Reported by IN Electronics and Design on . Summarized and analyzed by XAIPART Editorial.
What happened
Synaptics made Coralboard SL generally available through DigiKey, with the board built around an Astra SL2619 processor and a 1 TOPS Torq/Coral NPU.S1 The processor combines two Arm Cortex-A55 application cores operating at up to 2GHz and one Cortex-M52 processor.S1 Its supported Coral technology was developed through Synaptics' collaboration with Google Research.S1
Synaptics also introduced Coralboard SR, which uses an Astra SR250-series processor from the SR200 family.S1 This board pairs an Arm Cortex-M85 core operating at up to 800MHz, an additional Cortex-M52 and a Torq/Coral NPU rated at 400 GOPS.S1 The source did not confirm immediate worldwide ordering through DigiKey for SR.S1
Both boards use the open-source Torq compiler and runtime, while their hardware configurations remain different.S1 SL includes 2GB of DDR4 memory, NOR flash, a microSD interface, CSI, DSI, USB, Qwiic, mikroBUS and an M.2 expansion slot.S1 SR supports up to 8MB of integrated SRAM and up to 256MB of custom high-bandwidth DRAM, along with camera, display, image-signal-processing and digital-microphone resources.S1
| Metric | Reported value | Source |
|---|---|---|
| SL NPU capacity | 1 TOPS | S1 |
| SR NPU capacity | 400 GOPS | S1 |
| SL memory | 2GB DDR4 | S1 |
| Selected Gemma output rate | Approximately 12 to 16 generated tokens per second | S1 |
Background timeline
XAIPART take
Technical impact
XAIPART analysis: Engineering teams should treat 1 TOPS and 400 GOPS as accelerator peaks rather than application throughput. Model precision, supported operators, memory transfers and preprocessing or decoding determine achievable latency.
XAIPART analysis: Portability should be tested at the operator, numerical-precision and memory-footprint levels because the shared Torq toolchain does not make SL and SR interchangeable. Representative sensor and audio pipelines must be benchmarked rather than isolated model runs.
Market impact
XAIPART analysis: SL's immediate DigiKey ordering gives procurement teams an acquisition route, while the absence of confirmed ordering for SR limits supply-chain planning for that option. The source did not disclose prices, lead times or production quantities.
XAIPART analysis: Buyers should preserve platform flexibility until operating-system, memory and peripheral requirements are settled; neither development board automatically defines a production module or validated end equipment.
Action
XAIPART analysis: Request DigiKey quotation and availability data for Coralboard SL, then map required camera, storage, networking and expansion interfaces against its board resources. Track SR commercial terms separately rather than assuming launch equals orderability.
XAIPART analysis: Evaluate representative inference workloads using intended quantization settings, then budget for power delivery, thermal design, electromagnetic compatibility and production conversion. The development kit does not establish production readiness.
XAIPART Forecast
XAIPART analysis: XAIPART expects a published lead time for Coralboard SR within 6 months of the announcement; if Synaptics or DigiKey does not disclose a lead time of 12 weeks or less by , this forecast is wrong.XAIPART analysis
Facts are as reported by the cited source. The design-in, sourcing and forward-looking statements above are XAIPART's analysis, not the source's claims. This is a single-source report, and SR availability, pricing and lead time remain unconfirmed.
Corrections: none at publication. This brief will be updated with a timestamp if the source corrects its report.
替代料与生命周期
| 料号 | 关系 | 生命周期 | 依据 |
|---|---|---|---|
| — | 暂无收录替代料 待补充数据 | — | 需 match_type 后才可显示任何前代标签 |
“前代”和“替代”标签仅来自已记录的匹配类型、生命周期状态或来源文本。没有记录匹配时,不显示任何标签。我们自己的商品列表不构成市场参考。
关注要点
| 论断 | 阈值 | 发布方 | 状态 |
|---|---|---|---|
| : XAIPART expects a published lead time for Coralboard SR within 6 months of the announcement | Synaptics or DigiKey does not disclose a lead time of 12 weeks or less by April 20, 2027 | Pending |
被证明错误的预测仍保留可见并加以标注。我们不会删除它们。
受影响的料号
目录中无匹配。 此事件未映射到 XAIPART 当前上架的任何料号。我们不推断匹配,也不显示占位列表。
各维度成本压力
| Dimension | FRED series ID | Unit | Lag | As of |
|---|---|---|---|---|
| 投入成本 | PCOPPUSDM, PALUMUSDM, PNICKUSDM | USD/mt | 52 d | |
| 供需 | PCU334413334413, IPG3344S | index(1982=100) / index(2017=100) | 46 d | |
| 汇率与能源 | 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.
本文如何生成
过程证据——抓取、来源可靠性检查、模型与校验
| Source fetched | IN Electronics and Design · www.inelectronics.co.uk · 7,639 chars |
|---|---|
| Source sanity (S1) | ok — passed before any model call (no s1_ block recorded) |
| Model / prompt | MiniMax-M3 · prompt Blog Agent - News Summary (v2.8-final) · 6,959 tokens · 11.3s · run completed |
| Gate | verdict hold · 6/6 applicable checks passed · spec v2.9 · C10 ratio 0.01557 · C10 rounds 0 |
| Time contract | 4 <time datetime> values in this brief — 0 violations (+08:00 or date-only) |
上述每一行均由流水线生成,而非人工撰写。
评论
成为第一个评论的人。
🔐 请 登录 即可发表评论。
还没有账户? 注册