Broadcom– tag –
-
Broadcom Unveils Next-Gen “Tomahawk 6-O” Co-Packaged Optics Switch ASIC Platform for AI Networks, Achieving 30% Power Efficiency Boost Towards 2025 Commercial Deployment
Broadcom Investor Relations News USA Overview Broadcom has announced "Tomahawk 6-O," a new Co-Packaged Optics (CPO) switch ASIC platform specifically designed for AI networks. This platform aims to accelerate CPO adoption in AI data cent... -
OpenAI Develops Custom AI Inference Chip ‘Jalapeño’ with Broadcom, Adopting Apple-esque Vertical Integration to Reduce Nvidia Dependence
TechRadar USA Overview OpenAI has unveiled details of its custom AI inference processor, "Jalapeño," co-developed with Broadcom, signaling a strategic shift towards Apple-like vertical integration. This move aims to reduce OpenAI's relia... -
Broadcom’s $3B Share Buyback: A Strategic Move to Cement AI ASIC and Optical Interconnect Leadership
富途资讯 China Overview Broadcom is reinforcing its financial bedrock with a $3 billion debt-financed share repurchase, strategically bolstering its 'optical interconnects + AI ASIC' computing power strategy. This initiative focuses on a... -
OpenAI and Broadcom Unveil ‘Jalapeño,’ First LLM-Optimized AI Processor Delivering Significantly Enhanced Performance Per Watt
GLOBE NEWSWIRE USA Overview OpenAI and Broadcom have jointly launched 'Jalapeño,' their first intelligence processor specifically optimized for Large Language Model (LLM) inference. Designed from scratch based on OpenAI's model roadmap, ... -
OpenAI and Broadcom Unveil LLM-Optimized AI Chip “Jalapeño,” Significantly Outperforming State-of-the-Art in Performance per Watt
OpenAI / Broadcom USA Overview OpenAI and Broadcom have announced "Jalapeño," a custom AI chip specifically designed for Large Language Model (LLM) inference. This chip significantly surpasses current state-of-the-art products in perform... -
TechInsights Identifies Silicon Photonics as Backbone for HPC and AI Data Centers, Highlighting New Industry Opportunities
TechInsights Blog Canada Overview TechInsights' analysis highlights silicon photonics as an indispensable backbone rapidly emerging for High-Performance Computing (HPC) and AI data centers. This technology overcomes the limitations of tr... -
Tensordyne’s Napier AI Inference System, Taped Out on TSMC 3nm, Achieves 17x More Tokens/Watt and 13x Higher Throughput than NVIDIA Blackwell
Tensordyne USA Overview Tensordyne announced its Napier (TDN) AI inference system, fabricated on TSMC's 3nm process, delivers up to 17x more tokens per watt and 13x higher throughput compared to NVIDIA Blackwell systems. This breakthroug... -
Data Gravity Analysis: AI Interconnects Shift from Copper to Optical, with NVIDIA Leading with CPO-Equipped Spectrum-X Switches
Data Gravity USA Overview Data Gravity's analysis indicates that frontier AI performance constraints are shifting from accelerator supply to interconnects, highlighting challenges in chip-to-chip, GPU-to-GPU, and rack-to-rack connectivit... -
Broadcom Advances Next-Gen 200 Terabit Switch Tapeout with 1.6T DSP and CPO Technology, Targeting $100 Billion in AI Revenue
Techstock01 | Substack USA Overview Broadcom is progressing with the tapeout of its next-generation 200 terabit switch, championing Co-Packaged Optics (CPO), 1.6 terabit DSPs, CW, and EML lasers as industry standards. The company is stra... -
NVIDIA CEO Jensen Huang Unveils ‘Copper-and-Optics Roadmap,’ Positioning CPO as Core AI Infrastructure by 2028
Futubull Community Hong Kong Overview NVIDIA CEO Jensen Huang presented the 'Copper-and-Optics Roadmap' for AI infrastructure at COMPUTEX TAIPEI 2026, signaling a shift from copper to optical fiber for data center interconnects. The road...
