IntVector.fromValues is not optimized away ?

Remi Forax forax at univ-mlv.fr
Sat May 9 18:52:12 UTC 2020


Hi all,
this may be obvious but do we agree that IntVector.fromValues is not optimized thus really create an array destroying any hope of perf ?

I'm trying to see the difference between

    public int hashCode() {
      return i1 ^ i2 ^ i3 ^ i4;
    }

and

    public int hashCode() {
      var v1 = IntVector.fromValues(IntVector.SPECIES_64, i1, i3);
      var v2 = IntVector.fromValues(IntVector.SPECIES_64, i2, i4);
      var result = v1.lanewise(VectorOperators.XOR, v2);
      return result.lane(0) ^ result.lane(1);
    }

but taking a look to the generated assembly (below), the allocation of the two arrays are still there,
too bad because the last 6 instructions are more or less what i was expecting.


  0x00007fbb383324dc:   mov    0x14(%rsi),%r11d             ;*getfield i3 {reexecute=0 rethrow=0 return_oop=0}
                                                            ; - fr.umlv.vector.VectorizedHashCode$Data::hashCode2 at 16 (line 14)
  0x00007fbb383324e0:   mov    0xc(%rsi),%ebp
  0x00007fbb383324e3:   mov    0x120(%r15),%r8
  0x00007fbb383324ea:   mov    %r8,%r10
  0x00007fbb383324ed:   add    $0x18,%r10
  0x00007fbb383324f1:   cmp    0x130(%r15),%r10
  0x00007fbb383324f8:   jae    0x00007fbb383325db
  0x00007fbb383324fe:   mov    %r10,0x120(%r15)
  0x00007fbb38332505:   prefetchw 0xc0(%r10)
  0x00007fbb3833250d:   movq   $0x1,(%r8)
  0x00007fbb38332514:   prefetchw 0x100(%r10)
  0x00007fbb3833251c:   movl   $0x70cb1,0x8(%r8)            ;   {metadata({type array int})}
  0x00007fbb38332524:   prefetchw 0x140(%r10)
  0x00007fbb3833252c:   movl   $0x2,0xc(%r8)
  0x00007fbb38332534:   prefetchw 0x180(%r10)
  0x00007fbb3833253c:   mov    %ebp,0x10(%r8)
  0x00007fbb38332540:   mov    %r11d,0x14(%r8)              ;*newarray {reexecute=0 rethrow=0 return_oop=0}
                                                            ; - java.util.Arrays::copyOf at 1 (line 3584)
                                                            ; - jdk.incubator.vector.IntVector::fromValues at 19 (line 553)
                                                            ; - fr.umlv.vector.VectorizedHashCode$Data::hashCode2 at 20 (line 14)
  0x00007fbb38332544:   mov    0x18(%rsi),%r9d
  0x00007fbb38332548:   mov    0x120(%r15),%rax             ;*invokestatic extract {reexecute=0 rethrow=0 return_oop=0}
                                                            ; - jdk.incubator.vector.Int64Vector::laneHelper at 16 (line 482)
                                                            ; - jdk.incubator.vector.Int64Vector::lane at 36 (line 476)
                                                            ; - fr.umlv.vector.VectorizedHashCode$Data::hashCode2 at 64 (line 17)
  0x00007fbb3833254f:   mov    0x10(%rsi),%ebp              ;*getfield i2 {reexecute=0 rethrow=0 return_oop=0}
                                                            ; - fr.umlv.vector.VectorizedHashCode$Data::hashCode2 at 33 (line 15)
  0x00007fbb38332552:   mov    %rax,%r10
  0x00007fbb38332555:   add    $0x18,%r10
  0x00007fbb38332559:   nopl   0x0(%rax)
  0x00007fbb38332560:   cmp    0x130(%r15),%r10
  0x00007fbb38332567:   jae    0x00007fbb3833260d
  0x00007fbb3833256d:   mov    %r10,0x120(%r15)
  0x00007fbb38332574:   prefetchw 0xc0(%r10)
  0x00007fbb3833257c:   movq   $0x1,(%rax)
  0x00007fbb38332583:   prefetchw 0x100(%r10)
  0x00007fbb3833258b:   movl   $0x70cb1,0x8(%rax)           ;   {metadata({type array int})}
  0x00007fbb38332592:   prefetchw 0x140(%r10)
  0x00007fbb3833259a:   movl   $0x2,0xc(%rax)
  0x00007fbb383325a1:   prefetchw 0x180(%r10)
  0x00007fbb383325a9:   mov    %ebp,0x10(%rax)
  0x00007fbb383325ac:   mov    %r9d,0x14(%rax)              ;*newarray {reexecute=0 rethrow=0 return_oop=0}
                                                            ; - java.util.Arrays::copyOf at 1 (line 3584)
                                                            ; - jdk.incubator.vector.IntVector::fromValues at 19 (line 553)
                                                            ; - fr.umlv.vector.VectorizedHashCode$Data::hashCode2 at 44 (line 15)
  0x00007fbb383325b0:   vmovq  0x10(%rax),%xmm0             ;*invokestatic extract {reexecute=0 rethrow=0 return_oop=0}
                                                            ; - jdk.incubator.vector.Int64Vector::laneHelper at 16 (line 482)
                                                            ; - jdk.incubator.vector.Int64Vector::lane at 36 (line 476)
                                                            ; - fr.umlv.vector.VectorizedHashCode$Data::hashCode2 at 64 (line 17)
  0x00007fbb383325b5:   vpxor  0x10(%r8),%xmm0,%xmm0        ;*invokespecial <init> {reexecute=0 rethrow=0 return_oop=0}
                                                            ; - jdk.internal.vm.vector.VectorSupport$Vector::<init>@2 (line 104)
                                                            ; - jdk.incubator.vector.Vector::<init>@2 (line 1122)
                                                            ; - jdk.incubator.vector.AbstractVector::<init>@2 (line 67)
                                                            ; - jdk.incubator.vector.IntVector::<init>@2 (line 55)
                                                            ; - jdk.incubator.vector.Int64Vector::<init>@2 (line 58)
                                                            ; - jdk.incubator.vector.Int64Vector::vectorFactory at 5 (line 169)
                                                            ; - jdk.incubator.vector.Int64Vector::vectorFactory at 2 (line 41)
                                                            ; - jdk.incubator.vector.IntVector$IntSpecies::vectorFactory at 5 (line 3718)
                                                            ; - jdk.incubator.vector.IntVector::fromValues at 22 (line 553)
                                                            ; - fr.umlv.vector.VectorizedHashCode$Data::hashCode2 at 44 (line 15)
  0x00007fbb383325bb:   vpextrd $0x1,%xmm0,%r11d
  0x00007fbb383325c1:   vmovd  %xmm0,%eax
  0x00007fbb383325c5:   xor    %r11d,%eax
  0x00007fbb383325c8:   vzeroupper 

regards,
Rémi


More information about the panama-dev mailing list