Fujitsu A64FX
E1039956
The Fujitsu A64FX is a high-performance 64-bit ARM-based server CPU designed for supercomputing, notably powering the Fugaku supercomputer.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Fujitsu A64FX canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T13410491 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fujitsu A64FX Context triple: [Fugaku, processor, Fujitsu A64FX]
-
A.
Itanium
Itanium is a 64-bit server processor architecture developed by Intel (with early collaboration from HP) that was designed for high-end enterprise and technical computing but ultimately saw limited adoption and was discontinued.
-
B.
Habana Gaudi processor
The Habana Gaudi processor is a specialized AI training accelerator designed by Habana Labs (an Intel company) to deliver high-performance, scalable deep learning computation in data centers.
-
C.
Amdahl
Amdahl is the surname of Gene Amdahl, a pioneering computer architect best known for formulating Amdahl's Law and contributing to the design of IBM mainframe systems.
-
D.
POWER9
POWER9 is IBM's ninth-generation 64-bit POWER microprocessor architecture, designed for high-performance computing, enterprise servers, and AI workloads.
-
E.
POWER8
POWER8 is IBM's eighth-generation 64-bit RISC microprocessor architecture designed for high-performance enterprise servers and advanced virtualization workloads.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Fujitsu A64FX Target entity description: The Fujitsu A64FX is a high-performance 64-bit ARM-based server CPU designed for supercomputing, notably powering the Fugaku supercomputer.
-
A.
Itanium
Itanium is a 64-bit server processor architecture developed by Intel (with early collaboration from HP) that was designed for high-end enterprise and technical computing but ultimately saw limited adoption and was discontinued.
-
B.
Habana Gaudi processor
The Habana Gaudi processor is a specialized AI training accelerator designed by Habana Labs (an Intel company) to deliver high-performance, scalable deep learning computation in data centers.
-
C.
Amdahl
Amdahl is the surname of Gene Amdahl, a pioneering computer architect best known for formulating Amdahl's Law and contributing to the design of IBM mainframe systems.
-
D.
POWER9
POWER9 is IBM's ninth-generation 64-bit POWER microprocessor architecture, designed for high-performance computing, enterprise servers, and AI workloads.
-
E.
POWER8
POWER8 is IBM's eighth-generation 64-bit RISC microprocessor architecture designed for high-performance enterprise servers and advanced virtualization workloads.
- F. None of above. chosen
Statements (49)
| Predicate | Object |
|---|---|
| instanceOf |
ARM-based CPU
ⓘ
microprocessor ⓘ server CPU ⓘ |
| additionalCoreCount | 4 assistant cores ⓘ |
| architecture | ARMv8-A NERFINISHED ⓘ |
| architectureExtension |
ARMv8.2-A
NERFINISHED
ⓘ
SVE ⓘ |
| bitWidth | 64-bit ⓘ |
| cacheType |
L1 cache
ⓘ
L2 cache ⓘ L3 cache ⓘ |
| coreCount | 48 ⓘ |
| coreType | ARMv8-A compatible cores ⓘ |
| countryOfOrigin | Japan ⓘ |
| designedFor | supercomputing ⓘ |
| fabricationProcess | TSMC 7 nm NERFINISHED ⓘ |
| instructionSet | ARMv8-A NERFINISHED ⓘ |
| interconnect | Tofu Interconnect D NERFINISHED ⓘ |
| introducedFor | exascale-class computing ⓘ |
| manufacturer | Fujitsu NERFINISHED ⓘ |
| memoryBandwidth | over 1 TB/s ⓘ |
| memoryChannels | 4 ⓘ |
| memoryType | HBM2 ⓘ |
| notableFeature | first general-purpose CPU to implement SVE ⓘ |
| onPackageMemoryCapacity | 32 GB ⓘ |
| powering | Fugaku supercomputer NERFINISHED ⓘ |
| processNode | 7 nm ⓘ |
| segment | high-performance computing ⓘ |
| supports |
ARM Scalable Vector Extension
NERFINISHED
ⓘ
ARMv8-A AArch64 NERFINISHED ⓘ PCIe Gen3 ⓘ RAS features ⓘ SIMD ⓘ bfloat16 ⓘ double precision floating point ⓘ half precision floating point ⓘ hardware prefetching ⓘ single precision floating point ⓘ |
| targetMarket |
HPC
ⓘ
supercomputers ⓘ |
| top500Relevance |
used in system ranked #1 on TOP500 in June 2020
ⓘ
used in system ranked #1 on TOP500 in June 2021 ⓘ used in system ranked #1 on TOP500 in November 2020 ⓘ used in system ranked #1 on TOP500 in November 2021 ⓘ |
| totalCoreCount | 52 ⓘ |
| usedIn |
Fugaku
NERFINISHED
ⓘ
Fujitsu PRIMEHPC FX1000 NERFINISHED ⓘ Fujitsu PRIMEHPC FX700 NERFINISHED ⓘ |
| vectorLength | 512-bit SVE ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Fujitsu A64FX Description of subject: The Fujitsu A64FX is a high-performance 64-bit ARM-based server CPU designed for supercomputing, notably powering the Fugaku supercomputer.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject surface form:
Fugaku