HBM3
E1033644
HBM3 is a high-bandwidth memory standard used in advanced GPUs and accelerators to provide extremely fast, power-efficient access to large amounts of data.
All labels observed (1)
| Label | Occurrences |
|---|---|
| HBM3 canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T13320129 — 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: HBM3 Context triple: [AMD Instinct, supports, HBM3]
-
A.
HM-B
HM-B is the stock ticker symbol for H&M’s publicly traded shares on the Nasdaq Stockholm exchange.
-
B.
BHB
BHB is the stock exchange of the Kingdom of Bahrain, providing a regulated marketplace for trading securities and other financial instruments.
-
C.
HM7B
The HM7B is a European cryogenic rocket engine that powers the upper stages of Ariane launch vehicles, providing precise orbital insertion using liquid hydrogen and liquid oxygen propellants.
-
D.
BMH
BMH is the National Rail station code for Bournemouth railway station in Dorset, England.
-
E.
H-3
H-3 is a major Interstate highway in Hawaii that connects the Honolulu area on Oʻahu with the Marine Corps Base Hawaii at Kāneʻohe Bay through a series of tunnels and viaducts across the Koʻolau Range.
- 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: HBM3 Target entity description: HBM3 is a high-bandwidth memory standard used in advanced GPUs and accelerators to provide extremely fast, power-efficient access to large amounts of data.
-
A.
HM-B
HM-B is the stock ticker symbol for H&M’s publicly traded shares on the Nasdaq Stockholm exchange.
-
B.
BHB
BHB is the stock exchange of the Kingdom of Bahrain, providing a regulated marketplace for trading securities and other financial instruments.
-
C.
HM7B
The HM7B is a European cryogenic rocket engine that powers the upper stages of Ariane launch vehicles, providing precise orbital insertion using liquid hydrogen and liquid oxygen propellants.
-
D.
BMH
BMH is the National Rail station code for Bournemouth railway station in Dorset, England.
-
E.
H-3
H-3 is a major Interstate highway in Hawaii that connects the Honolulu area on Oʻahu with the Marine Corps Base Hawaii at Kāneʻohe Bay through a series of tunnels and viaducts across the Koʻolau Range.
- F. None of above. chosen
Statements (46)
| Predicate | Object |
|---|---|
| instanceOf |
DRAM memory standard
ⓘ
high-bandwidth memory standard ⓘ |
| category |
computer memory standard
ⓘ
graphics memory ⓘ server memory technology ⓘ |
| comparedTo | HBM2E NERFINISHED ⓘ |
| connectedTo |
GPU die
ⓘ
accelerator die ⓘ |
| connectedVia | silicon interposer ⓘ |
| designedFor |
high-bandwidth memory access
ⓘ
large-scale data processing ⓘ power-efficient memory access ⓘ |
| enables |
faster model training
ⓘ
higher GPU utilization ⓘ larger model sizes ⓘ |
| feature |
3D die stacking
ⓘ
high capacity per stack ⓘ low power per bit transferred ⓘ short signal paths ⓘ through-silicon vias ⓘ |
| follows | HBM2E NERFINISHED ⓘ |
| hasAdvantageOver |
HBM2E in bandwidth
ⓘ
HBM2E in energy efficiency ⓘ |
| integrationMethod |
2.5D packaging
ⓘ
advanced packaging technologies ⓘ |
| interfaceType | wide I/O ⓘ |
| memoryType |
3D DRAM
ⓘ
stacked DRAM ⓘ |
| optimizedFor |
AI inference workloads
ⓘ
AI training workloads ⓘ high-performance computing workloads ⓘ |
| partOf | HBM memory family NERFINISHED ⓘ |
| standardizedBy | JEDEC NERFINISHED ⓘ |
| supports | very high memory bandwidth ⓘ |
| targetMarket |
AI supercomputers
ⓘ
data centers ⓘ enterprise GPUs ⓘ |
| typicalFormFactor | multi-die memory stack ⓘ |
| usedFor |
GPU-based cloud services
ⓘ
data analytics accelerators ⓘ large language model training ⓘ scientific simulations ⓘ |
| usedIn |
AI accelerators
NERFINISHED
ⓘ
GPUs ⓘ HPC accelerators ⓘ data center processors ⓘ |
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: HBM3 Description of subject: HBM3 is a high-bandwidth memory standard used in advanced GPUs and accelerators to provide extremely fast, power-efficient access to large amounts of data.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.