> This patch optimizes LongVector multiplication by inferring VPMUL[U]DQ > instruction for following IR pallets. > > > MulVL ( AndV SRC1, 0xFFFFFFFF) ( AndV SRC2, 0xFFFFFFFF) > MulVL (URShiftVL SRC1 , 32) (URShiftVL SRC2, 32) > MulVL (URShiftVL SRC1 , 32) ( AndV SRC2, 0xFFFFFFFF) > MulVL ( AndV SRC1, 0xFFFFFFFF) (URShiftVL SRC2 , 32) > MulVL (VectorCastI2X SRC1) (VectorCastI2X SRC2) > MulVL (RShiftVL SRC1 , 32) (RShiftVL 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. > > VPMUL[U]DQ 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 ...
Jatin Bhateja has refreshed the contents of this pull request, and previous commits have been removed. Incremental views are not available. The pull request now contains seven commits: - Removing target specific hooks - Merge branch 'master' of http://github.com/openjdk/jdk into JDK-8341137 - Review resoultions - Merge branch 'master' of http://github.com/openjdk/jdk into JDK-8341137 - Handle new I2L pattern, IR tests, Rewiring pattern inputs to MulVL further optimizes JIT code - Review resolutions - 8341137: Optimize long vector multiplication using x86 VPMULUDQ instruction ------------- Changes: - all: https://git.openjdk.org/jdk/pull/21244/files - new: https://git.openjdk.org/jdk/pull/21244/files/eba586b5..43320063 Webrevs: - full: https://webrevs.openjdk.org/?repo=jdk&pr=21244&range=03 - incr: https://webrevs.openjdk.org/?repo=jdk&pr=21244&range=02-03 Stats: 70 lines in 7 files changed: 3 ins; 58 del; 9 mod Patch: https://git.openjdk.org/jdk/pull/21244.diff Fetch: git fetch https://git.openjdk.org/jdk.git pull/21244/head:pull/21244 PR: https://git.openjdk.org/jdk/pull/21244
