docs(readme): convert README.adoc -> Markdown (renders on Glama/profile/community-health)

README.md

@@ -0,0 +1,82 @@
+<!--
+SPDX-License-Identifier: CC-BY-SA-4.0
+SPDX-FileCopyrightText: 2025-2026 Jonathan D.A. Jewell <j.d.a.jewell@open.ac.uk>
+-->
+
+[![Topology](https://img.shields.io/badge/Project-Topology-9558B2)](TOPOLOGY.md)
+[![85](https://img.shields.io/badge/Completion-85%25-green)](TOPOLOGY.md) [![OpenSSF Best Practices](https://img.shields.io/badge/OpenSSF-Best_Practices-green?logo=opensourcesecurity)](https://www.bestpractices.dev/en/projects/new?repo_url=https://github.com/hyperpolymath/LowLevel.jl) ![License:
+PMPL-1.0](https://img.shields.io/badge/License-MPL--2.0-blue.svg) <embed
+src="https://api.thegreenwebfoundation.org/greencheckimage/github.com"
+data-link="https://www.thegreenwebfoundation.org/green-web-check/?url=github.com" />
+![Peak System](https://img.shields.io/badge/Status-Peak_System-red.svg)
+
+**The Definitive Bare-Metal & Coprocessor Foundation for Julia.**
+
+<div id="toc">
+
+</div>
+
+# Overview
+
+LowLevel.jl is not just a bridge; it is a **Resource-Aware Hardware
+Orchestrator**. It provides the Hyperpolymath ecosystem with deep-cycle
+diagnostics, self-healing fault tolerance, and native execution paths
+for every major processing unit in modern and future computing.
+
+It is designed for "High-Stakes Silicon"—where performance is
+non-negotiable and failure must be mathematically impossible.
+
+# Core Architectural Pillars
+
+## 1. Universal Coprocessor Support (X-PU)
+
+LowLevel.jl provides specialized kernels and dispatch logic for: \*
+**CPU**: Optimized for **Intel Core i9/Xeon** (AVX-512) and **AMD Ryzen
+9/Pro** (Zen 4/5 extensions). \* **GPU**: Native hooks for NVIDIA
+(CUDA), AMD (ROCm), and Apple (Metal). \* **NPU/TPU**: Dedicated paths
+for Neural and Tensor units (Intel NPU, Google TPU). \* **QPU**: Quantum
+Processing Unit abstraction layer for hybrid classical-quantum
+algorithms. \* **PPU/MPU**: Physics and Mathematical Processing Units
+for high-fidelity simulations. \* **DSP/APU**: Digital Signal and
+Audio/Accelerated Processing Units. \* **IOPU**: Specialized I/O
+Processing for high-frequency data ingestion.
+
+## 2. Resilience & Self-Healing
+
+- **Diagnostics**: Real-time monitoring of thermal throttling, cache
+  misses, and branch mispredictions.
+
+- **Self-Healing**: Automated kernel hot-swapping. If an AVX-512 kernel
+  triggers a hardware fault, the system transparently downgrades to a
+  verified scalar fallback.
+
+- **Fault-Tolerance**: Integration with Julia’s task system to handle
+  hardware-level MCE (Machine Check Exceptions) without crashing the
+  runtime.
+
+## 3. Resource Awareness
+
+- **Topology Mapping**: Deep awareness of NUMA nodes, L1/L2/L3 cache
+  boundaries, and memory bandwidth saturation.
+
+- **Energy-Aware Computing**: Dynamic frequency scaling hooks to
+  optimize for performance-per-watt during massive research simulations.
+
+# Project Structure
+
+```text
+LowLevel.jl/
+├── src/
+│   ├── LowLevel.jl           # Main Orchestrator
+│   ├── hardware/             # Topology & Feature Detection
+│   ├── accelerators/         # NPU, TPU, QPU, GPU modules
+│   ├── resilience/           # Self-healing & Fault tolerance
+│   ├── diagnostics/          # Telemetry & Performance monitoring
+│   ├── asm/                  # Multi-arch Assembly (x86, ARM, RISC-V)
+│   └── zig/                  # Safe systems logic
+└── deps/                     # Binary artifacts
+```
+
+# License
+
+Palimpsest-MPL-1.0 License.