Jungfraujoch/common/CUDAWrapper.h

// SPDX-FileCopyrightText: 2024 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only

#pragma once

#include <chrono>
#include <cstdint>
#include <string>
#include <vector>

int32_t get_gpu_count();

// Names of the visible GPUs, in device order and one entry per device, so repeated cards repeat.
// Empty without CUDA and on a machine with no device, which is also what get_gpu_count() == 0 says.
std::vector<std::string> get_gpu_names();

// The same list collapsed for a person: "4x NVIDIA A100-SXM4-80GB", or several such groups separated
// by ", " on a mixed machine. Empty when no GPU is visible.
std::string get_gpu_description();
void set_gpu(int32_t dev_id);

// Pin the calling thread to the next GPU in round-robin order, using a process-wide counter
// (counter++ % get_gpu_count()). Call once per thread; no thread id needed. No-op when no GPU
// is visible. Honours CUDA_VISIBLE_DEVICES via get_gpu_count().
void pin_gpu();

// From here on, pin_gpu() also keeps the calling thread on the CPUs of the NUMA node its GPU is
// attached to (ThreadAffinity.h) - on a machine with one node, or without CUDA, nothing changes.
// Off unless a program asks for it.
void enable_gpu_numa_binding();

// pin_gpu() onto a given device: set_gpu(dev_id), and the NUMA binding above where it is enabled.
// For a worker that takes its card by index rather than round-robin.
void pin_gpu(int32_t dev_id);

// pin_gpu(dev_id) for as long as the object lives; then the calling thread gets back the device and
// the CPUs it had before. For a thread that drives a card only for a while - the merging engine, whose
// calls come from a thread that goes on to other work - where a pin for the rest of its life would
// carry the card's node onto everything that thread does, and starts, afterwards.
class ScopedGpuPin {
public:
    explicit ScopedGpuPin(int32_t dev_id);
    ~ScopedGpuPin();
    ScopedGpuPin(const ScopedGpuPin &) = delete;
    ScopedGpuPin &operator=(const ScopedGpuPin &) = delete;
private:
    int32_t prev_device = -1;   // -1: nothing to give back
    std::vector<int> prev_cpus;  // empty: the CPUs were not changed
};

// Have every GPU's host threads BLOCK in a synchronisation (cudaDeviceScheduleBlockingSync) instead
// of spinning on a core until the device finishes. Must be called before anything creates a CUDA
// context; it creates none itself. No-op without CUDA.
void set_gpu_blocking_sync();

// Create the CUDA context of every device from first_device on, one thread per device, and return
// when they all exist - for a caller that runs it beside other work, so that the first use of a card
// does not wait for its context. No-op without CUDA.
void create_gpu_contexts(int32_t first_device);

// Destroy every device's CUDA context, one thread per device, for a program about to exit with no
// CUDA work left: at exit the runtime destroys them one after another, a fifth of a second per card.
// No-op without CUDA.
void release_gpu_contexts();

// Drop the error CUDA has recorded for the calling thread. Call it where a CUDA failure has been
// HANDLED - a device route that fell back to the host, an indexing attempt whose failure was turned
// into a result - because the error otherwise stays as the thread's last error and the next
// cuda_err(cudaGetLastError()) after some later kernel launch reports it, over work that went fine.
// A sticky error (an illegal access, say) is not cleared by this, and nothing here pretends it is:
// the context is gone in that case and every later call fails on its own. No-op without CUDA.
void cuda_clear_error();

// Throw if the CUDA context is lost - a sticky error (an illegal access, say) that every later call
// on this device will fail with. For a device route about to fall back to the host: there is no
// fallback from that, and falling back only moves the failure somewhere less clear. A handled,
// non-sticky failure passes. No-op without CUDA.
void cuda_throw_if_context_lost();

// GPU work that runs beside the main line of a process and gives all of its device memory back when it
// ends: a probe pass run on a copy of the run while the run itself scales and merges. Hold one for as
// long as that work runs. Build-independent - it only counts.
class GPUWorkBeside {
public:
    GPUWorkBeside();
    ~GPUWorkBeside();
    GPUWorkBeside(const GPUWorkBeside &) = delete;
    GPUWorkBeside &operator=(const GPUWorkBeside &) = delete;
};

// Wait until no GPUWorkBeside is held, for at most `timeout`. True once none is - at once if none was.
bool wait_for_gpu_work_beside(std::chrono::seconds timeout);