Paper Citation Record · LEDGER

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX

As of 9 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2606.25426.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2606.25426 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-25T19:32:13.860933Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact6
verified fuzzy0
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e2431b85-bb36-4312-85be-fe03d0c6ae4c · outbound

This paper cites Demysti- fying ARM SME to Optimize General Matrix Multiplica- tions,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX Demysti- fying ARM SME to Optimize General Matrix Multiplica- tions,

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-07-04T20:50:12.039305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 001c86f8-c623-4e8c-b459-fc27e3acc2de · outbound

This paper cites Performance Analysis of the Apple AMX Matrix Accelerator,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX Performance Analysis of the Apple AMX Matrix Accelerator,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-25T19:32:13.860933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f935cb25-9dff-4305-b2c8-14fba7d078c2 · outbound

This paper cites Apple vs. Oranges: Evaluating the Apple Silicon M-Series SoCs for HPC Performance and Efficiency.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX Apple vs. Oranges: Evaluating the Apple Silicon M-Series SoCs for HPC Performance and Efficiency

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T20:50:12.075522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a3643332-045c-47da-88a3-bea2559f1441 · outbound

This paper cites Bare-Metal Tensor Vir- tualization: Overcoming the Memory Wall in Edge-AI Inference on ARM64,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX Bare-Metal Tensor Vir- tualization: Overcoming the Memory Wall in Edge-AI Inference on ARM64,

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-04T20:50:12.069423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ba7e49c7-b746-466d-8116-37996f9bb40a · outbound

This paper cites corsix/amx: reverse-engineered Apple AMX instruction reference,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX corsix/amx: reverse-engineered Apple AMX instruction reference,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-25T19:32:13.860933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da641afc-13e9-4e74-8f54-9be3e8f0070e · outbound

This paper cites dougallj: Apple silicon reverse- engineering notes,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX dougallj: Apple silicon reverse- engineering notes,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-25T19:32:13.860933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b85919d-adbf-487d-bec2-7c7623f783d8 · outbound

This paper cites Anatomy of high- performance matrix multiplication,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX Anatomy of high- performance matrix multiplication,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-25T19:32:13.860933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8011997f-5e04-4a7d-8e82-6d41452d589a · outbound

This paper cites llama.cpp: eﬀicient LLM inference in pure C/C++,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX llama.cpp: eﬀicient LLM inference in pure C/C++,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-25T19:32:13.860933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c950b55b-1417-48e6-b517-b1693e860f76 · outbound

This paper cites amx-benchmarks: throughput measure- ments for the Apple matrix coprocessor,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX amx-benchmarks: throughput measure- ments for the Apple matrix coprocessor,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-25T19:32:13.860933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 100d09d4-7d83-4c2d-8a46-944e41cbc325 · outbound

This paper cites Accelerating Sparse Ternary GEMM for Quantized ML on Apple Silicon,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX Accelerating Sparse Ternary GEMM for Quantized ML on Apple Silicon,

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-04T20:50:12.065916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 24bcf866-d663-423c-9e8d-083b61f73559 · outbound

This paper cites Benchmarking and Characterization of Large Language Model Inference on Apple Silicon,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX Benchmarking and Characterization of Large Language Model Inference on Apple Silicon,

Reference 11

Resolution: verified exact; doi, observed 2026-06-27T04:40:32.598072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 80663765-f6fa-472b-8122-4c9ed30f22ac · outbound

This paper cites Benchmarking On- Device Machine Learning on Apple Silicon with MLX,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX Benchmarking On- Device Machine Learning on Apple Silicon with MLX,

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-04T20:50:12.062489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 50bbc685-34d8-4147-9097-2314f342748a · outbound

This paper cites ONNX Runtime: cross-platform infer- ence engine,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX ONNX Runtime: cross-platform infer- ence engine,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-25T19:32:13.860933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33391b70-c91f-4856-8f77-33b83b384653 · outbound

This paper cites XNNPACK: high-eﬀiciency neural- network inference operators,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX XNNPACK: high-eﬀiciency neural- network inference operators,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-25T19:32:13.860933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7f2aded-a840-4560-b8c9-fe2e251c1fbb · outbound

This paper cites oneDNN: weight pre-packing for matmul and inner-product primitives,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX oneDNN: weight pre-packing for matmul and inner-product primitives,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-25T19:32:13.860933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21ec3be4-fe74-4313-8638-e743a507ac23 · outbound

This paper cites What’s new in BNNS Graph,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX What’s new in BNNS Graph,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-25T19:32:13.860933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2cf6834-bd83-4e9e-9f31-1b48d260cc8a · outbound

This paper cites PQC-AMX: Accelerating Saber and FrodoKEM on the Apple M1 and M3 SoCs,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX PQC-AMX: Accelerating Saber and FrodoKEM on the Apple M1 and M3 SoCs,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-25T19:32:13.860933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ed1967b-2db5-4aa5-a4d9-5f9d3b4c707e · outbound

This paper cites A comparative per- formance and eﬀiciency analysis of Apple’s M architec- tures: A GEMM case study,.

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX A comparative per- formance and eﬀiciency analysis of Apple’s M architec- tures: A GEMM case study,

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-27T04:40:32.599268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.