POWER10
E771694
POWER10 is IBM’s latest generation of high-performance, energy-efficient server processor architecture designed for enterprise workloads, AI acceleration, and cloud-native computing.
All labels observed (1)
| Label | Occurrences |
|---|---|
| POWER10 canonical | 6 |
How this entity was disambiguated
This entity first appeared as the object of triple T8993487 — 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: POWER10 Context triple: [PowerVM, runsOn, POWER10]
-
A.
Arria 10
Arria 10 is an Intel (formerly Altera) mid-range FPGA family known for its high performance, power efficiency, and suitability for signal processing, networking, and embedded computing applications.
-
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.
Zen 3
Zen 3 is AMD’s high-performance CPU microarchitecture that significantly improved instructions-per-clock, gaming performance, and power efficiency over its predecessors in Ryzen and EPYC processors.
-
D.
Power ISA
Power ISA is IBM's modern 64-bit RISC instruction set architecture used in high-performance servers, embedded systems, and supercomputers, evolving from the earlier PowerPC architecture.
-
E.
Fugaku supercomputer
The Fugaku supercomputer is a Japanese exascale-class system that was ranked the world’s fastest supercomputer and is designed for large-scale simulations and advanced scientific research.
- 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: POWER10 Target entity description: POWER10 is IBM’s latest generation of high-performance, energy-efficient server processor architecture designed for enterprise workloads, AI acceleration, and cloud-native computing.
-
A.
Arria 10
Arria 10 is an Intel (formerly Altera) mid-range FPGA family known for its high performance, power efficiency, and suitability for signal processing, networking, and embedded computing applications.
-
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.
Zen 3
Zen 3 is AMD’s high-performance CPU microarchitecture that significantly improved instructions-per-clock, gaming performance, and power efficiency over its predecessors in Ryzen and EPYC processors.
-
D.
Power ISA
Power ISA is IBM's modern 64-bit RISC instruction set architecture used in high-performance servers, embedded systems, and supercomputers, evolving from the earlier PowerPC architecture.
-
E.
Fugaku supercomputer
The Fugaku supercomputer is a Japanese exascale-class system that was ranked the world’s fastest supercomputer and is designed for large-scale simulations and advanced scientific research.
- F. None of above. chosen
Statements (50)
| Predicate | Object |
|---|---|
| instanceOf |
IBM POWER architecture family member
ⓘ
microprocessor architecture ⓘ server processor ⓘ |
| announcedBy | IBM ⓘ |
| announcementYear | 2020 ⓘ |
| architectureFamily |
IBM POWER
ⓘ
linked to:
IBM POWER processors
|
| coreCountPerChip | up to 15 cores ⓘ |
| coreCountPerDie | up to 15 cores ⓘ |
| designer | IBM ⓘ |
| feature |
AI inference acceleration
ⓘ
OpenCAPI support ⓘ PCIe Gen4 support ⓘ enhanced cryptographic acceleration ⓘ hardware-assisted virtualization ⓘ high-bandwidth memory interfaces ⓘ improved reliability, availability, and serviceability ⓘ matrix math accelerator ⓘ memory encryption ⓘ |
| firstSystemsAvailabilityYear | 2021 ⓘ |
| firstSystemsShippedBy | IBM Power Systems ⓘ |
| intendedUse |
AI acceleration
ⓘ
cloud-native computing ⓘ enterprise workloads ⓘ |
| isa |
POWER ISA
ⓘ
linked to:
POWER instruction set architecture
|
| manufacturer |
Samsung Electronics
ⓘ
linked to:
Samsung
|
| optimizationFor |
AI inference workloads
ⓘ
cloud-native microservices ⓘ enterprise databases ⓘ transaction processing ⓘ |
| predecessor | POWER9 ⓘ |
| processNode | 7 nm ⓘ |
| processTechnologyProvider | Samsung 7 nm EUV ⓘ |
| socketConfiguration |
dual-chip module
ⓘ
single-chip module ⓘ |
| supports |
IBM AIX
ⓘ
linked to:
AIX
IBM i ⓘ Linux ⓘ SMT4 ⓘ SMT8 ⓘ containerized workloads ⓘ hybrid cloud deployments ⓘ scale-out servers ⓘ scale-up servers ⓘ simultaneous multithreading ⓘ virtualization ⓘ |
| targetMarket |
AI and analytics platforms
ⓘ
cloud service providers ⓘ enterprise servers ⓘ mission-critical workloads ⓘ |
| wordSize | 64-bit ⓘ |
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: POWER10 Description of subject: POWER10 is IBM’s latest generation of high-performance, energy-efficient server processor architecture designed for enterprise workloads, AI acceleration, and cloud-native computing.
Referenced by (6)
Full triples — surface form annotated when it differs from this entity's canonical label.