PennyLane
Install
Install
  1. Blog/
  2. High-Performance Computing/
  3. One program to drive them all, PennyLane to define them, Grace Hopper to decode them all, and Backline to bind them.

November 17, 2026

One program to drive them all, PennyLane to define them, Grace Hopper to decode them all, and Backline to bind them.

Hong-Sheng Zheng

Hong-Sheng Zheng

Ali Farazdaghi

Ali Farazdaghi

Joseph Lee

Joseph Lee

Cheick Doumbia

Cheick Doumbia

Lee O'Riordan

Lee O'Riordan

Josh Izaac

Josh Izaac

What does it take to run a Backline program on a different machine, with a different RDMA engine on the FPGA? Only a few settings on the controller and the coprocessor. Backline now runs on the NVIDIA GH200 Grace Hopper™ Superchip and, alongside AMD ERNIC™ and NVIDIA's open-source Holoscan Sensor Bridge, it supports ETH Zurich's open-source BALBOA RDMA engine — so neither the coprocessor nor the RDMA engine ties you to one vendor, and your quantum program stays the same.

Since we announced Backline with AMD in September, the question we hear most often from groups building quantum control systems is a simple one — will it work with our hardware?

It's a fair question. Control systems for different qubit technologies are built from very different classical hardware, with different FPGAs, network cards and host machines, and with different rules about which IP a team can license or change. For Backline to be useful across the ecosystem, it has to meet each group where its hardware already is.

In our last post, we added NVIDIA's Holoscan Sensor Bridge (HSB) to Backline, and showed how much the RDMA engine on the FPGA can change the round trip. Today, we're changing the other end of the link too. Backline now runs on Grace Hopper, with its Arm-based Grace CPU or its H100 GPU answering each round, and it supports a third RDMA engine, ETH Zurich's BALBOA.

So, whichever coprocessor and RDMA engine you choose — or bring yourself — your quantum program stays the same.

Read on to see a full Backline program running on Grace Hopper, how the three RDMA engines fare there, and how to bring your own.

What's new?

Here's a complete Backline program, with an AMD Versal™ VPK120 FPGA as the controller, Grace Hopper's H100 GPU as the coprocessor, and BALBOA as the RDMA engine:

import pennylane as qp

FPGA = qp.Controller(
    name="fpga-controller",
    remote=True,
    hardware="fpga",
    backend="balboa_hwhs",  # "hsb_hwhs" for HSB, or "hwhs" (default) for ERNIC
    executor_options={**FPGA_SERVER, "port": 9811},
)

GPU = qp.Coprocessor(
    name="gpu-coproc",
    coprocessor_fn="gpu_steane_launcher",
    remote=True,
    hardware="gpu",  # the H100
    endpoint=qp.Endpoint(GH200_ADDRESS, 7760),  # an address the board's Arm cores can reach
    executor_options={**GH200_SERVER, "port": 9813},
    # peer=hsb for HSB, or peer=catalyst (default) for ERNIC
    init_args={"config": "dev=mlx5_1;gid=5;peer=balboa"},
)

dev = qp.Backline(controller=FPGA, coprocessors=[GPU], transport="rdma", qec_code="steane")

@qp.qjit(capture=True)
@qp.set_shots(1000)
@qp.qnode(dev, mcm_method="one-shot")
def ghz():
    qp.Hadamard(0)
    qp.CNOT([0, 1])
    qp.CNOT([1, 2])
    return qp.sample([qp.measure(0), qp.measure(1), qp.measure(2)])

Here, FPGA_SERVER and GH200_SERVER hold the connection details for the FPGA board and Grace Hopper server respectively. Simply load the BALBOA bitstream (the FPGA design available via the backline-vpk120 repository) onto the board, and set the RDMA engine in two places — the controller’s backend argument, and the coprocessor's peer, which tells it which RDMA engine sits on the other end of the link.

As a reminder from our last post, the RDMA engine is the block of logic on the FPGA that turns data into network packets and back, using RDMA over Converged Ethernet (RoCE v2). In addition to AMD's ERNIC and NVIDIA's HSB, Backline now supports ETH Zurich's BALBOA. Like ERNIC, it uses reliable connections, and like HSB, it's open source (under the BSD 3-Clause and MIT licenses).

Three RDMA engines on Grace Hopper

How does this work (and perform!) in practice? To find out, we joined the VPK120 FPGA to an NVIDIA ConnectX®-7 network card in the GH200 by a single direct attach cable, with no switch in between, as in our last post. We then loaded each RDMA engine's bitstream in turn, and used Backline's benchmark harness to run a million rounds of an echo — where the coprocessor sends each request straight back without decoding it — with first the Grace CPU and then the H100 GPU answering each round.

The setup: one program running across an AMD Versal VPK120 FPGA and an NVIDIA GH200 Grace Hopper, joined by a direct attach cable
On the AMD Versal VPK120 FPGA, Backline's hardware handshake sits in front of whichever RDMA engine the bitstream holds — HSB, BALBOA or ERNIC. A single 100 Gbps connection joins the FPGA to a ConnectX-7 network card in the GH200, where the Grace CPU or the H100 GPU answers each round. The Python program is compiled and deployed to different parts of the machine for execution.

On Grace Hopper, the RDMA engine you pick changes the round trip by about 0.5 µs, whether the Grace CPU or the H100 GPU answers each round.

Histograms of a million echo round trips per RDMA engine, to the Grace CPU and to the H100 GPU
Every round of the echo, a million per RDMA engine, to the Grace CPU and to the H100 GPU. Counts are on a log scale, and past the break each axis jumps ahead to show the slowest rounds.

HSB has the lowest round trip of the three to both coprocessors, while BALBOA and ERNIC sit level on the median (the difference between those two instead shows up in the tail — ERNIC's is much longer than BALBOA's).

CoprocessorRDMA engineMedian (µs)99.999th pct. (µs)Rounds above 3 µs (CPU) / 6 µs (GPU)
Grace CPUHSB2.102.231
Grace CPUBALBOA2.643.2226
Grace CPUERNIC2.663.95668
H100 GPUHSB4.55.52
H100 GPUBALBOA5.05.50
H100 GPUERNIC5.06.375
Echo round trips from the VPK120 FPGA to the GH200 and back, a million rounds each, with the first dropped. GPU numbers have been rounded to one decimal place, since the median falls between the GPU's two bands and moves by up to 0.1 µs from run to run.

The open, swappable stack

With the addition of HSB and BALBOA to the PennyLane, Catalyst, and Backline stack, the RDMA engine is no longer a black box — you can read it, change it, or replace it with your own.

And this is critically important! The network stack affects more than the median latency. It also sets the tail of the latency distribution, how many FPGA resources you use up, which licenses apply to your design, and whether you can open the stack up and change it. Different needs require different choices, and Backline should work with all of them.

Not only that, but with HSB or BALBOA in the bitstream, every layer from your PennyLane program down to the RDMA engine on the FPGA can be open source (depending on your system's configuration!). With ERNIC, the RDMA engine itself is AMD's licensed IP.

What's open source and what's vendor-licensed on the controller and the coprocessor, with the claim bracketing everything from the program down to the RDMA engine
What's open source and what's vendor-licensed.

Which RDMA engine should I use?

Each RDMA engine makes a different trade-off, so you can pick the one that suits your experiment:

If you need...UseController backendCoprocessor peer
The shortest round trip over a direct attach cableNVIDIA HSB (Apache 2.0)hsb_hwhspeer=hsb
Reliable connections from an open-source engineETH Zurich BALBOA (BSD 3-Clause, MIT)balboa_hwhspeer=balboa
Reliable connections or many producers, with AMD IP already in many Versal designsAMD ERNIChwhs (default)peer=catalyst (default)
Something none of these engines doesYour ownThe name in your manifestpeer=catalyst, or your own coprocessor backend

Want to bring your own RDMA engine? Backline supports that as well. Build it into your bitstream behind Backline's hardware handshake, as we did for HSB and BALBOA, then write a library that implements Backline's controller interface. The name and settings for the engine live in a small JSON manifest — that name is what you pass as the controller's backend.

For more details, see Catalyst's Backline developer documentation.

Try it out and get involved

Backline now runs on Grace Hopper with three RDMA engines to choose from on the FPGA. Whichever coprocessor and RDMA engine you choose, your quantum program stays the same.

We're excited to see which RDMA engines you use with Backline, whether it's one of the many designs already out there, or one you've built for your own control system.

Ready to try Backline on Grace Hopper? Here's where to start:

  • Get the FPGA designs: Backline's HSB and BALBOA designs for the VPK120 are in the backline-vpk120 repository. BALBOA itself comes from ETH Zurich's fpga-network-stack, and HSB comes from NVIDIA's Holoscan Sensor Bridge project.

  • Explore the technology: Read the Backline paper for a technical overview of the architecture and its original measurements.

  • New to Backline? Read the announcement, and see how to go from local CPU prototyping to low-latency FPGA-GPU communication in our demo. Then bring your own decoder, and see how much the RDMA engine can change the round trip latency.

Have hardware you'd like to see running with Backline? Let us know! Head over to our GitHub repository to check out the ongoing work and join in on the development, or send us an email at backline@xanadu.ai to tell us how you are using PennyLane, Backline, and Catalyst in your workflows.

And if you are as excited as we are, make sure to sign up for the PennyLane newsletter for the latest PennyLane features and updates!

ERNIC, Versal, and Vivado are trademarks of Advanced Micro Devices, Inc. NVIDIA, Grace Hopper, Holoscan, ConnectX, CUDA, and NVLink are trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and other countries. Arm is a registered trademark of Arm Limited (or its subsidiaries) in the US and/or elsewhere.

About the authors

Hong-Sheng Zheng
Hong-Sheng Zheng

Hong-Sheng Zheng

Hong-Sheng Zheng is a compiler engineer on the Compilation team at Xanadu.

Ali Farazdaghi
Ali Farazdaghi

Ali Farazdaghi

Ali is a systems software developer focused on performance, low-latency communication, GPUs and compute accelerators.

Joseph Lee
Joseph Lee

Joseph Lee

Joseph is a physicist and software developer. At Xanadu, he leads the performance team and makes PennyLane go zoom.

Cheick Doumbia
Cheick Doumbia

Cheick Doumbia

Lee O'Riordan
Lee O'Riordan

Lee O'Riordan

Physicist, purveyor of angular momentum, GPUs, pointy guitars, and computational things. Working on quantum stuff.

Josh Izaac
Josh Izaac

Josh Izaac

Josh is a theoretical physicist, software tinkerer, and occasional baker. At Xanadu, he contributes to the development and growth of Xanadu’s open-source quantum software products.

Last modified: November 17, 2026

Related Blog Posts

Never miss a milestone

Get the latest quantum updates delivered to your inbox.

Join the list
PennyLane

PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.

Created with ❤️ by Xanadu.

Research

  • Research

  • Performance

  • Hardware and simulators

  • Demos library

  • Compilation hub

  • Quantum datasets

Education

  • Teach

  • Learn

  • Codebook

  • Coding challenges

  • Videos

  • Glossary

Software

  • Install

  • Features

  • PennyLane documentation

  • Catalyst documentation

  • Development guide

  • How-to guides

  • API

  • GitHub


Xanadu

© Copyright 2026 | Xanadu | All rights reserved

TensorFlow, the TensorFlow logo and any related marks are trademarks of Google Inc.

Privacy policyTerms of serviceCookies policyCode of conduct