TSMC 4N
E803291
TSMC 4N is a custom 5 nm-class semiconductor manufacturing process co-developed by TSMC and NVIDIA, optimized specifically for NVIDIA’s latest GPUs to improve performance, power efficiency, and density over previous nodes.
Observed surface forms (1)
| Surface form | Occurrences |
|---|---|
| TSMC N4 | 2 |
Statements (44)
| Predicate | Object |
|---|---|
| instanceOf |
custom foundry process node
ⓘ
semiconductor manufacturing process ⓘ |
| applicationDomain |
artificial intelligence computing
ⓘ
computer graphics ⓘ high-performance computing ⓘ |
| basedOn | TSMC 5 nm family NERFINISHED ⓘ |
| category | TSMC process node ⓘ |
| coDevelopedWith | NVIDIA NERFINISHED ⓘ |
| commercialUse | mass production for NVIDIA GPUs ⓘ |
| comparedTo |
TSMC N5
NERFINISHED
ⓘ
TSMC N6 NERFINISHED ⓘ TSMC N7 NERFINISHED ⓘ |
| designedFor |
improved performance over previous NVIDIA nodes
ⓘ
improved power efficiency over previous NVIDIA nodes ⓘ improved transistor density over previous NVIDIA nodes ⓘ |
| designGoal |
enable larger GPU die sizes
ⓘ
maximize GPU throughput ⓘ reduce power consumption at given performance ⓘ |
| developedBy | TSMC NERFINISHED ⓘ |
| ecosystem | TSMC Open Innovation Platform NERFINISHED ⓘ |
| feature |
custom design rules for NVIDIA
ⓘ
enhanced clock frequency potential ⓘ enhanced power delivery characteristics ⓘ higher performance-per-watt compared to prior NVIDIA nodes ⓘ improved yield for large-area chips ⓘ process tuning for large GPU dies ⓘ |
| foundry | TSMC NERFINISHED ⓘ |
| nodeType | FinFET process ⓘ |
| optimizedFor |
NVIDIA GPUs
NERFINISHED
ⓘ
high-performance graphics processing ⓘ |
| processFamily | TSMC 5 nm-class nodes NERFINISHED ⓘ |
| processGeneration | 5 nm ⓘ |
| relatedTo |
NVIDIA GeForce RTX 40 series
NERFINISHED
ⓘ
NVIDIA data center platforms ⓘ |
| supports |
advanced packaging with TSMC CoWoS
ⓘ
advanced packaging with TSMC InFO ⓘ |
| targetMarket |
AI accelerators
ⓘ
datacenter GPUs ⓘ high-end gaming GPUs ⓘ |
| technologyNodeClass | 5 nm-class ⓘ |
| usedBy | NVIDIA NERFINISHED ⓘ |
| usedIn |
NVIDIA Ada Lovelace architecture GPUs
NERFINISHED
ⓘ
NVIDIA Hopper architecture GPUs NERFINISHED ⓘ |
| waferSize | 300 mm ⓘ |
Referenced by (3)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
TSMC N4
this entity surface form:
TSMC N4