Overview
Epic Semi introduced Contrail AIX (Contrail Compute 5000 Series CPU+AI Superchip) at RISC-V Summit Europe 2026 (Bologna, June 8–12). Epic positions the platform as the “world’s first RISC-V AI Execution Platform” — not a training accelerator, but infrastructure purpose-built for the inference + reasoning + agentic + RAG workloads that define the post-training era.
The design consolidates CPU orchestration and AI execution into a single chip. The value proposition is structural: instead of streaming data and weights to a discrete GPU over PCIe, the AI acceleration cores sit on the same die and share memory coherently with the RISC-V cores, eliminating the “memory copy” latency and power penalty that traditional CPU+GPU systems pay on every inference call.
32 server-class RISC-V scalar cores + 16 integrated AI acceleration cores = 48-core heterogeneous design, up to 75 TOPS (INT8). Fully RVA23-compliant, supports RVV 1.0 and the new Vector Matrix Extension (VME). 4-channel DDR5-6400 up to 1 TB, 64-lane PCIe Gen5, CXL 2.0 memory expansion.
Compute Subsystem
Scalar Cores
32 high-performance server-class RISC-V cores — RVA23-compatible, single-core performance rated at >16/GHz SPECint2006. The cores support the RISC-V Hypervisor Extension (H Extension), giving native Type-1 and Type-2 hypervisor capability for cloud-native virtualization stacks (KVM, Kubernetes, Docker).
AI Acceleration Cores
16 integrated AI cores share a hardware-accelerated matrix computation engine. Combined throughput reaches 75 TOPS (INT8) with native support for INT4, INT8, FP16, FP32, and additional AI data formats. The accelerators are tightly coupled to the scalar cores via a coherent fabric, so inference calls don’t need explicit data movement.
RVV 1.0 + Vector Matrix Extension (VME)
The scalar cores execute RVV 1.0 vector code, while the AI engines implement the new Vector Matrix Extension (VME). VME introduces dedicated matrix-multiply-accumulate instructions that operate directly on the vector register file — the same model that drove AVX-512 + AMX adoption on x86. For RISC-V it removes the need to keep hand-rolling matrix kernels as long vector loops and is expected to become the standard AI extension across RVA23 server chips going forward.
Memory & I/O
DDR5 Memory
4-channel DDR5 at up to 6400 MT/s, scaling to 1 TB of system memory per socket. That’s the kind of capacity tier that lets you host a dense retrieval-augmented generation index entirely in DRAM, with the agent loop staying close to the data.
PCIe Gen5 + CXL 2.0
64 lanes of PCIe Gen5 with bifurcation support, plus a separate PCIe Gen3 expansion path. CXL 2.0 memory expansion lets a chassis pool CXL-attached memory across nodes — useful for KV-cache sharing, vector-database staging, and memory-bound retrieval workloads that don’t fit into local DDR5.
I/O Virtualization
RISC-V IOMMU with MSI interrupt virtualization — so virtual machines can directly assign NICs, NVMe controllers, and accelerators without host-mediated I/O. RISC-V AIA 1.0 (Advanced Interrupt Architecture) is supported for high-performance MSI/MSI-X routing in guest VMs.
Enterprise Virtualization & Security
Contrail AIX is designed to drop into the same operational stack as an x86 or Arm server:
- Hardware virtualization: full RISC-V H Extension + IOMMU + MSI virtualization. Optimized for KVM, Docker, Kubernetes.
- Trusted secure boot: hardware-rooted chain of trust from firmware to OS to workload.
- Hardware encryption acceleration: RSA-2048, SHA-512, AES-256, plus additional algorithms for full-chip security management — mandatory for sovereign-AI and regulated workloads.
- RAS: server-grade Reliability, Availability, Serviceability architecture, including CE / UC / UCE error detection and recovery, full-chip temperature monitoring, DVFS dynamic frequency and power management.
Software Stack
The platform is not delivered as bare hardware — Epic includes (or certifies) the full cloud-native open-source stack out of the box:
- OS: Ubuntu, Debian, RHEL-compatible distributions.
- Virtualization: KVM, QEMU.
- Containers / Orchestration: Docker, Kubernetes.
- Compilers: LLVM, GCC.
- AI Compiler: MLIR + IREE (the path that PyTorch / ONNX models take to land on RISC-V).
- Storage: Ceph, SPDK for kernel-bypass NVMe.
The IREE choice matters: MLIR-based compilation lets you take a model authored once (PyTorch, JAX, ONNX) and lower it through the same toolchain to the RVV 1.0 vector units on the scalar cores and the VME matrix engines, so a single model graph can be partitioned and scheduled across both fabrics.
Workload Targets
Epic’s message is consistent with what RISC-V International has been saying since the Server Platform Spec 1.0 ratification: 2026 is the year RVA23-class server silicon arrives, and the workloads to focus on are post-training AI — not greenfield training clusters. Concretely:
- LLM inference at single-digit ms latency budgets for 7B–70B models.
- RAG pipelines — vector search + LLM reasoning + memory-resident context.
- Agentic AI orchestration — multi-agent loops where the orchestrator is the CPU and each tool call drops into the on-chip AI engines.
- Edge AI and sovereign-AI deployments that need to run in-country without GPU dependencies.
- Cloud-native AI services on Kubernetes.
Reference Server Configuration
The launch ships a 1U-class enterprise server around the superchip:
| Component | Specification |
|---|---|
| CPU+AI Superchip | 1× Contrail Compute 5000 Series (RVA23 + VME) |
| Memory | 256 GB DDR5 (4× 64 GB @ 6400 MHz), upgradable to 1 TB |
| Boot / OS Drive | 1× 1 TB NVMe M.2 SSD |
| Data Drives | 2× 7.68 TB NVMe SSDs |
| Network | 1× OCP 3.0 NIC (Broadcom 57414, 10/25 GbE) |
| Power Supply | 1300 W Platinum efficiency |
| Cooling | 4× 80 mm fan modules, high-performance heatsink with air duct |
| PCIe | 64 lanes PCIe Gen5 + PCIe Gen3 expansion |
A future dual-socket variant, Contrail Compute 5050, scales single-core performance further and supports up to 4 TB DDR5, positioning it for HPC and large-model training-adjacent research workloads while keeping the open-RISC-V foundation.
Why This Matters for the RISC-V Ecosystem
Contrail AIX sits at the center of the broader 2026 RISC-V inflection point:
- The RVA23 Server Platform Spec 1.0 (ratified mid-2026) finally delivers a standardized boot + runtime contract (UEFI, ACPI 6.6, SBI, BMC, security), so multiple vendors’ server chips can run identical distros.
- Canonical Ubuntu 26.04 LTS ships full RVA23 support, removing the “build your own kernel” friction that hampered earlier generation hardware.
- SiFive, Akeana, NextSilicon, and StarFive have all announced server-class silicon in the same window. Epic Semi’s bet is that the right niche isn’t “yet another server CPU” but the AI-execution platform thesis — moving intelligence from “trained and then forgotten on disk” to “continuously executed close to the data.”
The Volta / Hopper-class “train bigger, run bigger” mantra doesn’t apply when the question is “how do I orchestrate 50 agents across a private cloud without burning 50 H100s?” Contrail AIX targets exactly that workload with a fully open ISA, open firmware, and open cloud stack.