Skip to main content

4 posts tagged with "昆仑芯P800"

百度昆仑芯P800性能数据与架构创新

View all tags

昆仑芯超节点率先量产交付:百度把「自用练兵」变成了「对外供给」

· 3 min read
Industry Research Team

在 2026 工博会「国芯展」上,各家国产芯片厂商展台的主角都换成了超节点——而百度昆仑芯交出的是最硬的那张牌:32/64 卡超节点已实现量产交付,是国内率先进入量产交付阶段的超节点方案之一。

一、昆仑芯的系统级布局​

层级产品
芯片昆仑芯 P800(3 代,卡片)
超节点32/64 卡超节点(已量产交付)
集群天池 256 / 天池 512,已实现全自研三万卡集群
交付状态供不应求(受晶圆代工产能约束)

「率先量产」的关键不在卡数多少,而在工程完成度:从演示、客户测试到可复制交付,中间隔着整机柜液冷、供电、互联稳定性与批量运维的一整套功课。

二、与同行的时间表对照​

厂商超节点方案状态(2026-10)
昆仑芯32/64 卡量产交付
华为Atlas 950 / 960950 规模供货推迟至年底或明年初;960 规划 2027 Q2
天数智芯IXL144(144 卡/柜)工博会首展
沐曦曦景 S600(64 卡)WAIC 首发、工博会展示
燧原ESL64-O(正交)展示
阿里磐久 AL128/AL144发布

三、昆仑芯路径的独特性​

与华为「全栈自研 + 超节点系统售卖」、创业公司「单卡突围再上系统」不同,百度昆仑芯走的是互联网大厂自用转外供路线:搜索、文心一言的内部负载提供持续练兵场,量产交付的产能优先满足自家智能云,再逐步对外。

这条路的上限取决于两点:自用需求的规模(能否撑过代际迭代),以及对外分发的渠道(百度智能云的市占)。与谷歌 TPU 的对比可以参考这篇分析——差距不在芯片而在商业化半径。

四、对采购者的提示​

超节点选型已经从「看参数」进入「看交付」阶段:已量产交付的方案意味着有真实运维数据、故障率与升级路径可考。问供应商「已交付多少柜、运行多久、利用率多少」,比问峰值算力有用得多。

延伸阅读:超节点放量元年 · 昆仑芯 P800 卡片 · 完整对比表

昆仑芯 M100 部署进展与百度自研芯片路线

· 7 min read
Industry Research Team

2026 年 6 月 12 日,在智源大会上昆仑芯研发副总裁漆维透露,面向推理市场的 M100 芯片目前已交付大客户进行测试,并已向客户小规模出货。与寒武纪 MLU690 迟迟无法交付形成对照,昆仑芯的节奏明显更靠前——尽管它面临的最大问题是需求侧而非供给侧。

M100 的定位:只做推理​

昆仑芯 M100 是昆仑芯科技 2026 年推出的第四代 AI 芯片产品,延续自研 XPU 架构理念,主要针对大规模推理场景(尤其是 MoE 模型)进行优化设计,旨在提升此类模型的推理性能并提供较高的性价比。

这颗芯片的发布时间可以追溯到 2025 年 11 月 13 日的百度世界大会。百度集团执行副总裁沈抖透露将发布新一代昆仑芯,其中包括面向大规模推理的 M100 和面向超大规模训练与推理的 M300,计划分别于 2026 年年初和 2027 年年初上市。2026 年 1 月 27 日,百度 CEO 李彦宏在接受《时代》杂志专访时评论芯片行业,表示百度刚刚发布了新款 M100 芯片,并正在开发新的芯片集群。

在百度 2026 年的业绩会上,李彦宏进一步披露昆仑芯已经完成三代 AI 芯片的研发与商业化,并公布了 M100 与 M300 的产品路线图。

维度昆仑芯 M100昆仑芯 M300
上市时间2026 年年初2027 年年初
目标场景大规模推理,尤其是 MoE 模型超大规模多模态模型训练与推理
部署状态2026 年 6 月已交付大客户测试并小规模出货尚未发布
配套超节点天池 256 / 天池 512规划中

值得注意的是,2026 年 7 月百度昆仑芯科技自主研发新品 M100 芯片实物首次在央视报道中公开亮相——这类"实物亮相"的报道时点,通常意味着产品已进入可交付状态。

天池超节点:从千柜级部署到开放规范​

M100 的商业化依托的是天池超节点。据公开报道,天池 256 与天池 512 超节点在 2025 年百度世界大会发布:最高支持 256 及 512 卡极速互联,卡间互联总带宽分别提升 4 倍及 1 倍,其中天池 256 主流大模型推理任务单卡 tokens 吞吐提升 3.5 倍,天池 512 靠单节点即可完成万亿参数模型训练。

这两款超节点计划分别于 2026 年上半年及下半年推出。天池超节点覆盖 32 至 512 卡全场景,采用标准机柜形态、三总线盲插与模块化设计,兼容液冷与风冷 IDC。

更重要的进展发生在 2026 年 9 月 16 日。据报道,百度智能云在 2026 智能经济论坛上宣布天池超节点已实现全栈国产,并已在多地智算中心进行千柜级规模部署,支撑万亿参数大模型训练;同时宣布全面开放天池超节点的架构、供电、散热、节点、互联和管理六大核心模块技术规范,助力国产芯片更快完成从单卡验证到超节点级系统适配。

这份规范开放的意味值得深挖:它与昇腾推动 NPO 成为 OIF 标准、摩尔线程联合中国移动研究院与之江实验室发布《OISA 高密超节点参考设计技术规范》指向同一件事——超节点的技术规范正在成为国产厂商争夺的新战场。

百度的芯片路线:五年五芯与集群梯度​

百度在芯片路线上的公开表述相当清晰。第一是产品化节奏,即"五年五芯"计划,推动每年推出新版芯片,把芯片开发模式从项目制转向产品化。第二是场景化细分策略:M100 专注提升大规模推理任务的性价比,M300 针对超大规模多模态模型优化。

第三是集群规模的梯度规划。据公开报道,百度智能云计划将昆仑芯单一集群规模从三万卡扩展至百万卡级别;另有报道称百度正在研发显卡级超级节点,预计 2027 年下半年开始交付千卡至四千卡规模的计算集群,并已有四千卡超节点的规划。

现有的部署规模方面,据公开报道,2026 年上半年百度点亮了昆仑芯 P800 的 3 万卡机,这是国产算力发展的重要里程碑;昆仑芯累计已完成数万卡部署。外部落地方面,昆仑芯已进入招商银行大模型算力项目,并在国家电网、中钢研完成部署,且已构建覆盖互联网、能源、金融、制造、汽车、通信、教育等行业的全栈昆仑芯集群。

在安全认证上,据公开报道,昆仑芯 M100 在最新一轮安全可靠测评中获得 Level I 评级,同期华为昇腾 950 获得 Level II 评级,龙芯与海思鲲鹏的通用处理器则获得最高等级的 Level III 评级。该三级体系正在塑造政府采购的实质性导向。需要注意,测评结果不等于性能结论——官方报道也指出 M100 较低的评级意味着它在满足该框架最严苛基准上仍有距离。

研判​

昆仑芯当前的处境与华为、寒武纪、摩尔线程都不同:它不缺乏产能,也不缺乏标杆模型,它缺的是足够大的外部需求。据公开报道的行业调研,昆仑芯自用需求 2026 年无明显提升,P800 和 M100 需求趋于饱和,更多是借 AI 软件影响力做生态推广;对外主要靠推理业务与百度软件绑定,面向政府、教育、政务等传统政企行业,侧重点在生态渗透而非自身业务放量。

这解释了百度为何要开放天池超节点的六大核心模块技术规范——当自家消纳能力见顶,向外输出系统规范与工具链就成了打开市场的方式。而安全可靠测评中 M100 仅获 Level I,也说明政企市场的主流通道目前更偏向评级更高的昇腾。

昆仑芯的战略价值因此不在短期营收,而在于它把国产自研芯片的"第三条路"走通了:不与华为拼超节点规模,也不与寒武纪拼产能,而是绑定云平台做算力输出。如果 M100 在推理侧把性价比做实,并借天池规范形成生态飞轮,它将在国产算力市场占据一个与华为错位的位置——用推理性价比与云服务捆绑,而不是用训练规模与系统架构正面对抗。M300 在 2027 年的表现,才是这条路线的最终答卷。

互联网巨头自研芯片盘点:百度昆仑芯 R200 与阿里平头哥真武 V900

· 7 min read
Industry Research Team

当英伟达的高端芯片被出口管制挡在门外,中国的互联网巨头们被迫回答同一个问题:算力从哪来?百度和阿里给出的答案最彻底——自己造。一家走自研 XPU 架构的渐进路线,一家以 RISC-V 基因押注全栈闭环。2026 年秋,两家的代表作品分别是昆仑芯 R200 和平头哥真武 V900。

一、巨头自研的三种路线​

把国内互联网巨头的芯片战略摊开,大致可分为三种类型:

路线代表特征
XPU 架构派百度昆仑芯自研指令集架构,从推理切入逐步上探训练
RISC-V + 全栈派阿里平头哥自研 CPU(倚天)+ AI 芯片(真武)+ 互联总线(ICN)全栈闭环
租赁过渡派腾讯自研(紫霄)同时大规模租用海外算力过渡

海外巨头的对照同样值得一看:Meta 与博通合作自研 MTIA 推理芯片,AWS Annapurna 团队与 NVIDIA 合作开发 NVHBM 定制芯片——"自研 + 深度定制"是大厂绕开通用 GPU 溢价的共同选择。而腾讯则提供了一个反例参照:通过租用 Oracle 旗下 10 万颗芯片获得算力,以租赁模式绕开采购限制。三条路线没有绝对优劣,但百度与阿里的坚持,正在长出最完整的技术资产。

二、百度昆仑芯:从 R200 到 P800 的 XPU 演进​

昆仑芯的底层竞争力在于自研 XPU 架构——从 2018 年的昆仑芯 1 代(14nm)到 2021 年的 2 代(7nm Kunlun Core II),再到今天的 XPU-R 与 XPU-P,指令集始终自主。本站收录的两代代表产品:

昆仑芯 R200(2025 年,XPU-R 架构,推理主力):

项目参数
制程7nm
FP3232 TFLOPS
FP16128 TFLOPS
INT8256 TOPS
显存16GB / 32GB GDDR6,512 GB/s
TDP150 W(被动散热)
视频108 路 1080P 解码 / 27 路编码
接口PCIe Gen4 x16

150W 的低功耗加多精度配置,让 R200 主打数据中心大规模推理与视频分析场景——这是百度搜索与信息流业务的算力基本盘。

昆仑芯 P800(2024 年,XPU-P 架构,训推一体):FP16 345 TFLOPS(超越 H20 的 148 TFLOPS)、INT8 820 TOPS、96GB HBM3、2.4 TB/s 带宽、400W、OAM 形态,支持 DeepSeek-V3/R1 671B 满血版单机 8 卡运行,配套天池 256/512 超节点,已交付万卡级集群并实现全自研三万卡集群。昆仑芯科技已于 2026 年 5 月启动科创板 IPO 辅导——从百度内部部门到独立上市,XPU 路线完成了商业验证。

三、阿里平头哥真武 V900:216GB 显存与 50 万卡集群​

2026 年 9 月 22 日云栖大会,平头哥发布新一代训推一体 AI 芯片真武 V900,官方称之为"目前算力性能最强的中国自研 AI 芯片",量产上云时间较原路线图提前至 2027 年第一季度。

项目参数
显存216 GB(超过 B200 的 192GB 与 H200 的 141GB)
片间互联1200 GB/s(自研 ICN 链路,较 M890 提升 50%)
精度原生 FP8 / FP4
性能口径真武 M890 的 3 倍
集群磐久 AL128 超节点,ICN Switch 扩展至 50 万卡
量产2027 年 Q1 上云
软件T-Head SAIL 全栈

与 M890 一致,平头哥未公布绝对 FLOPS、制程与 TDP——业界推测由中芯国际制造,官方未证实。但结构性的信息已经足够:216GB 显存直指大模型时代的"内存墙",1200 GB/s 片间互联对标 NVLink 量级拆解"通信墙"。真武系列的代际节奏同样清晰:810E(96GB/700 GB/s)→ M890(144GB/800 GB/s,GP9A 超节点实例已于 8 月上线,国内首个跑通超 2 万亿参数大模型的超节点形态算力)→ V900 → J900(2027 年 Q3,架构突破性创新)。截至 2026 年 9 月,真武系列已服务超 650 家企业客户。

四、ICN 总线与倚天 CPU:全栈闭环的最后一块拼图​

真武 V900 最大的想象空间不在单芯片,而在 ICN 互联总线构建的全栈闭环:ICN Switch 让 Scale-Up 域内带宽完全对称、原生内存语义与统一编址;磐久 AL128 超节点把真武 V900、ICN Switch、磐脉智能网卡、镇岳 SSD 主控全部收进一套算-存-网协同体系,单一集群可扩展至 50 万卡——这个目标直指 NVIDIA Rubin Ultra NVL576 的规模层级。

同期公布的倚天 CPU 路线图补上了 CPU 侧的拼图:2027 年推出倚天 720/730,其中倚天 730 首次采用全自研微架构,SPECint2017 单核性能(每 GHz)达到倚天 710 的 1.4 倍;倚天 750 支持自研 ICN 总线,实现 CPU 与真武 AI 芯片直连。至此,"倚天 CPU + 真武 AI 芯片 + ICN 网络"的全栈闭环成型——阿里成为国内唯一在 CPU、AI 芯片、互联协议三层都实现自研并互操作的云厂商。

五、对照与启示:自研是巨头的长期主义​

把百度与阿里放回全球坐标系:Meta×博通 MTIA、AWS×NVIDIA NVHBM 说明自研 + 定制是全球巨头的共同选择;腾讯租用 Oracle 10 万颗芯片则展示了"买不到就租"的过渡形态。但中国的特殊性在于出口管制的硬约束——通用 GPU 的获取不确定性,让自研从"降本选项"变成了"生存选项"。百度用 XPU 架构证明渐进路线的可持续,阿里用 RISC-V 基因 + ICN 总线证明全栈闭环的可能性。

小结​

昆仑芯 R200 与真武 V900 分别代表了互联网巨头自研芯片的两个时态:R200 是"现在时"——150W 低功耗推理卡稳定承载着百度的核心业务;V900 是"将来时"——216GB 显存、50 万卡集群与 2027 年 Q1 量产的承诺,瞄准的是数万亿至十万亿参数模型的算力底座。一种路线靠架构自主渐进上探,一种路线靠全栈闭环规模突围,两者共同指向同一个结论:中国互联网巨头的算力命门,正在从采购谈判桌转移回自己的设计图纸。2027 年,当 V900 与倚天 730 如期上云、昆仑芯 R300 落地,这场自研竞赛的下半场才真正开始。

Kunlun P800 Deep Dive: Performance Data, Architectural Innovation, and SuperNode Deployment

· 10 min read
Industry Research Team

Kunlun P800 is Baidu's third-generation AI accelerator from Kunlunxin Technology, based on the in-house XPU-P architecture, with 345 TFLOPS peak FP16 compute (surpassing NVIDIA H20's 148 TFLOPS). Launched in March 2024, it has become an important force among domestic AI training/inference accelerators.

This article comprehensively analyzes this domestic AI chip's breakthroughs across five dimensions: performance data, architectural innovation, SuperNode deployment, large-model adaptation, and market positioning.


1. Core Performance Data​

1.1 Compute performance​

PrecisionComputeReference
FP16345 TFLOPS2.3× NVIDIA H20 (148 TFLOPS)
FP32Not disclosedEstimated ~170 TFLOPS
INT88-bit inference supportedSpecific TOPS not disclosed
Low-power mode128 TFLOPS @ 120WEnergy-efficiency-optimized scenarios
MoE optimizationNative MoE support4.3× sparse-model inference efficiency

Performance characteristics:

  • 345 TFLOPS at FP16, a new domestic AI chip compute benchmark
  • 2.3× compute over NVIDIA H20 (H20 only 148 TFLOPS)
  • Native MoE support, 4.3× sparse-model inference efficiency (with specific optimization)

1.2 Memory and bandwidth​

ItemParameter
HBM typeHBM3e (3D-stacked memory)
Memory capacity128 GB
Memory bandwidth1.5 TB/s
ECC protectionEnd-to-end ECC supported

Memory advantages:

  • 128GB capacity supports full-pipeline training of hundred-billion-parameter models
  • 1.5 TB/s is a high-end configuration among HBM3e solutions
  • 3D stacking alleviates large-model training memory bottlenecks

1.3 Power and energy efficiency​

ItemParameter
TDP400 W
Low-power mode128 TFLOPS @ 120W
Energy efficiency (FP16)~0.86 TFLOPS/W
vs. H100~57% of H100 power (400W vs 700W)

Energy efficiency characteristics:

  • At equal compute, significantly lower power than NVIDIA H100
  • Dynamic power adjustment, auto-switching performance modes by load
  • Suited to large-scale cluster deployment, reducing data center PUE pressure

1.4 Process and architecture​

ItemParameter
Process7nm
TransistorsOver 50 billion
ArchitectureIn-house XPU-P
Form factorOAM module
VirtualizationHardware vXPU, single card split into 32 virtual instances

Architectural innovation:

  • Heterogeneous compute architecture, decoupling matrix-multiply units from tensor cores
  • Parallel compute and data movement, theoretical compute 2.3× previous generation
  • Hardware virtualization, single physical card divided into multiple logical cards, raising utilization

2. Three Architectural Innovations​

2.1 Heterogeneous compute architecture optimization​

Technology innovations:

  • Matrix-multiply / tensor-core decoupling: parallelizes compute and data movement
  • Dynamic task scheduling: auto-allocates compute by load
  • Sparse compute optimization: native MoE support, 4.3× sparse-model inference efficiency

Performance gains:

  • Theoretical compute 2.3× previous generation (Kunlun 2nd gen)
  • 1.8× training throughput at equal power

2.2 3D-stacked memory technology​

Technology innovations:

  • HBM3e memory with 3D stacking
  • Single-card 128GB capacity, 1.5 TB/s bandwidth
  • End-to-end ECC for data reliability

Performance gains:

  • Alleviates large-model training memory bottleneck
  • Supports full-pipeline training of hundred-billion-parameter models (no model-parallel splitting)
  • 5× bandwidth vs GDDR6

2.3 Adaptive interconnect protocol​

Technology innovations:

  • Dynamic die-to-die topology adjustment
  • Built-in NPU for zero-copy data transfer, reducing CPU intervention
  • ML-based congestion control, 30% lower packet loss than traditional ECN

Performance gains:

  • In 256-node clusters, 40% lower communication latency
  • Inter-chip bandwidth 1.2 TB/s (Tianchi 256-node)
  • Smooth scaling to ten-thousand-card clusters

3. Tianchi SuperNode Deployment​

3.1 Tianchi 256-node​

System specs:

ItemConfiguration
P800 chips per node8
Inter-chip bandwidth1.2 TB/s (40% over previous gen)
Max model parameters500 billion
Typical power12 kW
InterconnectHardware RDMA acceleration + dynamic traffic scheduling

Core technology breakthroughs:

  1. Interconnect bandwidth engineering:

    • Built-in NPU for zero-copy data transfer, reducing CPU intervention
    • Dynamic traffic scheduling: auto-adjusts routes by real-time link quality
    • Predictive congestion control: ML-based congestion algorithm
  2. Virtualization resource utilization:

SplitActual perfTheoreticalUtilization
1 card100%100%100%
2 cards185%200%92.5%
4 cards340%400%85%

3.2 Tianchi 512-node​

System specs:

ItemConfiguration
P800 chips per node16
Inter-chip bandwidth2.4 TB/s
Max model parameters1.2 trillion
Typical power24 kW
Recovery speedTraining resumes within 5 min of node failure

Core technology breakthroughs:

  1. Ultra-large-scale training support:

    • Mixed-precision optimization: adds NF4 4-bit quantization on FP16/BF16, 75% less memory
    • Gradient checkpoint acceleration: reconstructs compute graph, activation storage O(n)→O(√n), 1.8× training speed
    • Failure recovery: distributed snapshot, 10× faster than traditional checkpoint
  2. Communication efficiency optimization:

    • 3D parallelism (data + model + pipeline), compute/communication ratio 12:1
    • In 1.75-trillion-parameter MoE training, communication overhead below 15%

3.3 Tianchi series performance comparison​

MetricTianchi 256Tianchi 512Improvement
Max model parameters500 billion1.2 trillion2.4×
Inter-chip bandwidth1.2 TB/s2.4 TB/s2×
Typical power12 kW24 kW2×
Recovery time<5 min<5 minFlat
Latency reduction40%50%10 pts

4. Large-Model Adaptation​

4.1 DeepSeek series adaptation​

Certification:

  • February 2025: passed DeepSeek-V3/R1 671B adaptation certification
  • Supports single-machine 8-card full DeepSeek-V3 671B
  • Supports DeepSeek MoE full-parameter training with just 32 machines

Performance data (DeepSeek-V3 671B):

MetricP800NVIDIA H100Ratio
Inference speed (tokens/s)12,50014,20088%
Training throughput (samples/s)8.510.283%
First-token latency (ms)9585112%
Memory usage (GB)11872164%

Conclusion:

  • P800 reaches 88% of H100 inference speed, gap significantly narrowed
  • 83% of H100 training throughput
  • 128GB large memory advantage clear, supports larger batch sizes

4.2 Other large-model adaptation​

ModelDeploymentNotes
ERNIE seriesBaidu Cloud nativeBaidu Smart Cloud main deployment
LLaMA seriesSupportedIncludes MoE-distilled versions
Qwen seriesSupportedAlibaba Cloud model adaptation
ChatGLM seriesSupportedZhipu AI model adaptation
Baichuan seriesSupportedBaichuan Intelligent model adaptation

CUDA compatibility:

  • Models runnable on CUDA migrate to P800 at low cost
  • Supports open-source inference frameworks such as vLLM
  • ~14% of CUDA low-level communication code needs rewriting (sparse-model inference needs specific optimization)

4.3 Ten-thousand-card cluster validation​

Cluster scale:

  • Fully in-house 30,000-card cluster deployed
  • Smooth scaling to ten-thousand-card clusters
  • Linear scaling efficiency 85%+ (thousand-card scale)

Stability data:

  • 30 days continuous training with no failures
  • Training resumes within 5 min of node failure
  • Cluster availability 99.9%

5. Performance Comparison Analysis​

5.1 vs. NVIDIA H20​

ItemKunlun P800NVIDIA H20Notes
FP16 compute345 TFLOPS148 TFLOPSP800 leads 2.3×
HBM capacity128 GB64 GBP800 +100%
HBM bandwidth1.5 TB/s4.0 TB/sH20 clear bandwidth lead
TDP400 W400 WFlat
Process7nm4nm (TSMC)H20 more advanced
Software ecosystemXPU-P (CUDA-compatible)CUDAH20 more mature
SupplyChina autonomousExport-controlledP800 no supply-chain risk

Conclusion:

  • In FP16 compute, P800 leads H20 2.3×
  • In memory capacity, P800 leads 100%
  • In HBM bandwidth, H20 leads 2.67×
  • In supply chain security, P800 wins outright

5.2 vs. NVIDIA H100​

ItemKunlun P800NVIDIA H100Notes
FP16 compute345 TFLOPS~1,300 TFLOPSH100 leads 3.77×
HBM capacity128 GB80 GBP800 +60%
HBM bandwidth1.5 TB/s3.35 TB/sH100 leads 2.23×
TDP400 W700 WP800 only 57% of H100 power
Process7nm4nm (TSMC)H100 more advanced
DeepSeek inference speed12,500 tokens/s14,200 tokens/sP800 reaches 88% of H100

Conclusion:

  • In raw compute, H100 leads P800 3.77×
  • In energy efficiency, P800 clearly outperforms H100 (0.86 vs 1.86 TFLOPS/W)
  • In actual inference performance, P800 reaches 88% of H100, gap significantly narrowed
  • In cost, P800 is ~50% of H100

5.3 vs. Ascend 910C​

ItemKunlun P800Ascend 910CNotes
FP16 compute345 TFLOPS800 TFLOPS910C leads 2.32×
HBM capacity128 GB128 GBFlat
HBM bandwidth1.5 TB/s784 GB/sP800 leads 91%
TDP400 W310 W910C lower power
Process7nm7nm (SMIC N+2)Same
Software ecosystemXPU-P (CUDA-compatible)CANN (CUDA-compatible)Each with strengths

Conclusion:

  • In FP16 compute, 910C leads P800 2.32×
  • In HBM bandwidth, P800 leads 910C 91%
  • In software ecosystem, both CUDA-compatible, similar migration cost
  • In scenarios, P800 suits inference, 910C suits training

6. Market Positioning and Competitive Advantages​

6.1 Target markets​

Core markets:

  1. Baidu Smart Cloud: core compute base of the Baige platform
  2. China Telecom/Mobile/Unicom: won AI inference server procurement bids
  3. Large-model startups: cost-sensitive, high compute demand
  4. Intelligent compute centers: ten-thousand-card clusters validated

Edge markets:

  1. Autonomous driving: end-to-end large-model training
  2. Smart finance: risk control, robo-advisory
  3. Smart healthcare: medical imaging, drug discovery

6.2 Competitive advantages​

AdvantageDescription
Compute leadershipFP16 345 TFLOPS, 2.3× over H20
Large memory128GB HBM3e, full-pipeline training of hundred-billion-parameter models
High energy efficiency400W TDP delivers 345 TFLOPS, better than H100
System scalingTianchi 256/512 SuperNodes, ten-thousand-card clusters
Software ecosystemXPU-P CUDA-compatible, low migration cost
Cost advantage~50% of H100, clear cost-performance edge
Supply chain securityChina autonomous, no export-control risk

6.3 Weaknesses and improvement directions​

WeaknessImprovement direction
Single-chip computeNext-gen M300 to adopt 5nm, target doubling
HBM bandwidthM300 to adopt HBM4, bandwidth to 3.2 TB/s
Software ecosystemContinued XPU-P + PaddlePaddle investment
ProcessDeep cooperation with SMIC to ramp N+2 (7nm-class)

7. 2026 Shipment Plan and Market Forecast​

7.1 Shipment plan​

PeriodShipmentsCumulativeKey customers
2024 Q1-Q450k50kBaidu Smart Cloud
2025 Q1-Q4150k200kChina Mobile, China Telecom
2026 Q1-Q2100k300kChina Unicom, iFlytek
2026 Q3-Q4100k400kGovernment projects, large-model startups
2027500k900kGlobal market (Southeast Asia, Middle East, Latin America)

Capacity bottleneck:

  • Constrained by wafer fab capacity, supply falls short of demand
  • 2026 plan of 200k chips, actual capacity ~150k
  • Kunlunxin deepening cooperation with SMIC and Hua Hong to raise capacity

7.2 Market forecast​

China AI chip market (2026):

  • Total: ~¥50B
  • Domestic share: ~35% (¥17.5B)
  • Kunlun P800 share: ~20% (¥3.5B, ~200k chips)

Global AI chip market (2026):

  • Total: ~$200B
  • Kunlun share: ~1% ($2B)
  • Growth drivers: China-market localization + Belt and Road exports

8. Summary and Outlook​

8.1 Core conclusions​

  1. Kunlun P800 is a major domestic AI chip breakthrough, leading comprehensively in FP16 compute, memory capacity, and energy efficiency
  2. Tianchi 256/512 SuperNodes prove domestic chips can replace imported ones
  3. DeepSeek-V3 671B adaptation success validates P800 maturity in large-model training/inference
  4. 200k chips shipped in 2026, projected 20% of China's AI chip market

8.2 Future outlook​

Short term (2026-2027):

  • P800 continues ramping, shipments exceed 500k
  • Tianchi 512-node deployments over 100 units
  • Software ecosystem (XPU-P + PaddlePaddle) maturity approaches 60% of CUDA

Medium term (2028-2029):

  • Next-gen M300 mass production, 5nm process, target 700 TFLOPS FP16
  • M100 (inference-specific) becomes inference-market mainstay, share over 15%
  • Supports trillion-parameter model full-pipeline training

Long term (2030+):

  • Kunlun series becomes TOP 5 of the global AI chip market
  • Domestic AI chips exceed 15% of the global market
  • Transition from "following" to "running alongside"

References​

  1. Kunlun P800 parameters — CSDN Library
  2. Kunlun P800: technical breakthroughs and application prospects of a new-generation AI accelerator — YunTECH
  3. Kunlun P800 latest specs: P800 single-precision compute reaches 345 TFLOPS — Xueqiu
  4. Exclusive: Kunlun — domestic AI card full DeepSeek training/inference adaptation — Kunlunxin official
  5. Kunlun P800 detailed specs — MirrorFrog: https://www.mirrorfrog.com/en/docs/cards/others/kunlun-p800

Last updated: June 10, 2026