tiles=1472 matched=65321/65321 spanCycles=394122 spanMs=0.262748
name="idle" phases=40 tiles=1408 samples=56320 timelineCycles=393900 workCycles=554567904 range=0..393900 p95=6012 max=277578 useful=n/a coverage=0.0%
name="sync" phases=56 tiles=64 samples=1594 timelineCycles=184014 workCycles=6121584 range=0..393864 p95=12396 max=36462 useful=n/a coverage=0.0%
name="repeat-remainder" phases=8 tiles=64 samples=64 timelineCycles=179154 workCycles=11435046 range=112476..291630 p95=178716 max=178740 useful=n/a coverage=0.0%
name="exchange" phases=73 tiles=64 samples=3078 timelineCycles=127134 workCycles=4683636 range=0..393972 p95=3156 max=9696 useful=n/a coverage=0.0%
name="rearrange_row_major_to_amp_f16_o2_r0_p64_c80_p80_b64x16" phases=2 tiles=2 samples=2 timelineCycles=24990 workCycles=46932 range=322602..347592 p95=23466 max=23466 useful=0.7% coverage=100.0%
name="copy_u64" phases=127 tiles=64 samples=459 timelineCycles=23094 workCycles=137970 range=0..391176 p95=288 max=2838 useful=n/a coverage=0.0%
name="cast_f16_f8" phases=87 tiles=63 samples=504 timelineCycles=22710 workCycles=1041588 range=2850..388104 p95=2442 max=2448 useful=1.0% coverage=100.0%
name="copy_strided_u64" phases=31 tiles=9 samples=38 timelineCycles=16650 workCycles=31716 range=7068..379578 p95=1620 max=2424 useful=n/a coverage=0.0%
name="fill_zero_u64" phases=53 tiles=63 samples=234 timelineCycles=13632 workCycles=76974 range=5934..388404 p95=426 max=1500 useful=0.0% coverage=74.7%
name="static_copy_u32" phases=153 tiles=64 samples=827 timelineCycles=11952 workCycles=177708 range=10608..394122 p95=342 max=396 useful=n/a coverage=0.0%
name="rearrange_row_major_to_amp_f16_o2_r0_p64_c32_p32_b64x16" phases=2 tiles=2 samples=2 timelineCycles=10500 workCycles=19584 range=42792..53292 p95=9792 max=9792 useful=0.7% coverage=100.0%
name="add_f16" phases=132 tiles=64 samples=784 timelineCycles=10008 workCycles=408000 range=11364..393576 p95=546 max=546 useful=0.5% coverage=100.0%
name="layer_norm_moments" phases=18 tiles=16 samples=52 timelineCycles=6438 workCycles=63840 range=14538..370368 p95=1230 max=1230 useful=5.9% coverage=100.0%
name="gemm_f16_init_small_rows_k64_c80_r1_r1" phases=2 tiles=2 samples=2 timelineCycles=5838 workCycles=8628 range=351000..356838 p95=4314 max=4314 useful=0.1% coverage=100.0%
name="layer_norm_apply" phases=18 tiles=16 samples=52 timelineCycles=5250 workCycles=67584 range=16560..372030 p95=1302 max=1302 useful=5.5% coverage=100.0%
name="gemm_f8_init_small_rows_interleaved_k96_c16_r4_r4" phases=9 tiles=63 samples=117 timelineCycles=4734 workCycles=99306 range=6876..32970 p95=852 max=852 useful=4.6% coverage=100.0%
name="attention_merge_v72_p80_k64_out16_f16" phases=6 tiles=8 samples=10 timelineCycles=4716 workCycles=15948 range=60060..358428 p95=1596 max=1596 useful=n/a coverage=0.0%
name="reduce_sum_f16" phases=58 tiles=54 samples=162 timelineCycles=4656 workCycles=68202 range=9768..390906 p95=516 max=558 useful=7.0% coverage=100.0%
name="gemm_f8_init_large_rows_interleaved_k64_c16_r2_r4" phases=34 tiles=54 samples=153 timelineCycles=4188 workCycles=104004 range=91794..304440 p95=684 max=684 useful=3.7% coverage=100.0%
name="gemm_f16_init_small_rows_interleaved_k80_c16_r1_r1" phases=5 tiles=8 samples=10 timelineCycles=3522 workCycles=11688 range=55146..350970 p95=1170 max=1170 useful=0.4% coverage=100.0%
