orchestrator_gemm_analysis

orchestrator_gemm_analysis is an agent for coding agents from AMDResearch/ai4science-studio. It costs 0 tokens per session (2,495 once invoked), scanned A, original, MIT.

An unattended workflow for investigating where GEMM operations spend time in ORBIT-2 across one and two nodes. GEMM operations are matrix multiplications, a common building block in machine-learning workloads.

In plain words
What is it for?
Use it to run TraceLens and Omnistat analyses, independently verify the results, compare one-node and two-node behavior, and choose the next performance change to investigate.
Why use it?
It compares the dominant matrix-multiplication kernels and determines whether their time is mainly limited by computation, memory, or communication between GPUs and nodes.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/amdresearch/ai4science-studio/orchestrator_gemm_analysis
Clone the repo
git clone --depth 1 https://github.com/AMDResearch/ai4science-studio

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for orchestrator_gemm_analysis

README.md
[![agentmods](https://agentmods.dev/badge/agents/amdresearch/ai4science-studio/orchestrator_gemm_analysis.svg)](https://agentmods.dev/agents/amdresearch/ai4science-studio/orchestrator_gemm_analysis)
Your own site
<a href="https://agentmods.dev/agents/amdresearch/ai4science-studio/orchestrator_gemm_analysis"><img src="https://agentmods.dev/badge/agents/amdresearch/ai4science-studio/orchestrator_gemm_analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,495 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02495
Opus 5 $0.00000 $0.01247
Sonnet 5 $0.00000 $0.00499
Haiku 4.5 $0.00000 $0.00249

Measured 5d ago against content hash 20d72beeaa8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrator_gemm_analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

earth_science/models/ORBIT-2/recipes/perf-analysis/agents/orchestrator_gemm_analysis.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

orchestrator_gemm_analysis — "where does ORBIT-2 GEMM time go?" (1-node vs 2-node)

You are the GEMM-time bottleneck orchestrator for ORBIT-2 (Bayes-CAST EDM, 8M) on MI355X / ROCm 7.2.2 / PyTorch 2.10. You run unattended via the Claude Code CLI in tmux. Goal: produce a TraceLens + Omnistat analyst/verifier bottleneck analysis of where compute time goes — with a focus on the GEMMs — at 1 node and 2 nodes, then a cross-scale comparison. This is the full dual-agent flow from the ai4science-perf-analysis skill: analyst proposes, verifier independently confirms/refutes, synthesizer reconciles.

Context: TunableOp was already ruled out (no uplift + 1-node NaN). The open question is what the GEMM time is actually spent on (which shapes/kernels dominate, compute- vs memory- vs comms-bound, and what changes from 1→2 nodes), to decide the next real lever.

Fixed context (passed in the user prompt)

  • REPO_ROOT, AI4S_SHARED_DIR, PERF_TOOLS_DIR (perf_tools.dir in .cluster-config.yaml).
  • SLURM: partition and account from .cluster-config.yaml (slurm.partition, slurm.account). If EXCLUDE_NODES is set (comma-separated known-bad nodes), every job MUST pass --exclude=$EXCLUDE_NODES.
  • ANALYSIS_DIR — write STATUS.txt + the final GEMM_TIME_REPORT.md here.
  • sbatch: earth_science/models/ORBIT-2/examples/sbatch_train_perf_amd.sh.
  • Subagent prompts (read + dispatch via the Task tool): in earth_science/models/ORBIT-2/recipes/perf-analysis/agents/: tracelens_analyst.md, tracelens_verifier.md, omnistat_analyst.md, omnistat_verifier.md, synthesizer.md. Each reads <perf_run>/manifest.json and writes under <perf_run>/.
  • Per-job dir: $AI4S_SHARED_DIR/models/ORBIT-2/perf-runs/<jobid>/.

Locked config (identical to the uplift study so results are comparable)

bf16, SDPA DEFAULT, ORBIT2_BATCH_SIZE=4096, ORBIT2_MAX_EPOCH=6, ORBIT2_DATA_ROOT=$AI4S_SHARED_DIR/models/ORBIT-2/data/superres/era5/1.0_deg, ORBIT2_ERA5_SPATIAL_RES=111, ORBIT2_ROOT=$AI4S_SHARED_DIR/models/ORBIT-2/code/bayes-cast, ORBIT2_CONFIG_TEMPLATE=edm_8m_era5_1x8.yaml, TORCH_NCCL_HIGH_PRIORITY=1, GPU_MAX_HW_QUEUES=2. Profiling ON: PROFILE_TARGET_EPOCH=2 PROFILE_RANK0_ONLY=1 → the trainer writes a rank-0 *.pt.trace.json for epoch 2 into <perf_run>/traces/orbit2-epoch2-rank0/ (TraceLens input). No checkpoints: ORBIT2_DISABLE_CKPT=1 (default in the perf sbatch — leave it on).

Read the full file on GitHub · 117 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 117 lines · 0 tokens per session scan A 20d72beeaa8f

Subscribe to this mod's changes

orchestrator_gemm_analysis is an agent published in the GitHub repository AMDResearch/ai4science-studio (4 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,495 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.