einsum-opt_flops on zen5-cpu124aa12d7c70ae4e5d0f499c549999469118f6dedefaultcpueinsum (the provider in the measured revision; see library above)404f67bf286bbc2c9e10df8b18d0fee2f62bf977b71624bef111ce941bddaedcce3fdb6eab40f9ebe4d120a7d75fae4d098888d5ee59d79c1d4800d89bb33c37089c104ae8f9fd83zen5-cpudevelopment — provisional: recorded on a development host, superseded by the measurement host's dataset2026-10-31T11:09:05.889295Zscripts/v2/record_run.py zen5-cpu einsum-opt_flopsdata/v2-results/cpueinsum/zen5-cpu/einsum-opt_flops/20261031T110520Z/tenferro-einsum-benchmark problem set: pairwise matrix products, batched and elementwise products, outer products, a matrix-chain problem, MPS inner products, two MERA networks, two tensor-network permutation problems, and two likelihood contractions of 38 and 84 operands. The operands are generated by the harness (deterministic, dtype-templated) and the contraction order is taken from the corpus's own paths entry, so the rows measure one library against two declared schedules, not two libraries.
Source: The corpus is tenferro-einsum-benchmark data/instances/*.json at the revision in pins/tenferro-einsum-benchmark.rev, materialised by scripts/setup_extern_deps.sh. Each instance declares name, format_string, shapes, dtype and two opt_einsum-style positional paths; crates/cpueinsum-bench/src/corpus.rs in the measured revision translates them into cpueinsum's integer-label, SSA-order API.
Known blind spot: The corpus instance str_mps_varying_inner_product_200 is not declared: the harness's own cross-row verification refuses it (MISMATCH(opt_flops) rel_err=NaN, exit 1) at every declared thread budget. It is therefore not measured, not skipped, and not part of this suite's coverage; the evidence is in docs/verify-refusal-str_mps-varying-inner-product-200.md.
Known blind spot: The declared identity is the numeric sentinel n = 1: every instance has fixed extents, so the declaration grid has one shape and the real operand shapes are the harness's case_m (operand count), case_n (total input elements) and case_k (output elements) columns, not geometry the toolkit compares.
Known blind spot: The engine rows are two contraction orders of the same library, so a row here is a schedule comparison inside cpueinsum, not a comparison against an independent implementation; there is no reference engine and no vendor arm in the first record.
Known blind spot: Every instance has unit batch, so a cost proportional to batch elements is invisible.
Known blind spot: One size per instance: a ratio here says nothing about a neighbouring instance, and the set is not a sweep.
Known blind spot: A corpus revision is not one of the measured repository's invalidated_by paths: the declaration records the corpus pin it was generated from, and a corpus bump has to be a deliberate regeneration of this suite.opt_flops — cpueinsum executing the corpus's paths.opt_flops order: the order the corpus declares as minimizing the operation count.
Identity: the measured cpueinsum-rs revision in this run's manifest (library.commit), pinned by pins/cpueinsum-rs.rev
Caveat: The two orders coincide for most instances in this corpus; where they do, a small difference between the rows is measurement noise, not a scheduling effect.
As measured: cpueinsum (the provider in the measured revision; see library above)AMD Ryzen AI 9 HX 4702424 MiB (2 instances)0-3: 16 MiB shared; 4-11: 8 MiB sharedLinux 7.0.0-38-generic / x86_64shinaoka-EVO-X1Pro4, 4T -> 4-7Every 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 0.45%, worst 4.34% among cells of 1 us or more (a sub-microsecond row is timer and scheduler jitter, not kernel time); 0 of 26 engine cells exceed 5% and carry !; median within-process relative SD 0.37%. 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.
| case | opt_flops (ms) | notes |
|---|---|
| bin_batched_matmul_b32_m64_n64_k64/n1/b1 | 0.558895 ± 0.000814587 (W 0.00239534) | |
| bin_elementwise_mul_2048x2048/n1/b1 | 4.02009 ± 0.0383966 (W 0.0134363) | |
| bin_matmul_256/n1/b1 | 1.07024 ± 0.00289065 (W 0.00275378) | |
| bin_outer_product_4096/n1/b1 | 6.19889 ± 0.00403122 (W 0.022405) | |
| gm_queen5_5_3.wcsp/n1/b1 | 4568 ± 52.9609 (W 22.5582) | |
| lm_batch_likelihood_brackets_4_4d/n1/b1 | 26.9812 ± 0.176017 (W 0.330914) | |
| lm_batch_likelihood_sentence_3_12d/n1/b1 | 72.4797 ± 0.340885 (W 0.138893) | |
| lm_batch_likelihood_sentence_4_4d/n1/b1 | 27.3383 ± 0.156766 (W 0.173524) | |
| str_matrix_chain_multiplication_100/n1/b1 | 12.657 ± 0.0196279 (W 0.0312983) | |
| str_nw_mera_closed_120/n1/b1 | 1766.27 ± 0.155851 (W 1.28391) | |
| str_nw_mera_open_26/n1/b1 | 1165.41 ± 0.0126049 (W 1.18565) | |
| tensornetwork_permutation_focus_step409_316/n1/b1 | 233.829 ± 0.575277 (W 0.450488) | |
| tensornetwork_permutation_light_415/n1/b1 | 231.935 ± 0.0904404 (W 0.290097) | |
| case | opt_flops (ms) | notes |
|---|---|
| bin_batched_matmul_b32_m64_n64_k64/n1/b1 | 0.144242 ± 0.000306177 (W 0.00114546) | |
| bin_elementwise_mul_2048x2048/n1/b1 | 2.14403 ± 0.0149779 (W 0.0140393) | |
| bin_matmul_256/n1/b1 | 1.07535 ± 0.00814941 (W 0.00206279) | |
| bin_outer_product_4096/n1/b1 | 6.15475 ± 0.188765 (W 0.0170268) | |
| gm_queen5_5_3.wcsp/n1/b1 | 1839.03 ± 4.04695 (W 7.354) | |
| lm_batch_likelihood_brackets_4_4d/n1/b1 | 11.5854 ± 0.0838777 (W 0.0379017) | |
| lm_batch_likelihood_sentence_3_12d/n1/b1 | 22.6687 ± 0.154074 (W 0.800329) | |
| lm_batch_likelihood_sentence_4_4d/n1/b1 | 12.4302 ± 0.0397203 (W 0.12276) | |
| str_matrix_chain_multiplication_100/n1/b1 | 12.6621 ± 0.00399374 (W 0.0221998) | |
| str_nw_mera_closed_120/n1/b1 | 512.763 ± 6.95692 (W 5.87867) | |
| str_nw_mera_open_26/n1/b1 | 327.348 ± 1.5796 (W 4.44016) | |
| tensornetwork_permutation_focus_step409_316/n1/b1 | 87.7799 ± 0.0312548 (W 0.880862) | |
| tensornetwork_permutation_light_415/n1/b1 | 80.3255 ± 0.254893 (W 4.46232) | |
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.