// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only

#pragma once

#include <string>

#include "Logger.h"

// cuFFT ships its transforms as PTX (cuFFT 11 and 12 alike, for every card), so every plan it makes has
// the driver compile kernels - and makes them again for a second plan of the same shape. The driver keeps
// what it compiled in its JIT cache, CUDA_CACHE_PATH or else $HOME/.nv/ComputeCache: from there a plan
// takes about 1 ms, without it 60-130 ms, all under cuFFT's process-wide lock. A run that makes a hundred
// plans (molecular replacement) is then seconds slower, with nothing else to show for it.
struct CudaJitCache {
    std::string path;         // where the driver keeps it; empty when it keeps none
    std::string filesystem;   // the type of the filesystem it is on (Linux only)
    std::string problem;      // why the driver cannot use it, or only slowly; empty when none is seen
};

CudaJitCache InspectCudaJitCache();

// Where the driver would keep no usable cache - typically a service run as root by systemd without User=,
// so with no HOME - and CUDA_CACHE_PATH is not set, point CUDA_CACHE_PATH at a directory of this user's
// own, /var/tmp/jfjoch-cuda-cache-<uid> (0700). The driver reads it once, when it initialises, so this
// must run before anything touches CUDA. Linux only; a CUDA_CACHE_PATH set by the site is left alone.
void UsePrivateCudaJitCacheIfNeeded();

// One line for a program's start: the cache, and `plan_ms` - how long one cuFFT plan took to make once
// cuFFT was initialised (WarmUpCuFFT). A warning, saying what to do, when the cache is unusable or a plan
// is slow. Nothing when plan_ms is NaN: there is no GPU, so no cuFFT.
void LogCudaJitCache(Logger &logger, double plan_ms);