Skip to main content
VLSI Korea

Semiconductor graph

HBM2
Methods ↗

2 entities and 1 documented connections shown.

Connections

2 entities · 1 claims
100%

Drag the map or use pan buttons to move. Tab to a node or connection and press Enter to inspect its evidence. Arrows follow the actual claim direction.

STARTING ENTITYDIRECT CONNECTIONSUses memory technology · SUPPORTEDUses memory technologyHBM2 · memory technologyMEMORY TECHNOLOGYSTARTHBM2NVIDIA A100 Tensor Core GPU · productPRODUCTNVIDIA A100 TensorCore GPU
CompanyChip / productTechnologyPlace / facility
Select a connection for its evidence
Relationships & evidence (1)
Every displayed connection is a scoped claim. Arrows follow subject to object.
SubjectRelationshipObjectStatusEvidence
NVIDIA A100 Tensor Core GPUHBM2SUPPORTEDSource-reported snapshot: 2020-05-14
Why are these connected?

This is the cited 40 GB configuration; later A100 variants use HBM2e.

NVIDIA Ampere Architecture In-Depth

NVIDIA Technical Blog · Tier A · Primary source · supports

NVIDIA specifies 40 GB of HBM2 for the A100 discussed in the architecture article.

Location: lines 82-84 / 40 GB HBM2 and 40 MB L2 cache

Published
2020-05-14
Retrieved
2026-09-08

Store factual paraphrase, metadata and link only. No source document redistribution or inferred license; no source bytes retained.

Full claim history →
Find an evidence path

Find a documented path

From HBM2 · up to two relationship steps.

A path retains its original claims. Shared technology does not establish a supply contract.

2 nodes · 1 claims
Scope

Relationships may describe different dates. A path does not establish simultaneous activity. Bounded source-backed collection. Missing or filtered connections do not establish absence. Supported does not mean independently verified.