:7) RET (R30)
After:
"".f32 STEXT size=32 args=0x8 locals=0x0 leaf
0x0000 00000 (test.go:7) TEXT "".f32(SB), LEAF|NOFRAME|ABIInternal, $0-8
0x0004 00004 (test.go:7) MOVWU "".x(FP), R0
0x0008 00008 ($GOROOT/src/math/bits/bits.go:30) CLZW R0, R0
0x000c 00012 (test.go:7) MOVD R0, "".z(SB)
0x0018 00024 (test.go:7) RET (R30)
Benchmarks:
name old time/op new time/op delta
LeadingZeros-8 2.53ns ± 0% 2.55ns ± 0% +0.67% (p=0.000 n=10+10)
LeadingZeros8-8 3.56ns ± 0% 3.56ns ± 0% ~ (all equal)
LeadingZeros16-8 3.55ns ± 0% 3.56ns ± 0% ~ (p=0.465 n=10+10)
LeadingZeros32-8 3.55ns ± 0% 2.96ns ± 0% -16.71% (p=0.000 n=10+7)
LeadingZeros64-8 2.53ns ± 0% 2.54ns ± 0% ~ (p=0.059 n=8+10)
Change-Id: Ie5666bb82909e341060e02ffd4e86c0e5d67e90a
Reviewed-on: https://go-review.googlesource.com/c/157000
Run-TryBot: Cherry Zhang <cherryyz@google.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 | ||
| retjmp.dir | ||
| stress | ||
| syntax | ||
| uintptrescapes.dir | ||
| 64bit.go | ||
| 235.go | ||
| README.md | ||
| alg.go | ||
| alias.go | ||
| alias1.go | ||
| alias2.go | ||
| alias3.go | ||
| align.go | ||
| append.go | ||
| append1.go | ||
| args.go | ||
| armimm.go | ||
| assign.go | ||
| assign1.go | ||
| atomicload.go | ||
| bigalg.go | ||
| bigmap.go | ||
| blank.go | ||
| blank1.go | ||
| bom.go | ||
| bombad.go | ||
| bounds.go | ||
| chancap.go | ||
| chanlinear.go | ||
| char_lit.go | ||
| char_lit1.go | ||
| checkbce.go | ||
| clearfat.go | ||
| closedchan.go | ||
| closure.go | ||
| closure1.go | ||
| closure2.go | ||
| closure3.go | ||
| closure4.go | ||
| cmp.go | ||
| cmp6.go | ||
| cmplx.go | ||
| cmplxdivide.c | ||
| cmplxdivide.go | ||
| cmplxdivide1.go | ||
| complit.go | ||
| complit1.go | ||
| compos.go | ||
| const.go | ||
| const1.go | ||
| const2.go | ||
| const3.go | ||
| const4.go | ||
| const5.go | ||
| const6.go | ||
| convT2X.go | ||
| convert.go | ||
| convert1.go | ||
| convert2.go | ||
| convert3.go | ||
| convlit.go | ||
| convlit1.go | ||
| copy.go | ||
| copy1.go | ||
| crlf.go | ||
| ddd.go | ||
| ddd1.go | ||
| ddd2.go | ||
| decl.go | ||
| declbad.go | ||
| defer.go | ||
| deferfin.go | ||
| deferprint.go | ||
| deferprint.out | ||
| devirt.go | ||
| divide.go | ||
| divmod.go | ||
| empty.go | ||
| env.go | ||
| eof.go | ||
| eof1.go | ||
| escape.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_slice.go | ||
| escape_struct_param1.go | ||
| escape_struct_param2.go | ||
| escape_struct_return.go | ||
| fibo.go | ||
| finprofiled.go | ||
| float_lit.go | ||
| float_lit2.go | ||
| float_lit3.go | ||
| floatcmp.go | ||
| for.go | ||
| func.go | ||
| func1.go | ||
| func2.go | ||
| func3.go | ||
| func4.go | ||
| func5.go | ||
| func6.go | ||
| func7.go | ||
| func8.go | ||
| funcdup.go | ||
| funcdup2.go | ||
| gc.go | ||
| gc1.go | ||
| gc2.go | ||
| gcgort.go | ||
| gcstring.go | ||
| goprint.go | ||
| goprint.out | ||
| goto.go | ||
| heapsampling.go | ||
| helloworld.go | ||
| helloworld.out | ||
| if.go | ||
| import.go | ||
| import1.go | ||
| import2.go | ||
| import4.go | ||
| import5.go | ||
| import6.go | ||
| index.go | ||
| index0.go | ||
| index1.go | ||
| index2.go | ||
| indirect.go | ||
| indirect1.go | ||
| init.go | ||
| init1.go | ||
| initcomma.go | ||
| initialize.go | ||
| initializerr.go | ||
| initloop.go | ||
| inline.go | ||
| inline_big.go | ||
| inline_caller.go | ||
| inline_callers.go | ||
| inline_literal.go | ||
| inline_math_bits_rotate.go | ||
| inline_variadic.go | ||
| int_lit.go | ||
| intcvt.go | ||
| intrinsic.go | ||
| intrinsic_atomic.go | ||
| iota.go | ||
| label.go | ||
| label1.go | ||
| linkmain.go | ||
| linkmain_run.go | ||
| linkname.go | ||
| linkobj.go | ||
| linkx.go | ||
| linkx_run.go | ||
| literal.go | ||
| literal2.go | ||
| live.go | ||
| live1.go | ||
| live2.go | ||
| live_syscall.go | ||
| locklinear.go | ||
| loopbce.go | ||
| makechan.go | ||
| makemap.go | ||
| makenew.go | ||
| mallocfin.go | ||
| map.go | ||
| map1.go | ||
| mapclear.go | ||
| maplinear.go | ||
| mergemul.go | ||
| method.go | ||
| method1.go | ||
| method2.go | ||
| method3.go | ||
| method4.go | ||
| method5.go | ||
| method6.go | ||
| method7.go | ||
| named.go | ||
| named1.go | ||
| nil.go | ||
| nilcheck.go | ||
| nilptr.go | ||
| nilptr2.go | ||
| nilptr3.go | ||
| nilptr4.go | ||
| nilptr5.go | ||
| nilptr5_aix.go | ||
| nilptr5_wasm.go | ||
| nilptr_aix.go | ||
| nosplit.go | ||
| notinheap.go | ||
| notinheap2.go | ||
| notinheap3.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 | ||
| recover.go | ||
| recover1.go | ||
| recover2.go | ||
| recover3.go | ||
| recover4.go | ||
| recover5.go | ||
| reflectmethod1.go | ||
| reflectmethod2.go | ||
| reflectmethod3.go | ||
| reflectmethod4.go | ||
| rename.go | ||
| rename1.go | ||
| reorder.go | ||
| reorder2.go | ||
| retjmp.go | ||
| return.go | ||
| rotate.go | ||
| rotate0.go | ||
| rotate1.go | ||
| rotate2.go | ||
| rotate3.go | ||
| run.go | ||
| rune.go | ||
| runtime.go | ||
| shift1.go | ||
| shift2.go | ||
| sieve.go | ||
| sigchld.go | ||
| sigchld.out | ||
| simassign.go | ||
| sinit.go | ||
| sinit_run.go | ||
| sizeof.go | ||
| slice3.go | ||
| slice3err.go | ||
| slicecap.go | ||
| sliceopt.go | ||
| solitaire.go | ||
| stack.go | ||
| stackobj.go | ||
| stackobj2.go | ||
| stackobj3.go | ||
| strcopy.go | ||
| strength.go | ||
| string_lit.go | ||
| stringrange.go | ||
| struct0.go | ||
| switch.go | ||
| switch2.go | ||
| switch3.go | ||
| switch4.go | ||
| switch5.go | ||
| switch6.go | ||
| switch7.go | ||
| tinyfin.go | ||
| torture.go | ||
| turing.go | ||
| typecheck.go | ||
| typecheckloop.go | ||
| typeswitch.go | ||
| typeswitch1.go | ||
| typeswitch2.go | ||
| typeswitch3.go | ||
| uintptrescapes.go | ||
| uintptrescapes2.go | ||
| undef.go | ||
| utf.go | ||
| varerr.go | ||
| varinit.go | ||
| writebarrier.go | ||
| zerodivide.go | ||
README.md
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
gccgoand other Go tool chains.