NVIDIA Explores CoWoP Packaging for Next-Gen Rubin GR150 AI GPUs

NVIDIA explores CoWoP (Chip-on-Wafer-on-Platform) PCB packaging with next-gen Rubin GR150 GPUs

TL;DR: NVIDIA is exploring CoWoP PCB packaging for its next-gen Rubin R150 AI GPUs, offering improved signal and power integrity, enhanced thermals, and reduced costs by eliminating the package lid. Testing begins soon, with production-ready Rubin GR150 GPUs expected in late 2026 and availability in 2027. NVIDIA is reportedly considering the move to CoWoP (Chip-on-Wafer-on-Platform) PCB packaging for its next-gen Rubin R150 AI GPUs. In a new report from Digitimes, their sources have said NVIDIA is looking into CoWoP PCB packaging for its next-gen AI GPUs, with CoWoP (Chip-on-Wafer-on-Platform) PCB removing the package substrate and connects the interposer directly onto the motherboard. There are some major benefits to using CoWoP with Signal and Power integrity improvements, reduction in substrate losses, and bringing the voltage regulation closer to the main GPU die. These interfaces also increase the NVLink IC capabilities, while CoWoP packaging also doesn't require a package lid, which means the thermal solution is capable of making direct contact with the silicon. This means reduced costs as there's no need for a package lid, as it's eliminated with CoWoP. NVIDIA looks to have been working on early tests of CoWoP this month, with its early test unit based on the GB100 GPU with a dummy GPU/HBM solution. We have a form factor of 110 x 110mm, with the goal being to evaluate the process flow selection. NVIDIA will reportedly begin testing on a functional GB100 CoWoP next month, with a functional GPU and HBM, with the unit keeping the same form factor and designed to evaluate the manufacturability, structural, electrical functionality, thermal design, and NVLink interface throughput. It will use an e6540 board and two GB102 GPUs, but no external customers will evaluate this, as NVIDIA is doing it in-house. Moving into 2026, NVIDIA will debut its next-gen Rubin AI GPUs with the same CoWoP packaging, with reports that GR100 CoWoP will feature an SXM8 form factor, with the goals including Opportunistic POR and pipe clean for GR150. This means GR100 is the test bed that sets up for the full production-ready GR150 AI GPU. NVIDIA's next-gen Rubin GR150 CoWoP solution will be ready for production in late 2026, with availability of Rubin GR150 expected in 2027. NVIDIA moving into the use of CoWoP doesn't mean CoWoS (Chip-on-Wafer-on-Substrate) is going away, as they'll use both of the packaging technologies moving forward. It also doesn't mean CoWoP is absolutely superior, as the move to a totally new packaging technology means that the up front costs and preparing and setting up the supply chain is a huge job in itself, so CoWoP will add even more complexity and design changes to existing motherboards, with a rise in costs and production bottlenecks expected. Some of the key benefits of CoWoP include:

NVIDIA Considering CoWoP (Chip-on-Wafer-on-Platform PCB) Package Starting With Rubin GR150 GPUs

NVIDIA has reportedly been considering CoWoP as its next packaging solution, possibly being used by its next-gen Rubin GPUs. CoWoS or Chip-on-Wafer-on-Substrate is the go-to packaging solution for modern-day HPC and AI chips. This technology made its first debut almost 14 years ago, and is currently used by NVIDIA's and AMD's AI powerhouses. The other crucial thing about CoWoS is that it is a mature packaging technology with a robust supply chain that comprises various partners. So one can't go wrong with CoWoS, but it looks like AI giants such as NVIDIA are now planning to switch gears. According to a roadmap leak (via DigiTimes), it looks like NVIDIA has started looking into CoWoP for its next-generation GPUs. CoWoP or Chip-on-Wafer-on-Platform PCB removes the package substrate and connects the interposer directly to the motherboard. Some of the key benefits of CoWoP include: As you can tell, the Signal and Power integrity are better with CoWoP, reducing substrate losses, and also bringing the voltage regulation closer to the main GPU die. These interfaces also increase NVLINK IC capabilities. The other benefit is that CoWoP packaging doesn't require a package lid, which means that the thermal solution can make direct contact with the silicon. This also leads to reduced costs as you no the need a package and the lid is eliminated. Based on the leaked roadmap, it looks like NVIDIA started early testing for CoWoP this month. The early test unit is based on the GB100 GPU and features a Dummy GPU/HBM solution. This has a form factor of 110x110mm, and the goal is to evaluate the process flow selection. Next month (August 2025), NVIDIA is said to begin testing on a functional GB100 CoWoP, featuring a functional GPU/HBM. This unit will retain the same form factor and is designed to evaluate the manufacturability, structural, and electrical functionality, thermal design, and NVLINK interface throughput. An e6540 board with two GB102 GPUs will be used, but there aren't going to be any external customers to evaluate this. Next year, NVIDIA plans to start test work with its Rubin chips using the same CoWoP package. The GR100 CoWoP will feature an SXM8 form factor, and the goals include Opportunistic POR and pipe clean for GR150. To put it in simple words, the GR100 CoWoP will be the test bed that would pave the way for a fully production-ready GR150 "Rubin" solution. The Rubin GR150 CoWoP solution will be ready for production around late 2026, which means that it will be available sometime in 2027. But even with CoWoP, NVIDIA isn't going to do away with CoWoS; instead, they will utilize both technologies. But it's not roses and sunshine with CoWoP. A shift to a completely new packaging solution means that the initial cost of the technology and setting up an entire supply chain will be a huge undertaking, and along with this, CoWoP will add even more complexity and design changes to existing motherboards, so those would also incur a cost rise and production bottlenecks. Morgan Stanley has also reportedly said that there are little chances of NVIDIA adopting CoWoP for its next-generation GPUs, and several investor firms seem to be backing that. Though it all depends on the market trends and supply/demand factors. It will be a few years before Rubin comes to market, and only then will we be able to see if CoWoP is used; the good 'ol CoWoS is still rocking on Rubin.