// SPDX-FileCopyrightText: 2024 Filip Leonarski, Paul Scherrer Institute // SPDX-License-Identifier: GPL-3.0-only #include #include #include "CUDAWrapper.h" #include "JFJochException.h" inline void cuda_err(cudaError_t val) { if (val != cudaSuccess) throw JFJochException(JFJochExceptionCategory::GPUCUDAError, cudaGetErrorString(val)); } int32_t get_gpu_count() { int device_count; cudaError_t val = cudaGetDeviceCount(&device_count); switch (val) { case cudaSuccess: return device_count; case cudaErrorNoDevice: case cudaErrorInsufficientDriver: return 0; default: throw JFJochException(JFJochExceptionCategory::GPUCUDAError, cudaGetErrorString(val)); } } std::vector get_gpu_names() { std::vector names; const int32_t count = get_gpu_count(); names.reserve(count); for (int32_t i = 0; i < count; i++) { cudaDeviceProp prop{}; // A device that cannot be queried still exists and still gets work, so it is listed - just // without a name. Losing the whole list over one unreadable device would be worse. if (cudaGetDeviceProperties(&prop, i) == cudaSuccess) names.emplace_back(prop.name); else names.emplace_back("unknown GPU"); } return names; } void set_gpu(int32_t dev_id) { auto dev_count = get_gpu_count(); // Ignore if no GPU present if (dev_count > 0) { if ((dev_id < 0) || (dev_id >= dev_count)) throw JFJochException(JFJochExceptionCategory::InputParameterInvalid, "Device ID cannot be negative"); cuda_err(cudaSetDevice(dev_id)); } } void pin_gpu() { static std::atomic counter{0}; auto dev_count = get_gpu_count(); if (dev_count > 0) set_gpu(counter.fetch_add(1) % dev_count); }