drcrc28428 2015-10-25 00:41
浏览 132
已采纳

Golang:提高切片性能

Why these benchmark results are so different?

func Benchmark1(b *testing.B) {
    for n := 0; n < b.N; n++ {
        _ = make([]byte, 8)
    }
}

func Benchmark2(b *testing.B) {
    length := 1
    for n := 0; n < b.N; n++ {
        _ = make([]byte, 7+length)
    }
}

Benchmark results:

Benchmark1-8                    500000000            3.37 ns/op
Benchmark2-8                    30000000            50.6 ns/op
  • 写回答

1条回答 默认 最新

  • dongqin8652 2015-10-25 05:36
    关注

    The constant expression 8 is evaluated at compile time. The make is allocated on a goroutine stack (cheap). The variable expression 7 + length is evaluated at run time. The make is allocated on the program heap (expensive). If the make size is too large for a stack allocation (for example, constant (64*1024) and variable (64*1024-1)+length) then both allocations are made on the heap and the benchmark times are the same.

    $ go tool compile -m a_test.go
    a_test.go:5: Benchmark1 b does not escape
    a_test.go:7: Benchmark1 make([]byte, 8) does not escape
    a_test.go:14: make([]byte, 7 + length) escapes to heap
    a_test.go:11: Benchmark2 b does not escape
    $ 
    

    a_test.go:

    package a
    
    import "testing"
    
    func Benchmark1(b *testing.B) {
        for n := 0; n < b.N; n++ {
            _ = make([]byte, 8)
        }
    }
    
    func Benchmark2(b *testing.B) {
        length := 1
        for n := 0; n < b.N; n++ {
            _ = make([]byte, 7+length)
        }
    }
    

    Go pseudo-assembler:

    $ go tool compile -S a_test.go
    

    Benchmark1:

    "".Benchmark1 t=1 size=112 value=0 args=0x8 locals=0x20
        0x0000 00000 (a_test.go:5)  TEXT    "".Benchmark1(SB), $32-8
        0x0000 00000 (a_test.go:5)  SUBQ    $32, SP
        0x0004 00004 (a_test.go:5)  MOVQ    "".b+40(FP), CX
        0x0009 00009 (a_test.go:5)  FUNCDATA    $0, gclocals·87d20ce1b58390b294df80b886db78bf(SB)
        0x0009 00009 (a_test.go:5)  FUNCDATA    $1, gclocals·790e5cc5051fc0affc980ade09e929ec(SB)
        0x0009 00009 (a_test.go:6)  MOVQ    $0, AX
        0x000b 00011 (a_test.go:6)  NOP
        0x000b 00011 (a_test.go:6)  MOVQ    112(CX), BX
        0x000f 00015 (a_test.go:6)  CMPQ    BX, AX
        0x0012 00018 (a_test.go:6)  JLE $0, 98
        0x0014 00020 (a_test.go:7)  MOVQ    $0, BX
        0x0016 00022 (a_test.go:7)  MOVB    BL, "".autotmp_0001(SP)
        0x0019 00025 (a_test.go:7)  MOVB    BL, "".autotmp_0001+1(SP)
        0x001d 00029 (a_test.go:7)  MOVB    BL, "".autotmp_0001+2(SP)
        0x0021 00033 (a_test.go:7)  MOVB    BL, "".autotmp_0001+3(SP)
        0x0025 00037 (a_test.go:7)  MOVB    BL, "".autotmp_0001+4(SP)
        0x0029 00041 (a_test.go:7)  MOVB    BL, "".autotmp_0001+5(SP)
        0x002d 00045 (a_test.go:7)  MOVB    BL, "".autotmp_0001+6(SP)
        0x0031 00049 (a_test.go:7)  MOVB    BL, "".autotmp_0001+7(SP)
        0x0035 00053 (a_test.go:7)  LEAQ    "".autotmp_0001(SP), BX
        0x0039 00057 (a_test.go:7)  CMPQ    BX, $0
        0x003d 00061 (a_test.go:7)  JEQ $1, 103
        0x003f 00063 (a_test.go:7)  MOVQ    $8, "".autotmp_0002+16(SP)
        0x0048 00072 (a_test.go:7)  MOVQ    $8, "".autotmp_0002+24(SP)
        0x0051 00081 (a_test.go:7)  MOVQ    BX, "".autotmp_0002+8(SP)
        0x0056 00086 (a_test.go:6)  INCQ    AX
        0x0059 00089 (a_test.go:6)  NOP
        0x0059 00089 (a_test.go:6)  MOVQ    112(CX), BX
        0x005d 00093 (a_test.go:6)  CMPQ    BX, AX
        0x0060 00096 (a_test.go:6)  JGT $0, 20
        0x0062 00098 (a_test.go:9)  ADDQ    $32, SP
        0x0066 00102 (a_test.go:9)  RET
        0x0067 00103 (a_test.go:7)  MOVL    AX, (BX)
        0x0069 00105 (a_test.go:7)  JMP 63
    

    Benchmark2:

    "".Benchmark2 t=1 size=144 value=0 args=0x8 locals=0x58
        0x0000 00000 (a_test.go:11) TEXT    "".Benchmark2(SB), $88-8
        0x0000 00000 (a_test.go:11) MOVQ    (TLS), CX
        0x0009 00009 (a_test.go:11) CMPQ    SP, 16(CX)
        0x000d 00013 (a_test.go:11) JLS 129
        0x000f 00015 (a_test.go:11) SUBQ    $88, SP
        0x0013 00019 (a_test.go:11) FUNCDATA    $0, gclocals·87d20ce1b58390b294df80b886db78bf(SB)
        0x0013 00019 (a_test.go:11) FUNCDATA    $1, gclocals·790e5cc5051fc0affc980ade09e929ec(SB)
        0x0013 00019 (a_test.go:12) MOVQ    $1, "".length+56(SP)
        0x001c 00028 (a_test.go:13) MOVQ    $0, AX
        0x001e 00030 (a_test.go:13) MOVQ    "".b+96(FP), BP
        0x0023 00035 (a_test.go:13) NOP
        0x0023 00035 (a_test.go:13) MOVQ    112(BP), BX
        0x0027 00039 (a_test.go:13) MOVQ    AX, "".n+48(SP)
        0x002c 00044 (a_test.go:13) CMPQ    BX, AX
        0x002f 00047 (a_test.go:13) JLE $0, 124
        0x0031 00049 (a_test.go:14) MOVQ    "".length+56(SP), AX
        0x0036 00054 (a_test.go:14) ADDQ    $7, AX
        0x003a 00058 (a_test.go:14) LEAQ    type.[]uint8(SB), BX
        0x0041 00065 (a_test.go:14) MOVQ    BX, (SP)
        0x0045 00069 (a_test.go:14) MOVQ    AX, 8(SP)
        0x004a 00074 (a_test.go:14) MOVQ    AX, 16(SP)
        0x004f 00079 (a_test.go:14) PCDATA  $0, $0
        0x004f 00079 (a_test.go:14) CALL    runtime.makeslice(SB)
        0x0054 00084 (a_test.go:14) MOVQ    24(SP), BX
        0x0059 00089 (a_test.go:14) MOVQ    BX, "".autotmp_0005+64(SP)
        0x005e 00094 (a_test.go:14) MOVQ    32(SP), BX
        0x0063 00099 (a_test.go:14) MOVQ    BX, "".autotmp_0005+72(SP)
        0x0068 00104 (a_test.go:14) MOVQ    40(SP), BX
        0x006d 00109 (a_test.go:14) MOVQ    BX, "".autotmp_0005+80(SP)
        0x0072 00114 (a_test.go:13) MOVQ    "".n+48(SP), AX
        0x0077 00119 (a_test.go:13) INCQ    AX
        0x007a 00122 (a_test.go:13) NOP
        0x007a 00122 (a_test.go:13) JMP 30
        0x007c 00124 (a_test.go:16) ADDQ    $88, SP
        0x0080 00128 (a_test.go:16) RET
        0x0081 00129 (a_test.go:11) CALL    runtime.morestack_noctxt(SB)
        0x0086 00134 (a_test.go:11) JMP 0
    
    本回答被题主选为最佳回答 , 对您是否有帮助呢?
    评论

报告相同问题?

悬赏问题

  • ¥20 关于#stm32#的问题,请各位专家解答!
  • ¥15 (标签-python)
  • ¥15 第一个已完成,求第二个做法
  • ¥20 搭建awx,试了很多版本都有错
  • ¥15 java corba的客户端该如何指定使用本地某个固定IP去连接服务端?
  • ¥15 activiti工作流问题,求解答
  • ¥15 有人写过RPA后台管理系统么?
  • ¥15 Bioage计算生物学年龄
  • ¥20 如何将FPGA Alveo U50恢复原来出厂设置哇?
  • ¥50 cocos2d-x lua 在mac上接入lua protobuf?