RFR: 8317763: Follow-up to AVX512 intrinsics for Arrays.sort() PR [v2]

[iaroslavski]

On Tue, 10 Oct 2023 20:04:48 GMT, Srinivas Vamsi Parasa <duke at openjdk.org> wrote:

>> In #14227, you inadvertently added an extra space at line 230 in make/modules/java.base/Lib.gmk
>> (https://github.com/openjdk/jdk/pull/14227/files#diff-c2e113e4b2661697750fd5e6dcc0908fa98563ccfb3801c8b0e3a70174041b81).
>> 
>> Can you please revert it here?
>
>> In #14227, you inadvertently added an extra space at line 230 in make/modules/java.base/Lib.gmk 
> 
> Hi Magnus (@magicus), please see the extra space fixed in the latest commit.
> 
> Thanks,
> Vamsi

Hi @vamsi-parasa,

Both methods mixedInsertionSort and insertionSort are covered by intrinsics.
But insertionSort is run on leftmnost (one) part only and on small ( < MAX_INSERTION_SORT_SIZE = 44) arrays.
Do we actually need to use intrinsics for it?

To have clear picture could you please run benchmarking to compare both cases:
current implementation and implementation with Java insertionSort only?

see changes `sort(int.class, a, Unsafe.ARRAY_INT_BASE_OFFSET, low, high, DualPivotQuicksort::insertionSort);`
->
`insertionSort(a, low, high);`

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

PR Comment: https://git.openjdk.org/jdk/pull/16124#issuecomment-1756991305