RFR: 8282221: x86 intrinsics for divideUnsigned and remainderUnsigned methods in java.lang.Integer and java.lang.Long

[Vamsi Parasa]

On Wed, 23 Feb 2022 05:43:10 GMT, Jatin Bhateja <jbhateja at openjdk.org> wrote:

>> Optimizes the divideUnsigned() and remainderUnsigned() methods in java.lang.Integer and java.lang.Long classes using x86 intrinsics. This change shows 3x improvement for Integer methods and upto 25% improvement for Long. This change also implements the DivMod optimization which fuses division and modulus operations if needed. The DivMod optimization shows 3x improvement for Integer and ~65% improvement for Long.
>
> src/hotspot/cpu/x86/x86_64.ad line 8602:
> 
>> 8600:     __ jmp(done);
>> 8601:     __ bind(neg_divisor_fastpath); 
>> 8602:     // Fastpath for divisor < 0: 
> 
> Move in macro assembly routine.

Sure, will move it to a macro assembly routine

> src/hotspot/cpu/x86/x86_64.ad line 8633:
> 
>> 8631:     __ jmp(done);
>> 8632:     __ bind(neg_divisor_fastpath);
>> 8633:     // Fastpath for divisor < 0: 
> 
> Move in macro assembly rountine.

Sure, will move it to a macro assembly routine

> src/hotspot/cpu/x86/x86_64.ad line 8902:
> 
>> 8900:     __ subl(tmp_rax, divisor);
>> 8901:     __ andnl(tmp_rax, tmp_rax, rdx);
>> 8902:     __ sarl(tmp_rax, 31);
> 
> Please move this into a macro assembly routine.

Sure, will move it to a macro assembly routine

> src/hotspot/cpu/x86/x86_64.ad line 8932:
> 
>> 8930:     // Fastpath when divisor < 0: 
>> 8931:     // remainder = dividend - (((dividend & ~(dividend - divisor)) >> (Long.SIZE - 1)) & divisor)
>> 8932:     // See Hacker's Delight (2nd ed), section 9.3 which is implemented in java.lang.Long.remainderUnsigned()
> 
> Please move it into a macro assembly routine.

Sure, will move it to a macro assembly routine

> src/hotspot/share/opto/compile.cpp line 3499:
> 
>> 3497:       Node* d = n->find_similar(Op_UDivI);
>> 3498:       if (d) {
>> 3499:         // Replace them with a fused unsigned divmod if supported
> 
> Can you explain a bit here, why can't this transformation be handled earlier ?

This is following the existing approach being used for signed DivMod

> test/micro/org/openjdk/bench/java/lang/LongDivMod.java line 75:
> 
>> 73:         }
>> 74:         return quotients;
>> 75:     }
> 
> Do we need to return quotients, since it's a field  being explicitly modified.

Will remove it.

> test/micro/org/openjdk/bench/java/lang/LongDivMod.java line 82:
> 
>> 80:             remainders[i] = Long.remainderUnsigned(dividends[i], divisors[i]);
>> 81:         }
>> 82:         return remainders;
> 
> Same as above

Will remove it.

-------------

PR: https://git.openjdk.java.net/jdk/pull/7572