正如另一个答案所指出的那样,由于case值是连续的(而不是稀疏的),因此您为各种测试生成的字节码使用了一个交换表(bytecode指令tableswitch
)。
但是,一旦JIT开始工作并将字节码编译为汇编代码,该tableswitch
指令就不会总是产生一个指针数组:有时,切换表会转换为看起来像a lookupswitch
(类似于if
/ else if
结构)的表。
对由JIT(热点JDK 1.7)生成的程序集进行反编译显示,如果在17个案例以下的情况下,它将使用一系列if / else,而在18个案例以下的情况下将使用一个指针数组(效率更高)。
使用此神奇数字18的原因似乎可以归结为MinJumpTableSize
JVM标志的默认值(在代码中的第352行附近)。
我已经在热点编译器列表中提出了这个问题,这似乎是过去测试的遗留问题。请注意,执行更多基准测试后,此默认值已在JDK 8中删除。
最后,当方法变得太长时(在我的测试中为25种以上的情况),该方法不再使用默认的JVM设置进行内联-这是此时性能下降的最可能原因。
在5种情况下,反编译后的代码如下所示(注意cmp / je / jg / jmp指令,if / goto的汇编):
[Verified Entry Point]
# {method} 'multiplyByPowerOfTen' '(DI)D' in 'javaapplication4/Test1'
# parm0: xmm0:xmm0 = double
# parm1: rdx = int
# [sp+0x20] (sp of caller)
0x00000000024f0160: mov DWORD PTR [rsp-0x6000],eax
; {no_reloc}
0x00000000024f0167: push rbp
0x00000000024f0168: sub rsp,0x10 ;*synchronization entry
; - javaapplication4.Test1::multiplyByPowerOfTen@-1 (line 56)
0x00000000024f016c: cmp edx,0x3
0x00000000024f016f: je 0x00000000024f01c3
0x00000000024f0171: cmp edx,0x3
0x00000000024f0174: jg 0x00000000024f01a5
0x00000000024f0176: cmp edx,0x1
0x00000000024f0179: je 0x00000000024f019b
0x00000000024f017b: cmp edx,0x1
0x00000000024f017e: jg 0x00000000024f0191
0x00000000024f0180: test edx,edx
0x00000000024f0182: je 0x00000000024f01cb
0x00000000024f0184: mov ebp,edx
0x00000000024f0186: mov edx,0x17
0x00000000024f018b: call 0x00000000024c90a0 ; OopMap{off=48}
;*new ; - javaapplication4.Test1::multiplyByPowerOfTen@72 (line 83)
; {runtime_call}
0x00000000024f0190: int3 ;*new ; - javaapplication4.Test1::multiplyByPowerOfTen@72 (line 83)
0x00000000024f0191: mulsd xmm0,QWORD PTR [rip+0xffffffffffffffa7] # 0x00000000024f0140
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@52 (line 62)
; {section_word}
0x00000000024f0199: jmp 0x00000000024f01cb
0x00000000024f019b: mulsd xmm0,QWORD PTR [rip+0xffffffffffffff8d] # 0x00000000024f0130
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@46 (line 60)
; {section_word}
0x00000000024f01a3: jmp 0x00000000024f01cb
0x00000000024f01a5: cmp edx,0x5
0x00000000024f01a8: je 0x00000000024f01b9
0x00000000024f01aa: cmp edx,0x5
0x00000000024f01ad: jg 0x00000000024f0184 ;*tableswitch
; - javaapplication4.Test1::multiplyByPowerOfTen@1 (line 56)
0x00000000024f01af: mulsd xmm0,QWORD PTR [rip+0xffffffffffffff81] # 0x00000000024f0138
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@64 (line 66)
; {section_word}
0x00000000024f01b7: jmp 0x00000000024f01cb
0x00000000024f01b9: mulsd xmm0,QWORD PTR [rip+0xffffffffffffff67] # 0x00000000024f0128
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@70 (line 68)
; {section_word}
0x00000000024f01c1: jmp 0x00000000024f01cb
0x00000000024f01c3: mulsd xmm0,QWORD PTR [rip+0xffffffffffffff55] # 0x00000000024f0120
;*tableswitch
; - javaapplication4.Test1::multiplyByPowerOfTen@1 (line 56)
; {section_word}
0x00000000024f01cb: add rsp,0x10
0x00000000024f01cf: pop rbp
0x00000000024f01d0: test DWORD PTR [rip+0xfffffffffdf3fe2a],eax # 0x0000000000430000
; {poll_return}
0x00000000024f01d6: ret
在18种情况下,程序集如下所示(注意使用了指针数组,并取消了所有比较的需要:jmp QWORD PTR [r8+r10*1]
直接跳转到正确的乘法)-这可能是性能提高的原因:
[Verified Entry Point]
# {method} 'multiplyByPowerOfTen' '(DI)D' in 'javaapplication4/Test1'
# parm0: xmm0:xmm0 = double
# parm1: rdx = int
# [sp+0x20] (sp of caller)
0x000000000287fe20: mov DWORD PTR [rsp-0x6000],eax
; {no_reloc}
0x000000000287fe27: push rbp
0x000000000287fe28: sub rsp,0x10 ;*synchronization entry
; - javaapplication4.Test1::multiplyByPowerOfTen@-1 (line 56)
0x000000000287fe2c: cmp edx,0x13
0x000000000287fe2f: jae 0x000000000287fe46
0x000000000287fe31: movsxd r10,edx
0x000000000287fe34: shl r10,0x3
0x000000000287fe38: movabs r8,0x287fd70 ; {section_word}
0x000000000287fe42: jmp QWORD PTR [r8+r10*1] ;*tableswitch
; - javaapplication4.Test1::multiplyByPowerOfTen@1 (line 56)
0x000000000287fe46: mov ebp,edx
0x000000000287fe48: mov edx,0x31
0x000000000287fe4d: xchg ax,ax
0x000000000287fe4f: call 0x00000000028590a0 ; OopMap{off=52}
;*new ; - javaapplication4.Test1::multiplyByPowerOfTen@202 (line 96)
; {runtime_call}
0x000000000287fe54: int3 ;*new ; - javaapplication4.Test1::multiplyByPowerOfTen@202 (line 96)
0x000000000287fe55: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe8b] # 0x000000000287fce8
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@194 (line 92)
; {section_word}
0x000000000287fe5d: jmp 0x000000000287ff16
0x000000000287fe62: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe86] # 0x000000000287fcf0
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@188 (line 90)
; {section_word}
0x000000000287fe6a: jmp 0x000000000287ff16
0x000000000287fe6f: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe81] # 0x000000000287fcf8
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@182 (line 88)
; {section_word}
0x000000000287fe77: jmp 0x000000000287ff16
0x000000000287fe7c: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe7c] # 0x000000000287fd00
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@176 (line 86)
; {section_word}
0x000000000287fe84: jmp 0x000000000287ff16
0x000000000287fe89: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe77] # 0x000000000287fd08
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@170 (line 84)
; {section_word}
0x000000000287fe91: jmp 0x000000000287ff16
0x000000000287fe96: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe72] # 0x000000000287fd10
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@164 (line 82)
; {section_word}
0x000000000287fe9e: jmp 0x000000000287ff16
0x000000000287fea0: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe70] # 0x000000000287fd18
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@158 (line 80)
; {section_word}
0x000000000287fea8: jmp 0x000000000287ff16
0x000000000287feaa: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe6e] # 0x000000000287fd20
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@152 (line 78)
; {section_word}
0x000000000287feb2: jmp 0x000000000287ff16
0x000000000287feb4: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe24] # 0x000000000287fce0
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@146 (line 76)
; {section_word}
0x000000000287febc: jmp 0x000000000287ff16
0x000000000287febe: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe6a] # 0x000000000287fd30
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@140 (line 74)
; {section_word}
0x000000000287fec6: jmp 0x000000000287ff16
0x000000000287fec8: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe68] # 0x000000000287fd38
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@134 (line 72)
; {section_word}
0x000000000287fed0: jmp 0x000000000287ff16
0x000000000287fed2: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe66] # 0x000000000287fd40
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@128 (line 70)
; {section_word}
0x000000000287feda: jmp 0x000000000287ff16
0x000000000287fedc: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe64] # 0x000000000287fd48
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@122 (line 68)
; {section_word}
0x000000000287fee4: jmp 0x000000000287ff16
0x000000000287fee6: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe62] # 0x000000000287fd50
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@116 (line 66)
; {section_word}
0x000000000287feee: jmp 0x000000000287ff16
0x000000000287fef0: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe60] # 0x000000000287fd58
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@110 (line 64)
; {section_word}
0x000000000287fef8: jmp 0x000000000287ff16
0x000000000287fefa: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe5e] # 0x000000000287fd60
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@104 (line 62)
; {section_word}
0x000000000287ff02: jmp 0x000000000287ff16
0x000000000287ff04: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe5c] # 0x000000000287fd68
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@98 (line 60)
; {section_word}
0x000000000287ff0c: jmp 0x000000000287ff16
0x000000000287ff0e: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe12] # 0x000000000287fd28
;*tableswitch
; - javaapplication4.Test1::multiplyByPowerOfTen@1 (line 56)
; {section_word}
0x000000000287ff16: add rsp,0x10
0x000000000287ff1a: pop rbp
0x000000000287ff1b: test DWORD PTR [rip+0xfffffffffd9b00df],eax # 0x0000000000230000
; {poll_return}
0x000000000287ff21: ret
最后,具有30种情况(下)的程序集看起来类似于18种情况,除了@cHao发现的movapd xmm0,xmm1
,出现在代码中间的其他情况之外-但是性能下降的最可能原因是该方法也可以内联默认的JVM设置:
[Verified Entry Point]
# {method} 'multiplyByPowerOfTen' '(DI)D' in 'javaapplication4/Test1'
# parm0: xmm0:xmm0 = double
# parm1: rdx = int
# [sp+0x20] (sp of caller)
0x0000000002524560: mov DWORD PTR [rsp-0x6000],eax
; {no_reloc}
0x0000000002524567: push rbp
0x0000000002524568: sub rsp,0x10 ;*synchronization entry
; - javaapplication4.Test1::multiplyByPowerOfTen@-1 (line 56)
0x000000000252456c: movapd xmm1,xmm0
0x0000000002524570: cmp edx,0x1f
0x0000000002524573: jae 0x0000000002524592 ;*tableswitch
; - javaapplication4.Test1::multiplyByPowerOfTen@1 (line 56)
0x0000000002524575: movsxd r10,edx
0x0000000002524578: shl r10,0x3
0x000000000252457c: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe3c] # 0x00000000025243c0
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@364 (line 118)
; {section_word}
0x0000000002524584: movabs r8,0x2524450 ; {section_word}
0x000000000252458e: jmp QWORD PTR [r8+r10*1] ;*tableswitch
; - javaapplication4.Test1::multiplyByPowerOfTen@1 (line 56)
0x0000000002524592: mov ebp,edx
0x0000000002524594: mov edx,0x31
0x0000000002524599: xchg ax,ax
0x000000000252459b: call 0x00000000024f90a0 ; OopMap{off=64}
;*new ; - javaapplication4.Test1::multiplyByPowerOfTen@370 (line 120)
; {runtime_call}
0x00000000025245a0: int3 ;*new ; - javaapplication4.Test1::multiplyByPowerOfTen@370 (line 120)
0x00000000025245a1: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe27] # 0x00000000025243d0
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@358 (line 116)
; {section_word}
0x00000000025245a9: jmp 0x0000000002524744
0x00000000025245ae: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe22] # 0x00000000025243d8
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@348 (line 114)
; {section_word}
0x00000000025245b6: jmp 0x0000000002524744
0x00000000025245bb: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe1d] # 0x00000000025243e0
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@338 (line 112)
; {section_word}
0x00000000025245c3: jmp 0x0000000002524744
0x00000000025245c8: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe18] # 0x00000000025243e8
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@328 (line 110)
; {section_word}
0x00000000025245d0: jmp 0x0000000002524744
0x00000000025245d5: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe13] # 0x00000000025243f0
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@318 (line 108)
; {section_word}
0x00000000025245dd: jmp 0x0000000002524744
0x00000000025245e2: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe0e] # 0x00000000025243f8
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@308 (line 106)
; {section_word}
0x00000000025245ea: jmp 0x0000000002524744
0x00000000025245ef: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe09] # 0x0000000002524400
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@298 (line 104)
; {section_word}
0x00000000025245f7: jmp 0x0000000002524744
0x00000000025245fc: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe04] # 0x0000000002524408
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@288 (line 102)
; {section_word}
0x0000000002524604: jmp 0x0000000002524744
0x0000000002524609: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffdff] # 0x0000000002524410
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@278 (line 100)
; {section_word}
0x0000000002524611: jmp 0x0000000002524744
0x0000000002524616: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffdfa] # 0x0000000002524418
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@268 (line 98)
; {section_word}
0x000000000252461e: jmp 0x0000000002524744
0x0000000002524623: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffd9d] # 0x00000000025243c8
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@258 (line 96)
; {section_word}
0x000000000252462b: jmp 0x0000000002524744
0x0000000002524630: movapd xmm0,xmm1
0x0000000002524634: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffe0c] # 0x0000000002524448
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@242 (line 92)
; {section_word}
0x000000000252463c: jmp 0x0000000002524744
0x0000000002524641: movapd xmm0,xmm1
0x0000000002524645: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffddb] # 0x0000000002524428
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@236 (line 90)
; {section_word}
0x000000000252464d: jmp 0x0000000002524744
0x0000000002524652: movapd xmm0,xmm1
0x0000000002524656: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffdd2] # 0x0000000002524430
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@230 (line 88)
; {section_word}
0x000000000252465e: jmp 0x0000000002524744
0x0000000002524663: movapd xmm0,xmm1
0x0000000002524667: mulsd xmm0,QWORD PTR [rip+0xfffffffffffffdc9] # 0x0000000002524438
;*dmul
; - javaapplication4.Test1::multiplyByPowerOfTen@224 (line 86)
; {section_word}
[etc.]
0x0000000002524744: add rsp,0x10
0x0000000002524748: pop rbp
0x0000000002524749: test DWORD PTR [rip+0xfffffffffde1b8b1],eax # 0x0000000000340000
; {poll_return}
0x000000000252474f: ret
switch
陈述中都将恰好有22个案例,因为这显然是最佳的解决方案。:D(请不要显示给我的线索。)