Nvidia announced the Rubin CPX, a solution that is specifically designed to be optimized for the prefill phase, with the single-die Rubin CPX heavily emphasizing compute FLOPS over memory bandwidth. This is a game changer for inference, and its significance is surpassed only by the March 2024 announcement of the GB200 NVL72 Oberon rack-scale form factor. Only with hardware specialized to the very different phases of inference, prefill and decode, can disaggregated serving achieve its full potential.

As a result, the rack system design gap between Nvidia and its competitors has become canyon-sized. AMD and custom silicon competitors may have made a small step forward in emulating Nvidia’s 72-GPU rack scale design, but Nvidia has just made another Giant Leap, again leaving competitors very distant objects in the rear-view mirror.

AMD and ASIC providers have already been investing heavily to catch up in terms of their own rack-scale solutions. AMD in particular has been working tirelessly to improve their software stack to try to close the gap with Nvidia, but now everyone will needs to redouble their investments yet again as they will have to develop their own prefill chips, delaying further the timeframe with which they can close this gap. With this announcement, all of Nvidia’s competitors will be sent back to the drawing board to reconfigure their entire roadmaps again in a repeat of how Oberon changed roadmaps across the industry.

The Rubin CPX

Because the prefill stage during inference tends to heavily utilize compute (FLOPS) and only lightly use memory bandwidth, running prefill on a chip with lots of expensive HBM featuring very high memory bandwidth is a waste. The answer is a chip that is skinny on memory bandwidth and relatively fat on compute. Enter the Rubin CPX GPU.

The Rubin CPX features 20 PFLOPS of FP4 dense compute but only 2TB/s of memory bandwidth. It also features 128GB of GDDR7 memory, a lower quantity of less expensive memory when compared to the VR200. By comparison, the dual-die R200 chip offers 33.3 PFLOPS of FP4 dense and 288GB of HBM offering 20.5 TB/s of memory bandwidth.

The introduction of the Rubin CPX expands the VR200 family of rack scale servers into three flavors:

1. VR200 NVL144: 72 GPUs packages across 18 compute trays, with 4 R200 GPU packages in each compute tray.
2. VR200 NVL144 CPX: 72 Logical GPUs packages in addition to 144 Rubin CPX GPU packages across 18 compute trays, with 4 R200 GPU packages and 8 Rubin CPX GPU  packages in each compute tray.
3. Vera Rubin CPX Dual Rack: Two discrete racks – one VR200 NVL144 rack plus one VR CPX rack with 144 Rubin CPX GPUs across 18 compute trays, with 8 Rubin CPX GPUs in each compute tray.

In this report, we will first explain the story so far and the impetus for the development of the Rubin CPX because of the different role memory plays during prefill and decode phases of inference. We will then dive deep into the architecture of the Rubin CPX chip and the rack-scale solutions where it is deployed. We will then shift focus from the past and present to what the future holds with respect to disaggregated inference serving and how today’s announcement impacts future roadmaps and competitiveness for other merchant accelerator providers and custom silicon projects. In the final part of this article, we will briefly present a comprehensive list of key bill of materials (BoM) items for both racks and a power budget analysis by major component groups.

Memory: The Story So Far

The memory wall has been the most important constraint for AI. Larger memory capacities have been necessary to load larger models into accelerators, while memory bandwidth has been the main gating factor for inference and training token throughput. This is why high bandwidth memory (HBM) capacity and bandwidth per GPU have increased rapidly – from 80GB and 3.4TB/s for the H100 to 288GB and 8.0TB/s for the GB300, more than tripling memory capacity and increasing bandwidth by ~2.5x in less than three years.

Consequently, HBM has consistently increased as a % of accelerator BOM from Hopper to Blackwell, with HBM now being the largest single component of the package BOM for the GB300. HBM is extremely valuable for both training and inference, but when we break down inference to its constituent parts of prefill and decode steps, HBM only has high value for the decode step. During prefill, which is compute intensive, the generation of KVCache is much less bandwidth intensive due to the parallel nature of prefill, therefore the HBM is underutilized during this step.

HBM carries such an expensive premium relative to other forms of DRAM because of its additional bandwidth, and when this B/W is underutilized, this HBM is “wasted”. The escalating proportion of BOM taken up by HBM presents yet another “wall” and is the impetus behind the development of the Rubin CPX GPU.

Now that we have briefly explored the role memory has played thus far, let’s pivot to today’s announcement and explore in detail the architecture of the Rubin CPX and the rack scale servers where it is deployed.

Bandwidth and Compute Difference

Each Rubin CPX chip will be a monolithic SoC on a conventional flip chip BGA package. Instead of HBM, Rubin CPX will have 128GB of GDDR7 DRAM. Switching from using HBM to cheaper GDDR7 memory reduces the cost per GB by more than 50%.

Memory speeds will likely be at 32Gbps with a 512-bit bus. This results in 2TB/s of memory bandwidth per Rubin CPX compared to 20.5TB/s of memory bandwidth per R200. Notably, with this keynote, Nvidia also confirms a significant bandwidth upgrade for regular Rubin. R200’s HBM4 speeds have been significantly increased to 10Gbps to achieve 20.5TB/s of memory bandwidth per R200 as we discussed in the Accelerator and HBM model previously. This compares to the R200 being first unveiled as “only” having 13TB/s of memory bandwidth specifications at a 6.4Gbps speed bin. We discussed and quantify the impacts to HBM suppliers in the model as well. The 144 CPX chips that each deliver 2.0 TB/s of memory bandwidth and the 72 R200 chips that deliver 20.5TB/s will combine to deliver total system memory bandwidth of 1.7PB/s.

For compute, each CPX offers 30 PFLOPs of sparse FP4 computing throughput (20 PFLOP dense) compared to the R200 at 50 PFLOPs sparse FP4 (33.3 PFLOPs dense). Dense PFLOPs for the Rubin CPX follow the same 3:2 sparse to dense ratio as the R200 because it inherits a similar tensor core architecture as Rubin R200. The CPX offers very strong FP4 compute throughput for a single compute die relative to the two dies for R200. The gains are likely from reducing higher precision compute units to have more FP4 ALUs. This was what was implemented with the B300 to get higher FP4 throughput than the B200 while staying on the same 4NP node.

However, as always, peak theoretical FLOPs are extremely hard to attain in practice. Like Nvidia’s other GPUs that are power-limited, it will be very difficult for Rubin CPX to sustain anywhere close to peak FLOPs given what we estimate to be rated power of only around 800W: we do not see it feasible to break past 1W/mm2 of power density, especially as the board comes is integrated in a sandwiched form factor (more on this below).

What is also different is the network. There is no NVLink SerDes for scale-up, instead Rubin CPX relies on PCIe Gen 6 to talk to other GPUs through the CX-9 NICs on the scale-out network. This reduced network capability is more than feasible through implementing pipeline parallelism which we discuss below.

Because of the lower total silicon content and less expensive memory, the production cost of Rubin CPX is drastically lower than that of the R200. Lowering total memory capacity and using lower cost GDDR7 means that memory cost is 5x lower. The chip architecture is also far simpler since avoiding HBM and only have a single reticle-sized die without any I/O chiplets means CoWoS packaging is not required. For perspective, the design of Rubin CPX is similar to a next-generation RTX 5090 or RTX PRO 6000 Blackwell, as both use a large monolithic die with a 512-bit wide GDDR7 memory interface. As these chips are based on the consumer Blackwell GPU die, those chips only have 20% of the FLOPS as their HBM-enabled big brother, the B200. With Rubin CPX, this ratio jumps to 60% as it will be a separate tapeout that looks closer to the R200 compute die. As an exercise in achieving maximum FLOPS per unit cost – Rubin CPX is unmatched.

Later in the article, we will break down the BOM advantage of Rubin CPX and estimate how much can be saved by moving prefill off R200 and onto Rubin CPX.

Nvidia Oberon Rack Architecture Upgrade: VR NVL144 CPX, VR NVL144, VR CPX

Let’s move outside of the Rubin CPX chip and into the two new Vera Rubin racks that will host the CPX.

In March of last year, at GTC 2024, Nvidia presented the first generation of its Oberon Architecture: the GB200 NVL72. Fast forward a year and a half later, the second generation of Oberon, the GB300 NVL72, is about to ship in mass production volume. There are very few design changes and upgrades between the two generations. The third generation of Oberon architecture, Vera Rubin (VR), was the focus of Ian’s talk today at the AI Infra Summit. Available in 2026, less than three years after the debut of the Oberon rack-scale form factor, VR will see significant design changes and upgrades from GB200/GB300.

Vera Rubin Oberon pushes power density of the Oberon architecture to its limits, requiring a significant upgrade in power delivery content and design changes in cooling solutions. The cableless design is chosen with consideration to overcome the difficulties with routing flyover cables in the GB200/GB300 assembly & the reliability challenges that the intra-tray cables caused. The cables connecting the OSFP cages to the ConnectX NIC have been removed. Cables connecting from PCIe to the frontend Bluefield DPU & to local NVMe storage have also been removed amongst other side band cables.

The key changes and upgrades found in Vera Rubin are focused on a revamp of the following three Vera Rubin (VR) Compute Tray SKUs:

• VR NVL144 (Rubin Only)
• VR CPX (Rubin CPX Only)
• VR NVL144 CPX (Rubin + Rubin CPX in same tray)

These three compute tray flavors are the building blocks for the three rack solutions discussed:

• VR NVL144
• VR NVL144 CPX
• VR NVL144 + VR CPX (Dual Rack)

The first rack presented was the VR NVL144 CPX. This is similar to the VR NVL144, except that for the VR NVL144 CPX, in each of the 18 Compute Trays, in addition to 4 R200 GPUs and 2 Vera CPUs, we now also have 8 Rubin CPX GPUs in each compute tray as well.

The VR NVL144 CPX rack will also be liquid cooled – but will have a much higher power budget at ~370kW vs the ~190kW for the VR NVL144.

The other deployment option is the Vera Rubin CPX Dual Rack. As the name suggests, this solution allows customers that will have deployed VR NVL144 racks to subsequently add VR CPX racks to their datacenter later, enabling specialized hardware for disaggregated PD inferencing. VR CPX is not connected via NVLink, hence the VR CPX rack does not contain NVSwitch Trays. The VR CPX rack is connected to the cluster through scale-out InfiniBand or Ethernet networking and can be added on subsequently to a cluster in a convenient physical location – it need not be physically adjacent to a VR NVL144.

The dual rack solution offers a lot more flexibility compared to VR NVL144 CPX as the customers can design the prefill to decode ratio to their likings. Also, not everyone’s datacenter infra will be ready for the ~370kW VR NVL144 CPX. In addition there is a smaller blast radius of failures compared to the single rack variant.

In the table below, we can see how much compute and networking content is crammed into one compute tray – a total of 22 Nvidia chips (14 of them being XPUs) in each compute tray, or 396 chips per VR NVL144 CPX rack. To cram all this content above into a single compute tray, Nvidia has moved to a cableless and modular design and is also redesigning the cooling loops within the compute tray.

The NVL144 CPX will maintain a similar compute board set up as GB200/GB300 for the back half of the compute tray chassis. The notable difference is the adoption of socketable SOCAMM DRAM modules instead of soldered LPDDR5X for the memory that runs off the CPU. Most of the difference between VR NVL144 CPX and GB200/GB300 is in the front half of the chassis below the Host Processor Motherboard (‘HPM’) compute board, also known as the “Bianca” board for Blackwell generation.

At the front, the VR NVL144 CPX design is modular made up of 7 daughter card modules.

• Four daughter card modules are placed on both sides of the chasis. Each side has two daughter cards stacked on top of each other. These four daughter cards each contain two 800G CX-9 NICs, one 1.6T OSFP cage, one E1.S SSD NVMe Module, and two Rubin CPXs.
• One daughter card in the middle of the chassis (lower center of the diagram below) houses the Bluefield-4 Module, which contains one grace CPU and one CX-9 NIC.
• One daughter card stacked on top of this Bluefield-4 module houses the power delivery board (PDB). The PDB is responsible for stepping down power from 48-54V to 12-13.5V as it enters the chassis from the busbar connector at the back.
• The last daughter card is much smaller and is placed just to the right of the Bluefield-4 module. It is much slimmer and houses the utility management module containing items such as the BMC, HMC, DC-SCM, and management I/O.

We estimate the TDP of the Rubin CPX chip to be around 800W, though that rises to 880W in total when factoring in the whole module which contains the GDDR7 memory. To cool down the 7,040W of Rubin CPX modules at the front of the compute tray, the front of chassis cooling must be upgraded from air cooling to liquid cooling.

To accomplish this, NVIDIA has brought back a design from its 2009 GTX 295. The Rubin CPX and CX9 daughter cards are arranged in a sandwiched design with a shared liquid-cooled cold plate in between.

On the outer sides of the PCBs, heat pipes and heat spreaders transfer heat from the back of each clamshell GDDR7 memory modules to the main cold plate. Halving the compute tray area needed to house these GPUs by making full use of the 1U tray height and using both sides of the cold plate allows for maximum density.

Another key design change of VR NVL144 CPX is the adoption of cableless design. As we discussed in our PCB Supercycle Core Research note as well as our recent Core Research note on Amphenol’s AI Content, there are two reasons for this design. First, flyover cables present multiple different points of failure as they can easily be damaged during assembly. Second, the high-density design of VR NVL144 CPX leaves no space for cables to be routed.

So how are the signals routed without cables? The answer is simple: signals from the HPM (Bianca) board travel off the board via the Paladin board to board connector from Amphenol. This is discussed in more detail in our recent article on Amphenol’s AI Content. The signal is then routed through a PCB midplane sitting in the middle of the chassis. On the other side of the PCB midplane, the daughter cards connect to the PCB midplane via another set of Paladin B2B connectors.

To accommodate this cableless design, the CX-9 NICs on the upper part of the HPM (Bianca) board are moved from the back half to the front half of the chassis as illustrated in the diagram below. For the GB200/GB300, the PCIe signal distance between the GPU/CPU and the CX-7/8 is shorter than the Ethernet/Infiniband signal distance between the CX-7/8 and the OSFP cages.

Previously – having to transmit a 200G Ethernet/InfiniBand signal from the NIC in the back half of the compute tray to the OSFP cage in the front of the compute tray necessitated the use of flyover cables as the signal loss over PCB at 200Gbit/s (uni-directional) per lane is too high.

But now that the NIC is closer to the OSFP cage, the lower speed per lane PCIe Gen6 signals (64Gbit/s per lane uni-directional) travel the longer distance, and this connectivity can now be routed over PCB. Although it is still challenging to drive PCIe Gen6 signals over PCB, proper signal integrity can still be achieved by upgrading PCB materials.

For better serviceability, the daughter cards are also designed as a module. Each daughter card module can slide in and out of the daughter card module bay. Within the compute tray, there are internal rail kits designed for this purpose.

Below we show how the signals are routed within different Vera Rubin compute tray SKUs as well as the compute tray topology of the VR Rubin SKUs. One highlight from these diagrams is that CX-9 plays a critical role in enabling Rubin CPX and scale out connections, as it is an integrated PCIe switch too.

The Giant Leap: Disaggregated Serving

Today’s announcement of Rubin CPX is a game changer for inference, and its significance is surpassed only by the first announcement of the GB200 NVL72 Oberon rack-scale form factor. Only with hardware specialized to the very different phases of inference, prefill and decode, can disaggregated serving truly be attained.

In this section we will explain the evolution from traditional serving to disaggregated serving with uniform hardware and end with an analysis on disaggregated serving with specialized hardware. We will demonstrate how much waste is incurred by disaggregated serving with uniform hardware. Once specialized inference hardware becomes ubiquitous, using uniform hardware will feel like buying a jackhammer to squash a bug.

As we mentioned earlier in the article, the release of the Rubin CPX will send Nvidia’s competitors back to the drawing board to reshape their roadmaps. To not release a prefill specialized chip of their own will mean saddling their own customers with inefficient systems that will guarantee those customers will lose in the tokenomics marketplace.

Serving an LLM request involves two phases: the prefill phase and decode phase. In the prefill phase, the LLM generates the first token from the user prompt. This phase affects the time-to-first token (TTFT), and it is usually compute-bounded, under-utilizing the memory bandwidth. On the other hand, the decode phase generates a new token while loading the previous tokens from the KV cache. This phase affects time-per-output-token (TPOT), and it is always memory-bounded, under-utilizing the compute.

In the chart below, we see an illustrative example highlighting the tradeoff between memory bandwidth and FLOPS utilization when conducting prefill and decode on the same system. The FLOPS required to prefill a single token scales linearly with respect to input sequence length. FLOPS requirements for decode also scales with respect to users on the system (i.e. batch size) and sequence lengths.

A short input sequence length may not fully saturate the FLOPS available on an inference system, in which case the system’s output will be limited by the speed at which parameters can be loaded into chip memory – which is a function of memory bandwidth. As input sequence length increases, however, eventually the workload will grow to use all available FLOPS on the inference system, and the workload will be constrained by the total system FLOPS. In the right half of the chart below, we illustrate that when sequence length exceeds 32k, the FLOPS utilization reaches 100% while the memory bandwidth utilization drops.

Thus we can see that when a node is conducting a very prefill heavy workload – with long sequence lengths or large batch sizes, the memory bandwidth goes unutilized. As mentioned in the previous section, with the % of Chip BOM dedicated to memory increasing continually over the past few years, this ends up being a very expensive underutilization of resources!

Inefficiency also comes from the fact that the workload characteristics of the prefill and the decode phases are so inherently different that prefill and decode requests always interfere with each other’s performance when they are processed concurrently. There are many optimizations to try to balance both – for example adding prefill calculations to decide to ensure a somewhat uniform request length to improve utilization, but they always result in tradeoffs. Another approach is to separate the prefill and decode phases completely, but if you prioritize the decode phase, then your prefill will need to wait – resulting in a long time to first token. Conversely, if you prioritize prefill, your decode phase will be forced to wait and your inter-token latency will be slow as memory bandwidth then goes underutilized.

An Initial Step: Disaggregated Prefill and Decode with the Same Hardware

The first order solution is to implement disaggregated serving to first tackle the interference by routing prefill and decode requests to separate compute units, making it simpler to reason about performance. This has the benefit of being able to better manage service level agreements (SLAs) that tend to focus on a certain level of token/s/user. There are a few catches however. This complete disaggregation only seems to provide excellent results under certain input/output sequence length ratios and for long decode lengths, with other scenarios seeing underwhelming benefits. In addition, this disaggregation still leaves the “wrong sizing” problem whereby a pure prefill operation will almost always heavily underutilize memory bandwidth. 

In the illustrative example below, we show how an R200 would hardly use much of its memory bandwidth when being used solely for prefill. As we increase sequence length and more efficiently use FLOPS available, the memory bandwidth utilization becomes increasingly minimal – effectively wasting very expensive HBM memory.

The Next Step: Disaggregated Prefill and Decode on Specialized Hardware – Enter the Rubin CPX

Since prefill is inherently going to underutilize memory bandwidth resources one approach to reduce wastage is to reduce the quantity and cost of the memory. This is exactly the approach the Rubin CPX has taken by using lower quantities of less expensive GDDR7 memory.

In the illustrative example below, we show how an R200 hardly use much of its memory bandwidth when being used solely for prefill. In contrast, the Rubin CPX actually utilizes a higher percent of its memory bandwidth at fairly short input lengths before dropping even further for input lengths that we would consider typical.

Indeed, we stress this is not about efficiency for efficiency’s sake –and there is a huge impact to the bottom line! In the table below, we use provide an example to compare the memory bandwidth utilization for the R200 GPU and the Rubin CPX GPU. In this scenario, both suffer from very low memory bandwidth utilization, but the difference is that the Rubin CPX GPU is at least leaving lower quantities of far less expensive memory on the table. For the R200 – we see that the exact same prefill workload as is run on the CPX results in a $0.90/hr total cost of ownership wastage!

Rubin CPX brings more memory capacity but the bits are “lower quality” as they are GDDR7, which is less than half the cost of HBM on a per GB basis. From a memory vendor perspective, GDDR7 is less margin because it is a less technically demanding product with more competition (i.e. Samsung can supply it).

What this means is that the use of CPX systems lowers HBM’s share of total system content. For every dollar spent on the VR200 NVL144 CPX or a VR CPX rack, a lower share of that dollar is spent on HBM when compared to the same dollar spend on a standalone VR200 NVL144 rack. All else being equal, assuming a fixed dollar spent on AI systems, HBM demand per dollar spent will decline.

Why Not Just Reduce Memory Further?

Many readers are doubtless salivating at the idea of spending less on HBM and are thinking: Why not curtail the amount of memory in a system even further? If a typical prefill sequence length means a memory utilization of low double digits or even single digits – why not reduce memory capacity to 1/10^th the size? Does this mean doom for HBM demand and memory demand in general?

However, things are not so simple in technology. What Rubin CPX does is reduce the cost of pre-fill and tokens. Lower cost of tokens increases demand, which means more demand for decode increases as well. Like many other technological innovations that drive down cost, increases in demand usually more than offsets a drop in cost, netting out to a higher total dollar market size.

There are additional supply chain implications of this GDDR7 demand. The RTX Pro 6000 also uses GDDR7 but at a lower 28Gbps speed. Nvidia has put in huge supply chain orders for the RTX Pro SKU, with the original plan being to sell chips to China as a replacement for the H20 before export licenses for the H20 were reissued. These orders were primarily placed with Samsung, who had the capacity to meet these sudden rush orders. SK Hynix and Micron were not able to meet this demand as their wafer capacity was tied up to serve their HBM orders among other things. As Samsung can deliver competitive GDDR7, Samsung could similarly benefit from the Rubin CPX.

More on Prefill Pipeline Parallelism: One Interesting Upside of Disaggregated Prefill with the Rubin CPX

In the prior section we outlined how the Rubin CPX reduces memory wastage, but Rubin CPX foregoes the use of very fast scale-up network capabilities solutions such as NVLink is another key saving. Rubin CPX’s off-chip I/O is limited to 16 lanes of PCIe Gen6 which is approximately 1Tbit/s of unidirectional bandwidth vs 14.4Tbit/s of NVLink for R200. This is enough I/O for performing prefill even for modern MoE frontier LLMs.

For instance, DeepSeek V3 when running on the NVFP4 number format will require 335GB of memory capacity to load all the model weights – this exceeds the 128GB of memory capacity of a single CPX chip. This can be overcome by using pipeline parallelism (‘PP’), where multiple layers of a model are split across different GPUs. In PP, each GPU processes tokens sequentially and will pass activations down the pipeline.

The disadvantage of PP is that the tokens are passed sequentially across many GPUs, incurring latency from inter-stage communications. The important implication is that PP will tend to deliver higher token throughput per GPU than Expert Parallelism (EP), but the tradeoff is that PP suffers from a higher time to first token (TTFT) than EP. PP has higher tok/s/gpu throughput because EP has high communications overhead as it involves all-to-all collective operations vs a simple send and receive operation in the case of PP.

So, for pipeline parallel inference, the simpler communications requirements mean that prefill will almost never saturate communications links – meaning there is no need to provision expensive fast scale-up networking. Like with HBM, this is another area where one can find savings by peeling away yet another layer of equipment that goes unused during prefill-only operations – sparing the system owner wasted TCO dollars.

In the table below, we show that prefill for DeepSeek using a parallelism scheme of PP8 or PP4 results in a message size per token of 7kB. If we were to fully saturate the PCIe Gen6 x16 lanes of I/O with messages, this means we could at most transmit (and therefore process) 18.3M tokens per second. This is the communications bound.

Turning to the compute bound scenario, we see that prefill FLOP per token is 0.074 TFLOP. So, if we divide the Rubin CPX’s dense FP4 throughput of 19,800 PFLOPS by 0.074 TFLOP, we arrive a maximum token throughput of 267.6k tokens/second.

This is far below the communications bound and vastly under saturates even a fairly vanilla PCIe Gen6 I/O let alone NVLink which delivers over 14x the bandwidth of 16 lanes of PCIe Gen6.

We estimate that the total NVLink Scale-up cost to the end system owner (inclusive of NVSwitches and Backplane) stands at around ~$8k per GPU – which is just over 10% of the all-in cluster cost per GPU. This is the other dimension along which Rubin CPX delivers considerable savings to the end user.

However, attempting to use Expert Parallelism with lower speed networking connectivity will lead to latency issues and bottlenecks. Communications need scale with respect to the product of top_k times number of layers. DeepSeek V3 has a top_k of 8 and has 61 layers, so a back of the envelope calculation would indicate that using EP over PP would increase communications requirements by ~488x.

One More Thing on Scaling and Huang’s Law

Today’s discussion focused on metrics for inference using the NVFP4 number format. Indeed, inference providers have been continually unlocking more throughput by pulling the level of adopting lower and lower precision number formats. However – once we are at FP4 – we will start to run out of juice to squeeze.

Sparsity has been presented as another lever to pull to keep unlocking more throughput, a key reason why most marketing specifications and decks communicate in terms of Sparse TFLOPS, however sparsity has yet to actually deliver the promised benefits – falling well short of the 2x pickup it promises.

Today’s announcement also unveiled sparsity for Rubin. This sparsity scheme is unlike the 2:4 structured sparsity used in Hopper and Ampere, and it isn’t like Blackwell’s 4:8 pairwise structured sparsity either. We hope Rubin Sparsity is able to yield meaningful throughput benefits and keep Huang’s law on track!

Downsides of Hardware-specialized Disaggregated Serving

As exciting as the advent of prefill specialized chips are, we have not yet reached Nirvana, and hardware specialized disaggregated serving comes with its downsides too. As a provider’s workloads and models change, it is crucial for them to be able to change the prefill to decode instance ratio (PD ratio).

What Now For Custom Silicon?

The optimum PD ratio is sensitive to numerous factors, including model architecture, SLA, networking bandwidth, etc. However, one key disadvantage of the Vera Rubin NVL144 CPX is that it has a fixed number and ratio of Rubin and Rubin CPX chips, which makes it less flexible should one wish to change the PD ratio.

Nvidia’s agility in evolving chips is shifting the landscape rapidly around its competitors. Just as soon as competitors are in striking distance of parity in terms of performance or architecture, Nvidia evolves its products along another dimension. Let’s discuss how widespread adoption of Rubin CPX GPU could impact competing solutions.

Google TPU

The TPU’s 3D Torus scale-up network provides a unique advantage in that it allows a maximum pod size of up to 9,216 TPUs. This is the largest world size in the industry, yet it offers some of the lowest scale-up networking cost per accelerator. This enables a very broad array of parallelism schemes that other smaller world sizes might not support.

With that said, it would be ideal for Google to develop a prefill only chip to continue to maintain their performance per dollar advantage for internal workloads. They have the internal workloads to generate anchor demand to bootstrap and fund the development of a prefill-only chip that can also be later marketed for external use.

Google’s unique topology means that there will be certain inference system configurations and models where performance may even exceed that of certain Nvidia systems.

AWS Trainium3 Max NVL72, AWS EFA NICs and Meta MTIAv4 SUE72

Systems from providers that have internal workloads but are pursuing designs that emulate the NVL72 rack form factor form another category. These providers also have the internal workloads to bootstrap the development of prefill only chips, and it is ideal for them to do so in order to remain at parity with Nvidia’s VR200 NVL144 CPX.

For instance, a prefill only chip for use in conjunction with the Trainium3 Teton-3 Max NL72 (featuring a 72-logical GPU with all to all switched scale-up size just like the VR200 NVL144) can lean on Anthropic’s demand to codesign and gain adoption for their inference workloads.

There will be major time to market challenges for AWS for its VR 144 CPX due to the fact that their 1U compute tray is already tightly integrated and packed with 4 large Rubin  GPU packages and 8 CPX GPU packages leaving no space to add AWS’s custom EFA NICs into the compute tray. Amazon does not want to use ConnectX-9. AWS LOVES EFA!

We believe that they will continue using EFA and overcome this challenge by disaggregating their EFA NICs into an EFA NIC only sidecar rack and use external PCIe AEC cables to connect between the VR 144 CPX rack and the EFA NIC only sidecar rack. Furthermore, since they will not use the ConnectX-9 NIC, which has an integrated PCIe switch, they would also need to use Astera Labs’ dedicated PCIe switches to connect between the Vera CPU, local NVMe, Rubin CPX GPU as well as the external PCIe AEC cable to the EFA NIC in the sidecar rack.

MTIAv4’s SUE72 (featuring a 72-logical GPU with all to all switched scale-up size just like the VR200 NVL144) design similarly can lean on Meta internal inference workloads. Even emerging designs such as OpenAI’s chip with Broadcom stand to compete given they will be codesigned with Frontier Models in mind and with an internal workload as a backstop.

Despite enjoying the benefit of internal demand, the MTIAv3 is excluded from this category due to its small 16 GPU world size. It will effectively now need to develop prefill-only silicon to even have a shot at parity with upcoming Nvidia systems.

AMD MI400 Series UALoE72 and MI500 UAL256

However, with the launch of Rubin CPX GPU, AMD’s comeback strategy is now looking to be not fast or aggressive, and AMD will find itself chasing Nvidia once again. AMD was about to catch up with the rack scale MI400, but Nvidia raised the bar.

The key difference between AMD and the aforementioned providers is AMD’s lack of robust internal workloads to provide the revenue and demand backstop for yet another chip development project just to keep up.

AMD had made waves earlier this year with its Advancing AI Event where it debuted its MI400 72 GPU rack scale system. Our analysis at the time pointed out that the MI400 could offer a lower total cost of ownership relative to FP4 FLOPS than a VR200 NVL144 system – all while providing 19.8TB/s of memory bandwidth vs the 13.0 TB/s of memory bandwidth initially advertised for the VR200 NVL144.

Nvidia’s VR200 NVL144 is now advertising a memory bandwidth of ~20.5TB/s per logical GPU by requesting much faster speed bins from their suppliers. VR200 memory bandwidth now matches that of the AMD MI400 with fewer HBM sites.

If the MI400’s FP4 effective dense FLOPS (i.e. what microbenchmarks will actually deliver in performance as opposed to marketed throughput) turns out to be on par with or lower than the VR200 NVL144, AMD will effectively show up later than Nvidia to market with a carbon copy of the VR200 NVL144. Meanwhile, Nvidia will yet again pull ahead as the VR200 CPX NVL144 delivers better performance per TCO for long context lengths. AMD will then have to wait again until 2027 to catch up.

However, we believe that AMD remains in war mode, and it now needs to open another front to fight the prefill only silicon battle on top of developing their rack scale system and improving their software to have a shot at catching up with Nvidia by 2027.

Nvidia

Lastly – why should Nvidia stop at only having a prefill focused chip – why not a decode focused chip as well? Nvidia has so far only debuted a prefill focused chip, and the decode step stays with the existing R200 chip rather than a decode specialized SKU.

A decode specialized chip would be the opposite of the prefill chip: skinny compute, fat on memory bandwidth. This chip would look like a R200 but without the need for as much compute. Ideally, I/O would be preserved for both memory and off-package I/O by maintaining the size of the I/O chiplets, but the edges of the main compute die facing the I/O dies can be reduced, whilst keeping the same edge to fit 2 HBM site per edge. The result is a much smaller compute die.

Additional savings could be also had from a significant increase in parametric yields with a lot of defeatured SMs as well as much TDP reducing costs associated with power delivery and thermal management. This is the opposite of the case of the pre-fill chip where the amount of HBM is preserved, while there are reductions in other parts of the system, bringing HBM’s share of BOM back up.

Compute is the lifeblood of AI. He who controls the spice controls the universe the compute will control the production of tokens and reap the benefits of AI. Without compute you do not have a seat at the table. The United States technology community is all in on compute and AI as the next platform and is now adding compute at a staggering pace.

There is competition, and it not only comes from companies but from countries, and the US government has placed a series of export controls to limit China’s rising compute. Today the US controls and is the undisputed leader in compute with more than 70% of the worlds deployed FLOPs. One way to stay ahead is to keep going full steam while hindering your competition. Limiting your competitor nation state from compute, which will limit them from intelligence, is the current policy to stay ahead in the AI race.

These moves have led to backlash, including with China cutting rare earth minerals and magnets off from the US. Secretary of Commerce Howard Lutnick says the resumption of Nvidia GPU sales to China were required to restart China’s shipments of their linchpin supply chain materials.

But constraints have also led to adaptation, and Chinese companies have adapted. High batch sizes and disaggregated serving are but two examples. Despite advances, in the case of DeepSeek, most of their tokens are still inferenced on western hardware. We wrote about this dynamic in our recent DeepSeek debrief. Training of DeepSeek’s next generation model was also delayed by the use of Huawei chips, as we also said in the debrief.

This is not a stable equilibrium. There are always moving pieces in the race for intelligence. Beijing plans for the long term and knows it must secure its own domestic compute destiny. There is an irony: in the 2010s China kicked out Google to enforce its Great Firewall and foster its domestic industry, this time the US government is withholding hardware technology so they cannot seize the lead in AI.

We believe that at China’s core, they want to control not only its internet and AI, but the hardware that supports it. From silicon to tokens, China seeks sovereignty over every layer of the stack, and given recent history will never want to be beholden to foreign powers. Enter Huawei.

China loves national champions, and in it’s characteristic capitalism, tends to funnel resources to a few national champions. Today’s champion is probably Nvidia’s greatest adversary: Huawei. We expect Huawei to be able to make millions of chips this year, and to be bottlenecked by HBM next year. Today we want to talk about Huawei, which can translate as “China’s achievement”.

All In with Huawei’s chips

Huawei is the key piece for China’s compute destiny. Huawei’s chip ecosystem is vertically integrated and capable network of tools, fabs, and design that allows it to express a full stack vision of hardware. This hardware is very impressive although less efficient then western hardware.

Our previous investigation into Huawei’s fab network is a great example of their broad reaching network.

Huawei wants to vertically integrate the entire manufacturing process. The goal is to own not just the manufacturing of the logic die, the brains of the chip, but also the memory and packaging. They have even created their own tool company, SiCarrier to copy foreign firms tools. Huawei has bought over $9B of tools to put in their own fabs as well as reverse engineer to replicate.

Their efforts are not to be underestimated. SiCarrier, for example, has recently raised $2.8B in funding. That money is going into building fabs dedicated for Huawei staffed by Huawei employees. Some reporting on these fabs, which we believe to be Huawei owned and operated, suggests that their combined production by next year could entirely exceed SMIC, the current leader and where production is currently outsourced. With Huawei ramping up their own efforts, allocation at SMIC can be freed up for other chips, including Cambricon. The Cambricon chip is itself popular among Chinese companies, especially ByteDance.

Huawei operating their own fabs will represent a material increase in Chinese production, but also in their ability to iterate, control, and improve on processes. Huawei and SMIC will directly work on increasing yields, refining R&D for the next node, and bolstering Chinese semiconductor manufacturing capability.

Currently, all high volume chip production is outsourced to SMIC, the leading Chinese pure-play foundry. This includes the Ascend series of accelerator chips along with the Kirin mobile processors. Yields are poor for SMIC’s 7 nm-class processes due to a combination of immaturity, export controls, and the inherent difficulty in yielding large die such as the Ascend. Thus a relatively low percentage of SMIC’s overall capacity is allocated to producing Ascend die, since smaller mobile processors just make better business sense at this point. But this can change quickly. Let’s discuss what is possible for Huawei….

Huawei Production Numbers and SMIC’s Ramp

Our data shows Huawei’s production is 507k Ascend units shipped in 2024, the majority of which are 910Bs, and 805k this year, 653k of those being 910C. The 910C is the more advanced version. This includes die made by TSMC and SMIC.

SMIC, hampered by export controls, struggled to get production off the ground. But Huawei got Ascend die fabricated at TSMC while SMIC ramped. This was a violation of export controls and Huawei ended up receiving more than 2.9M Ascend die, which can be used for both 910B and 910C. We detailed this here.

It is specifically this “Die Bank” of foreign chips from TSMC that gets them through 2024 and 2025. Without this Die Bank, Huawei’s Ascend production numbers would be much lower.

We expect that the TSMC die bank to run out within the next 9 months. SMIC, however, now has more than enough capacity to produce meaningful volumes of chips. We forecast that SMIC will no longer be the bottleneck for Ascend production, as they will have sufficiently ramped capacity by end of year.

The chart above shows a baseline scenario with a modest increase in SMIC capacity allocation for Ascend. It requires at most 20k wafers per month (wspm) of SMIC capacity to produce millions of Ascend die per month.

For reference, a conservative estimate of SMIC’s total advanced node capacity (7nm and below) is 45k wspm by end of 2025, increasing to 60k wspm in 2026 and 80k wspm in 2027. In addition, Huawei is building their own fabs, not all of which are export controlled, and collaborating with SMIC on process technology, so production could ramp higher for advanced process technologies.

If 100% of capacity was allocated to Ascend die, their production capability would be in the tens of millions per year. They are on track to be more than capable of supporting a large domestic demand for China-produced compute die.

Our forecasts above use a conservative estimate for both yield and its rate of improvement in the future. It’s very likely that SMIC can exceed these estimated as its 7nm nodes mature. Our estimates for yields are lower than TSMC, Intel, Samsung, ASE, Amkor, etc for front end wafers and packaging.

Indeed, yield is an important lever that can be pulled to increase production without giving up more allocation. With just small increases in yield beyond our forecast above, SMIC will be able to produce several million Ascend die at lower allocation amounts than they would otherwise. Every percentage counts and SMIC has their best engineers working on exactly this problem.

In other words, SMIC only needs small amounts, as low as single digit percentages, of allocation to produce more than a million die as soon as early next year. Production to a couple million is possible, more allocation is all that is needed. For the reasons we articulate above, we believe the reported number of 200k Ascend chips to be significantly off the mark.

While SMIC is expanding and is no longer the bottleneck and Ascend production, Huawei’s long-term ambitions include its own fab network buildout. We noted in our Fab Whack-A-Mole report:

Huawei is clearly taking full advantage to the tune of $7.3B of WFE expenditure in 2024, up 27% year-on-year. They’ve gone from effectively zero in 2022 to the 4^th largest WFE customer globally in two years.

Since we published that report in fall of 2024, the Huawei fab buildout has, if anything, accelerated. Their ecosystem of semiconductor-related shell companies is expanding. Massive new cleanroom buildouts are in progress. And improved domestic options and possible diversion of $30B+ of imports of wafer fabrication equipment means they are likely able to equip these fabs as well. The details are worthy of their own report, but suffice to say Huawei continues with a large, concentrated effort to own every vertical in the Ascend supply chain.

TSMC Access

Huawei currently makes many mobile chips, but there is zero reason to do so from a strategic geopolitical perspective. Oppo and Xiaomi currently fabricate mobile SoCs at TSMC. They are ramping up their own designs to decrease dependence on companies like MediaTek and Qualcomm.

Huawei can reduce their mobile SoC production while not consuming, in any meaningful volume, SMIC allocation. The continued access to TSMC for other Chinese entities decreases the pressure for SMIC to make mobile SoCs, meaning more can be allocated to AI chips.

Huawei and SMIC can ramp up AI production without having to worry about serving all the nation’s demand for mobile chips due to other companies’ access to TSMC.

Export Control Lag Benefits SMIC

Another part of SMIC’s expansion strategy is stockpiling considerable amounts of semiconductor tooling. The controls are released on an announced schedule and it’s usually easy to anticipate what will be included.

This is due to timing differences in controls that they can take advantage of. For example, the U.S. routinely exempts Japanese and Dutch companies from its equipment export controls. Ostensibly this is done because they are allied countries and have their own export control regimes and semiconductor industries.

The problem, however, is that when new export controls come out, Japan and the Netherlands do not immediately follow. In many instances, matching controls are delayed by 6 months or never. Chinese companies can rush order years’ worth of equipment to stockpile, while American vendors are shut out of the process.   Japanese WFE vendors are happy to sell into this gap with margins fattened by order expedites. Many key suppliers are seeing well above 40% revenue share from China:

In cases where controls do follow the US, Japan and the Netherlands do not have any matching controls on re-exporting. This means that it is possible for restricted tooling to reach China if it goes through a different country first.

In addition, the use of “advanced ICs” as the bar for restricting tools leaves room for issues. ASML’s NXT:1980 scanners are perfectly capable of 7nm-class logic, and likely beyond if economics (throughput and yield) can be ignored or subsidized. These are allowed into China and even to certain SMIC facilities.

Export controls, as noted, can be expanded in addition to very stringent enforcement of existing mechanisms. This includes tighter coordination with allies on timelines for matching controls and getting buy in on re-exporting.

We are broadly encouraged by the administration’s Action Plan. As an example, we are pleased to see controls on semiconductor subsystems being called out. This is a drum SemiAnalysis has been beating for a while and think it is the right direction. With that said, many subsystem firms that supply western players such as VAT Group in countries like Switzerland without controls will not be stopped from shipping critical chambers to China.

The Action Plan also included concrete suggestions around aligning protection measures globally, which we think if implemented, will greatly ameliorate the issue of alliance’s lags in export controls described above. The issue is that SMIC and CXMT are able to continue to expand production because the sanctions on them are flimsy. International co-operation, especially with partners in Korea, is key to get right and ensure that Chinese commercial bottlenecks are not eased. Korea manufactures a huge amount of memory and Samsung has historically supplied large amounts of memory into China, so tight alignment of goals and enforcement is critical.

The other part of the supply chain that is just as critical is memory. This is where we believe the key constraint lies.

HBM Is the Bottleneck

We believe HBM production is the bottleneck. China does too, which is why they have asked US officials to relax controls on HBM as part of the recent trade talks. What the ask omits is telling: it does not include more TSMC access or lithography tools. Beijing is specifically asking Washington to loosen HBM restrictions.

Much like how Huawei was able to stockpile TSMC logic wafer inventory, they were also able to stockpile HBM inventory. Samsung, due to their failures in entering the accelerator supply chain for Western chips, sold their product to Chinese customers that funneled this inventory to Huawei. This is why it is so critical to work with Korea on enforcement of memory controls moving forward.

Samsung alone has directly provided 11.4 million stacks of HBM to China, including a staggering 7M stacks in the 1-month gap between controls announcement and enforcement dates. When including other providers and methods of shipment, that is 13 million stacks of HBM.

Specifically, on December 2^nd 2024, the Bureau of Industry and Security (BIS) announced controls on anything more advanced than HBM2E. Full compliance was required on December 31^st 2024. Samsung exported as much as possible to China in that one quarter. This comprises the majority of China’s HBM. They were able to achieve this due to the US Government and media telecasting the restrictions for many months before they came out.

After the ruling, Samsung HBM still made it into China. We previously detailed how companies like CoAsia Electronics and Faraday supplied non-functional chips with HBM into China, though we believe due to our efforts in exposing this both privately in late January and publicly later that it has now stopped with revenue numbers returning to normal. This does not mean that HBM smuggling has stopped entirely, though. There could be other sources.

In sum, China has procured 13M HBM stacks which is sufficient for 1.6M Ascend 910C packages. Despite this, we expect that China will be bottlenecked by HBM by the end of the year as they run out of foreign HBM.

China can easily make more than 805k Huawei Ascends this year from TSMC and SMIC capacity, but they will not because they do not have enough HBM.

We expect SMIC’s production to be 1M 910Cs and almost half a million 910Bs this year, however, not all of them will be turned into ASICs as the HBM is not available. If some HBM enters through smuggling, then Huawei can produce more Ascend AI ASICs.

Without Foreign HBM, China has no Domestic AI Accelerator Industry

Without access to more foreign HBM, Huawei will not be able to fabricate even 1 million Huawei Ascend chips next year. They must rely entirely on domestic production which we will detail below. Nvidia and AMD have effectively 0 competition in China once these HBM banks run out.

The other option available to China is utilize slower GDDR and LPDDR memory, but this is not suitable for the leading language models with modern reinforcement learning techniques or for large scale inference deployments.

Domestic HBM Industry – CXMT

China’s main DRAM player, CXMT, has caught up with the west rapidly. This is due to a combination of extremely strong domestic engineering capabilities, poaching engineers from Samsung, SK Hynix, and Micron, as well as the leading tool vendors Applied Materials, Lam Research, and Tokyo Electron teaching them sub-processes.

CXMT is able to ship DDR5 memory, only a couple years behind SK Hynix, Micron, and Samsung, and is winding down profitable DDR4 production previously reserved for PCs and mobile. While they have not shipped much HBM, their roadmap is aggressive. By next year, their production capacity will rival that of Micron’s, though not fast enough to save Huawei Ascend’s production. In 2026, we expect them to be producing 257k WPM, which would be just under 15% of global DRAM production. In our estimates, this scales to 490k in 2030.

CXMT’s shift in focus and production ramp are driven in part by investments from the CCP. China’s “Big Fund III”, which started in May 2024, invested $2B into the company. CXMT is also expanding in Shanghai as well as Beijing, with HBM packaging subsidiaries being set up in the former.

Expecting, though ultimately averting, an entity listing by USG, CXMT stockpiled years of tools in 2024 and is likely still adding HBM-specific gear. CXMT is still not entity listed! While HBM was noted as a key focus in that salvo of controls, the previous administration failed to include China’s HBM champion. The Trump administration needs to solve this failure from the Biden administration immediately.

The stockpiling matters as advanced tools, like Hanmi’s TCB systems for HBM3, are restricted, but they are not that instrumental. Older systems can be run slower without impacting cost too much. More importantly, CXMT can still procure leading edge equipment for Through Silicon Via (TSV) formation – that is critical for making HBM -through Japanese suppliers. In addition, Chinese OSATs such as JCET and Tong Fu are also racing ahead with their R&D efforts and building capacity for the critical TSV and stacking processes to package front end HBM wafers from CXMT. This is unlike the Western memory incumbents who have vertically integrated these processes. This is a typical example of Chinese industrial development where multiple players are encouraged to develop domestic manufacturing capabilities: creating cutthroat competition that accelerates the speed of development. It is therefore critical to not just focus controls on CXMT, but the whole of China as critical process steps can always be outsourced.

Because front-end logic is currently not the binding constraint, Beijing’s main asks in the trade deal target HBM and the relaxation of controls relating to this set of tooling. Given the importance of HBM, it is critical to understand CXMT’s future production depending on various allocation scenarios.

CXMT Production Forecast

This can play out in several ways, depending on how much wafer capacity is given to HBM. China can easily produce tens of millions of stacks with less than 50% of wafer capacity. CXMT is at a bit over ~250,000 wafers a month of production capacity and is expected to reach 300,000 wafers by the end of the year.

Currently they have not built out the tooling required to convert standard DRAM production lines to HBM, but it is inevitable. Properly designed, targeted sanctions can slow this conversion massively.

Different scenarios lead to different amounts of Huawei Ascends produced. As noted, SMIC can produce the die needed to match the HBM.

To be clear, this could change. The rate of production for CXMT could increase if they continue stockpiling key tooling or significantly improve yields. The might of China’s manufacturing capability and capacity knows no bounds. This estimate is somewhat conservative, it is likely that CXMT is able to produce the significantly more capable HBM3e in 2026.

We believe CXMT will only be able to make ~2 million stacks of HBM next year, which is only sufficient for 250,000-300,000 Ascend 910C’s. Yields and capacity conversion will take some time to improve for CXMT to commit significant capacity.

If all leading edge logic die capacity could be paired with HBM, Huawei production of Ascend would grow from 805k this year to 1,175k in 2025. More importantly, production next year would grow from 300k to over 5 million Ascend 910C!

Our analysis indicates that export controls have been effective in constraining and limiting Chinese chip production capabilities. Assuming no smuggling, China will be able to make less Ascends next year, not more. CXMT is squeezed tight. Had controls not been present, the Ascend ramp would be fully realized, Chinese models would be served on Huawei Ascend at scale, and there would be enough compute capacity that advanced models like DeepSeek R2 and V4 would already be here. Not to mention, with more capacity, China would be better positioned to export their AI on their chips.

As such, it is absolutely critical to ensure the application, enforcement, and continued updating of export controls to prevent CXMT and related entities from ramping production. As mentioned, this includes not just CXMT but OSATs and subsidiaries they work with. Second, it is also important for the intelligence community to track and identify any instances of HBM smuggling, like the Faraday + CoAsia scheme which we disclosed privately in January and publicly reported on later.

By no means should HBM be allowed to be shipped into China. Production of AI chips over the next few years is heavily gated by CXMT’s ramp and foreign shipments of HBM.

There is very strong incentive to find ways to ship HBM into China. This is why enforcement of controls are so critical.

There is another pillar to China’s production strategy, separate from memory and logic. This pillar is about networking the chips together and where they are made.

Networking and Datacenter CPU

Chips do not exist in isolation. We have argued that the system matters more than the microarchitecture for years. Clusters are comprised of many tens of thousands of interconnected chips and how they are interconnected matters.

We detailed Huawei’s CloudMatrix 384, or CM384, system below.

We believe the networking equipment used, specifically the scale up switches, are being made at TSMC and not at SMIC through shell companies. We also think they are stockpiling this equipment.

We believe Huawei has also been able to manufacture their datacenter CPU at TSMC. This showcases that current controls aimed to limit Huawei’s access to TSMC are insufficient. The Ascend AI ASIC is 7nm, but because of poor screening, Huawei has been able to procure technology from the more advanced TSMC 5nm node.

By producing these chips at TSMC, this frees up capacity at SMIC, meaning more allocation can be given to the Ascend or Cambricon programs (HBM permitting). This, as mentioned earlier in the report, is a critical variable. If SMIC had to make the networking equipment, this would squeeze the wafer allocations towards Ascend significantly.

There is all the incentive in the world for China to offload as much production as possible to TSMC. They have used shell companies before and there is ample evidence they are still doing it. While some ideas around KYC and red flags have been implemented, we believe that existing frameworks are insufficient.

Nvidia and Huawei: Blackwell and the H20

The US government previously banned the Nvidia H20 chip from going into China, but recently indicated that Nvidia will be granted a license to be able to export the chip. As we have previously noted, the H20 is a capable chip with more memory than the banned the H100, though it has less much fewer FLOPs. Having more memory is helpful for inference performance.

Nvidia is poised to sell its existing inventory of the H20 and H20E (a variant with even more memory) at a minimum. This will amount to more than several hundreds of thousands of chips and billions of dollars of revenue.

There have also been reports of a more advanced version based on the Blackwell series. This is slated to have just as much memory as the H20 but will also contain significantly more FLOPs. Specifically, the B30A could have more than 10x the FLOPs than the H20, significantly above the export control threshold. The B30A could be positioned at half the price and have half the performance of the B300. The solution to this is rather simple: just buy 2x the chips for equivalent performance. Given how strong and weak scaling work in machine learning workloads, this is a valid path to remain competitve.

The B30A is argued as needed to be shipped to China due to decreased interest from China in the H20. A lot of this is due to government pressure of China’s major tech firms. While there is significant messaging that China has decreased interest in the H20, we do not believe this to be true.

Specifically, we do not believe this is reflective of China’s demand for compute or foreign chips. It is an incorrect policy being pushed from the top down which will be reversed as soon as Huawei runs out of HBM to produce more Ascend chips, or it could even be orchestrated brinkmanship to get approval to a more powerful chip.

This is on the tail of other news, like DeepSeek unable to get acceptable performance on Huawei’s chips. That is no coincidence. Export controls are working and the biggest blocker for more progress is compute.

China may be trying to psyop their way into getting the significantly more performant Blackwell chip. While the H20 and the H20E have much, much better software than the 910C, it is arguable that they are in the same league. However, it is unquestionable that the B30A would be in a league of its own. Given that the H20, H20E, and especially the B30A are good at inference, this also allows Chinese companies more compute to serve their models and applications.

It will allow them to export Chinese AI on hardware they own. This will increase the proliferation of Chinese AI and Chinese apps, inevitably taking market share away from American applications. The American AI stack is American AI on American chips, not just the chips.

The US needs to balance having China on the US AI stack and slowing the development of their own, while also limiting the quality and volumes that are shipped into China.

The H20 is allowed into China, but the progression of shipping more powerful chips into China should be closely guarded and watched considering China’s domestic capabilities.

The US should only move the quality of a chip shipped to China when it becomes clear China can ship something competitive to the H20E in significant volumes.

Regardless of the exact SKU, the export licenses have several implications discussed below.

Implications of Compute Diplomacy

First, it means that there will be more chips for top players like DeepSeek and Alibaba to use for Reinforcement Learning (RL). RL is a big driver of progress right now. The majority of RL compute is inference, which the H20 and especially the H20E, are good at. The B30A will have even better performance.

Players like DeepSeek had enough compute to keep improving – R1 received a major update with performance increases on a timeline that is like o1 -> o3. We firmly believe GPT-5, Claude 4, and Grok 4 are considerably ahead of R1 though, especially in agentic tasks.

However, problems in AI are solvable by two things: talent and compute. DeepSeek has always had the former, now they will have more of the latter. We expect DeepSeek’s rate of progress to materially increase as they receive substantial volumes of any chip that gets into China. DeepSeek has ambitions to release a multimodal model in V4, but scarce compute is slowing progress.

Alibaba (Qwen) and Moonshot (Kimi K2), have also yet to produce a large multimodal model, primarily focusing on text only due to compute limitations. They will release multimodal models this year, but they are still squarely behind OpenAI, Anthropic, and Google in many capabilties. If Blackwell GPU shipments come too early, that will accelerate China’s pace.

The second major implication of this is that China will now have more compute to serve and inference models to its population. Compute constraints affect user experience, with DeepSeek deliberately serving R1 at low speeds to users to preserve compute.

Poor user experience from the lack of compute has greatly limited China’s ability to deploy AI. As user experience improves, so will adoption, and the economic benefits from AI. It is easy see a future in which models are pre-trained via H800s, post-trained on H20s, then served to the population on Ascends and H20s. There is so much demand for AI powered products that should more capacity to serve these models exist, it would immediately be satisfied. One of the reasons Chinese models are open sourced is that it allows for other people to serve their models for them. With more capacity, models can be closed sourced and dependence on American providers cut off.

Claims that models trained on one chip must be inferenced on the same type are entirely false. Anthropic did different stages of research and training for Claude 4 on GPUs and TPUs. Additionally, Claude 4 inference is offered on Nvidia GPUs, Google TPUs, and Amazon Trainiums. This complexity is all while Anthropic is also the fastest growing AI company in terms of revenue with by far the most capable model for software engineering.

DeepSeek, Alibaba, Moonshot, etc primarily train their models on Nvidia chips and we do not think this will change anytime soon. If the Blackwell version ships, gains across all levels will be more pronounced.

China’s compute at a snapshot

With the H20 approved, this represents a material increase in the number of FLOPs and memory that China has access to. The 910C will be the first meaningful effort of indigenous production in China in terms of realized FLOPs and memory. We also expect some re-exportation into China by various bad actors, constituting meaningful volumes of H100 and low volumes of B200.

Should the Blackwell version ship, gains around FLOPs will be even more pronounced as the chip has significantly more FLOPs. China will end up having more FLOPs in that scenario, in addition to more memory.

This is not to mention that Chinese players, including major ones like ByteDance, can still access compute through renting in non-restricted countries. For example, ByteDance can still access top of the line Blackwell GPUs from providers like Oracle and Google. We have previously covered this relationship in detail. Malaysia, in no uncertain terms, has become a huge market for Nvidia. Export controls were also effective in ensuring that it remains that way, with Malaysia immediately distancing themselves from any effort around the Huawei Ascend.

Renting enables a path for Chinese dependence on Nvidia without Nvidia chips being in China, which is possible because the chips do not need to be in China. Bytedance’s Seed models were trained in the US on a US cloud.

Inspecting GPUs is much easier in Malaysia than in China. As such, it is an effective way to limit any unauthorized re-exporting by bad actors, as we believe methods like location tracking are technically intractable and easy to bypass. Note that renting will still allow China access to the capability of training advances models. If allowed to be used for serving the models, this allows China the chance to proliferate their AI through new and improved AI powered applications, taking market share away from American products. The critical difference, though, is that access can be cut off.

With that said, China will not allow their data to be shipped out of China in large volumes hence there is still significant need for domestic AI capabilities. Selling chips into China does not change China’s drive for total silicon self sovereignty and will only serve to help provide a buffer while local production meets demand.

It is worth remembering that China’s focus on silicon self sovereignty predates US export controls. The argument Blackwell needs to be sold into China is a false narrative as Huawei will soon run out of HBM. Selling chips into China only served to bail them out until domestic production ramps. The production ramp will not slow until self sufficiency is achieved. Shipments of Blackwell must be weighed with a close eye on production of domestic capabilties. If Huawei, Cambricon, and CXMT accelerate production faster than expected, then the US should raise the bar sooner.

Next, we dive into Nvidia’s future in China. This includes expected revenue from the H20 and newer China specific chips on the horizon. We also compare how much compute China has relative to the US how the is absolutely dominating China when it comes to both memory and FLOPs.

Two-and-a-half years ago, we flagged a looming “cloud crisis” at AWS. Today, the evidence has mounted. AWS is the crown jewel of the Amazon empire, generating ~60% of group profits, and dominating the lucrative Cloud Computing market. But it struggles to translate this strength into the new GPU/XPU Cloud era.

Microsoft Azure now leads the market on quarterly new cloud revenue, and the gap between Google Cloud and AWS has materially narrowed especially with Google’s big moves on the TPU that we’ve been posting about for over a month. Markets have noticed. Year-to-date, Amazon is the clear laggard among the four tech-and-AI titans as investors mark down the company most for losing momentum in AI.

Today, SemiAnalysis is back with another out-of-consensus call. While the market overplays the Cloud Crisis theme, we call for an AWS AI Resurgence. We laid out our thesis a month ago to our Core Research subscribers, forecasting an upcoming acceleration beyond 20% year-over-year growth by the end of 2025.

Amazon’s savior has a name: Anthropic. The startup has been the clear outperformer in the GenAI market in 2025, multiplying revenue fivefold year-to-date to reach $5B annualized.

To keep that trajectory, Anthropic is betting hard on Scaling Laws. While Dario’s startup draws fewer headlines than OpenAI, xAI and Meta Superintelligence, it isn’t shy about investment. AWS has well over a gigawatt of datacenter capacity in final stages of construction for its anchor customer. AWS is building datacenters faster than it ever has in its entire history. And there’s much more on the horizon.

To understand and forecast GPU/XPU power capacity by AI Lab broken down by Cloud Provider, we rely on our proprietary Datacenter Industry Model powered by real-time satellite imagery. Trusted by all hyperscalers, AI labs, and the world’s largest investors, it provides a quarterly building-by-building datacenter forecast for OpenAI, Anthropic, xAI, Meta Superintelligence, Google DeepMind, and more. Contact us for more information.

Trainium vs GPUs

While Amazon’s AI Datacenters are impressive in scale and speed, the design of individual building is unremarkable. Hyper-optimized for air-cooling, this blueprint is identical to 5-year-old traditional AWS Cloud datacenters.

What makes these facilities unique is their inside: they’ll host the world’s largest cluster of non-Nvidia AI chips, with just under a million Trainium2 in the largest campus. To understand everything about the Trainium2 system, read our December 2024 technical deep dive.

Trainium2 lags Nvidia’s systems in many ways, but it was pivotal to the multi-gigawatt AWS/Anthropic deal. Its memory bandwidth per TCO advantage perfectly fits into Anthropic’s aggressive Reinforcement Learning roadmap. Dario Amodei’s startup was heavily involved in the design process, and its influence on the Trainium roadmap only grows from here.

Put plainly: Trainium2 is converging toward an Anthropic custom-silicon program. This will enable Anthropic to be, alongside Google DeepMind, the only AI labs benefiting from tight hardware–software co-design in the near horizon.

This report will dig into all aspects of Amazon’s AI resurgence: the Anthropic partnership, datacenters, and Trainium. At the end of the report, we provide a longer-term outlook on Anthropic, AWS Bedrock and internal models, and explain why everything isn’t rosy.

First, a step back on why AWS has underperformed rival AI Clouds to date.

AWS GenAI underperformance

To understand the causes of Amazon’s underperformance in the GenAI era, we can analyze drivers of success in the GPU/XPU cloud market. In the most simplistic way, we see two primary customer groups for GPU/XPU capacity:

• Wholesale bare metal users: large-scale customers like OpenAI, Anthropic, ByteDance, and other hyperscalers.
• Managed SLURM/Kubernetes: Smaller customers such as startups, research institutes, and enterprise pilot projects.

Cloud Crisis and ClusterMAX underperformance

In the second category, our ClusterMax AI cloud rating is the best way to compare relative strengths and weaknesses. Platinum and gold-rated AI Clouds have seen more traction than others and boast higher-than-average pricing power. As such, the likes of CoreWeave, Oracle, Nebius, Crusoe and Azure have outperformed the market for multitenant GPU clusters – which require high performance and advanced software layers.

As predicted two years ago, key to Amazon’s underperformance is the use of custom networking fabric EFA. AWS’s success with ENA on the frontend network has not yet translated to EFA on the backend. EFA still lags behind other networking options on performance: NVIDIA’s InfiniBand and Spectrum-X, as well as RoCEv2 options from Cisco, Arista, and Juniper. Raw performance isnt the only metric, the user experience of EFA isn’t as good as InfiniBand & RoCEv2 either. That being said, with Amazon’s newest EFAv4 performance at real world msg sizes is improving, albeit still behind the competiton.

Amazon’s custom networking also reduces their time-to-market due to customization requirements of Nvidia systems. Other items like advanced passive and active automated weekly scheduled health check strategies aren’t as solid as gold & platinum-rated clouds.

Our upcoming ClusterMAXv2 rating will provide an update on all major cloud providers based on our proprietary testing. Stay tuned!

Searching for an anchor customer

More important to AWS’ XPU business growth is the ability to secure anchor customers – the market-makers in this first wave of GenAI demand. Scale, time-to-market, deep partnerships, and pricing are key to winning these accounts, more so than advanced software layers.

No firm better illustrates this than Microsoft. Azure’s AI outperformance over peers is entirely driven by its OpenAI partnership. As of Q2 2025 (June 2025), all of OpenAI’s >$10B cloud spending is booked by Azure.

Amazon understood early on the need for an anchor customer and invested $1.25B, expandable to $4B in Anthropic in September 2023. The partnership expanded in March 2024 with Anthropic committing to use Tranium and Inferentia chips. In November 2024, Amazon invested an additional $4B into Anthropic, with the latter naming AWS as its primary LLM training partner.

Anthropic’s outperformance, AWS underperformance?

Amazon’s bet has been the right one. Anthropic is the clear outperformer in 2025 in the GenAI market, with revenue surging from $1B to $5B annualized. In this context, AWS’ underperformance understandably frustrates investors, but they’re misunderstanding the composition of Anthropic’s spending on training and inference.

There are two clear reasons explaining why Amazon isn’t yet truly benefiting from its relationship with Anthropic:

1. As of Q2 2025, Anthropic’s cloud spending is over 2x smaller than that of OpenAI.
2. A large share of Anthropic’s spending is going to Google Cloud – one of Anthropic’s first major investors ($300M round late-2022) and preferred cloud partner in 2023 and 2024, before the expanded AWS deal.

Anthropic & AWS multi-gigawatt AI Training infrastructure

In particular, we believe that most of Anthropic’s skyrocketing inference needs are served by Google Cloud. Having the world’s best inference system (TPU) is a key competitive advantage.

The AWS infrastructure buildout is aimed at taking a chunk of this for its key customer will also focusing on training. While Anthropic makes less headlines than peers like OpenAI, xAI and Meta, is it all-in on the AGI race and isn’t planning to be shy on training spending. Anthropic leadership truly believes in Scaling for RL.

Their belief will materialize as early as this year. We show below three AWS campuses in final stages of construction, boasting over 1.3GW of IT capacity for the sole purpose of serving Anthropic’s training needs. The speed of construction is remarkable.

While these datacenters look built from the skies, we don’t think they are generating any meaningful revenue yet. Trainium has faced some yield issues on the assembly phase – fairly standard for a new system. We think the three large AWS campuses will meaningfully contribute to AWS’ top line by the end of 2025 and jack up growth above the 20% YoY threshold.

Anthropic isn’t stopping there. Its ~$13B funding round at a $183B valuation will provide capital to sign additional deals with AWS, Google, and others. AWS isn’t waiting standing still – they’re already breaking ground on upcoming GW-scale datacenters to capture this growth.

As explained earlier, these datacenters will primarily be filled with AWS’ custom chip Trainium. Given the sheer scale, we can’t understate how bold Anthropic’s bet is. Not only are they committing to spending tens of billions of dollars, they’re doing it on a largely unproven chip!

Let’s try to make some sense of their bet by digging into Trainium’s TCO and roadmap.

Trainium2 TCO analysis – how Anthropic’s big bet could pay off

Trainium2 supply chain signals are currently extremely strong. Our industry-leading AI Accelerator Model track both the package shipments and the system/rack shipments and they’ve surged since the beginning of the year. It provides quarterly volume forecasts for the 10+ SKUs comprising the Trainium2 and Trainium3 product family and calls out suppliers set to disproportionately benefit from specific SKUs. Contact us for more information.

Note this is chip production, rack production is lagged, but we also track it.

Competing with Nvidia and Google’s TPU is, of course, no small feat. While Google is rolling out its seventh generation TPU, Ironwood, Trainim2 is only Amazon’s third-generation AI Accelerator.

Chip specifications: Trainium2 inferior on all fronts, but…

A simple look at chip specifications shows Trainium as a clear laggard relative to Nvidia:

• Nvidia’s GB200 has a 3.85x FP16 FLOPs advantage, at 2500 TFLOP/s/chip vs Trainium2’s 667 TFLOP/s/chip. Note that spec sheet numbers are inflated compared to actual achievable FLOPs.
• In terms of Memory bandwidth, the gap narrows to 2.75x, at 8000GB/s/GPU vs 2900GB/s/Trn2

Evaluating scale-up network bandwidth is another key item. We’ve explained several times the importance of scale-up networks for reasoning model inference. Our deep-dive on Reinforcement Learning highlighted the similarities of RL with inference workloads, making memory bandwidth a crucial item to scale post-training.

• Nvidia’s GB200 NVL72 boasts an aggregate 576TB/s memory bandwidth across World Size.
• This is a 3.1x advantage relative to Trainium2’s (Teton2-PD-Ultra-3L SKU) 186 TB/s – with the caveat that it varies across SKUs.

While Trainium appears materially behind, the picture changes once we factor-in Total Cost of Ownership.

Trainium’s memory bandwidth per TCO advantage

In the table below, we incorporate TCO into our comparison. While Nvidia has a material head on a TCO per effective training PFLOP, Trainium2 is highly competitive on a TCO per million Tokens and TCO per TB/s of memory bandwidth.

And we don’t see Nvidia’s upcoming VR200 NVL144 change the picture relative to AWS’ Trainium3. To be clear, TCO has many other moving parts. AWS has other system-level architecture deployments that better fit some use cases. Later down the road, Nvidia’s Kyber rack will boast the world’s most advanced scale-up network architecture.

For a full understanding of the TCO of 50+ Nvidia SKU and a detailed TCO comparison with all AMD, Trainium and TPU SKUs, check out our AI Cloud TCO Model. The largest hyperscalers, Neoclouds and their financial sponsors rely on our model to time their investment decisions.

Anthropic is betting on hardware-software codesign

Trainium2’s memory bandwidth per TCO advantage is key to understanding Anthropic’s choice. While Nvidia’s chips and systems are better on most fronts, Trainium2 fits perfectly into Anthropic’s roadmap. They’re the most aggressive AI Lab on scaling post-training techniques like Reinforcement Learning. Their roadmap is more memory-bandwidth-bound than FLOPs bound. Our recent HBM report explains in-depth which AI workloads tend to be memory-bound.

Anthropic’s ramp will make it not only the only large external end-user of Trainium2, it’ll also be materially larger than Amazon’s internal needs (e.g. Bedrock, Alexa, etc). They’re now heavily involved in all Trainium design decisions and, essentially, use Amazon’s Annapurna Labs as a custom silicon partner! This makes Anthropic the only AI lab, alongside Google DeepMind, benefiting from tight hardware-software codesign.

Trainium’s roadmap: doubling down on systems

Amazon is rolling out a new system-level architecture for its anchor customer. Currently, the two systems deployed by AWS are Teton PD and Teton PD Ultra. Next year, the new Teton PDS and Teton Max are set to ship in large volumes. Our AI Accelerator Model provides the exact volumes and SKU-by-SKU breakdown on a quarterly basis.

The key difference is the introduction of an all-to-all scale-up network dubbed NeuronLinkv3. Trainium’s architecture is thus converging towards Nvidia’s NVL72 NVLink.

Four NeuronLinkv3 switch trays will be placed in the middle of the rack with 16 compute trays above and below split evenly. Certain supply chain vendors are set to benefit disproportionately, as highlighted two months ago on Core Research – our institutional research service trusted by the world’s largest hedge funds. That vendor is up 73% since our post. We see the introduction of PDS as an intermediate step in Trainium’s path to catch up with Nvidia. We also believe that Anthropic was heavily involved in the launch of this new system-level architecture.

Anthropic’s increased involvement in design decisions bodes well for future volumes. But they’re not giving up on TPUs and Nvidia GPUs either. Our Accelerator Model forecasts Amazon and Google Cloud’s chip purchases broken down by precise SKU, and our Datacenter model to understand which datacenter and cloud partners support Anthropic’s ramp. The TPU ramp for Anthropic in 2026 is huge, and their are unique aspects to their deal as we have been posting about for over a month.

Let’s now take a longer-term view and evaluate what the future of AWS might look like. Behind paywall, we discuss the following items:

• The outlook for Amazon’s key customer: Anthropic.
• Amazon’s GenAI business beyond Anthropic: Bedrock and internal LLM efforts.
• The Trainium ramp in 2026 & 2027, potential new external customers, and how it might impact Amazon’s financial profile in future years.

The first portion of this report will explain HBM, the manufacturing process, dynamics between vendors, KVCache offload, disaggregated prefill decode, and wide / high-rank EP. The rest of the report will dive deeply into the future of HBM. We will cover the revolutionary change coming to HBM4 with custom base dies for HBM, what various different accelerators are doing with custom HBM including OpenAI, Nvidia, and AMD, the shoreline area problem, memory controller offload, repeater PHYs, LPDDR + HBM combos, and various beachfront expansion techniques. We will also discuss SRAM tags, compute under memory, supply chain implications, and Samsung.

A Brief Overview of HBM

As AI models grow in complexity, AI systems require memory with higher capacity, lower latency, higher bandwidth, and improved energy efficiency. Different forms of memory have different tradeoffs. SRAM is extremely fast but low density. DDR DRAM is high density and cheap but lacks bandwidth. The most popular memory today is on-chip HBM which strikes the balance between capacity and bandwidth.

HBM combines vertically stacked DRAM chips with ultra-wide data paths and has the optimal balance of bandwidth, density, and energy consumption for AI workloads. HBM is much more expensive to produce and has a warranted price premium to DDR5, but demand remains strong for HBM. All leading AI accelerators deployed for GenAI training and inference use HBM. The common trend across accelerator roadmaps is to scale memory capacity and bandwidth per chip by adding more stacks, higher layer counts, with faster generations of HBM. Architectures that rely on other forms of memory offer sub-optimal performance, as we have demonstrated.

In this report, we will examine HBM’s present state, what’s happening in the supply chain, and the groundbreaking changes happening in the future. We’ll examine HBM’s critical role in AI accelerator architecture, the impact HBM is having on the DRAM market, and why it is upending the way memory market analysis is being performed. For subscribers, we will also address the major questions on Samsung’s future viability as a supplier, as well as highlight one technological change that may reverse the trend of increasing HBM capacity.

HBM Primer

First, a brief primer on HBM – what makes it special and challenging to manufacture. While HBM is commonly associated with multiple DRAM dies stacked in a 3DIC assembly, the other key feature is HBM’s much wider data bus, improving bandwidth even with mediocre signaling speeds. This significantly wider bus results in HBM being far superior in terms of bandwidth per package than any other form of memory.

The implication of having much more I/O is increased routing density and complexity. Each I/O requires an individual wire/trace, with additional wiring required for power and control. For a HBM3E stack, there are over a 1,000 wires between the adjacent XPU and the HBM. This level of routing density is not achievable on a PCB or package substrate; therefore, an interposer (silicon or organic) in a 2.5D package assembly like CoWoS is required.

To reduce latency and energy consumption for data transfer, HBM needs to be placed directly adjacent to the shoreline of the compute engine. This makes shoreline (the edge of a SOC) more valuable as HBM can only be limited to the 2 edges of the SOC with the other 2 edges reserved for I/O off the package. This limits the area HBM can be placed in and requires vertical stacking of memory die to provide enough capacity.

To enable the 3DIC form factor, each layer of the stack needs to have TSVs (excluding the top of stack) that can deliver power and signal to the layer above. The additional area required to fit these TSVs is what makes HBM die sizes larger than their DDR equivalent: SK Hynix D1z DDR4 has a bit density of 0.296 Gb/mm², 85% more dense than their HBM3 which is 0.16 Gb/mm². This TSV process is one of the key differences between standard DRAM, and tooling for this is the main bottleneck when it comes to converting regular DDR DRAM wafer capacity to HBM capacity.

The other difference is at the back-end, where the HBM needs to be stacked to 9 or 13 layers in total (8/12 DRAM layers on top of a logic base die at the bottom). Along with CoWoS, HBM has brought packaging technology to the mainstream. Niche packaging technologies like MR-MUF have now become common knowledge for industry participants.

Explosive Bit Demand

We can see the huge growth in HBM bit demand that has come alongside AI accelerator demand. Despite the rapid rise of custom ASICs, Nvidia will still command the lion’s share of HBM demand in 2027, driven by its aggressive roadmap, where Rubin Ultra alone pushes per GPU capacity to 1 TB. Broadcom follows as TPU and MTIA volumes surge, while incremental OpenAI and SoftBank projects add a smaller but noticeable lift. Amazon also emerges as one of the top HBM customers. For Amazon, it has a strategy of procuring HBM directly rather than through design partners, helping them to lower their cost. For a detailed, chip-by-chip bit forecast, refer to our Accelerator Model. It includes projections for revenue and bit demand by memory vendor, as well as wafer starts and TSV capacity, broken down by supplier. The model also tracks HBM pricing across different generations, and provides chip-by-chip HBM type, layers, stack counts, capacity and bandwidth.

Process Flow: Front End

When regular DDR DRAM capacity “converts” to HBM capacity – the main change is the addition of tools for forming the TSVs, and more bumping capacity as HBM wafers are bumped on both sides. Both of these steps are to enable the 3D stack, although they are omitted for wafers used for the top die which only need a single side of bumps and don’t require TSVs.

TSVs require etchers to create the vias, and deposition and plating tools to fill them. To reveal the TSVs, grinders, another etch step, and temporary bonders to attach carrier wafers used in this process are required. This is why HBM capacity is now quoted in terms of TSV capacity, as this is the main incremental set of processes that turn DDR wafers into HBM wafers.

For bumping, this is mainly deposition, plating and stripping. Also, optical inspection tools from Camtek and Onto are available to check that the bumps are not defective and are of the correct profile.

Process Flow: Packaging

The other part of this is back-end packaging which Hynix continues to push forward with MR-MUF which we wrote about extensively here. In short, MR-MUF offers higher productivity and better thermal performance. Hynix’s proprietary (co-developed with NAMICS) molded underfill material offers more thermal dissipation than the Non-Conductive Film that Micron and Samsung use. Hynix has been able to sidestep thermal compression bonding (TCB) because they have found other ways to manage warpage. One of the benefits of TCB is the use of force to stabilize the bonding matter.

The use of force on the other hand increases the risk of causing damages to bumps. With stress applied to bumps, SK can also add more dummy bumps which also helps with thermal dissipation.

The process is also far more productive. A batch mass reflow and single over-mold step are used for joint formation, compared to a complete TCB step for joint formation for each and every layer with TC-NCF.

Process Flow: Yields

HBM is a more technically sophisticated product than other DRAM form factors, especially given the high 3DIC stack. As such, packaging yields are not going to be comparable to what manufacturers are accustomed to compared to their more conventional products. However, yields at the front end are also challenging, and we think yield is more of a problem at the front end. As mentioned above, HBM is not demanding with regards to speed bins, so why is this the case?

The reason goes back to the 3DIC assembly and the TSVs. One of the challenges is the Power Distribution Network (PDN) with the TSVs needing to be able to deliver power up the stack. TSV layout and design is proprietary and one of the main areas of differentiation between the various manufacturers.

One of HBM’s key challenges is delivering power up the stack with power TSVs. Refresh operations especially draw a lot of power, and the design of the power distribution network is important. Hynix’s HBM3E has reduced peripheral area and introduced all-around power TSVs on the die instead of having two banks of power TSVs, thereby increasing the number of TSVs by almost 6x. As a result, SKH has achieved a much lower IR drop, up to 75% lower for VPP.

Similarly, Micron’s surprising leapfrog in HBM technology (Micron didn’t even offer standard HBM3) was due to its focus on TSVs and the power delivery network. The TSV network seems likely to be the point of differentiation that allows Micron to claim 30% lower power consumption, though that claim is yet to be verified.

The other thing is delivering the promised speeds within the power and thermal envelope. As with any 3DIC assembly, thermal dissipation is an issue, and DRAM especially doesn’t like heat. As data from hyperscalers have shown, HBM failures are the number one cause of GPU failures, which happen more frequently than other chips in the data center.

All manufacturers have absolute yields well below what they’re accustomed to compared to their conventional memory wafers, so it is a question of relative yields and the end economics. For SK and Micron, yield loss is more than made up for by high pricing, and hence, HBM is margin accretive. For Samsung, yields are even worse. Ironically, their low yields tighten up the total DRAM wafer supply, leading to higher pricing.

This leads us to layer counts. Higher layer counts are harder to achieve. Simplistically if the stack yield of a single layer is x%, each layer’s yield will accumulate to x% to the power of n bond steps (which is just total layers less 1). Take an 8-layer stack with 99% stack yield per layer; total yield will be 92%. For a 12-layer stack, this becomes 87%. Of course, this is overly simplified. Yield degrades at higher layer counts as non-critical stack defects can accumulate. For example, a small but acceptable amount of non-co-planarity at a few layers can result in an unacceptable amount of co-planarity at higher levels.

Process Flow: Bonding Tools, SK Hynix + Hanmi Drama

The bonding or die attach step is a key contributor to yield and thus requires sophisticated tools. With TSV pitches around 40 µm, the bonders must be capable of single-digit or even sub-micron alignment accuracy. Even pressure distribution is also crucial to avoid warpage that will compound over many layers. And throughput of course is important as it drives cost.

Hanmi made an early bet to focus on thermocompression (TC) bonders for HBM, a segment at that time ignored by market leaders Besi and ASMPT. This paid off in a near monopoly in current HBM processes. At SK Hynix their share was 100% until last fall, when Hynix placed a large order with competing tools from Hanwha. Allegedly, they paid Hanwha a higher price for the tools.

This set off a firestorm at Hanmi who, understandably, were upset to see a competitor winning with higher prices despite not being qualified on Hynix’s process for HBM supply to Nvidia, the largest and most important HBM customer.

The dispute reached a fever pitch in early April when Hanmi pulled its field service teams out of SK Hynix fabs. Without service, it would be months if not weeks before Hynix was unable to ship its marquee products. Longer-term it would threaten the entire accelerator supply chain as Micron and Samsung would not quickly be able to fill the capacity void. Hanwha’s tools had not yet been delivered and a batch of ASMPT bonders ordered last fall do not work for Hynix’s HBM3E 12-high. This left the fabs with little choice but to beg forgiveness from Hanmi.

Under enormous pressure, SK Hynix placed a small order with Hanmi in recent weeks. It appears this was more to placate Hanmi than a large volume order, but it was enough to restore field service to the tools. There may not be much more juice for Hanmi to squeeze from their monopoly power, as ASMPT, Besi, and others are rushing to improve their HBM-specific TC bonders.

China: CXMT & Huawei HBM

Export restrictions ban the transfer of all raw HBM stacks into China; however, chips with HBM can still be shipped as long as they don’t exceed the FLOPS regulations. Currently, banned HBM is still being reexported to China through a network involving CoAsia Electronics, Faraday and SPIL which allows end users in China to desolder and reclaim the HBM from GPU packages.

As HBM is one of the key ingredients for accelerators, and with export restrictions threatening to cut off HBM supply, China is naturally pouring resources into domestic development efforts. China has planned 200B USD in subsidies for home-grown semiconductors over the next five years. Expect a material portion will go towards HBM. DRAM national champion CXMT is aggressively expanding HBM capacity, with a large stockpile of tools to insulate from updated export controls (U.S. increased HBM controls in Dec. 2024, Korea more recently). HBM2 8-high will enter mass production in the first half of 2025, with TSV capacity matching Micron’s by the end of the year.

Huawei, which has never seen a high-tech market it doesn’t want to enter, has its own HBM affiliates with XMC (Wuhan Xinxin) producing the HBM wafers and SJSemi (Shenghe Jingwei Semiconductor) packaging them. Current capacity is at R&D scale, not high volume, but is planned to ramp in coming years. Both XMC and SJSemi are entity listed and thus restricted from buying equipment with U.S.-origin content (GlobalFoundries recently got a slap on the wrist despite selling more than $17 million in chips to SJSemi without a license).

HBM Stack Counts – Let’s Get High, to Hybrid Bond or Not?

More layers in the HBM stack means more memory capacity. With each generation, layer counts have gone higher. This stack height has been contained within a 720-micron height cube (the current JEDEC standard) up until now. To fit in more layers, each die (excluding the top die, which needs to be much thicker to withstand handling during subsequent packaging steps) has been made thinner, and the bump gap between the dies has also been made thinner to create more space to fit in more layers. Thinner dies are increasingly difficult to handle and, therefore, more vulnerable to warpage and breakage, which hurts yields.

The main benefit of Hybrid bonding (HB) for HBM is it is bump-less. By eliminating the bump gap this frees up room for more DRAM core layers to fit. This introduces a whole host of new challenges for yield and cost which may not be worth it, especially as HBM doesn’t need the level of interconnect density that hybrid bonding offers. If anything, manufacturers are exploring how much the pad density can be relaxed in hybrid bonding to ease bond accuracy requirements to make the technology more viable for HBM. HB also offers a one off power and heat benefit but the primary benefit is stack height.

HB adoption for HBM has always been a “next generation” technology and the goalposts continue to keep shifting. For D2W hybrid bonding, getting yields to be acceptable is extremely difficult and expensive for a 2 layer. Imagine scaling that problem for 16 layers and higher. The memory players are still very early in their hybrid bonding technology development. In TSMC’s experience, HB adoption has taken a long time to reach volume production and even when the performance benefits are clearer in advanced logic – adoption has taken a long time.

HBM3 and HBM3E are going up to 12-hi stacks and with bump-based interconnect, 12-hi has approached the limit within the current 720um cube thickness. The two solutions to go higher are either bump-less or making the stack taller/thicker. In a blow to hybrid bonding adoption, the latter has been chosen with JEDEC confirming a relaxation to 775 um stack height.

Height relaxation can go even further. 775um is the standard thickness of a silicon wafer. HBM needs to be the same height as the logic die it is co-packaged with. To have something higher than a 775 um stack, the logic wafer would also need to be thicker and the current equipment is not designed to accept thicker wafers. One potential solution could be to raise the molding of the interposer underneath the logic to raise it and ensure coplanarity with the neighboring HBM, though this lengthens the traces and implementing silicon bridges for interconnect will not be straightforward.

While initially there was more talk about HB implementation for HBM4, this has been shifted back to 4E. Recently, both Hynix and Micron have been far quieter on HB adoption, while Samsung is the loudest. This is typical for Samsung which often promotes the most aggressive technology implementations in attempts to catch up, only to expectedly fail on execution. This leads to them falling even further behind.

While 16 layer is solved by the higher stack height, to get to 20 layer and beyond, there is likely a further reduction of the bump gap and more wafer thinning, or we simply cap out at 16 layers. With higher stacks you can get more density but more stacks offer bandwidth and density.

Throughput Optimized: I/O is the Lifeblood of the AI Accelerator

The key defining feature of an AI accelerator is they are highly parallelized and optimized for throughput. Accelerators are designed to maximize the total number of operations an accelerator can perform per second by sacrificing the complexity of these operations. Most accelerators focus on multiplication and addition operations for General Matrix Multiplication (GEMMs), which dominate AI training and inference workloads. This compares to CPUs, which are also focused on how many instructions per second they can execute, but CPU cores are much “smarter,” which requires far more circuitry and area. Therefore they are designed to execute a broad range of more complicated tasks but at much lower throughput.

The implication is that AI accelerators need a lot of off-chip bandwidth for memory and the scale up and scale out fabrics. Bandwidth is needed to move the processed data off-chip whilst also feeding the accelerator unit with more data to process. Without sufficient bandwidth, the XPU’s compute elements will be left unutilized, defeating the purpose of having all this parallel computing power available. Let’s start with memory needs

Memory content increases

To deliver more performance – increasing memory capacity and bandwidth along with FLOPs has been paramount and easily observed in accelerator roadmaps. There are 3 dimensions where capacity and bandwidth are scaling:

1. Newer generations of HBM deliver higher bandwidth through faster signalling speeds, and denser core die
2. Adding the number of layers per stack increases capacity. We are on the cusp of 12-high HBM becoming the mainstream configuration
3. Adding more HBM stacks per package adds more bandwidth and capacity

Here we can see this in Nvidia’s roadmap. HBM capacity explodes from the A100’s 80 GB of HBM2E to a 1024 GB of HBM4E for Rubin Ultra. Memory bandwidth per chip also increases dramatically. From Ampere to Blackwell Ultra, the biggest absolute and relative increase in the bill of materials comes from the additional HBM content- benefitting the memory vendors (primarily SK Hynix).

This is related to the need for non-memory I/O as well. Scaling up more GPUs in a single memory-coherent domain delivers more aggregate memory capacity and bandwidth. This allows scaling inference of larger parameter models and support for much longer context lengths that are becoming prevalent in reasoning models and complex workloads.

Just as Parkinson’s Law observes that work expands to fill the time allotted, modern AI follows a “memory‑Parkinson” dynamic in which neural‑network architectures relentlessly grow to occupy whatever HBM becomes available. Each generational bump in HBM capacity and throughput, whether 80 GB at 3 TB/s on H100 or 192 GB at 8 TB/s on GB200, quickly encourages designers to increase parameter counts, context lengths, and KVCache footprints, nullifying the headroom that seemed ample only months earlier. Techniques once deployed to squeeze models into tight budgets (activation checkpointing, optimizer off‑loading, weight quantization) are relaxed as soon as new HBM space appears, until the memory wall is hit again and efficiency tricks must be rediscovered. In effect, the mere presence of larger, faster HBM does not yield sustained slack; instead it resets the baseline for “reasonable” model size, ensuring that capacity and bandwidth remain limiting factors despite silicon advances. Essentially, as AI chips get more HBM, developers immediately build larger models to fill it, so memory is always the next bottleneck. Let’s go through how HBM is used, and where the pressures are.

HBM Usage in Inference

In LLM inference, all the model weights reside permanently in the on-package HBM memory so the GPU can fetch them without delay. Alongside the weights, HBM also holds the KVcache. Each time the model is asked to produce the next token, the GPU first reads the weights from HBM and simultaneously retrieves the entire KV cache so it can compare the new token against the conversation history during the self‑attention phase. After computing, the GPU appends a fresh key and value for the newly generated token back into HBM, enlarging the cache. This is very demanding on bandwidth as every token decode step repeatedly reads both the static weights and the ever‑growing KV cache. If memory bandwidth is not able to move this data at terabytes per second the GPU spends more time waiting for memory than performing computation. This is what happens in reality, as bandwidth significantly overwhelms the compute intensity of token decode, making most LLM inference workloads memory bandwidth-bound rather than compute bound.

As models improve, they have increased in horizon lengths. What this means is that models are able to think, plan, and act for longer periods of time. This rate of increase has been exponential and has already manifested itself in superior products. Deep Research from OpenAI, for example, can think for tens of minutes at a time, while GPT-4 mustered mere tens of seconds.

As models can now think and reason over a long period of time, the pressure on memory capacity explodes as context lengths regularly exceed hundreds of thousands of tokens. Despite recent advances that have reduced the amount of KVCache generated per token, memory constraints still grow quickly. One way to deal with this has been to serve reasoning models at lower batch sizes which is harmful to economics.

The main driver of AI progress is Reinforcement Learning (RL) and a huge part of the RL paradigm is inference. As an example, often what is needed for RL is synthetic data satisfying strict requirements, which means conducting many GPU-hours worth of inference to generate data that is later filtered by another model. Another example of heavy inference loads is RL for hard-to-verify tasks like creative writing. Unlike code, which can be checked and verified easily, things like creative writing, legal work, and teaching cannot be verified trivially. The way to get around this, and thus to get a signal to reinforce and improve the model, is to have another model judging the answers. This LLM-as-a-judge is then given a rubric, currently hand written but soon to be automated by LLMs, which it uses to grade the answer.

KVCache offload

There are various algorithmic or setup improvements that are designed to reduce pressure on scarce HBM. One technique is offloading the KVCache to a cheaper and more available tier of memory such as conventional DDR or even storage.

Today, KVCache offloading is already commonly used . Nvidia has a framework for this called Dynamo Distributed KVCache Manager. Conceptually this is not so different from the multiple tiers of memory available in general purpose CPUs: extremely fast but low density L1/2/3 Cache and slower but high density DRAM. In an AI system, where the where the KVs are stored based are managed based on frequency of usage. A well-optimized system keeps all currently used KVs in HBM, infrequently used KV in DDR, and very rarely used KV in NVMe.

Just like how DRAM is not cannibalistic to L1/L2/L3 cache demand for CPU, HBM and DDR/SSD offload do not compete with each other directly. In fact, for most modern LLM workloads, the prefill speed (aka the rate at which KVCache is produced) is typically slower than the transfer rate to DDR or NVMe SSD, meaning KV rarely ‘lives in HBM’ in their entirety. They get produced and evicted or sent to the decode node to be used to produce the next token. Mostly it’s the system prompt that is used for every user that is kept in HBM as well as other hot KVs such as the active sequence window and some prefetch buffers.

As for whether DDR or NVMe is used, it depends on workload needs and size of workload. It also depends on how often the workload is cycled as frequently cycled KVs are not a good fit for the limited write/rewrite tolerance of NAND. Agentic use cases that use tool calling to pull in documents and data at very low latency and high cycle rates today further push caching from NVMe to DDR. These are architectural and user experience tradeoffs to consider, rather than direct substitutes to each other.

As use cases evolve, there may be different hardware setups used for different inference needs. For example, querying a fixed code base or document would benefit from accessing larger amounts of KVCache per user per GPU as the memory demands of those user behaviors is extremely high compared to normal chat.

HBM for Pre-Training

For traditional pre-training, everything the GPU needs for a forward‑and‑backward step passes across HBM. First, the model’s weights are stored in HBM so each layer can read them quickly while computing the forward pass on a batch of data. As every layer processes the batch, it writes intermediate activations into HBM so they are available later. Once the forward pass finishes and the loss is calculated, the backward pass begins: the GPU revisits those stored activations and weights, reading them from HBM to compute gradients. The resulting weight gradients, plus any auxiliary optimizer statistics (for example, momentum or variance terms in Adam), are also written to HBM. Finally, the optimizer reads those gradients and statistics from HBM to update the weights in place, ready for the next iteration. However, training operations require more compute relative to data transfer, meaning training is more often compute bound. But as mentioned above, RL is now key to improving model capability – so what was traditionally achieved with pre-training is becoming more like inference in the form of reinforcement learning.

The rest of this piece will discuss OpenAI’s ASIC project, shoreline area challenges, the revolutionary change coming to HBM4 with custom base dies for HBM, the advantages on PHYs, memory controller offload, repeater PHYs, LPDDR + HBM combos, and various beachfront expansion techniques. It will also discuss SRAM, compute under memory, supply chain implications, and Samsung’s struggles.