RFR: 8341137: Optimize long vector multiplication using x86 VPMULUDQ instruction [v4]

[Quan Anh Mai]

On Fri, 18 Oct 2024 02:03:21 GMT, Jatin Bhateja <jbhateja at openjdk.org> wrote:

>> This patch optimizes LongVector multiplication by inferring VPMULUDQ instruction for following IR pallets.
>>   
>> 
>>        MulL   ( And  SRC1,  0xFFFFFFFF)   ( And  SRC2,  0xFFFFFFFF) 
>>        MulL   (URShift SRC1 , 32) (URShift SRC2, 32)
>>        MulL   (URShift SRC1 , 32)  ( And  SRC2,  0xFFFFFFFF)
>>        MulL   ( And  SRC1,  0xFFFFFFFF) (URShift SRC2 , 32)
>> 
>> 
>> 
>>  A  64x64 bit multiplication produces 128 bit result, and can be performed by individually multiplying upper and lower double word of multiplier with multiplicand and assembling the partial products to compute full width result. Targets supporting vector quadword multiplication have separate instructions to compute upper and lower quadwords for 128 bit result. Therefore existing VectorAPI multiplication operator expects shape conformance between source and result vectors.
>> 
>> If upper 32 bits of quadword multiplier and multiplicand is always set to zero then result of multiplication is only dependent on the partial product of their lower double words and can be performed using unsigned 32 bit multiplication instruction with quadword saturation. Patch matches this pattern in a target dependent manner without introducing new IR node.
>>  
>> VPMULUDQ instruction performs unsigned multiplication between even numbered doubleword lanes of two long vectors and produces 64 bit result.  It has much lower latency compared to full 64 bit multiplication instruction "VPMULLQ", in addition non-AVX512DQ targets does not support direct quadword multiplication, thus we can save redundant partial product for zeroed out upper 32 bits. This results into throughput improvements on both P and E core Xeons.
>> 
>> Please find below the performance of [XXH3 hashing benchmark ](https://mail.openjdk.org/pipermail/panama-dev/2024-July/020557.html)included with the patch:-
>>  
>> 
>> Sierra Forest :-
>> ============
>> Baseline:-
>> Benchmark                                 (SIZE)   Mode  Cnt    Score   Error   Units
>> VectorXXH3HashingBenchmark.hashingKernel    1024  thrpt    2  806.228          ops/ms
>> VectorXXH3HashingBenchmark.hashingKernel    2048  thrpt    2  403.044          ops/ms
>> VectorXXH3HashingBenchmark.hashingKernel    4096  thrpt    2  200.641          ops/ms
>> VectorXXH3HashingBenchmark.hashingKernel    8192  thrpt    2  100.664          ops/ms
>> 
>> With Optimization:-
>> Benchmark                                 (SIZE)   Mode  Cnt     Score   Error   Units
>> VectorXXH3HashingBenchmark.hashingKernel   ...
>
> Jatin Bhateja has updated the pull request with a new target base due to a merge or a rebase. The pull request now contains two commits:
> 
>  - Review resolutions
>  - 8341137: Optimize long vector multiplication using x86 VPMULUDQ instruction

The issues I have with this patch are that:
- It convolutes the graph with machine-dependent nodes early in the compiling process.
- It overloads `MulVL` with alternative behaviours, it is fine now as we do not perform much analysis on this node but it would be problematic later. I think it is more preferable to have a separate IR node for this like `MulVLowIToLNode`, or have this transformation be done only just before matching, or both.

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

PR Comment: https://git.openjdk.org/jdk/pull/21244#issuecomment-2421157206