llnl

Communication-component (MPI/collective/network) bottleneck-to-optimization mappings, papers, and L1/L2/L3 strategies for the dftracer optimization pipeline

Compute-component bottleneck-to-optimization mappings, papers, and L1/L2/L3 strategies for the dftracer optimization pipeline

Key literature, bottleneck-to-optimization mappings, and strategies for the dftracer I/O optimization pipeline

Memory-component bottleneck-to-optimization mappings, papers, and L1/L2/L3 strategies for the dftracer optimization pipeline

VPIC-Kokkos-specific knowledge: build/annotation quirks, the two-stage deck-compile pattern, deck sizing for smoke vs validation runs, and the measured MPI-communication-bound diagnosis on Tuolumne. Load this skill whenever working with vpic-kokkos (github.com/lanl/vpic-kokkos).

Install and build dftracer into the session using the MCP install tool and record tool pitfalls early.

Diagnose traces and convert symptoms into actionable bottlenecks with MCP tools.

Cross-session, citation-backed knowledge base of every MEASURED dftracer optimization, partitioned into system-centric (L3), software-centric (L2), and workload-centric (L1) findings. Load this FIRST in any optimization loop to avoid re-deriving what is already known.

Fetch and apply GitHub pull-request review comments locally, especially when the task includes reconciling new review traffic, following reply chains from specific reviewers/authors, and keeping a scratch notes file that maps comment IDs to fixes.

Generate nanobind C++ wrapper code for user-supplied callback functions in the sundials4py Python bindings. Use this skill whenever adding a new user-supplied function (callback) to any sundials4py submodule (arkode, cvodes, idas, kinsol, core/sundials), wrapping a C function-pointer-based API for Python, adding a `python` member to a SUNDIALS C struct that does not yet have one, or when a function cannot be autogenerated by litgen because it takes a function pointer argument. Also trigger when the user mentions "callback wrapper", "user_supplied_fn_caller", "BIND_ARKODE_CALLBACK", "BIND_CVODE_CALLBACK", "BIND_IDA_CALLBACK", "BIND_KINSOL_CALLBACK", or references any *_usersupplied.hpp or *_impl.h file in the context of Python bindings. If the user says something like "wrap this Set callback for Python", "add a new user function to cvodes", or "this object needs a python member for callbacks", this is the skill to use.

Build, install, and test SUNDIALS from source as an end user or as a SUNDIALS developer. Use when a request involves configuring CMake, selecting compilers/options (MPI, GPU backends, Fortran), building/installing, running CTest, enabling dev/unit tests, or troubleshooting common build/test issues.

Add a new SUNDIALS module (e.g., NVECTOR_*, SUNMATRIX_*, SUNLINSOL_*, SUNNONLINSOL_*, SUNMEMORY_*, or a new shared component) including source/header layout, CMake wiring, enable/disable options, exported CMake targets, installed component registration, and developer tests/examples/docs updates.

Guide for building the tool when asked by the user or testing a code change that requires a new build of the tool

Guide for understanding the structure and content of HTML reports generated by the tool

Guide for writing tests in the project

Guide for understanding the tool's functionality and usage in error tracking

C++ coding style and naming conventions for Smith (primarily src/smith), including formatting via the CMake `style` target.

Instructions for building Smith

Instructions for creating unit tests for Smith

C++ coding style and naming conventions for Axom (primarily src/axom), including formatting via the CMake `style` target.

Instructions for building Axom

Instructions for creating unit tests for Axom