Alb*_*ymk 7 java assembly jit jvm jmh
使用jmh对以下Java代码进行基准测试:
interface MyInterface {
public int test(int i);
}
class A implements MyInterface {
public int test(int i) {
return (int)Math.sin(Math.cos(i));
}
}
@State(Scope.Thread)
public class MyBenchmark {
public MyInterface inter;
@Setup(Level.Trial)
public void init() {
inter = new A();
}
@Benchmark
public void testMethod(Blackhole sink) {
int[] res = new int[2];
res[0] = inter.test(1);
res[1] = inter.test(1);
sink.consume(res);
}
}
使用mvn package && java -XX:-UseCompressedOops -XX:CompileCommand='print, *.testMethod' -jar target/benchmarks.jar -wi 10 -i 1 -f 1,我是能够得到大会,如果我们着眼于从C2的一个(如下图所示),我们可以看到,无论是cos和sin被调用两次.
ImmutableOopMap{}pc offsets: 796 812 828 Compiled method (c2) 402 563 4 org.sample.MyBenchmark::testMethod (42 bytes)
total in heap [0x00007efd3d74fb90,0x00007efd3d7503a0] = 2064
relocation [0x00007efd3d74fcd0,0x00007efd3d74fd08] = 56
constants [0x00007efd3d74fd20,0x00007efd3d74fd40] = 32
main code [0x00007efd3d74fd40,0x00007efd3d750040] = 768
stub code [0x00007efd3d750040,0x00007efd3d750068] = 40
oops [0x00007efd3d750068,0x00007efd3d750070] = 8
metadata [0x00007efd3d750070,0x00007efd3d750080] = 16
scopes data [0x00007efd3d750080,0x00007efd3d750108] = 136
scopes pcs [0x00007efd3d750108,0x00007efd3d750358] = 592
dependencies [0x00007efd3d750358,0x00007efd3d750360] = 8
handler table [0x00007efd3d750360,0x00007efd3d750390] = 48
nul chk table [0x00007efd3d750390,0x00007efd3d7503a0] = 16
----------------------------------------------------------------------
org/sample/MyBenchmark.testMethod(Lorg/openjdk/jmh/infra/Blackhole;)V [0x00007efd3d74fd40, 0x00007efd3d750068] 808 bytes
[Constants]
0x00007efd3d74fd20 (offset: 0): 0x00000000 0x3ff0000000000000
0x00007efd3d74fd24 (offset: 4): 0x3ff00000
0x00007efd3d74fd28 (offset: 8): 0xf4f4f4f4 0xf4f4f4f4f4f4f4f4
0x00007efd3d74fd2c (offset: 12): 0xf4f4f4f4
0x00007efd3d74fd30 (offset: 16): 0xf4f4f4f4 0xf4f4f4f4f4f4f4f4
0x00007efd3d74fd34 (offset: 20): 0xf4f4f4f4
0x00007efd3d74fd38 (offset: 24): 0xf4f4f4f4 0xf4f4f4f4f4f4f4f4
0x00007efd3d74fd3c (offset: 28): 0xf4f4f4f4
Argument 0 is unknown.RIP: 0x7efd3d74fd40 Code size: 0x00000328
[Entry Point]
# {method} {0x00007efd35857f08} 'testMethod' '(Lorg/openjdk/jmh/infra/Blackhole;)V' in 'org/sample/MyBenchmark'
# this: rsi:rsi = 'org/sample/MyBenchmark'
# parm0: rdx:rdx = 'org/openjdk/jmh/infra/Blackhole'
# [sp+0x30] (sp of caller)
0x00007efd3d74fd40: cmp 0x8(%rsi),%rax ; {no_reloc}
0x00007efd3d74fd44: jne 0x7efd35c99c60 ; {runtime_call ic_miss_stub}
0x00007efd3d74fd4a: nop
0x00007efd3d74fd4c: nopl 0x0(%rax)
[Verified Entry Point]
0x00007efd3d74fd50: mov %eax,0xfffffffffffec000(%rsp)
0x00007efd3d74fd57: push %rbp
0x00007efd3d74fd58: sub $0x20,%rsp ;*synchronization entry
; - org.sample.MyBenchmark::testMethod@-1 (line 64)
0x00007efd3d74fd5c: mov %rdx,(%rsp)
0x00007efd3d74fd60: mov %rsi,%rbp
0x00007efd3d74fd63: mov 0x60(%r15),%rbx
0x00007efd3d74fd67: mov %rbx,%r10
0x00007efd3d74fd6a: add $0x1a8,%r10
0x00007efd3d74fd71: cmp 0x70(%r15),%r10
0x00007efd3d74fd75: jnb 0x7efd3d74ffcc
0x00007efd3d74fd7b: mov %r10,0x60(%r15)
0x00007efd3d74fd7f: prefetchnta 0xc0(%r10)
0x00007efd3d74fd87: movq $0x1,(%rbx)
0x00007efd3d74fd8e: prefetchnta 0x100(%r10)
0x00007efd3d74fd96: mov %rbx,%rdi
0x00007efd3d74fd99: add $0x18,%rdi
0x00007efd3d74fd9d: prefetchnta 0x140(%r10)
0x00007efd3d74fda5: prefetchnta 0x180(%r10)
0x00007efd3d74fdad: movabs $0x7efd350d9b38,%r10 ; {metadata({type array int})}
0x00007efd3d74fdb7: mov %r10,0x8(%rbx)
0x00007efd3d74fdbb: movl $0x64,0x10(%rbx)
0x00007efd3d74fdc2: mov $0x32,%ecx
0x00007efd3d74fdc7: xor %rax,%rax
0x00007efd3d74fdca: shl $0x3,%rcx
0x00007efd3d74fdce: rep stosb (%rdi) ;*newarray {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@4 (line 65)
0x00007efd3d74fdd1: mov 0x10(%rbp),%r10 ;*getfield inter {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@20 (line 67)
0x00007efd3d74fdd5: mov 0x8(%r10),%r10 ; implicit exception: dispatches to 0x00007efd3d74fffd
0x00007efd3d74fdd9: movabs $0x7efd3587f8c8,%r11 ; {metadata('org/sample/A')}
0x00007efd3d74fde3: cmp %r11,%r10
0x00007efd3d74fde6: jne 0x7efd3d74fffd ;*synchronization entry
; - org.sample.A::test@-1 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fdec: vmovsd 0xffffff2c(%rip),%xmm0 ; {section_word}
0x00007efd3d74fdf4: vmovq %xmm0,%r13
0x00007efd3d74fdf9: movabs $0x7efd35c53b33,%r10
0x00007efd3d74fe03: callq %r10 ;*invokestatic cos {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@2 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fe06: movabs $0x7efd35c5349c,%r10
0x00007efd3d74fe10: callq %r10 ;*invokestatic sin {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@5 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fe13: vcvttsd2si %xmm0,%r11d
0x00007efd3d74fe17: cmp $0x80000000,%r11d
0x00007efd3d74fe1e: jne 0x7efd3d74fe30
0x00007efd3d74fe20: sub $0x8,%rsp
0x00007efd3d74fe24: vmovsd %xmm0,(%rsp)
0x00007efd3d74fe29: callq 0x7efd35ca745b ; {runtime_call StubRoutines (2)}
0x00007efd3d74fe2e: pop %r11
0x00007efd3d74fe30: mov %r11d,0x18(%rbx) ;*iastore {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@29 (line 67)
0x00007efd3d74fe34: mov $0x1,%ebp
0x00007efd3d74fe39: jmp 0x7efd3d74fe43
0x00007efd3d74fe3b: nopl 0x0(%rax,%rax)
0x00007efd3d74fe40: mov %r11d,%ebp ;*synchronization entry
; - org.sample.A::test@-1 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fe43: vmovq %r13,%xmm0
0x00007efd3d74fe48: movabs $0x7efd35c53b33,%r10
0x00007efd3d74fe52: callq %r10 ;*invokestatic cos {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@2 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fe55: movabs $0x7efd35c5349c,%r10
0x00007efd3d74fe5f: callq %r10 ;*invokestatic sin {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@5 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fe62: vcvttsd2si %xmm0,%r11d
0x00007efd3d74fe66: cmp $0x80000000,%r11d
0x00007efd3d74fe6d: jne 0x7efd3d74fe7f
0x00007efd3d74fe6f: sub $0x8,%rsp
0x00007efd3d74fe73: vmovsd %xmm0,(%rsp)
0x00007efd3d74fe78: callq 0x7efd35ca745b ; {runtime_call StubRoutines (2)}
0x00007efd3d74fe7d: pop %r11
0x00007efd3d74fe7f: mov %r11d,0x18(%rbx,%rbp,4) ;*synchronization entry
; - org.sample.A::test@-1 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fe84: vmovq %r13,%xmm0
0x00007efd3d74fe89: movabs $0x7efd35c53b33,%r10
0x00007efd3d74fe93: callq %r10 ;*invokestatic cos {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@2 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fe96: movabs $0x7efd35c5349c,%r10
0x00007efd3d74fea0: callq %r10 ;*invokestatic sin {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@5 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fea3: vcvttsd2si %xmm0,%r11d
0x00007efd3d74fea7: cmp $0x80000000,%r11d
0x00007efd3d74feae: jne 0x7efd3d74fec0
0x00007efd3d74feb0: sub $0x8,%rsp
0x00007efd3d74feb4: vmovsd %xmm0,(%rsp)
0x00007efd3d74feb9: callq 0x7efd35ca745b ; {runtime_call StubRoutines (2)}
0x00007efd3d74febe: pop %r11
0x00007efd3d74fec0: mov %r11d,0x1c(%rbx,%rbp,4) ;*synchronization entry
; - org.sample.A::test@-1 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fec5: vmovq %r13,%xmm0
0x00007efd3d74feca: movabs $0x7efd35c53b33,%r10
0x00007efd3d74fed4: callq %r10 ;*invokestatic cos {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@2 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fed7: movabs $0x7efd35c5349c,%r10
0x00007efd3d74fee1: callq %r10 ;*invokestatic sin {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@5 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74fee4: vcvttsd2si %xmm0,%r11d
0x00007efd3d74fee8: cmp $0x80000000,%r11d
0x00007efd3d74feef: jne 0x7efd3d74ff01
0x00007efd3d74fef1: sub $0x8,%rsp
0x00007efd3d74fef5: vmovsd %xmm0,(%rsp)
0x00007efd3d74fefa: callq 0x7efd35ca745b ; {runtime_call StubRoutines (2)}
0x00007efd3d74feff: pop %r11
0x00007efd3d74ff01: mov %r11d,0x20(%rbx,%rbp,4) ;*synchronization entry
; - org.sample.A::test@-1 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74ff06: vmovq %r13,%xmm0
0x00007efd3d74ff0b: movabs $0x7efd35c53b33,%r10
0x00007efd3d74ff15: callq %r10 ;*invokestatic cos {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@2 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74ff18: movabs $0x7efd35c5349c,%r10
0x00007efd3d74ff22: callq %r10 ;*invokestatic sin {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@5 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74ff25: vcvttsd2si %xmm0,%r11d
0x00007efd3d74ff29: cmp $0x80000000,%r11d
0x00007efd3d74ff30: jne 0x7efd3d74ff42
0x00007efd3d74ff32: sub $0x8,%rsp
0x00007efd3d74ff36: vmovsd %xmm0,(%rsp)
0x00007efd3d74ff3b: callq 0x7efd35ca745b ; {runtime_call StubRoutines (2)}
0x00007efd3d74ff40: pop %r11
0x00007efd3d74ff42: mov %r11d,0x24(%rbx,%rbp,4) ;*iastore {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@29 (line 67)
0x00007efd3d74ff47: mov %ebp,%r11d
0x00007efd3d74ff4a: add $0x4,%r11d ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@30 (line 66)
0x00007efd3d74ff4e: cmp $0x61,%r11d
0x00007efd3d74ff52: jl 0x7efd3d74fe40 ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@13 (line 66)
0x00007efd3d74ff58: cmp $0x64,%r11d
0x00007efd3d74ff5c: jnl 0x7efd3d74ffac
0x00007efd3d74ff5e: add $0x4,%ebp ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@30 (line 66)
0x00007efd3d74ff61: nop ;*synchronization entry
; - org.sample.A::test@-1 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74ff64: vmovq %r13,%xmm0
0x00007efd3d74ff69: movabs $0x7efd35c53b33,%r10
0x00007efd3d74ff73: callq %r10 ;*invokestatic cos {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@2 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74ff76: movabs $0x7efd35c5349c,%r10
0x00007efd3d74ff80: callq %r10 ;*invokestatic sin {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.A::test@5 (line 49)
; - org.sample.MyBenchmark::testMethod@24 (line 67)
0x00007efd3d74ff83: vcvttsd2si %xmm0,%r10d
0x00007efd3d74ff87: cmp $0x80000000,%r10d
0x00007efd3d74ff8e: jne 0x7efd3d74ffa0
0x00007efd3d74ff90: sub $0x8,%rsp
0x00007efd3d74ff94: vmovsd %xmm0,(%rsp)
0x00007efd3d74ff99: callq 0x7efd35ca745b ; {runtime_call StubRoutines (2)}
0x00007efd3d74ff9e: pop %r10
0x00007efd3d74ffa0: mov %r10d,0x18(%rbx,%rbp,4) ;*iastore {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@29 (line 67)
0x00007efd3d74ffa5: incl %ebp ;*iinc {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@30 (line 66)
0x00007efd3d74ffa7: cmp $0x64,%ebp
0x00007efd3d74ffaa: jl 0x7efd3d74ff64
0x00007efd3d74ffac: mov (%rsp),%rsi
0x00007efd3d74ffb0: test %rsi,%rsi
0x00007efd3d74ffb3: je 0x7efd3d74ffe8 ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@13 (line 66)
0x00007efd3d74ffb5: mov %rbx,%rdx
0x00007efd3d74ffb8: nop
0x00007efd3d74ffbb: callq 0x7efd362c50e0 ; ImmutableOopMap{}
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@38 (line 69)
; {optimized virtual_call}
0x00007efd3d74ffc0: add $0x20,%rsp
0x00007efd3d74ffc4: pop %rbp
0x00007efd3d74ffc5: test %eax,0x18f98035(%rip) ; {poll_return}
0x00007efd3d74ffcb: retq
0x00007efd3d74ffcc: mov $0x64,%edx
0x00007efd3d74ffd1: movabs $0x7efd350d9b38,%rsi ; {metadata({type array int})}
0x00007efd3d74ffdb: callq 0x7efd35d5fd60 ; ImmutableOopMap{rbp=Oop [0]=Oop }
;*newarray {reexecute=0 rethrow=0 return_oop=1}
; - org.sample.MyBenchmark::testMethod@4 (line 65)
; {runtime_call _new_array_Java}
0x00007efd3d74ffe0: mov %rax,%rbx
0x00007efd3d74ffe3: jmpq 0x7efd3d74fdd1
0x00007efd3d74ffe8: mov $0xfffffff6,%esi
0x00007efd3d74ffed: mov %rbx,%rbp
0x00007efd3d74fff0: nop
0x00007efd3d74fff3: callq 0x7efd35c9b560 ; ImmutableOopMap{rbp=Oop }
;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@38 (line 69)
; {runtime_call UncommonTrapBlob}
0x00007efd3d74fff8: callq 0x7efd55167aa0 ; {runtime_call}
0x00007efd3d74fffd: mov $0xffffff86,%esi
0x00007efd3d750002: mov %rbx,0x8(%rsp)
0x00007efd3d750007: callq 0x7efd35c9b560 ; ImmutableOopMap{rbp=Oop [0]=Oop [8]=Oop }
;*aload_3 {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@16 (line 67)
; {runtime_call UncommonTrapBlob}
0x00007efd3d75000c: callq 0x7efd55167aa0 ;*newarray {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@4 (line 65)
; {runtime_call}
0x00007efd3d750011: mov %rax,%rsi
0x00007efd3d750014: jmp 0x7efd3d750019
0x00007efd3d750016: mov %rax,%rsi ;*invokevirtual consume {reexecute=0 rethrow=0 return_oop=0}
; - org.sample.MyBenchmark::testMethod@38 (line 69)
0x00007efd3d750019: add $0x20,%rsp
0x00007efd3d75001d: pop %rbp
0x00007efd3d75001e: jmpq 0x7efd35d64160 ; {runtime_call _rethrow_Java}
0x00007efd3d750023: hlt
0x00007efd3d750024: hlt
0x00007efd3d750025: hlt
0x00007efd3d750026: hlt
0x00007efd3d750027: hlt
0x00007efd3d750028: hlt
0x00007efd3d750029: hlt
0x00007efd3d75002a: hlt
0x00007efd3d75002b: hlt
0x00007efd3d75002c: hlt
0x00007efd3d75002d: hlt
0x00007efd3d75002e: hlt
0x00007efd3d75002f: hlt
0x00007efd3d750030: hlt
0x00007efd3d750031: hlt
0x00007efd3d750032: hlt
0x00007efd3d750033: hlt
0x00007efd3d750034: hlt
0x00007efd3d750035: hlt
0x00007efd3d750036: hlt
0x00007efd3d750037: hlt
0x00007efd3d750038: hlt
0x00007efd3d750039: hlt
0x00007efd3d75003a: hlt
0x00007efd3d75003b: hlt
0x00007efd3d75003c: hlt
0x00007efd3d75003d: hlt
0x00007efd3d75003e: hlt
0x00007efd3d75003f: hlt
我期待结果来自inter.test缓存或某种东西,以便inter.test(sin和cos)只被调用一次.我可以使用任何选项让JVM(JIT)这样做吗？或者是什么阻止JVM(JIT)看到该方法是纯粹的？
ENV:
$ java -version
openjdk version "9-internal"
OpenJDK Runtime Environment (build 9-internal+0-2016-04-14-195246.buildd.src)
OpenJDK 64-Bit Server VM (build 9-internal+0-2016-04-14-195246.buildd.src, mixed mode)
# jmh version
<jmh.version>1.19</jmh.version>
Bee*_*ope 11
据我所知,HotSpot不能优化对纯方法的冗余调用(即调用具有相同参数的纯方法),除非间接通过内联.
也就是说,如果在调用站点处全部内联对纯方法的冗余调用,则通过常规优化(例如CSE和GVN)间接地在内联代码中检测冗余,并且以这种方式,额外调用的成本通常消失.但是,如果没有内联方法,我认为JVM不会将它们标记为"纯",因此无法消除它们(例如,不像许多本机编译器那样).
仍然认为内联可以删除多余的调用,问题仍然存在:为什么不冗余Math.sin并Math.cos调用内联并最终优化掉？
事实证明,Math.sin并且Math.cos,像MathJDK中的其他几个方法一样,特别是作为内部函数处理.下面你将详细了解Java 8和某些版本的Java 9中发生的情况.你展示的反汇编来自Java 9的更高版本,它以不同的方式处理这个问题,最后介绍了这一点.
在JVM中处理trig方法的方式很复杂.原则上,Math.sin并且Math.cos在x86上使用本机FP指令作为内在方法内联,但有一些警告.
您的基准测试中有许多无关紧要的因素会使分析变得更难,例如数组分配,调用Blackhole.consume,使用Math.sin和Math.cos传递常量(这可能导致某些trig指令被完全优化),接口的使用和该接口A的实现等.
相反,让我们删除那个残余并将其缩小为更简单的版本,只Math.sin(x)使用相同的参数调用三次,并返回总和:
private double i = Math.PI / 4 - 0.01;
@Benchmark
public double testMethod() {
double res0 = Math.sin(i);
double res1 = Math.sin(i);
double res2 = Math.sin(i);
return res0 + res1 + res2;
}
使用JHM args运行时,-bm avgt -tu ns -wi 5 -f 1 -i 5我得到大约40 ns/op,这是fsin现代x86硬件上单个调用的低端范围.我们来看看大会:
[Constants]
0x00007ff2e4dbbd20 (offset: 0): 0x54442d18 0x3fe921fb54442d18
0x00007ff2e4dbbd24 (offset: 4): 0x3fe921fb
0x00007ff2e4dbbd28 (offset: 8): 0xf4f4f4f4 0xf4f4f4f4f4f4f4f4
0x00007ff2e4dbbd2c (offset: 12): 0xf4f4f4f4
0x00007ff2e4dbbd30 (offset: 16): 0xf4f4f4f4 0xf4f4f4f4f4f4f4f4
0x00007ff2e4dbbd34 (offset: 20): 0xf4f4f4f4
0x00007ff2e4dbbd38 (offset: 24): 0xf4f4f4f4 0xf4f4f4f4f4f4f4f4
0x00007ff2e4dbbd3c (offset: 28): 0xf4f4f4f4
(snip)
[Verified Entry Point]
0x00007ff2e4dbbd50: sub $0x28,%rsp
0x00007ff2e4dbbd57: mov %rbp,0x20(%rsp) ;*synchronization entry
; - stackoverflow.TrigBench::testMethod@-1 (line 38)
0x00007ff2e4dbbd5c: vmovsd 0x10(%rsi),%xmm2 ;*getfield i
; - stackoverflow.TrigBench::testMethod@1 (line 38)
0x00007ff2e4dbbd61: vmovapd %xmm2,%xmm1
0x00007ff2e4dbbd65: sub $0x8,%rsp
0x00007ff2e4dbbd69: vmovsd %xmm1,(%rsp)
0x00007ff2e4dbbd6e: fldl (%rsp)
0x00007ff2e4dbbd71: fsin
0x00007ff2e4dbbd73: fstpl (%rsp)
0x00007ff2e4dbbd76: vmovsd (%rsp),%xmm1
0x00007ff2e4dbbd7b: add $0x8,%rsp ;*invokestatic sin
; - stackoverflow.TrigBench::testMethod@20 (line 40)
0x00007ff2e4dbbd7f: vmovsd 0xffffff99(%rip),%xmm3 ; {section_word}
0x00007ff2e4dbbd87: vandpd 0xffe68411(%rip),%xmm2,%xmm0
; {external_word}
0x00007ff2e4dbbd8f: vucomisd %xmm0,%xmm3
0x00007ff2e4dbbd93: jnb 0x7ff2e4dbbe4c
0x00007ff2e4dbbd99: vmovq %xmm3,%r13
0x00007ff2e4dbbd9e: vmovq %xmm1,%rbp
0x00007ff2e4dbbda3: vmovq %xmm2,%rbx
0x00007ff2e4dbbda8: vmovapd %xmm2,%xmm0
0x00007ff2e4dbbdac: movabs $0x7ff2f9abaeec,%r10
0x00007ff2e4dbbdb6: callq %r10
0x00007ff2e4dbbdb9: vmovq %xmm0,%r14
0x00007ff2e4dbbdbe: vmovq %rbx,%xmm2
0x00007ff2e4dbbdc3: vmovq %rbp,%xmm1
0x00007ff2e4dbbdc8: vmovq %r13,%xmm3
0x00007ff2e4dbbdcd: vandpd 0xffe683cb(%rip),%xmm2,%xmm0
;*invokestatic sin
; - stackoverflow.TrigBench::testMethod@4 (line 38)
; {external_word}
0x00007ff2e4dbbdd5: vucomisd %xmm0,%xmm3
0x00007ff2e4dbbdd9: jnb 0x7ff2e4dbbe56
0x00007ff2e4dbbddb: vmovq %xmm3,%r13
0x00007ff2e4dbbde0: vmovq %xmm1,%rbp
0x00007ff2e4dbbde5: vmovq %xmm2,%rbx
0x00007ff2e4dbbdea: vmovapd %xmm2,%xmm0
0x00007ff2e4dbbdee: movabs $0x7ff2f9abaeec,%r10
0x00007ff2e4dbbdf8: callq %r10
0x00007ff2e4dbbdfb: vmovsd %xmm0,(%rsp)
0x00007ff2e4dbbe00: vmovq %rbx,%xmm2
0x00007ff2e4dbbe05: vmovq %rbp,%xmm1
0x00007ff2e4dbbe0a: vmovq %r13,%xmm3 ;*invokestatic sin
; - stackoverflow.TrigBench::testMethod@12 (line 39)
0x00007ff2e4dbbe0f: vandpd 0xffe68389(%rip),%xmm2,%xmm0
;*invokestatic sin
; - stackoverflow.TrigBench::testMethod@4 (line 38)
; {external_word}
0x00007ff2e4dbbe17: vucomisd %xmm0,%xmm3
0x00007ff2e4dbbe1b: jnb 0x7ff2e4dbbe32
0x00007ff2e4dbbe1d: vmovapd %xmm2,%xmm0
0x00007ff2e4dbbe21: movabs $0x7ff2f9abaeec,%r10
0x00007ff2e4dbbe2b: callq %r10
0x00007ff2e4dbbe2e: vmovapd %xmm0,%xmm1 ;*invokestatic sin
; - stackoverflow.TrigBench::testMethod@20 (line 40)
0x00007ff2e4dbbe32: vmovq %r14,%xmm0
0x00007ff2e4dbbe37: vaddsd (%rsp),%xmm0,%xmm0
0x00007ff2e4dbbe3c: vaddsd %xmm0,%xmm1,%xmm0 ;*dadd
; - stackoverflow.TrigBench::testMethod@30 (line 41)
0x00007ff2e4dbbe40: add $0x20,%rsp
0x00007ff2e4dbbe44: pop %rbp
0x00007ff2e4dbbe45: test %eax,0x15f461b5(%rip) ; {poll_return}
0x00007ff2e4dbbe4b: retq
0x00007ff2e4dbbe4c: vmovq %xmm1,%r14
0x00007ff2e4dbbe51: jmpq 0x7ff2e4dbbdcd
0x00007ff2e4dbbe56: vmovsd %xmm1,(%rsp)
0x00007ff2e4dbbe5b: jmp 0x7ff2e4dbbe0f
在前面,我们看到生成的代码将字段加载i到x87 FP堆栈1并使用fsin指令进行计算Math.sin(i).
下一部分也很有趣:
0x00007ff2e4dbbd7f: vmovsd 0xffffff99(%rip),%xmm3 ; {section_word}
0x00007ff2e4dbbd87: vandpd 0xffe68411(%rip),%xmm2,%xmm0
; {external_word}
0x00007ff2e4dbbd8f: vucomisd %xmm0,%xmm3
0x00007ff2e4dbbd93: jnb 0x7ff2e4dbbe4c
第一条指令是加载常量0x3fe921fb54442d18,0.785398...也就是说pi / 4.第二个是使用其他常vpand量值i.然后我们将pi / 4其与结果进行比较,vpand如果后者小于或等于前者,则跳转到某处.
咦？如果你按照跳转,有一系列(冗余)vpandpd和vucomisd指令反对相同的值(并使用相同的常量vpand),这很快导致这个序列:
0x00007ff2e4dbbe32: vmovq %r14,%xmm0
0x00007ff2e4dbbe37: vaddsd (%rsp),%xmm0,%xmm0
0x00007ff2e4dbbe3c: vaddsd %xmm0,%xmm1,%xmm0 ;*dadd
...
0x00007ff2e4dbbe4b: retq
这简单地使从fsin调用返回的值(在各种跳转中r14和[rsp]在各种跳转期间被隐藏)返回三倍.
所以我们在这里看到Math.sin(i),在"跳转"的情况下已经消除了两个冗余调用,尽管消除仍然明确地将所有值加在一起,好像它们是唯一的并且做了一堆冗余and和比较指令.
如果我们不进行跳转,我们会得到callq %r10您在反汇编中显示的相同行为.
这里发生了什么？
如果我们深入研究热点JVM源代码中的inline_trig调用library_call.cpp,我们将找到启示.在这个方法的开头附近,我们看到了这一点(为简洁起见省略了一些代码):
// Rounding required? Check for argument reduction!
if (Matcher::strict_fp_requires_explicit_rounding) {
// (snip)
// Pseudocode for sin:
// if (x <= Math.PI / 4.0) {
// if (x >= -Math.PI / 4.0) return fsin(x);
// if (x >= -Math.PI / 2.0) return -fcos(x + Math.PI / 2.0);
// } else {
// if (x <= Math.PI / 2.0) return fcos(x - Math.PI / 2.0);
// }
// return StrictMath.sin(x);
// (snip)
// Actually, sticking in an 80-bit Intel value into C2 will be tough; it
// requires a special machine instruction to load it. Instead we'll try
// the 'easy' case. If we really need the extra range +/- PI/2 we'll
// probably do the math inside the SIN encoding.
// Make the merge point
RegionNode* r = new RegionNode(3);
Node* phi = new PhiNode(r, Type::DOUBLE);
// Flatten arg so we need only 1 test
Node *abs = _gvn.transform(new AbsDNode(arg));
// Node for PI/4 constant
Node *pi4 = makecon(TypeD::make(pi_4));
// Check PI/4 : abs(arg)
Node *cmp = _gvn.transform(new CmpDNode(pi4,abs));
// Check: If PI/4 < abs(arg) then go slow
Node *bol = _gvn.transform(new BoolNode( cmp, BoolTest::lt ));
// Branch either way
IfNode *iff = create_and_xform_if(control(),bol, PROB_STATIC_FREQUENT, COUNT_UNKNOWN);
set_control(opt_iff(r,iff));
// Set fast path result
phi->init_req(2, n);
// Slow path - non-blocking leaf call
Node* call = NULL;
switch (id) {
case vmIntrinsics::_dsin:
call = make_runtime_call(RC_LEAF, OptoRuntime::Math_D_D_Type(),
CAST_FROM_FN_PTR(address, SharedRuntime::dsin),
"Sin", NULL, arg, top());
break;
break;
}
基本上,trig方法有一个快速路径和慢速路径 - 如果参数sin大于Math.PI / 4我们使用慢速路径.检查涉及一个Math.abs调用,这是神秘的vandpd 0xffe68411(%rip),%xmm2,%xmm0行为:它正在清除顶部位,这是absSSE或AVX寄存器中浮点值的快速方法.
现在剩下的代码也是有道理的:我们看到的大部分代码都是优化后的三条快速路径:两条冗余fsin调用已被删除,但周围的检查没有.这可能只是优化器的一个限制:要么优化器不够强大,不能消除所有内容,要么这些内部方法的扩展发生在将它们组合在一起的优化阶段之后2.
在缓慢的路径上,我们做了一个make_runtime_call调用的东西,它显示为一个callq %r10.这是一个所谓的存根方法调用,它将在内部实现sin,包括注释中提到的"参数减少"问题.在我的系统上,慢速路径不一定比快速路径慢得多:如果在初始化时更改-为a :+i
private double i = Math.PI / 4 - 0.01;
你调用慢速路径,这对于一个单一的 Math.sin(i)通话大约需要50纳秒与40纳秒的快速路径3.优化三个冗余Math.sin(i)调用时会出现问题.正如我们从上面的来源看到的那样,callq %r10发生了三次(并且通过追踪执行路径,我们看到它们都是在第一次跳跃后才被捕获).这意味着三次调用的运行时间约为150 ns,快速路径的情况几乎是4倍.
显然,JDK runtime_call在这种情况下不能组合节点,即使它们是相同的参数.很可能runtime_call内部表示中的节点相对不透明,并且不受CSE和其他有用的优化的影响.这些调用主要用于内部扩展和一些内部JVM方法,并且实际上并不是这种类型优化的关键目标,因此这种方法似乎是合理的.
所有这些都在Java 9中随着这一变化而改变.
fsin删除了直接内联的"快速路径" .我在这里使用"快速路径"的引用是故意的:有理由相信SSE或AVX感知软件sin方法可能比x87更快,而x87 fsin在十多年里没有得到太多的爱.实际上,这一变化正在取代fsin"使用英特尔LIBM实现" 的呼吁(这里的算法正在为那些感兴趣的人带来充分的荣耀).
很好,所以也许它现在更快(也许 - OP没有提供数字,即使在请求之后,所以我们也不知道) - 但副作用是没有内联,我们总是明确地调用每个Math.sin并且Math.cos出现在源中:没有CSE发生.
您可能会将此文件作为热点错误提交,特别是因为它可以定位为回归 - 尽管我怀疑已知相同的参数重复传递给trig函数的用例非常小.即使是合法的性能错误,清楚地解释和记录也经常萎缩多年(除非你当然与甲骨文签订了付费的支持合同 - 然后萎靡不振).
1实际上是以一种愚蠢的,迂回的方式:它从内存开始[rsi + 0x10],然后从那里加载xmm2,然后一个reg-reg进入xmm1并将其存储回堆栈顶部的内存(vmovsd %xmm1,(%rsp)),最后用它将它加载到x87 FP堆栈中fldl (%rsp).当然,这可能只是装载它直接从它在原来的位置[rsp + 0x10]有一个fld!这可能会使总延迟增加5个周期或更多.
2应该注意的是,fsin这里的指令在运行时占主导地位,因此额外的东西并没有真正向运行时添加任何内容:如果将方法减少到单行,return Math.sin(i);则运行时在40ns时大致相同.
3至少对于接近的论点Math.PI / 4.在该范围之外,时序各不相同 - 对于接近pi / 2(约40ns - 与"快速路径"一样快)的值非常快,对于非常大的值通常约为65ns,这可能通过除法/ mod进行降低.
| 归档时间： |
|
| 查看次数： |
189 次 |
| 最近记录： |