Running benchmarks...
  Threads: 6
  QoS: User Interactive
Determining FP64 Neon FMLA performance...
  Repetitions:  500000000
  Duration (s): 1.5004
  GOPS:         239.936
Determining FP32 Neon FMLA performance...
  Repetitions:  500000000
  Duration (s): 1.48517
  GOPS:         484.792
Determining FP16 Neon FMLA performance...
  Repetitions:  500000000
  Duration (s): 1.47984
  GOPS:         973.075
Determining BF16-BF16-FP32 BFMMLA Neon performance
  Repetitions:  100000000
  Duration (s): 1.89012
  GOPS:         304.743
Determining FP32 SSVE FMLA (Z accumulation) performance...
  Repetitions:  50000000
  Duration (s): 5.39097
  GOPS:         53.4227
Detemining FP64 SSVE FMLA (Z accumulation) performance...
  Repetitions:  50000000
  Duration (s): 5.39074
  GOPS:         26.7125
Determining FP32 AMX performance...
  Repetitions:  300000000
  Duration (s): 7.86868
  GOPS:         2342.45
Determining FP32 SME FMOPA performance (1 tile)...
  Repetitions:  35000000
  Duration (s): 1.62489
  GOPS:         2117.45
Determining FP32 SME FMOPA performance (2 tiles)...
  Repetitions:  75000000
  Duration (s): 3.15475
  GOPS:         2337.05
Determining FP32 SME FMOPA performance (4 tiles)...
  Repetitions:  125000000
  Duration (s): 5.375
  GOPS:         2286.14
Determining FP32 SME predicated (8/16) FMOPA performance (4 tiles)...
  Repetitions:  125000000
  Duration (s): 6.17303
  GOPS:         995.297
Determining FP32 SME predicated (15/16) FMOPA performance (4 tiles)...
  Repetitions:  125000000
  Duration (s): 6.2025
  GOPS:         1857.31
Determining FP32 SME FMOPA performance (4 tiles, reordering)...
  Repetitions:  125000000
  Duration (s): 6.21734
  GOPS:         1976.41
Determining FP32 SME SMSTART-SMSTOP performance (8 instructions per block)..
  Repetitions:  125000000
  Duration (s): 2.35871
  GOPS:         1302.4
Determining FP32 SME SMSTART-SMSTOP performance (16 instructions per block)...
  Repetitions:  125000000
  Duration (s): 3.99549
  GOPS:         1537.73
Determining FP32 SME SMSTART-SMSTOP performance (32 instructions per block)...
  Repetitions:  125000000
  Duration (s): 7.10087
  GOPS:         1730.49
Determining FP32 SME SMSTART-SMSTOP performance (64 instructions per block)...
  Repetitions:  100000000
  Duration (s): 10.6754
  GOPS:         1841.69
Determining FP32 SME SMSTART-SMSTOP performance (128 instructions per block)...
  Repetitions:  50000000
  Duration (s): 10.2449
  GOPS:         1919.08
Determining FP16-FP16-FP32 SME FMOPA performance...
  Repetitions:  75000000
  Duration (s): 6.48989
  GOPS:         2272.09
Determining BF16-BF16-FP32 SME BFMOPA performance...
  Repetitions:  75000000
  Duration (s): 6.50585
  GOPS:         2266.51
Determining FP64 SME FMOPA performance ...
  Repetitions:  125000000
  Duration (s): 6.11911
  GOPS:         502.034
Determining I8-I8-I32 SME SMOPA performance...
  Repetitions:  75000000
  Duration (s): 6.34016
  GOPS:         4651.49
Determining I16-I16-I32 SME FMOPA performance...
  Repetitions:  75000000
  Duration (s): 6.29441
  GOPS:         2342.65
Determining FP32 SME FMLA performance...
  Repetitions:  125000000
  Duration (s): 4.84791
  GOPS:         633.675
Determining FP64 SME FMLA performance...
  Repetitions:  150000000
  Duration (s): 6.17698
  GOPS:         298.398
Determining BF16-BF16-FP32 SME BFDOT performance...
  Repetitions:  100000000
  Duration (s): 6.40405
  GOPS:         767.514