feat(xtask): run AArch64 QEMU with max CPU type instead of Cortex-A72

[mkroening]

This PR works around #2543 by explicitly disabling LPA2 but otherwise enables QEMU's max CPU type.

This enables the ARM v8.5 RNG, for example. For details, see #2528.

[github-actions]

Benchmark Results

Details

Benchmark	Current: 24ada90	Previous: 496a427	Performance Ratio
startup_benchmark Build Time	82.69 s	80.41 s	1.03 ❗
startup_benchmark File Size	0.80 MB	0.80 MB	1.00 ❗
Startup Time - 1 core	0.73 s (±0.02 s)	0.73 s (±0.02 s)	0.99
Startup Time - 2 cores	0.74 s (±0.03 s)	0.73 s (±0.02 s)	1.01
Startup Time - 4 cores	0.74 s (±0.02 s)	0.74 s (±0.02 s)	1.00
multithreaded_benchmark Build Time	82.43 s	81.45 s	1.01 ❗
multithreaded_benchmark File Size	0.86 MB	0.86 MB	1.00 ❗
Multithreaded Pi Efficiency - 2 Threads	86.70 % (±5.96 %)	89.19 % (±7.29 %)	0.97
Multithreaded Pi Efficiency - 4 Threads	44.15 % (±3.36 %)	43.23 % (±2.22 %)	1.02
Multithreaded Pi Efficiency - 8 Threads	25.54 % (±2.11 %)	25.70 % (±1.35 %)	0.99
micro_benchmarks Build Time	81.35 s	80.50 s	1.01 ❗
micro_benchmarks File Size	0.86 MB	0.86 MB	1.00 ❗
Scheduling time - 1 thread	62.23 ticks (±2.53 ticks)	61.77 ticks (±3.53 ticks)	1.01
Scheduling time - 2 threads	35.76 ticks (±5.30 ticks)	34.80 ticks (±4.41 ticks)	1.03
Micro - Time for syscall (getpid)	3.43 ticks (±0.53 ticks)	3.24 ticks (±0.53 ticks)	1.06
Memcpy speed - (built_in) block size 4096	80366.63 MByte/s (±55754.13 MByte/s)	82518.62 MByte/s (±57031.72 MByte/s)	0.97
Memcpy speed - (built_in) block size 1048576	30705.27 MByte/s (±24770.14 MByte/s)	30748.73 MByte/s (±24797.64 MByte/s)	1.00
Memcpy speed - (built_in) block size 16777216	27099.88 MByte/s (±22365.79 MByte/s)	26790.22 MByte/s (±22121.79 MByte/s)	1.01
Memset speed - (built_in) block size 4096	80495.83 MByte/s (±55853.19 MByte/s)	82944.82 MByte/s (±57257.89 MByte/s)	0.97
Memset speed - (built_in) block size 1048576	31472.31 MByte/s (±25218.24 MByte/s)	31513.05 MByte/s (±25249.82 MByte/s)	1.00
Memset speed - (built_in) block size 16777216	27867.31 MByte/s (±22845.41 MByte/s)	27578.05 MByte/s (±22634.55 MByte/s)	1.01
Memcpy speed - (rust) block size 4096	76816.12 MByte/s (±53364.58 MByte/s)	77062.45 MByte/s (±53546.55 MByte/s)	1.00
Memcpy speed - (rust) block size 1048576	30489.94 MByte/s (±24738.40 MByte/s)	30445.41 MByte/s (±24660.75 MByte/s)	1.00
Memcpy speed - (rust) block size 16777216	27228.70 MByte/s (±22453.90 MByte/s)	27553.35 MByte/s (±22787.50 MByte/s)	0.99
Memset speed - (rust) block size 4096	77233.70 MByte/s (±53659.96 MByte/s)	77521.43 MByte/s (±53878.01 MByte/s)	1.00
Memset speed - (rust) block size 1048576	31230.53 MByte/s (±25168.91 MByte/s)	31217.22 MByte/s (±25122.56 MByte/s)	1.00
Memset speed - (rust) block size 16777216	28000.08 MByte/s (±22932.71 MByte/s)	28357.26 MByte/s (±23299.40 MByte/s)	0.99
alloc_benchmarks Build Time	75.60 s	75.20 s	1.01 ❗
alloc_benchmarks File Size	0.87 MB	0.87 MB	1.00 ❗
Allocations - Allocation success	91.31 %	91.31 %	1
Allocations - Deallocation success	100.00 %	100.00 %	1
Allocations - Pre-fail Allocations	61.44 %	61.44 %	1
Allocations - Average Allocation time	4373.46 Ticks (±676.79 Ticks)	5199.04 Ticks (±177.30 Ticks)	0.84 ❗
Allocations - Average Allocation time (no fail)	5292.10 Ticks (±575.60 Ticks)	5969.39 Ticks (±137.74 Ticks)	0.89 ❗
Allocations - Average Deallocation time	1687.54 Ticks (±256.73 Ticks)	1612.60 Ticks (±268.46 Ticks)	1.05
mutex_benchmark Build Time	85.68 s	76.02 s	1.13 ❗
mutex_benchmark File Size	0.86 MB	0.86 MB	1.00 ❗
Mutex Stress Test Average Time per Iteration - 1 Threads	12.08 ns (±0.27 ns)	11.94 ns (±0.37 ns)	1.01
Mutex Stress Test Average Time per Iteration - 2 Threads	39.96 ns (±2.74 ns)	40.06 ns (±2.30 ns)	1.00

This comment was automatically generated by workflow using github-action-benchmark.