On Tue, 10 May 2022 01:23:55 GMT, Xiaohong Gong <xg...@openjdk.org> wrote:
> Checking whether the indexes of masked lanes are inside of the valid memory > boundary is necessary for masked vector memory access. However, this could be > saved if the given offset is inside of the vector range that could make sure > no IOOBE (IndexOutOfBoundaryException) happens. The masked load APIs have > saved this kind of check for common cases. And this patch did the similar > optimization for the masked vector store. > > The performance for the new added store masked benchmarks improves about > `1.83x ~ 2.62x` on a x86 system: > > Benchmark Before After Gain Units > StoreMaskedBenchmark.byteStoreArrayMask 12757.936 23291.118 1.826 ops/ms > StoreMaskedBenchmark.doubleStoreArrayMask 1520.932 3921.616 2.578 ops/ms > StoreMaskedBenchmark.floatStoreArrayMask 2713.031 7122.535 2.625 ops/ms > StoreMaskedBenchmark.intStoreArrayMask 4113.772 8220.206 1.998 ops/ms > StoreMaskedBenchmark.longStoreArrayMask 1993.986 4874.148 2.444 ops/ms > StoreMaskedBenchmark.shortStoreArrayMask 8543.593 17821.086 2.086 ops/ms > > Similar performane gain can also be observed on ARM hardware. Maybe we could use `a.length - vsp.length() > 0 && offset u< a.length - vsp.length()` which would hoist the first check outside of the loop. Thanks. ------------- PR: https://git.openjdk.java.net/jdk/pull/8620
