Graphcore Bow Pod1024
by Graphcore · enterprise · Last verified 2026-03-30
The Graphcore Bow Pod1024 is a supercomputing-scale AI system, delivering over 250 PetaFLOPS of AI compute. It leverages 1,024 Bow IPU processors linked by a high-bandwidth fabric, specifically engineered for training massive, next-generation AI models and complex graph analytics workloads at an unprecedented scale.
https://www.graphcore.com/products/bow-pod1024 ↗C+
C+—Average
Adoption: C+Quality: AFreshness: A+Citations: C+Engagement: B
Specifications
- License
- Proprietary
- Pricing
- enterprise
- Capabilities
- Massively Parallel MIMD Architecture, Over 250 PetaFLOPS of AI Compute, Wafer-on-Wafer (WoW) 3D Stacking Technology, High-Speed IPU-Fabric Interconnect, Large In-Processor Memory for Model Parallelism, Optimized for Sparsity and Graph-based Models, Poplar SDK for Graph Compilation and Execution, Support for PyTorch, TensorFlow, and ONNX, Scalable from 16 to 1024 IPUs
- Integrations
- [object Object], [object Object], [object Object], [object Object], [object Object]
- Use Cases
- [object Object], [object Object], [object Object], [object Object]
- API Available
- Yes
- Tags
- ipu, ai-hardware, supercomputer, hpc, large-scale-ai, llm-training, graph-analytics, deep-learning, parallel-computing, wafer-on-wafer, mimd
- Added
- 2026-03-30
- Completeness
- 0.95%
Index Score
59.5Adoption
55
Quality
80
Freshness
90
Citations
50
Engagement
60