Expand description
§RingKernel Core
Core traits and types for the RingKernel GPU-native persistent actor system.
This crate provides the foundational abstractions for building GPU-accelerated actor systems with persistent kernels, lock-free message passing, and hybrid logical clocks for temporal ordering.
§Core Abstractions
RingMessage- Trait for messages between kernelsMessageQueue- Lock-free ring buffer for message passingRingKernelRuntime- Backend-agnostic runtime managementRingContext- GPU intrinsics facade for kernel handlersHlcTimestamp- Hybrid Logical Clock for causal ordering
§Example
ⓘ
use ringkernel_core::prelude::*;
#[derive(RingMessage)]
struct MyMessage {
#[message(id)]
id: MessageId,
payload: Vec<f32>,
}Re-exports§
pub use context::RingContext;pub use control::ControlBlock;pub use domain::Domain;pub use domain::DomainMessage;pub use error::Result;pub use error::RingKernelError;pub use hlc::HlcTimestamp;pub use memory::DeviceMemory;pub use memory::GpuBuffer;pub use memory::MemoryPool;pub use memory::PinnedMemory;pub use message::priority;pub use message::MessageHeader;pub use message::MessageId;pub use message::Priority;pub use message::RingMessage;pub use queue::MessageQueue;pub use queue::QueueStats;pub use runtime::Backend;pub use runtime::KernelHandle;pub use runtime::KernelId;pub use runtime::KernelState;pub use runtime::KernelStatus;pub use runtime::LaunchOptions;pub use runtime::RingKernelRuntime;pub use telemetry::TelemetryBuffer;pub use types::BlockId;pub use types::GlobalThreadId;pub use types::ThreadId;pub use types::WarpId;
Modules§
- alerting
- Alert routing system for enterprise monitoring.
- analytics_
context - Analytics context for grouped buffer lifecycle management.
- audit
- Audit logging for enterprise security and compliance.
- auth
- Authentication framework for RingKernel.
- checkpoint
- Kernel checkpointing for persistent state snapshot and restore.
- config
- Unified configuration for RingKernel enterprise features.
- context
- Ring context providing GPU intrinsics facade for kernel handlers.
- control
- Control block for kernel state management.
- dispatcher
- Multi-Kernel Message Dispatcher
- domain
- Business domain classification for kernel messages.
- error
- Error types for RingKernel operations.
- health
- Health monitoring and resilience infrastructure for RingKernel.
- hlc
- Hybrid Logical Clock (HLC) implementation for causal ordering.
- hybrid
- Hybrid CPU-GPU Processing
- k2k
- Kernel-to-Kernel (K2K) direct messaging.
- logging
- Structured logging with trace correlation.
- memory
- GPU and host memory management abstractions.
- message
- Message types and traits for kernel-to-kernel communication.
- multi_
gpu - Multi-GPU coordination, topology discovery, and cross-GPU messaging.
- observability
- Observability infrastructure for RingKernel.
- persistent_
message - Persistent Message Traits for Type-Based Kernel Dispatch
- prelude
- Prelude module for convenient imports
- pubsub
- Topic-based publish/subscribe messaging.
- queue
- Lock-free message queue implementation.
- rate_
limiting - Rate limiting for enterprise workloads.
- rbac
- Role-Based Access Control (RBAC) for RingKernel.
- reduction
- Global Reduction Primitives
- resource
- Resource guard module for preventing system overload.
- runtime
- Runtime traits and types for kernel management.
- runtime_
context - Unified runtime context for RingKernel enterprise features.
- secrets
- Secrets management for secure key storage and retrieval.
- security
- Security features for GPU kernel protection and compliance.
- state
- Control block state helpers for GPU-compatible kernel state.
- telemetry
- Telemetry and metrics collection for kernel monitoring.
- telemetry_
pipeline - Real-time telemetry pipeline for streaming metrics.
- tenancy
- Multi-tenancy support for RingKernel.
- timeout
- Operation-level timeouts and deadline management.
- types
- Core type definitions for GPU thread identification and coordination.
Macros§
- gpu_
profile - Macro for scoped GPU profiling.