Comment 3 for bug 1928508

I've ran the same test on an Intel system, to ensure we aren't introducing any regressions there. Besides basic smoke tests, the benchmarks from the description showed that the performance on Intel is not significantly affected by this patch.

halves@rotom:~$ head -n5 /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 63
model name : Intel(R) Xeon(R) CPU E5-2683 v3 @ 2.00GHz

halves@rotom:~$ .cargo/bin/hyperfine -n focal-2.31-0ubuntu9.2 'lxc exec halves-focal ./test_memcpy64 32' -n focal-patched 'lxc exec halves-focal-patched ./test_memcpy64 32'
Benchmark #1: focal-2.31-0ubuntu9.2
  Time (mean ± σ): 2.662 s ± 0.058 s [User: 53.4 ms, System: 79.6 ms]
  Range (min … max): 2.559 s … 2.718 s 10 runs

Benchmark #2: focal-patched
  Time (mean ± σ): 2.650 s ± 0.074 s [User: 61.5 ms, System: 76.1 ms]
  Range (min … max): 2.558 s … 2.759 s 10 runs

Summary
  'focal-patched' ran
    1.00 ± 0.04 times faster than 'focal-2.31-0ubuntu9.2'

halves@rotom:~$ .cargo/bin/hyperfine -n groovy-2.32-0ubuntu3 'lxc exec halves-groovy ./test_memcpy64 32' -n groovy-patched 'lxc exec halves-groovy-patched ./test_memcpy64 32'
Benchmark #1: groovy-2.32-0ubuntu3
  Time (mean ± σ): 2.643 s ± 0.044 s [User: 52.4 ms, System: 76.0 ms]
  Range (min … max): 2.575 s … 2.746 s 10 runs

Benchmark #2: groovy-patched
  Time (mean ± σ): 2.626 s ± 0.036 s [User: 63.1 ms, System: 79.7 ms]
  Range (min … max): 2.590 s … 2.701 s 10 runs

Summary
  'groovy-patched' ran
    1.01 ± 0.02 times faster than 'groovy-2.32-0ubuntu3'