Found 14 packages
Core abstractions and interfaces for DotCompute compute acceleration framework. Contains accelerator interfaces, kernel definitions, and memory abstractions.
Unified memory management for DotCompute. Provides zero-copy buffers, memory pooling, and cross-device memory transfers.
Core runtime and abstractions for DotCompute compute acceleration framework. Provides kernel execution, accelerator management, and service orchestration.
Plugin system for DotCompute compute acceleration framework. Provides hot-reload capability, plugin discovery, circuit breaker patterns, and fault tolerance infrastructure.
Production-ready NVIDIA CUDA GPU backend for DotCompute. Provides GPU acceleration (21-92x speedup) through CUDA with NVRTC compilation, P2P transfers, Ring Kernels with NCCL support, and unified memory. Requires CUDA 12.0+ and Compute Capability 5.0+ NVIDIA GPU. Benchmarked on RTX 2000 Ada (CC 8.9).
GPU-accelerated algorithms for DotCompute. Includes FFT, AutoDiff, sparse matrix operations, signal processing, and cryptographic primitives.
Runtime services and dependency injection integration for DotCompute. Provides kernel execution orchestration, automatic kernel discovery, service registration, and DI container integration with Microsoft.Extensions.DependencyInjection. Production-ready with comprehensive service lifetime management.
Production-ready OpenCL backend for DotCompute. Cross-platform GPU acceleration for NVIDIA, AMD, Intel, ARM Mali, and Qualcomm Adreno GPUs. Supports OpenCL 1.2+, Ring Kernels with atomic message queues, runtime kernel compilation, and multi-device workload distribution. Works with nvidia-opencl-icd, ROCm, intel-opencl-icd, and vendor drivers.
Production-ready CPU compute backend for DotCompute. Provides SIMD vectorization (3.7x faster) using AVX2/AVX512/NEON instructions, multi-threaded kernel execution, and Ring Kernel simulation. Benchmarked: Vector Add (100K elements) 2.14ms → 0.58ms. Native AOT compatible with sub-10ms startup.
GPU-accelerated LINQ extensions for DotCompute. Transparent GPU execution for LINQ queries with automatic kernel generation, fusion optimization, and Reactive Extensions support.
Package Description
Metal backend for DotCompute with GPU acceleration for Apple Silicon (macOS/iOS). Foundation complete with native API bindings, device management, unified memory support, and command buffer execution. MSL (Metal Shading Language) compilation in development. Supports M1/M2/M3/M4 and A-series chips.
Attributes and enums for DotCompute kernel definition. This package provides the [Kernel], [RingKernel], and [RingKernelMessage] attributes used to define compute kernels.
DotCompute backend provider for Orleans.GpuBridge.Core - Enables GPU acceleration via CUDA, OpenCL, Metal, and CPU with attribute-based kernel definition.