Compileiq Run Search

What it does

When your agent uses it

• Composing the Search(...) call and calling .start()
• IsoMultiProcessWorker

Example prompts

• “Search()”
• “tuner.start()”
• “poolsize”
• “/compileiq-run-search”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Bash, Read

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Confirm the search space resolves at all (cheaper than the bootstrap
2. 2Eyeball that the dicts have the keys your objective expects.
3. 3Feed a single sample into the objective by hand to verify it runs.

What it can do on your machine

Read from SKILL.md and the folder at commit 743aca4. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Compileiq Run Search loads about 2.2k tokens when it runs. Until then it costs about 142 tokens; SKILL.md has 651 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~142

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteRuns commands with sudoSKILL.md:174

  sudo nvidia-smi -pm 1

• NoteRuns commands with sudoSKILL.md:177

  sudo nvidia-smi --lock-gpu-clocks=$MAX_GPU,$MAX_GPU --lock-memory-clocks=$MAX_MEM,$MAX_MEM

• NoteRuns commands with sudoSKILL.md:188

  a CI container or a shared cluster where sudo isn't available, skip

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from NVIDIA/CompileIQ at commit 743aca4, republished under its Apache-2.0 licence (© NVIDIA). 651 words, ~2,183 tokens.

name

compileiq-run-search

description

Use when composing the Search(...) call and calling .start(). Covers the four worker classes (MultiProcessWorker / IsoMultiProcessWorker / RayWorker / AsyncWorker) and when to pick each, SearchConfiguration sizing rules, dump_results checkpointing, tracker_config choice (Disabled / Loguru / MLflow), num_workers/task_timeout semantics, and GPU clock locking for stable measurements. Triggers on "Search()", "tuner.start()", "pool_size", "num_workers", "task_timeout", "IsoMultiProcessWorker", "RayWorker", "dump_results", "MLflow", "GPU clocks".

allowed-tools

Bash, Read

when_to_use

- About to instantiate Search() and call .start(). - Search converges too slow / too fast and the user is unsure how to size. - Search is hanging on a few…

license

Apache-2.0

metadata.version

1.0.0

metadata.author

NVIDIA CompileIQ

metadata.domain

compiler-optimization

paths

**/*.py

from compileiq.types import WorkerTypes
from compileiq.worker import (
    MultiProcessWorker,    # default
    IsoMultiProcessWorker, # spawns fresh process per task; kill-safe
    RayWorker,             # distributed
    AsyncWorker,           # asyncio for async def objectives
)

from compileiq.types import SearchConfiguration, ProblemType

config = SearchConfiguration(
    problem_type=ProblemType.MIN,   # MIN for latency; MAX for throughput
    generations=10,                  # required, > 0
    pool_size=15,                    # > 5; auto-derives if omitted
    # cull_size auto-derives to 75% of pool, rounded down to even
    # mutate_rate defaults to 0.25
    # num_objectives defaults to 1
    # normalize defaults to False (set True for cross-GPU runs)
)

from pathlib import Path
from compileiq.ciq import Search
from compileiq.search_spaces.compilers import PtxasSearchSpace
from compileiq.tracker import LoguruTrackerConfig

tuner = Search(
    objective_function=objective,
    search_space=PtxasSearchSpace(version="13.3", variant="att"),
    search_config=config,
    worker_type=IsoMultiProcessWorker,                 # or WorkerTypes.ISOLATED
    tracker_config=LoguruTrackerConfig(sink="optimization.log"),
    dump_results=Path("results.csv"),                  # ALWAYS set this
    cache_folder=None,                                  # default ~/.cache/compileiq
    disable_progress_bar=False,
    exit_on_failure=True,
    debug=False,
)

results = tuner.start(num_workers=4, task_timeout=120)

from compileiq.tracker import DisabledTrackerConfig, LoguruTrackerConfig, MLflowTrackerConfig

sample = tuner.sample(1)[0]
print(sample)
print(objective(sample))   # should return a real float, not raise

sudo nvidia-smi -pm 1
MAX_GPU=$(nvidia-smi --query-gpu=clocks.max.graphics --format=csv,noheader,nounits | head -1)
MAX_MEM=$(nvidia-smi --query-gpu=clocks.max.memory --format=csv,noheader,nounits | head -1)
sudo nvidia-smi --lock-gpu-clocks=$MAX_GPU,$MAX_GPU --lock-memory-clocks=$MAX_MEM,$MAX_MEM

import atexit, subprocess
def unlock():
    subprocess.run(["sudo", "nvidia-smi", "--reset-gpu-clocks", "--reset-memory-clocks"],
                   check=False)
atexit.register(unlock)

python scripts/smoke_search.py

© NVIDIA, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in agent-skills/compileiq-run-search of NVIDIA/CompileIQ.

• SKILL.md
• scripts/smoke_search.py

Open the folder on GitHubat commit 743aca4