AMD CDNA 2
E1033640
AMD CDNA 2 is a data center–focused GPU architecture from AMD designed to accelerate high-performance computing and AI workloads in its Instinct accelerator lineup.
All labels observed (1)
| Label | Occurrences |
|---|---|
| AMD CDNA 2 canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T13320093 — 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: AMD CDNA 2 Context triple: [AMD Instinct, usesArchitecture, AMD CDNA 2]
-
A.
AMD RDNA
AMD RDNA is a modern GPU architecture from AMD designed to deliver high-performance, power-efficient graphics for gaming and compute workloads across desktops, laptops, and consoles.
-
B.
AMD FidelityFX Super Resolution
AMD FidelityFX Super Resolution is AMD’s open, cross-platform spatial and temporal upscaling technology designed to boost gaming performance and image quality on a wide range of GPUs.
-
C.
Naughty Dog Game Engine
Naughty Dog Game Engine is the proprietary in-house game development engine used by Naughty Dog to power its cinematic, narrative-driven PlayStation titles.
-
D.
Radeon Pro Vega 20
Radeon Pro Vega 20 is a professional-grade mobile graphics processor from AMD’s Vega lineup, designed to deliver high-performance graphics and compute capabilities in thin-and-light laptops.
-
E.
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.
- 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: AMD CDNA 2 Target entity description: AMD CDNA 2 is a data center–focused GPU architecture from AMD designed to accelerate high-performance computing and AI workloads in its Instinct accelerator lineup.
-
A.
AMD RDNA
AMD RDNA is a modern GPU architecture from AMD designed to deliver high-performance, power-efficient graphics for gaming and compute workloads across desktops, laptops, and consoles.
-
B.
AMD FidelityFX Super Resolution
AMD FidelityFX Super Resolution is AMD’s open, cross-platform spatial and temporal upscaling technology designed to boost gaming performance and image quality on a wide range of GPUs.
-
C.
Naughty Dog Game Engine
Naughty Dog Game Engine is the proprietary in-house game development engine used by Naughty Dog to power its cinematic, narrative-driven PlayStation titles.
-
D.
Radeon Pro Vega 20
Radeon Pro Vega 20 is a professional-grade mobile graphics processor from AMD’s Vega lineup, designed to deliver high-performance graphics and compute capabilities in thin-and-light laptops.
-
E.
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.
- F. None of above. chosen
Statements (46)
| Predicate | Object |
|---|---|
| instanceOf |
GPU microarchitecture
ⓘ
data center GPU architecture ⓘ |
| announcedBy | AMD Data Center and Embedded Solutions Group NERFINISHED ⓘ |
| architectureFamily | CDNA NERFINISHED ⓘ |
| architectureGeneration | second generation CDNA ⓘ |
| designedFor | exascale computing systems ⓘ |
| developer |
AMD
NERFINISHED
ⓘ
Advanced Micro Devices NERFINISHED ⓘ |
| focusesOn | compute performance over graphics ⓘ |
| followedBy | AMD CDNA 3 NERFINISHED ⓘ |
| graphicsSupport | no display outputs ⓘ |
| introducedInProductLine | AMD Instinct accelerators NERFINISHED ⓘ |
| marketSegment | data center ⓘ |
| memoryType | HBM2E ⓘ |
| optimizedFor |
AI inference
ⓘ
AI training ⓘ HPC simulations ⓘ double-precision floating-point performance ⓘ |
| predecessor | AMD CDNA NERFINISHED ⓘ |
| subseriesOf | AMD CDNA NERFINISHED ⓘ |
| succeeds | first-generation AMD CDNA architecture ⓘ |
| supports |
BF16 compute
ⓘ
FP16 compute ⓘ FP32 compute ⓘ FP64 compute ⓘ HBM2E memory ⓘ Infinity Fabric Link NERFINISHED ⓘ Infinity Fabric interconnect NERFINISHED ⓘ PCI Express 4.0 ⓘ matrix operations acceleration ⓘ mixed-precision compute ⓘ multi-GPU scaling ⓘ tensor operations ⓘ |
| supportsSoftwareStack |
HIP
GENERATED
ⓘ
OpenCL GENERATED ⓘ OpenMP offload GENERATED ⓘ ROCm GENERATED ⓘ |
| targetApplication |
artificial intelligence workloads
ⓘ
data center acceleration ⓘ high-performance computing ⓘ |
| usedIn |
AMD Instinct MI200 series
NERFINISHED
ⓘ
AMD Instinct MI210 NERFINISHED ⓘ AMD Instinct MI250 NERFINISHED ⓘ AMD Instinct MI250X NERFINISHED ⓘ |
| usedInSystem |
Frontier supercomputer
NERFINISHED
ⓘ
HPE Cray EX supercomputers NERFINISHED ⓘ |
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: AMD CDNA 2 Description of subject: AMD CDNA 2 is a data center–focused GPU architecture from AMD designed to accelerate high-performance computing and AI workloads in its Instinct accelerator lineup.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject surface form:
AMD Instinct