TickerTain — Make Analysis Fun Again

▶ 19:19 · Semiconductors · Vera CPU and Bluefield-4 STX co-designed to accelerate storage and GPU data paths

now playing · Semiconductors

AI Infrastructuretailwindscore 9/10jason hardy

Enterprise storage evolving into real-time AI data platform for agentic workloads

Storage must shift from passive system of record to active AI data plane that ingests, cleanses, enriches, chunks, embeds, indexes, and governs data at the moment of creation — enabling age…

AI Agentstailwindscore 8/10jason hardy

Agentic workloads demand 24/7 active data, blending structured, unstructured, and context at machine scale

Agents run long-running sessions (hours to years), consume data at GPU speed not human speed, blend SQL and PDFs, and generate persistent context (KV cache, memory, ontology) that must be g…

AI Agentstailwindscore 8/10jason hardy

Agentic AI creates 24/7 data consumption at machine speed, requiring new storage paradigms

Agents run long-running sessions (hours to years), blend structured and unstructured data, operate at machine speed far exceeding human interaction rates, and generate persistent context (K…

AI Infrastructuretailwindscore 9/10jason hardy

Enterprise storage must evolve from system of record to AI data platform for agentic AI

Agentic AI creates a new paradigm where storage must continuously prepare, index, govern, and serve multimodal data at creation time — not just store it — requiring co-designed compute, net…

Semiconductorstailwindscore 7/10jason hardy

Vera CPU and Bluefield-4 STX co-designed to accelerate storage and GPU data paths

Vera's 3x memory bandwidth and best-in-class single-thread performance — originally built to feed GPUs — directly benefit storage workloads; Bluefield-4 STX integrates Vera with storage acc…

Memory & Storagetailwindscore 8/10jason hardy

New memory hierarchy G1-G4 plus G3.5 tier addresses KV cache bottleneck in AI factories

Nvidia defines a five-tier memory hierarchy (HBM=G1, system RAM=G2, NVMe=G3, high-perf storage=G4, enterprise storage=G4 extended) and introduces G3.5 as a cost-effective KV cache tier that…

Memory & Storagetailwindscore 8/10jason hardy

Nvidia introduces G3.5 memory tier for KV cache to boost token throughput in AI factories

A new storage tier (CMX) sits between GPU memory (G1/G2) and high-performance storage (G4) to offload KV cache, eliminating recompute on prefill/decode stages and scaling token output cost-…

Data Center Infrastructuretailwindscore 8/10jason hardy

Extreme vertical and horizontal co-design across GPU, CPU, DPU, networking, and storage defines next-gen AI factories

Nvidia's Vera, Bluefield-4, Spectrum-X, and Rubin/RTX Pro GPUs are co-designed with storage partners (Dell, NetApp, IBM, HPE) to create turnkey AI data platforms where compute, network, and…

←

▶ 19:19 · Semiconductors · Vera CPU and Bluefield-4 STX co-designed to accelerate storage and GPU data paths

now playing · Semiconductors

AI Infrastructuretailwindscore 9/10jason hardy

Enterprise storage evolving into real-time AI data platform for agentic workloads

Storage must shift from passive system of record to active AI data plane that ingests, cleanses, enriches, chunks, embeds, indexes, and governs data at the moment of creation — enabling age…

AI Agentstailwindscore 8/10jason hardy

Agentic workloads demand 24/7 active data, blending structured, unstructured, and context at machine scale

Agents run long-running sessions (hours to years), consume data at GPU speed not human speed, blend SQL and PDFs, and generate persistent context (KV cache, memory, ontology) that must be g…

AI Agentstailwindscore 8/10jason hardy

Agentic AI creates 24/7 data consumption at machine speed, requiring new storage paradigms

Agents run long-running sessions (hours to years), blend structured and unstructured data, operate at machine speed far exceeding human interaction rates, and generate persistent context (K…

AI Infrastructuretailwindscore 9/10jason hardy

Enterprise storage must evolve from system of record to AI data platform for agentic AI

Agentic AI creates a new paradigm where storage must continuously prepare, index, govern, and serve multimodal data at creation time — not just store it — requiring co-designed compute, net…

Semiconductorstailwindscore 7/10jason hardy

Vera CPU and Bluefield-4 STX co-designed to accelerate storage and GPU data paths

Vera's 3x memory bandwidth and best-in-class single-thread performance — originally built to feed GPUs — directly benefit storage workloads; Bluefield-4 STX integrates Vera with storage acc…

Memory & Storagetailwindscore 8/10jason hardy

New memory hierarchy G1-G4 plus G3.5 tier addresses KV cache bottleneck in AI factories

Nvidia defines a five-tier memory hierarchy (HBM=G1, system RAM=G2, NVMe=G3, high-perf storage=G4, enterprise storage=G4 extended) and introduces G3.5 as a cost-effective KV cache tier that…

Memory & Storagetailwindscore 8/10jason hardy

Nvidia introduces G3.5 memory tier for KV cache to boost token throughput in AI factories

A new storage tier (CMX) sits between GPU memory (G1/G2) and high-performance storage (G4) to offload KV cache, eliminating recompute on prefill/decode stages and scaling token output cost-…

Data Center Infrastructuretailwindscore 8/10jason hardy

Extreme vertical and horizontal co-design across GPU, CPU, DPU, networking, and storage defines next-gen AI factories

Nvidia's Vera, Bluefield-4, Spectrum-X, and Rubin/RTX Pro GPUs are co-designed with storage partners (Dell, NetApp, IBM, HPE) to create turnkey AI data platforms where compute, network, and…