runtime: use bit-parallel operations to compute heap bit summaries

runtime: use bit-parallel operations to compute heap bit summaries

The new implementation is much faster in all cases.

name                                             old time/op  new time/op  delta
PallocBitsSummarize/Unpacked00-16                 142ns ± 1%     7ns ± 2%  -94.75%  (p=0.000 n=10+9)
PallocBitsSummarize/UnpackedFFFFFFFFFFFFFFFF-16   172ns ± 0%    24ns ± 0%  -86.02%  (p=0.000 n=9+9)
PallocBitsSummarize/UnpackedAA-16                 145ns ± 0%    32ns ± 0%  -78.16%  (p=0.000 n=8+10)
PallocBitsSummarize/UnpackedAAAAAAAAAAAAAAAA-16   172ns ± 0%    33ns ± 0%  -80.95%  (p=0.000 n=9+9)
PallocBitsSummarize/Unpacked80000000AAAAAAAA-16   162ns ± 1%    60ns ± 0%  -62.69%  (p=0.000 n=10+9)
PallocBitsSummarize/UnpackedAAAAAAAA00000001-16   163ns ± 0%    68ns ± 1%  -58.47%  (p=0.000 n=8+10)
PallocBitsSummarize/UnpackedBBBBBBBBBBBBBBBB-16   172ns ± 0%    35ns ± 0%  -79.70%  (p=0.000 n=9+9)
PallocBitsSummarize/Unpacked80000000BBBBBBBB-16   161ns ± 0%    63ns ± 0%  -60.61%  (p=0.000 n=8+10)
PallocBitsSummarize/UnpackedBBBBBBBB00000001-16   163ns ± 0%    60ns ± 0%  -63.14%  (p=0.000 n=9+10)
PallocBitsSummarize/UnpackedCCCCCCCCCCCCCCCC-16   172ns ± 0%    39ns ± 0%  -77.41%  (p=0.000 n=7+10)
PallocBitsSummarize/Unpacked4444444444444444-16   172ns ± 0%    39ns ± 0%  -77.42%  (p=0.000 n=7+10)
PallocBitsSummarize/Unpacked4040404040404040-16   173ns ± 2%    51ns ± 1%  -70.55%  (p=0.000 n=10+10)
PallocBitsSummarize/Unpacked4000400040004000-16   160ns ± 1%    53ns ± 0%  -66.78%  (p=0.000 n=10+10)
PallocBitsSummarize/Unpacked1000404044CCAAFF-16   169ns ± 1%    59ns ± 1%  -65.28%  (p=0.000 n=10+10)

Change-Id: I94daa645b76a9cf9c93edeb2058d7132216fcb72
Reviewed-on: https://go-review.googlesource.com/c/go/+/240900
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Michael Knyszek <mknyszek@google.com>