Skip to main content

Hygon Shensuan DCU

Vendor: Hygon

Category: ASIC Dedicated Accelerator

Architecture: GPGPU (ROCm-compatible)

Introduction

Hygon Shensuan series DCU (GPGPU). The only domestic vendor with both x86 CPU and GPGPU DCU dual-chip products. Shensuan Z100/ZK2 series is compatible with ROCm/CUDA ecosystem, with FP64 double precision at approximately 10 TFLOPS, suitable for HPC+AI hybrid scenarios. Approximately 83,000 units shipped in 2025, market cap of 330 billion RMB.

Specifications

ModelComputeMemoryInterfaceTDPProcess
Shensuan II (K100-AI)192 TFLOPS (FP16) / 49 (FP32)64GB HBM2OAM300W7nm
Shensuan I (Z100)21.6 TFLOPS (FP16) / 10.8 (FP32)32GB HBM2PCIe 4.0250W7nm

Official Website

Visit Official Website

Driver Downloads

Linux

OS Support

WindowsLinuxmacOSAndroid
⚠️ (Partial)

Version History

VersionRelease DateDescription
DTK 3.02024Z200 support + CUDA compatibility optimization
DTK 2.52023PyTorch compatibility layer enhancement

Performance Benchmarks

ModelTaskPerformance Metric
Shensuan II Z200BF16 TrainingNear MI250X efficiency
Shensuan I Z100General AI InferenceCompatible with ROCm ecosystem

Pricing

ModelReference PriceNotes
Z200Contact vendorDomestic alternative to AMD Instinct
Z100Contact vendorIn mass production

Quick Installation

Linux (Kylin / UOS / Ubuntu)

# Hygon DCU is compatible with ROCm ecosystem
# Install DCU driver (similar to ROCm)
sudo ./dcu-driver-*.run --install

# Verify
dcu-smi

Code Examples

Python (Hygon DCU PyTorch)

import torch
# Hygon DCU is compatible with ROCm/CUDA backend
assert torch.cuda.is_available()
print(f"DCU: {torch.cuda.get_device_name(0)}")

Architecture Highlights

  • GPGPU Architecture: Based on AMD Zen architecture license + proprietary DCU design, compatible with ROCm ecosystem
  • Domestic Substitution: Independent R&D based on AMD license, targeting the Xinchuang/domestic substitution market
  • ROCm-like Ecosystem: Can directly use ROCm toolchain and PyTorch ROCm versions

Model Compatibility

Model/FrameworkSupportNotes
PyTorch✅ ROCmROCm backend compatible
Kylin/UOS✅ NativeDomestic OS adaptation
General AI⚠️Via ROCm ecosystem
Large Model Training⚠️Gradually improving

If you're evaluating alternatives, the following products may also fit your scenario: