Sugon scaleX40-3G: 40 Accelerators and 5.62 TB of HBM in 16U

Written and maintained by Haink's infrastructure team · Compiled from Sugon's product page, product brochure, 45-page solution manual and 207-page user manual, 5 September 2026

The scaleX40-3G (曙光 scaleX40-3G) is Sugon's enterprise superpod, announced 26 March 2026. It places 40 Hygon DeepComputing 3 accelerators and 5.62 TB of HBM in 16U of a standard 19-inch rack, on a single-tier interconnect providing 448 GB/s between any two cards with unified memory addressing across all forty.

At the time of writing there is no English-language specification for this product anywhere. This page is compiled directly from Sugon's own documentation. Where a figure is derived rather than published we show the arithmetic; where Sugon publishes nothing we say so rather than estimating.

Specifications at a glance

Node composition

A pod comprises fifteen field-replaceable units in three roles. Compute and switch nodes mate orthogonally — they plug directly into one another with no cables between them.

The PCIe 5.0 slots in each compute node are the scale-out path — this is where scaleFabric or another cluster network attaches. HSL handles traffic inside the pod; anything leaving it goes out through PCIe.

The accelerator: DeepComputing 3

The DCU (Deep Computing Unit) is Hygon's GPGPU accelerator line, and DeepComputing 3 — 深算三号 — is the third generation. The lineage traces to the same 2016 AMD licensing relationship that produced Hygon's x86 processors: the architecture is AMD CDNA-derived and the software stack, DTK (Deep Toolkit), descends from AMD's ROCm rather than being written from scratch.

Sugon does not name the part. We searched the full text of the product page, the brochure, the 45-page solution manual and the 207-page user manual: the accelerator is called only 深算三号 GPU, and no part number appears anywhere. Hygon ships at least two third-generation cards — one with 64 GB and no FP8 support, one with 144 GB that does run FP8 — and only the second is consistent with what Sugon publishes here. Our page on the DCU line sorts the part numbers out.

What can be derived from Sugon's published aggregate: 28 PFLOPS FP8 across 40 cards is approximately 700 TFLOPS FP8 per accelerator. For scale, NVIDIA's H200 delivers 1,979 TFLOPS of dense FP8, and the B300 around 7,000 by vendor figures whose dense-or-sparse basis NVIDIA has not stated.

That produces a clear design read. DeepComputing 3 carries more memory than an H200 (144 GB against 141 GB) with roughly a third of its FP8 throughput. It is a memory-forward part, and the system built around it is a memory-forward system. Whether that is the right machine depends entirely on whether the workload is bounded by memory or by arithmetic.

HSL, and why "ten times InfiniBand NDR" needs unpacking

Sugon's literature describes HSL as delivering "ten times the bandwidth of an IB NDR network, with latency down to hundreds of nanoseconds." The arithmetic checks out: InfiniBand NDR runs at 400 Gb/s, which is 50 GB/s, and ten times that is 500 GB/s — consistent with the published 448 GB/s peer-to-peer figure.

But the comparison is drawn against the wrong layer, and this trips up almost everyone reading the specification for the first time. NVIDIA operates two networks that do different jobs:

HSL performs NVLink's job, but Sugon benchmarks it against InfiniBand — NVIDIA's slower network, by a factor of eighteen to thirty-six. Compared like with like, HSL sits below NVLink on both current NVIDIA generations.

The comparison Sugon is actually making becomes fair above eight accelerators, and that is the point worth understanding. An NVIDIA DGX holds eight GPUs on NVLink. Reaching forty means five DGX chassis, and traffic between them drops onto InfiniBand at roughly 50 GB/s per card. In a job spanning forty accelerators, most peer traffic crosses a chassis boundary. The scaleX40 keeps all forty on 448 GB/s uniformly.

So the honest reading is a crossover, not a verdict:

• Up to 8 accelerators: NVIDIA is faster — 900 or 1,800 GB/s against 448.
• From 9 to 40: the scaleX40 is faster, by close to an order of magnitude, because the NVIDIA alternative has fallen back to the network.
• Above 40: undetermined. Traffic leaves the pod through PCIe onto scaleFabric or another cluster network, and Sugon does not publish what the resulting profile looks like.

Separately, NVIDIA's NVL72 rack keeps 72 GPUs on 1,800 GB/s NVLink and beats HSL in every regime — at rack scale and around 140 kW.

What Sugon says it is for

Worth quoting, because vendors rarely narrow their own claims: the product brochure states the scaleX40-3G "can cover inference, fine-tuning and most artificial intelligence application scenarios." Inference and fine-tuning — not training from scratch.

The design agrees with the scoping. Large pooled memory, moderate arithmetic, KV-cache offload into ParaStor storage, DeepEP support for mixture-of-experts communication, 800+ models pre-adapted on the SothisAI platform. This is a machine built to serve models, not to train them from nothing.

Sugon's solution manual does also market into scientific computing — cryo-EM three-dimensional reconstruction, meteorological forecasting, genomics — and states that reconstruction workloads carry a "rigid requirement" for double-precision arithmetic. The system supports FP64. How much of it, Sugon does not say.

How it compares

Set against the two NVIDIA systems a buyer would realistically weigh it against. Sugon figures are published. H200 figures are dense, from NVIDIA's datasheet; B300 figures are vendor numbers whose dense-or-sparse basis NVIDIA has not stated.

The shape of it: more pooled memory than either NVIDIA system — five times a DGX H200 and 2.4 times a DGX B300 — with compute between the two and roughly three times the power draw. A memory-bound workload that will not fit in 2.3 TB is the case where this machine has an argument no NVIDIA box in the same footprint can answer. A compute-bound training run is not.

Three figures to request before you sign

We reviewed the product page, the product brochure, the 45-page solution manual and the 207-page user manual. Three numbers appear in none of them.

The omissions are consistent across every channel, which makes them a disclosure policy rather than an oversight — and a policy is something a buyer can push against. Ask for all three in writing before a purchase order, and specify dense figures — NVIDIA quotes two numbers for every precision, one with structured sparsity applied, and comparing a vendor's dense figure against NVIDIA's sparse one doubles the apparent gap for free.

Deployment realities

Three constraints deserve checking before anything else, because they are physical rather than commercial.

Power. 45 kW typical and 50 kW peak into 16U. Many enterprise halls cannot deliver that to a single rack position regardless of what the budget allows. Sugon's air/liquid hybrid design and CDU option genuinely do make it deployable in an air-cooled room, which is unusual at this density — but the electrical supply still has to be there.

Floor loading. Approximately 500 kg over a footprint of 446 × 1020 mm is on the order of 1,100 kg/m². A large number of raised floors will not accept that without reinforcement, and it is not mentioned in Sugon's documentation.

Coolant. The main coolant inlet and outlet use 1.5-inch standard clamp fittings. Where a facility already has a liquid loop, confirm the fitting standard, supply temperature and flow rate against the pod's requirement rather than assuming compatibility.

Storage and software

The pod is designed to be paired with ParaStor, Sugon's distributed unified storage, quoted at 220 GB/s and 10 million IOPS per device. Two features are specifically relevant to accelerator workloads: XDS moves data directly between accelerator memory and NVMe storage, bypassing host CPU and system memory, with a reported 30–70% reduction in CPU utilisation and 2–3× the peak bandwidth of the conventional path; and KV cache offload extends a model's attention cache beyond HBM into DRAM, local SSD and ParaStor — the mechanism by which a system with finite accelerator memory serves long contexts.

Software is SothisAI, covering development, scheduling and operations, with Sugon stating that 800+ large models are pre-adapted and optimised. The accelerator toolchain is Hygon's DTK. Because DTK descends from AMD's ROCm, code that already runs on AMD Instinct ports comparatively cheaply, while hand-tuned CUDA does not.

Design details worth knowing

Two engineering choices are unusual enough to be worth calling out, because they affect operations rather than benchmarks.

Cableless orthogonal mating. Compute and switch nodes plug directly into each other with no cables in between. Sugon claims a tenfold availability improvement over cabled designs and 40–70% lower power than an optical interconnect, with assembly and maintenance falling from hours to minutes. Cables and optics are among the most common failure sources in dense accelerator systems, so removing them from the scale-up path is a real reliability argument rather than a marketing one.

Single-tier topology. All 40 accelerators sit on one switching layer rather than two. Fewer hops means lower latency and fewer components that can fail — at the cost of capping the pod at 40, which is why anything larger becomes a scale-out problem.

Frequently asked questions

How much memory does the Sugon scaleX40 have?

5.62 TB of HBM across 40 accelerators, which works out to 144 GB per card. Sugon publishes the total and states "≥ 5 TB"; the per-card figure follows from 144 × 40 = 5,760 GiB ÷ 1,024 = 5.625 TiB. That is roughly five times the accelerator memory of an eight-GPU DGX H200 and 2.4 times a DGX B300.

What accelerator does the scaleX40 use?

The Hygon DeepComputing 3 (深算三号), four per compute node across ten compute nodes. Sugon publishes no part number for it in any of its documentation. The architecture is AMD CDNA-derived under the 2016 AMD–Hygon licensing arrangement, and it is programmed through DTK, Hygon's ROCm-derived toolkit.

What is HSL and how fast is it?

HSL is Sugon's scale-up bus — the layer performing the role NVLink performs for NVIDIA. It provides 448 GB/s between any two of the 40 accelerators on a single-tier CLOS topology, more than 17 TB/s aggregate, latency in the hundreds of nanoseconds, with Load/Store memory semantics and unified memory addressing across the pod.

How much power does a scaleX40 draw?

Typical peak around 45 kW, maximum 50 kW, fed from a 2U 60 kW power shelf with twelve modules in 9+3 redundancy. It accepts 380 V three-phase AC, three 220 V single-phase feeds, or three 190–400 V DC feeds.

Can the scaleX40 be air cooled?

Partly. The design is a cold-plate liquid and air hybrid: high-power silicon is liquid cooled while the rest is air cooled, and with an air/liquid CDU the pod can be deployed in a conventional air-cooled machine room. That is unusual at 45 kW in 16U and is one of the more practically useful things about the product.

What is the FP64 performance of the scaleX40?

Sugon states that FP64 is supported alongside FP32, TF32, BF16, FP16 and FP8, but publishes no FP64 figure in any document we have reviewed — product page, brochure, solution manual or user manual. Given that the company markets the system into cryo-EM and meteorological workloads it describes as having a rigid double-precision requirement, the number exists and should be requested directly.

Is the scaleX40 a training or an inference machine?

Sugon scopes it to inference and fine-tuning in its own product brochure, and the design supports that: large pooled memory, moderate arithmetic, KV-cache offload into storage, and mixture-of-experts communication support. For training large models from scratch, a DGX B300 offers twice the FP8 throughput in a third of the power.

Related

• Sugon — the company, the product lines and the Hygon relationship
• Hygon DCU and DeepComputing 3 — the accelerator, and how to tell the cards apart
• HSL, NVLink and InfiniBand — where the domain-size crossover sits
• scaleX40 vs DGX H200 vs DGX B300 · ParaStor · Sugon liquid cooling
• AI cluster architecture — how scale-up and scale-out layers fit together
• Liquid cooling for AI servers — what 45 kW in 16U requires
• GPU server buying guide · AI infrastructure cost guide
• Huawei enterprise IT · xFusion FusionServer

Sources

• Sugon — scaleX40 product page (40 cards, 28 PFLOPS FP8, 5.62 TB HBM, 448 GB/s peer-to-peer, node composition, power and physical specifications)
• Sugon — scaleX40 solution manual, 45 pp. (precision support list, aggregate FP8 and HBM figures, memory-bandwidth bottleneck statement, eight-card OAM server comparisons)
• Sugon — scaleX40-3G product brochure (node composition, system power and weight, HSL memory semantics, vendor scoping to inference and fine-tuning, orthogonal cableless design)
• Sugon — scaleX40 solution manual, 45 pp. (aggregate 17 TB/s, ParaStor and XDS, KV cache architecture, scientific computing scenarios)
• Sugon — scaleX40-3G server user manual, 207 pp. (system power, node specifications)
• Sugon — scaleX40 announcement, 26 March 2026
• NVIDIA — H200 datasheet · NVIDIA — GB300 NVL72
• Hygon DCU generations and the CDNA lineage