작성자 Maksym Misichenko · Yahoo Finance ·
AI 에이전트가 이 뉴스에 대해 생각하는 것
The panelists generally agree that Marvell's (MRVL) high valuation (54x forward P/E) is based on aggressive growth assumptions, particularly in AI optical interconnects. They express concerns about potential execution issues, competition from Broadcom, and the risk of hyperscalers internalizing critical optical IP. The upcoming Q1 FY27 earnings are seen as crucial for providing guidance on optical revenue growth rates and customer concentration risk.
리스크: Margin compression due to competition and potential internalization of critical optical IP by hyperscalers.
기회: Sustained growth in AI optical interconnects and durable customer lock-in through design wins.
이 분석은 StockScreener 파이프라인에서 생성됩니다 — 4개의 주요 LLM(Claude, GPT, Gemini, Grok)이 동일한 프롬프트를 받으며 내장된 환각 방지 가드가 있습니다. 방법론 읽기 →
반도체 회사 마벨 테크놀로지(MRVL)의 주가는 5월 26일 HSBC로부터 등급 상향을 받은 후 장중 6.08% 상승했다. HSBC의 분석가들은 마벨의 등급을 “보유(Hold)”에서 “매수(Buy)”로 올리고 목표 주가를 85달러에서 300달러로 인상(현재 수준에서 44.1% 상승)하며 AI 네트워킹과 관련된 “슈퍼사이클”을 지적했다.
분석가인 프랭크 리는 광 인터커넥트의 수익 성장이 여전히 시장에서 과소평가되고 있으며, 이 기술이 향후 몇 년 동안 컨센서스 전망에 대한 긍정적인 요인이 될 수 있다고 믿고 있다. 또한, 에이전트 AI CPU에 영향을 미치는 메모리 부족은 추가적인 상승 요인으로 이어질 수 있다. 분석가는 마벨이 AI 클러스터가 AI 팩토리로 성숙해짐에 따라 광 인터커넥트의 중요성이 높아짐에 따라 “주요 수혜자”가 될 것으로 예상하고 있다.
현재 시점에서 마벨에 대해 좀 더 자세히 살펴보자.
마벨 테크놀로지는 이더넷 스위치, 광 링크, 맞춤형 AI 가속기, 스토리지 컨트롤러 등 데이터 인프라 칩을 구축하는 반도체 회사이다. 델라웨어주 윌밍턴에 본사를 둔 마벨은 생성형 AI 워크로드에 필요한 막대한 데이터 전송과 가속화된 컴퓨팅을 처리하는 맞춤형 실리콘과 고속 광 연결을 제공하여 AI에서 중요한 역할을 수행한다.
아마존(AMZN), 마이크로소프트(MSFT), 알파벳(GOOG)(GOOGL) 구글을 포함한 주요 하이퍼스케일러는 마벨의 맞춤형 칩과 네트워킹 기술에 의존하여 AI 인프라를 지원하며, 이를 통해 전 세계 AI 확장의 핵심 촉진제 역할을 하고 있다. 이 회사의 시가총액은 1868억 8천만 달러이다.
마벨의 사업이 폭발적인 광 연결 및 이더넷 스위치 수요에 힘입어 AI 데이터 센터 성장에 결정적으로 전환됨에 따라, 지난 52주 동안 212.43% 상승했으며, 연초 이후(YTD) 134.63% 상승했다. 이 주식은 5월 26일 52주 최고치인 217.45달러를 기록했지만, 그 수준에서 7.1% 하락했다.
급격한 상승으로 인해 마벨의 가치가 상승했다. 전방 조정 주당순이익(비GAAP) 비율 54.09배는 업계 평균 24.99배보다 높다.
마벨은 오늘 5월 27일 장 마감 후 2027 회계연도 1분기 실적을 발표할 예정이다. 월스트리트 분석가들은 마벨의 주당순이익(희석 기준)이 전년 동기 대비 29.8% 증가한 0.61달러로 예상하고 있다. 지난 회계연도(2026년 1월 31일 종료)에 회사는 AI에 대한 강력한 수요에 힘입어 전년 동기 대비 42.1% 증가한 81억 9,500만 달러의 순 매출을 보고했다.
4개 주요 AI 모델이 이 기사를 논의합니다
"Marvell's valuation already prices in the supercycle, so the upgrade's impact hinges entirely on whether Q1 results and guidance exceed the high bar set by the 134% YTD rally."
The HSBC upgrade to $300 highlights Marvell's positioning in AI optical interconnects as clusters evolve into factories, with potential underestimation in consensus models. Yet the 54x forward P/E already embeds aggressive growth assumptions after a 212% 52-week run. Earnings due today carry elevated expectations of 29.8% EPS growth, and any shortfall in optical or Ethernet ramp could trigger de-rating. Memory shortages may help or hinder depending on supply chain dynamics, while hyperscaler custom silicon efforts and competition from Broadcom remain unaddressed risks. The article downplays execution and valuation compression potential.
Even at 54x, sustained 40%+ AI revenue growth through 2027 could justify further multiple expansion if Marvell captures disproportionate optical share as factories scale.
"Marvell's optical interconnect thesis is plausible but priced for perfection; the 54x forward P/E demands proof that this supercycle is real, not just a narrative, and today's earnings will be the test."
MRVL's 54x forward P/E versus 25x industry average is not justified by growth alone—it's a valuation bet on optical interconnect upside that remains speculative. Yes, AI clusters-to-factories transition is real, and yes, Marvell has custom silicon moats with hyperscalers. But the article conflates two separate claims: (1) optical interconnect will be important, and (2) Marvell will capture disproportionate value. The memory shortage thesis is also vague—who benefits if memory-constrained agentic CPUs drive more networking spend? Unclear. HSBC's $300 target implies 38% upside from current $217 level; that's not a 44% move from $85. The math doesn't hold. Watch Q1 FY27 earnings today for guidance on optical revenue growth rates and customer concentration risk.
If hyperscalers internalize more optical design or shift to competing suppliers (AMD, Intel custom silicon), Marvell's premium valuation collapses fast—and a 54x multiple leaves zero margin for error on execution.
"Marvell's current valuation of 54x forward earnings assumes a flawless execution trajectory that ignores the cyclical volatility inherent in hyperscaler infrastructure spending."
The HSBC upgrade to a $300 target is a classic case of chasing momentum under the guise of an 'AI supercycle.' While Marvell's (MRVL) optical interconnects are vital for high-bandwidth data center scaling, a 54x forward P/E is a massive premium that leaves zero room for execution errors. The market is pricing in near-perfect growth, but historical semiconductor cycles show that hyperscaler capex can be lumpy and prone to sudden digestion phases. If AI infrastructure shifts from initial build-outs to optimization, Marvell’s custom ASIC margins could compress as competition from Broadcom and internal silicon efforts at Google and Amazon intensify.
If the transition to 'AI factories' creates an insatiable demand for low-latency optical interconnects that exceeds current supply, Marvell could maintain pricing power that justifies a premium valuation well beyond current consensus.
"MRVL’s upside hinges on a durable, multi-year AI networking capex cycle; without it, the current valuation is vulnerable to multiple contraction."
HSBC’s Buy upgrade for MRVL feeds a narrative that AI networking will sustain a multi-year data-center capex cycle, with optical interconnects as a core driver. But the implied upside—a jump to a $300 target and a 54x forward non-GAAP P/E—rests on several fragile bets: a persistent hyperscaler capex boom, durable AI throughput gains, and ongoing margin expansion. None are guaranteed, and MRVL’s growth is heavily concentrated among a handful of customers. The stock’s ~212% gain year-to-date already prices in aggressive bets, raising the odds of a sharp re-rating if AI demand cools, supply chains normalize, or competitive pricing pressure arises in optics.
The upgrade could prove prescient: AI networking demand may prove durable, and MRVL’s optics/connectivity stack could become a structural anchor as hyperscalers expand. If that cycle proves long-lived, the $300 target and high multiple could be justified.
"Memory shortages could delay optical ramps and link directly to guidance shortfalls via supply chain prioritization."
Claude flags the $300 target math, but misses how memory shortages Grok mentioned could specifically hinder optical ramps by diverting supplier capacity to DRAM. This creates downside risk to the 29.8% EPS growth expected today if hyperscalers delay networking purchases. No one has connected these supply dynamics to potential margin pressure from Broadcom competition.
"Memory supply constraints hurt optical *pricing* as much as volume, a distinction Grok missed that matters for a 54x multiple."
Grok's memory-to-optical capacity diversion thesis is plausible but unverified. TSMC and Samsung have publicly guided flat-to-growth capex; no evidence yet that DRAM demand is starving optical node allocation. More critically: if memory constraints *do* hit optical ramps, that's deflationary for Marvell's ASPs, not just a volume miss. Broadcom faces the same constraint. The real risk is margin compression, not just EPS growth shortfall—which Claude and Gemini flagged but Grok didn't quantify.
"Marvell's primary long-term valuation risk is not Broadcom competition, but the strategic internalization of SerDes and custom silicon by hyperscalers."
Claude, you’re missing the structural shift in Marvell’s custom ASIC business. While you focus on ASP deflation, you ignore the 'design win' stickiness. Once a hyperscaler commits to Marvell’s silicon for a specific cluster architecture, the switching costs are prohibitive. The real risk isn't just margin compression from Broadcom; it’s the 'internalization' risk where hyperscalers like Google or Amazon bring the SerDes design in-house to capture those margins. That’s the true long-term threat to the 54x multiple.
"Hyperscalers internalizing SerDes and optical IP could erode Marvell's moat and justify a lower multiple than 54x."
Gemini argues Marvell’s SerDes/design wins create lasting stickiness, but that assumes competitors won't commoditize. The bigger risk is hyperscalers internalizing SerDes and critical optical IP at scale; that would shrink Marvell’s addressable market, pressure ASPs, and force a re-rating if the 'custom silicon moat' proves easier to replicate or bypass. Until we see durable customer lock-in, the 54x multiple rests on fragile assumptions about moat durability.
The panelists generally agree that Marvell's (MRVL) high valuation (54x forward P/E) is based on aggressive growth assumptions, particularly in AI optical interconnects. They express concerns about potential execution issues, competition from Broadcom, and the risk of hyperscalers internalizing critical optical IP. The upcoming Q1 FY27 earnings are seen as crucial for providing guidance on optical revenue growth rates and customer concentration risk.
Sustained growth in AI optical interconnects and durable customer lock-in through design wins.
Margin compression due to competition and potential internalization of critical optical IP by hyperscalers.