Stable sorting order for -0.0 and +0.0 for float and double.

[canonizer]

This modifies digit extraction in radix sorting to sort -0.0 and +0.0 in stable order.

[alliepiper]

@canonizer Have you looked into at the performance impact of this? If not, I can use this as a case study for my new benchmarking code, but that will probably mean this won't make the 1.11.0 release.

[alliepiper]

This implementation looks good to me, and the performance difference is negligible (<1% difference on GV100/GA100 from @canonizer's benchmarks).

Though now I'm curious whether this is actually expected behavior for users, or if it's better to just let them pre-condition their data when they want these to be treated equivalently. I'll do some polls and confirm whether or not this is something folks expect.

[alliepiper]

Looks like the stl already does stable sorts this way, so that's a nice, definitive answer :)

@canonizer Can you update the DeviceRadixSort documentation to specify this behavior, and add a regression test to test/test_device_radix_sort.cu? I'll take a look at the other backends in Thrust to see if we can provide this guarantee there, too.

[canonizer]

I will update the documentation and add the test.

[alliepiper]

@canonizer Any updates on this? I'd need to land this by Friday to make the 1.11.0 release, otherwise we can slip to 1.12.0.

Changes addressed.

[alliepiper]

This looks good to me, I'll start testing soon. Thanks Andy!

[alliepiper]

Heads up -- I rebased and squashed this to make this work with our scripts. We don't handle merging main into topic branches very well.

[alliepiper]

DVS CL: 29407401