Reported by Tom's Hardware on . Summarized and analyzed by XAIPART Editorial.
What happened
Rapidus has reportedly missed a required demonstration of functional SRAM cells on its 2nm-class node, leaving its plan for commercial production in the second half of fiscal 2027 exposed to further delay.S1 The report also describes contamination problems involving dust and particle control at the company's IIM-1 cleanroom.S1
The company produced 2nm-class Gate-All-Around transistor test structures at IIM-1 in Hokkaido in and reported that the prototypes had the expected electrical characteristics.S1 Working transistors do not establish that Rapidus can build interconnected SRAM cells, larger arrays, peripheral circuits, or production-yielding macros.S1
According to the report, Rapidus has not achieved the functional SRAM milestone and therefore has a reported SRAM yield of 0%.S1 The available account does not distinguish between isolated cells, larger arrays, electrical performance, and yield.S1 Rapidus says it remains committed to mass production in the second half of fiscal 2027, which ends in , but it has not confirmed a mass-production delay.S1
Before commercial production, Rapidus must demonstrate functional SRAM, integrate it into larger arrays, obtain acceptable yields, qualify the process, and begin risk production roughly one year before high-volume manufacturing.S1 GAA fabrication adds nanosheet release, inner-spacer formation, gate-stack integration, EUV variability, contact resistance, and interconnect challenges that can become more restrictive in SRAM structures.S1
| Metric | Reported value | Source |
|---|---|---|
| Rapidus SRAM yield | 0% | S1 |
| Transistors in a conventional 6T SRAM bitcell | 6 | S1 |
| Example SRAM macro size | 256 KB | S1 |
| TSMC N2 SRAM test-chip size | 256 Mb | S1 |
| TSMC N2 SRAM yield, May 2025 | Over 90% | S1 |
Background timeline
- - TSMC reported more than 80% of its target device performance and over 50% yield on a 256 Mb N2 SRAM test chip.S1
- - TSMC reported more than 90% target performance and over 80% SRAM yield for N2.S1
- - TSMC reported N2 transistor performance near 100% and average 256 Mb SRAM yield above 90%.S1
- - Rapidus produced 2nm-class GAA test structures at IIM-1 and reported expected transistor electrical characteristics.S1
- - A nanosheet study reported that small etching changes can affect spacer geometry and nanosheet integrity.S1
- - Tom's Hardware reported that Rapidus had not demonstrated functional SRAM cells and had a reported SRAM yield of 0%.S1
Supply-chain ripple
- Rapidus reportedly produced no functional SRAM cells, while cleanroom contamination remained an issue.S1 S1
- Weak cell demonstrations prevent buyers from validating process yield, design rules, and reliability.XAIPART analysis
- That uncertainty compresses the window for tape-out support, risk production, and process qualification.XAIPART analysis
- Customers without another qualified foundry may face later design-in, qualification, or volume-delivery dates.XAIPART analysis
XAIPART take
Technical impact
A functional transistor test does not establish manufacturability because SRAM requires six-transistor cells, local interconnects, peripheral circuitry, and repetitive arrays.XAIPART analysis
The combination of GAA nanosheet variability, EUV defects, spacer geometry, and particle control could narrow Rapidus's process window before yield data become available.XAIPART analysis
Market impact
The reported 0% SRAM yield means buyers currently lack a process indicator for production readiness at IIM-1.XAIPART analysis
If qualification slips beyond the planned second-half fiscal 2027 production window, customers may need to extend tape-out schedules or evaluate an already qualified foundry before placing a binding volume order.XAIPART analysis
Action
Design teams should request separate evidence for functional cells, array yield, macro yield, and reliability rather than treating the working-transistor demonstration as process qualification.XAIPART analysis
If Rapidus has not disclosed a functional SRAM yield above 0% by Q2 2027, buyers should secure a second foundry or keep volume allocation flexible before the next BOM review.XAIPART analysis
XAIPART Forecast
XAIPART expects Rapidus to publish a functional SRAM yield above 1% within 12 months; if no such result is disclosed, this forecast is wrong.XAIPART analysis
Facts are as reported by the cited sources. The design-in, sourcing and forward-looking statements above are XAIPART's analysis, not the sources' claims. The SRAM status is single-source reporting within S1, remains unverified by Rapidus, and the source did not disclose the specific failing cell, array, macro, or yield stage.
Corrections: none at publication. This brief will be updated with a timestamp if the source corrects its report.
대체품 및 수명 주기
| 부품 | 관계 | 수명 주기 | 근거 |
|---|---|---|---|
| — | 등록된 대체품 없음 데이터 필요 | — | 요구 사항 match_type 어떤 전임자 라벨이 표시되기 전에 |
"전임자" 및 "대체품" 라벨은 기록된 일치 유형, 수명 주기 상태 또는 출처 텍스트에서만 부여됩니다. 일치가 기록되지 않은 경우 라벨이 표시되지 않습니다. 당사 자체 등록 상품은 시장 기준이 아닙니다.
주시할 사항
| 주장 | 임계값 | 작성: | 상태 |
|---|---|---|---|
| XAIPART expects Rapidus to publish a functional SRAM yield above 1% within 12 months | no such result is disclosed | within 12 months | Pending |
잘못된 예측도 계속 표시하고 표시를 남깁니다. 삭제하지 않습니다.
영향받는 부품
카탈로그 일치 없음. 이 보도는 현재 XAIPART에 등록된 어떤 부품과도 매핑되지 않습니다. 일치를 추론하지 않으며 자리 표시자 목록도 표시하지 않습니다.
차원별 비용 압력
| Dimension | FRED series ID | Unit | Lag | As of |
|---|---|---|---|---|
| Input cost | PCOPPUSDM, PALUMUSDM, PNICKUSDM | USD/mt | 52 d | |
| Supply/demand | PCU334413334413, IPG3344S | index(1982=100) / index(2017=100) | 48 d | |
| FX & energy | DEXCHUS, DCOILBRENTEU, DHHNGSP | rate / USD/bbl / USD/MMBtu | 5 d |
No free authoritative interface for: gold · silver · rare earth · polysilicon · lithium carbonate · market share — listed rather than approximated.
이 콘텐츠의 제작 방식
프로세스 증거 — 수집, 출처 온전성, 모델 및 게이트
| Source fetched | Tom's Hardware · www.tomshardware.com · 13,211 chars · fetch status success |
|---|---|
| Source sanity (S1) | ok — passed before any model call (no s1_ block recorded) |
| Model / prompt | MiniMax-M3.1-Flash · prompt Blog Agent - News Summary (v3.0.2-news) · 14,522 tokens · 40.1s · run completed |
| Gate | verdict pass · 6/6 applicable checks passed · spec v2.9 · C10 ratio 0.007982 · C10 rounds 0 |
| Time contract | 9 <time datetime> values in this brief — 0 violations (+08:00 or date-only) |
위의 모든 행은 파이프라인에서 생성되며 수작업으로 작성되지 않습니다.
댓글
첫 번째 댓글을 남겨 보십시오.
🔐 먼저 로그인 댓글을 게시하려면
계정이 없으십니까? 회원가입