RFR: 8332856: C2: Add new transform for bool eq/ne (cmp (and (urshift X const1) const2) 0) [v2]

[Jasmine Karthikeyan]

On Tue, 28 May 2024 20:11:35 GMT, Tobias Hotz <duke at openjdk.org> wrote:

>> This PR adds a new ideal optimization for the following pattern:
>> 
>> public boolean testFunc(int a) {
>>     int mask = 0b101;
>>     int shift = 12;
>>     return ((a >> shift) & mask) == 0;
>> }
>> 
>> Where the mask and shift are constant values and a is a variable. For this optimization to work, the right shift has to be idealized to a unsinged right shift earlier in the pipeline, which here: https://github.com/openjdk/jdk/blob/b92bd671835c37cff58e2cdcecd0fe4277557d7f/src/hotspot/share/opto/mulnode.cpp#L731
>> If the shift is already an unsiged bit shift, it works as well.
>> On AMD64 CPUs, this means that this whole line computation can be reduced to a simple `test` instruction.
>
> Tobias Hotz has updated the pull request incrementally with two additional commits since the last revision:
> 
>  - LF endings...
>  - Add a benchmark to measure effect of new ideal transformation

I had a chance to test the patch on a Raspberry Pi 4B (Cortex-A72 CPU), and I got these results on the attached benchmark:

                                                           Baseline                       Patch          Improvement
Benchmark                                   Mode  Cnt    Score   Error  Units     Score   Error  Units
ShiftAndCmpZeroIdeal.testConstantShiftMask  avgt    9  232.528 ± 2.385  ns/op   166.497 ± 2.292  ns/op   + 33.1%

So it does seem like there's a similar benefit there! I think it would be nice to test RISC-V as well. FWIW, it would be possible to match this pattern in the ad files with a `predicate(...)` block, like how we match `cmov(0, 1)` into a `setcc` instruction ([here](https://github.com/openjdk/jdk/blob/master/src/hotspot/cpu/x86/x86_64.ad#L6126-L6130)). Though, if the pattern is beneficial on most architectures it might be easier to keep it in the middle-end.

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

PR Comment: https://git.openjdk.org/jdk/pull/19310#issuecomment-2198280869