Compileiq Author Objective

What it does

When your agent uses it

• Writing the objectivefunction= passed to Search()
• Objective function
• Savecompilerconfig
• Baseline knockout

Example prompts

• “objective function”
• “apply-controls”
• “INVALIDSCORE”
• “/compileiq-author-objective”

Requirements

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

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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

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

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • helionlang.com

  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 Author Objective loads about 2.3k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 162 tokens; SKILL.md has 659 words of instructions outside code blocks.

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

~162

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

~2.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.4k

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

• 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); files beside SKILL.md are not scanned.

SKILL.md

The full file from NVIDIA/CompileIQ at commit 743aca4, republished under its Apache-2.0 licence (© NVIDIA). 659 words, ~2,268 tokens.

name

compileiq-author-objective

description

Use when writing the objective_function= passed to Search(). Covers the two legal signatures (compiler-only str vs mixed list), the baseline-knockout branch, per-eval cache busting, framework-specific --apply-controls injection (raw PTXAS, NVCC, Triton, Helion, cuTeDSL/FA4, FlashInfer), correctness-before-timing, INVALID_SCORE handling, and the Debug-pack O0/O3 ACF-injection canary that must pass before launching a search. Triggers on "objective function", "apply-controls", "INVALID_SCORE", "save_compiler_config", "baseline knockout", "BASELINE_CONFIG", "every config returns the same score", "TypeError fromhex".

allowed-tools

Bash, Read

when_to_use

- About to write or modify the function passed as objective_function=. - Search runs but every config returns an identical score (canary fails). - Getting…

license

Apache-2.0

metadata.version

1.0.0

metadata.author

NVIDIA CompileIQ

metadata.domain

compiler-optimization

paths

**/*.py, **/*.cu, **/*.cuh

from compileiq.types import INVALID_SCORE, BASELINE_CONFIG
from compileiq.utils.helpers import save_compiler_config

import os, tempfile
env = os.environ.copy()
env["TRITON_ALWAYS_COMPILE"] = "1"
env["HELION_SKIP_CACHE"]     = "1"
env["TRITON_CACHE_DIR"]      = tempfile.mkdtemp(prefix="ciq_triton_")

def objective(config):
    if isinstance(config, dict) and not config:   # config == BASELINE_CONFIG
        return measure_without_acf()              # establish baseline run
    # config is a hex string (or list with hex tail) — apply ACF
    ...

if not torch.allclose(actual, reference, atol=1e-2, rtol=0):
    return INVALID_SCORE
return triton.testing.do_bench(lambda: kernel(...), warmup=100, rep=1000, return_mode="mean")

try:
    ...
except (subprocess.TimeoutExpired, RuntimeError, FileNotFoundError, ValueError, OSError) as e:
    return INVALID_SCORE

# Shape check — does the objective even run?
sample = tuner.sample(1)[0]
score = objective(sample)
print(f"sample run: {score}")
assert isinstance(score, (int, float)) and score == score   # not NaN

# ACF-injection canary using the Debug pack (downloaded once)
from compileiq.utils.helpers import load_compiler_config
O0_HEX = load_compiler_config("booster-pack-debug/ptxas_opt0.acf")
O3_HEX = load_compiler_config("booster-pack-debug/ptxas_opt3.acf")

baseline = objective({})                  # BASELINE_CONFIG path
score_O0 = objective(O0_HEX)
score_O3 = objective(O3_HEX)

assert score_O0 > baseline * 1.05, (
    f"O0 should regress (got {score_O0} vs baseline {baseline}). "
    "ACF is NOT reaching PTXAS — fix the cache-bust."
)
assert abs(score_O3 - baseline) / baseline < 0.05, (
    f"O3 should match baseline (got {score_O3} vs {baseline})."
)
print("ACF injection canary PASSED — safe to start the search.")

def smoke_objective(config):
    return 1.0   # constant; useful to verify Search() shape, not measurement

© 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 (references) in agent-skills/compileiq-author-objective of NVIDIA/CompileIQ.

• SKILL.md
• references/templates.md

Open the folder on GitHubat commit 743aca4