> 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.

Xiaohong Gong has updated the pull request with a new target base due to a 
merge or a rebase. The pull request now contains three commits:

 - Merge branch 'jdk:master' to JDK-8286279
 - Wrap the offset check into a static method
 - 8286279: [vectorapi] Only check index of masked lanes if offset is out of 
array boundary for masked store


Changes: https://git.openjdk.java.net/jdk/pull/8620/files
 Webrev: https://webrevs.openjdk.java.net/?repo=jdk&pr=8620&range=02
  Stats: 216 lines in 9 files changed: 179 ins; 0 del; 37 mod
  Patch: https://git.openjdk.java.net/jdk/pull/8620.diff
  Fetch: git fetch https://git.openjdk.java.net/jdk pull/8620/head:pull/8620

PR: https://git.openjdk.java.net/jdk/pull/8620

Reply via email to