News
CAPACITY TEST:

Intel Lists Starfire Space AI Chip At 75 TOPS As Radiation Data Stays Pending

Newsroom brief

Tom's Hardware reported that Intel has listed Starfire, a space-grade system-on-chip for the U.S. government, with up to 75 TOPS and Intel 18A CPU and NPU tiles. The sell sheet says samples are planned for Q3 2026, while radiation qualification data and final specifications remain pending.

Verified against source materialEdited by SendTech Times Chips & Compute DeskSource: tomshardware.com
Intel Lists Starfire Space AI Chip At 75 TOPS As Radiation Data Stays Pending
Image source: tomshardware.com

Intel has listed Starfire as a space-grade AI system-on-chip for the U.S. government with up to 75 TOPS, Tom's Hardware noted, but the same sell sheet still leaves radiation qualification data in progress.

Records cited by Tom's Hardware show Intel Government Technologies is handling Starfire and that samples are planned for Q3 2026.

The chip combines Intel 18A compute and NPU tiles with an Intel 3 graphics tile in a Foveros package.

Intel Starfire Uses 18A CPU And NPU Tiles

Specifications highlighted by Tom's Hardware show Starfire has eight CPU cores and a three-tile NPU on Intel 18A, paired with a four-core Xe GPU built on Intel 3.

Intel lists two versions of the chip: a 10 W low-power version rated at 45 TOPS and a 35 W performance version rated at 75 TOPS.

The sell sheet, as described by Tom's Hardware, gives the part an operating range from -55 to 125 Celsius, lists 12 PCIe Gen4 lanes, supports LPDDR5 or DDR5 memory, and gives both versions a 10-plus year lifetime rating.

For clocks, Tom's Hardware lists the low-power version at 1.0 GHz for its P-cores, 850 MHz for its efficiency cores and between 800 MHz and 1.0 GHz for its GPU.

The performance version raises those clocks to 3.1 GHz for the P-cores, 2.1 GHz for the efficiency cores and 2.0 GHz for the GPU.

Starfire Targets On-Orbit AI Inference Rather Than Telemetry

In its comparison, Tom's Hardware set Starfire against BAE Systems' RAD750, the radiation-hardened PowerPC processor that has been used for two decades.

Public specifications cited by the outlet list RAD750 at 110 MHz to 200 MHz, 10.4 million transistors and 150nm or 250nm lithography.

The article describes RAD750 as having flown on the Mars rovers, Kepler, Fermi and more than 150 spacecraft.

It also points to BAE's multi-core RAD5545 and a NASA-backed Microchip processor as newer reference points; the NASA-backed processor has a 100-times throughput goal.

Starfire's listed 75 TOPS ceiling and dedicated NPU put Intel's pitch closer to on-orbit AI inference.

Tom's Hardware did not present Starfire as a flight-qualified replacement for those existing processors.

Radiation Characterisation Is Still In Process

Tom's Hardware states that Intel lists radiation data for total-dose exposure, latch-up and single-event effects as characterisation still in process.

The article adds that the part is not radiation-qualified yet and that Intel notes the specifications remain subject to change.

Its breakdown of the design notes that Intel's use of Intel 18A for CPU and NPU tiles and Intel 3 for the GPU resembles the node split used in Clearwater Forest.

The piece adds that smaller transistors hold less charge per stored bit, which can make leading-edge silicon more exposed to radiation-induced bit flips.

Elsewhere, Tom's Hardware ties Intel's domestic-manufacturing pitch to its Trusted Foundry status and Pentagon programmes.

The outlet notes that RAMP-C and SHIP include Intel 18A and advanced packaging work, and adds that 18A yields are not expected to reach industry-standard levels until 2027.

Intel has not disclosed completed radiation qualification, final specifications, production pricing, named mission customers or confirmed flight dates for the two listed Starfire SKUs.

Share this article
inXf

Related articles

More
Keep Reading

More Stories

Latest
Hugging Face Hack Pushes AI Agents Into Cybersecurity SpotlightAIAug 8, 2026Hugging Face Hack Pushes AI Agents Into Cybersecurity SpotlightCNBC reported that Black Hat cybersecurity leaders treated the Hugging Face AI-agent breach as a turning point for governing autonomous cyber models rather than a one-off failure.Alibaba Tests Revenue Sharing For Commercial Qwen AI UseAIAug 8, 2026Alibaba Tests Revenue Sharing For Commercial Qwen AI UseAI News reported that Alibaba plans revenue-sharing terms for some commercial users of its next Qwen open-weight AI model, following a licensing pattern already used by Moonshot for Kimi K3.Meta Ordered To Fund $567M New Mexico Youth Mental Health PlanCapital & PolicyAug 8, 2026Meta Ordered To Fund $567M New Mexico Youth Mental Health PlanArs Technica reported that a New Mexico judge ordered Meta to provide $567 million for treatment, screening, awareness and prevention after finding that its platforms contributed to a public nuisance.Harvey Funding Talks Could Lift Legal AI Startup To $15.5B ValuationAIAug 8, 2026Harvey Funding Talks Could Lift Legal AI Startup To $15.5B ValuationSiliconANGLE reported that Harvey AI is seeking at least $500 million in new funding that could value the legal AI startup at $15.5 billion after annualized revenue passed $350 million.Vietnam Shows Shopee-TikTok Shop Race Tightening In Southeast AsiaScience & TechAug 7, 2026Vietnam Shows Shopee-TikTok Shop Race Tightening In Southeast AsiaTech Collective SEA wrote that Shopee’s Vietnam share fell from 61% to 53% between May 2025 and April 2026 as TikTok Shop rose from 33% to 44%, showing how social commerce is reshaping regional ecommerce infrastructure.China Opens Security Review Of Palo Alto Networks ProductsCybersecurityAug 7, 2026China Opens Security Review Of Palo Alto Networks ProductsChina's cyberspace regulator opened a security review of Palo Alto Networks products, with no named product line, technical flaw or decision timetable disclosed.AI Pioneers Split Over Risk As Compute Buildout AcceleratesAIAug 7, 2026AI Pioneers Split Over Risk As Compute Buildout AcceleratesData Center Knowledge reported that Geoffrey Hinton, Fei-Fei Li and Andrew Ng disagreed at Ai4 over AI risk, jobs, openness and regulation, leaving infrastructure investors to plan capacity amid unsettled deployment rules.SpaceX Asks FCC To Wind Down $4.5bn Rural Broadband SupportTelco & ConnectivityAug 7, 2026SpaceX Asks FCC To Wind Down $4.5bn Rural Broadband SupportLight Reading reported that SpaceX urged the FCC to sunset High-Cost rural broadband subsidies, while rural telecom and electric-cooperative groups said LEO satellite coverage cannot replace terrestrial network support.OpenAI Expands Free ChatGPT Access In GPT-5.6 RolloutAIAug 7, 2026OpenAI Expands Free ChatGPT Access In GPT-5.6 RolloutBleepingComputer reported that OpenAI is rolling out GPT-5.6 Sol for paid ChatGPT users and GPT-5.6 Luna for Free and Go users, pairing unlimited free text chats with a new reasoning control and additional safeguards for users believed to be under 18.JLL Data Centre Report Shows Middle East Pipeline Pause As FLAPD GrowsCapital & PolicyAug 7, 2026JLL Data Centre Report Shows Middle East Pipeline Pause As FLAPD GrowsData Center Dynamics reported that JLL's EMEA Mid-Year Data Centre Report 2026 put FLAPD live capacity at 3.8GW, while the Middle East had 2.6GW in development paused and 13.8GW in planning.AWS Adds Persistent Runtime Instances For Production AI AgentsCloud & Data CentersAug 7, 2026AWS Adds Persistent Runtime Instances For Production AI AgentsAWS announced runtime instances for Amazon Bedrock AgentCore Runtime, adding managed infrastructure for multi-agent workflows, shared sessions lasting up to 14 days and GPU-supported production agent deployments.AI Patch Study Keeps Humans In Vulnerability ReviewsCybersecurityAug 7, 2026AI Patch Study Keeps Humans In Vulnerability ReviewsThe Register reported that 1Password Off-by-1 Labs tested 6,080 AI-generated patches across six CVEs and found clean autonomous fixes in 26.0 percent of cases, leaving security teams with a supervision problem rather than a replacement for vulnerability review.