Wirewalk Instituteof AI
hw-301 Expert Waitlist

AI Accelerators Beyond GPUs: TPU, Trainium, Gaudi and Wafer-Scale

For senior hardware and infrastructure engineers who must evaluate non-GPU AI accelerators on architecture, system design, software maturity and total cost, and decide when one beats a GPU for a given workload.

The curriculum is being prepared and reviewed. Enrollment is not open yet.

About this course

GPUs dominate AI compute, but a growing share of training and inference runs on accelerators built around different bets: large systolic arrays with compiler-scheduled dataflow, on-chip SRAM instead of HBM, whole-wafer silicon, or chips co-designed with a single company's models. This course teaches the architecture behind those bets well enough to predict where each wins and where it struggles. It opens with the design space (spatial versus temporal architectures, systolic arrays, dataflow, SRAM-versus-HBM memory strategies and deterministic scheduling) and the roofline and memory-capacity reasoning that separates them.

It then examines the platforms current in October 2026: Google TPUs through Trillium and Ironwood (TPU v7) with optical circuit-switched pods and the JAX and XLA stack; AWS Trainium2 and Trainium3 UltraServers, Inferentia2 and the Neuron SDK; Intel Gaudi 3 and Intel's announced Crescent Island inference GPU; Cerebras WSE-3 and CS-3 systems; Groq LPUs, including NVIDIA's Groq 3 LPX inference accelerator for Vera Rubin following NVIDIA's December 2025 licensing agreement with Groq; SambaNova reconfigurable dataflow units; Tenstorrent; Qualcomm AI200 and AI250; and in-house chips such as Microsoft Maia 200 and Meta MTIA. Each is treated through the same lens: compute and number formats, memory hierarchy, scale-up and scale-out interconnect, compiler and framework support, availability model (cloud-only or purchasable), and operational maturity. The course closes with a rigorous evaluation method: workload characterization, porting cost, benchmark design that avoids vendor-favorable traps, and total-cost modeling. Vendor performance figures are presented as vendor claims; announced-but-not-shipping products are labeled. The course ends with an automated exam and a Wirewalk Institute certificate of completion and assessment; it is not a vendor certification.

What you will be able to do

  • Classify accelerator architectures by compute organization, memory strategy and scheduling model, and predict the workloads each favors
  • Explain systolic-array and dataflow execution and the role of the compiler in mapping models onto them
  • Compare Google TPU, AWS Trainium and Inferentia, Intel Gaudi, Cerebras, Groq, SambaNova and hyperscaler in-house accelerators on compute, memory, interconnect and software maturity
  • Analyze SRAM-centric and wafer-scale designs for capacity limits, model-sharding requirements and latency advantages
  • Assess the porting cost and operational risk of moving a training or inference workload from GPUs to a non-GPU accelerator
  • Design a fair benchmark comparing an accelerator with a GPU baseline, controlling for precision, batch size, sequence length and system scale
  • Build a total-cost and risk model that supports a defensible accelerator decision for a stated workload

Syllabus

6 modules · 21 lessons · about 18 hours

Module 1: The Accelerator Design Space

The architectural choices that distinguish non-GPU accelerators and how to reason about them.
4 lessons
  1. Spatial Versus Temporal Architectures: Systolic Arrays, Dataflow and SIMT
  2. Memory Strategies: HBM-Centric, SRAM-Centric and Hybrid Designs
  3. Compiler-Scheduled Execution and Determinism
  4. Roofline and Capacity Reasoning Across Architectures

Module 2: Google TPU

TPU architecture, pods and the software stack, from Trillium to Ironwood.
3 lessons
  1. TPU Architecture: MXUs, SparseCores and HBM
  2. Ironwood and TPU Pods: ICI, Optical Circuit Switching and Slices
  3. XLA, JAX and PyTorch on TPU: What Ports Easily and What Does Not

Module 3: AWS Trainium and Inferentia

AWS's training and inference silicon, UltraServers and the Neuron stack.
3 lessons
  1. Trainium Architecture: NeuronCores, HBM and Number Formats
  2. Trainium3 UltraServers and NeuronLink Scale-Up
  3. Inferentia2 and the Neuron SDK: Compilation, Kernels and Framework Support

Module 4: Intel Gaudi and Merchant Alternatives

Gaudi's Ethernet-native design, Intel's roadmap, and other purchasable accelerators.
3 lessons
  1. Gaudi 3: Matrix Engines, TPCs and Integrated Ethernet Scale-Out
  2. Intel's Roadmap: Crescent Island and Beyond
  3. Tenstorrent, Qualcomm AI200 and AI250 and Other Merchant Options

Module 5: Wafer-Scale, LPU and Dataflow Designs

Cerebras, Groq and SambaNova, and the in-house chips of hyperscalers.
4 lessons
  1. Cerebras WSE-3 and CS-3: Wafer-Scale Compute and Weight Streaming
  2. Groq LPUs and NVIDIA Groq 3 LPX: Deterministic SRAM Inference
  3. SambaNova Reconfigurable Dataflow and Three-Tier Memory
  4. Hyperscaler In-House Chips: Microsoft Maia and Meta MTIA

Module 6: Evaluating and Choosing an Accelerator

A disciplined method for comparing accelerators with GPUs and making a defensible decision.
4 lessons
  1. Workload Characterization: Prefill, Decode, Training and Fine-Tuning
  2. Fair Benchmarking: Precision, Batch, Sequence Length and Scale
  3. Porting Cost, Software Maturity and Vendor Risk
  4. Total Cost Modeling and the Decision Memo

Exam and certificate

The exam unlocks once you have completed every lesson. It draws 25 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 55 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by Google Cloud, AWS, Intel, Cerebras, Groq, NVIDIA, SambaNova, Microsoft, Meta, Qualcomm, Tenstorrent, or AMD. Product and company names are trademarks of their respective owners.

hw-001 Free intro Available

Inside an AI Data Center: GPUs, Networks and Storage in One Hour

A plain-English, one-hour walk through an AI data center: what a model asks of hardware, what is inside a GPU server, how GPUs talk over NVLink, InfiniBand and Ethernet, where the data lives, and why AI racks need so much power and cooling.

1 h · 6 lessons Free intro
hw-101 Basic Available

AI Hardware Fundamentals: GPUs, CPUs, Memory, Networking and Storage

A plain-language tour of the hardware that runs AI: why AI is limited by compute, memory bandwidth and data movement; what GPUs, HBM and precision formats are; how servers, networks, storage, power and cooling fit together; and how to size a simple inference or training system and weigh cloud against buying.

8 h · 20 lessons See price at checkout
hw-201 Intermediate Available

GPU Hardware Deep Dive: Architecture, Memory and Interconnects

An engineer's tour of the modern data center GPU: how SMs and CUs, warps and wavefronts, tensor and matrix cores and the on-chip memory hierarchy work; what FP64 through FP4 and sparsity really buy you; how HBM, PCIe, NVLink, Infinity Fabric, UALink and CXL move data; and how power, cooling and reliability features shape real deployments. Reviewed against vendor sources as of October 2026.

14 h · 21 lessons See price at checkout