einsum-opt_size on zen5-cpu

What was measured

Hardware

Every timed cell matches a successful verification census, including operation variants. Each cell is median of process medians ± sample SD of those medians; W is the median within-process sample SD. All values are milliseconds. These are descriptive spreads, not confidence intervals. The between-process spread includes the rotating-order schedule. Each process retains 5 chronological calls; 2 complete process sets are recorded. Spread guide (computed from this run's own rows): per-engine between-start range median 0.48%, worst 6.65% among cells of 1 us or more (a sub-microsecond row is timer and scheduler jitter, not kernel time); 1 of 26 engine cells exceed 5% and carry !; median within-process relative SD 0.50%. A cell whose ±, ! or p is as large as the difference you are reading is not evidence of a regression. no row, so no ratio there is position-balanced). ! marks a cell where some engine's own per-start median range exceeds 5% of its median, and p a balanced cell whose estimated position-effect ratio exceeds 1.05. Flagged cells are retained, not discarded; the between-start variation can exceed the difference being compared. ! between-start range over 5%, p position effect over 5%, dispatch-dominated means the row is under 20 us so 4T/8T pay thread-region start-up). Per-start ratios and every chronological sample are in the run directory named at the top of this page (run*.csv). These describe the recorded revisions; they are not a regression claim.

cpueinsum, float64, 1T (CPU 4)

| case | opt_size (ms) | notes | |---|---| | bin_batched_matmul_b32_m64_n64_k64/n1/b1 | 0.555303 ± 0.00224577 (W 0.00203681) | | | bin_elementwise_mul_2048x2048/n1/b1 | 4.45272 ± 0.0123425 (W 0.0107548) | | | bin_matmul_256/n1/b1 | 1.07435 ± 0.00548291 (W 0.000420243) | | | bin_outer_product_4096/n1/b1 | 6.1783 ± 0.0427524 (W 0.0207439) | | | gm_queen5_5_3.wcsp/n1/b1 | 1640.93 ± 1.317 (W 1.65217) | | | lm_batch_likelihood_brackets_4_4d/n1/b1 | 23.321 ± 0.266023 (W 0.107464) | | | lm_batch_likelihood_sentence_3_12d/n1/b1 | 87.3276 ± 1.57777 (W 0.545784) | | | lm_batch_likelihood_sentence_4_4d/n1/b1 | 26.8873 ± 0.0706937 (W 0.162786) | | | str_matrix_chain_multiplication_100/n1/b1 | 12.7199 ± 0.0448044 (W 0.0338162) | | | str_nw_mera_closed_120/n1/b1 | 1697.11 ± 0.111872 (W 0.954695) | | | str_nw_mera_open_26/n1/b1 | 1183.81 ± 1.06703 (W 0.720321) | | | tensornetwork_permutation_focus_step409_316/n1/b1 | 242.254 ± 3.4272 (W 1.85886) | | | tensornetwork_permutation_light_415/n1/b1 | 237.858 ± 0.013814 (W 0.328326) | |

cpueinsum, float64, 4T (CPU 4-7)

| case | opt_size (ms) | notes | |---|---| | bin_batched_matmul_b32_m64_n64_k64/n1/b1 | 0.14437 ± 2.82843e-05 (W 0.0013362) | | | bin_elementwise_mul_2048x2048/n1/b1 | 2.15147 ± 0.0048451 (W 0.0434525) | | | bin_matmul_256/n1/b1 | 0.313295 ± 0.00631871 (W 0.0102947) | | | bin_outer_product_4096/n1/b1 | 4.2265 ± 0.0967237 (W 0.0501473) | | | gm_queen5_5_3.wcsp/n1/b1 | 529.906 ± 0.461702 (W 4.24514) | | | lm_batch_likelihood_brackets_4_4d/n1/b1 | 10.9638 ± 0.0872754 (W 0.0829693) | | | lm_batch_likelihood_sentence_3_12d/n1/b1 | 26.4494 ± 0.086634 (W 0.537745) | | | lm_batch_likelihood_sentence_4_4d/n1/b1 | 15.4098 ± 0.131842 (W 0.195181) | | | str_matrix_chain_multiplication_100/n1/b1 | 6.85411 ± 0.00978848 (W 0.655965) | | | str_nw_mera_closed_120/n1/b1 | 509.83 ± 0.782011 (W 5.91522) | | | str_nw_mera_open_26/n1/b1 | 325.078 ± 0.684881 (W 3.0398) | | | tensornetwork_permutation_focus_step409_316/n1/b1 | 90.4748 ± 0.661445 (W 1.32435) | | | tensornetwork_permutation_light_415/n1/b1 | 72.2887 ± 3.39912 (W 3.43573) | ! between-start range over 5% |

Repeated process sets describe observed repeatability under the recorded order schedule; they are not a paired baseline/candidate experiment and do not establish equal performance between engines.