Tag Archives: Hot Chips 2025

Google’s Ironwood TPU Swings for Reasoning Model Leadership at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/googles-ironwood-tpu-swings-for-reasoning-model-leadership-at-hot-chips-2025/

Closing out the machine learning sessions at Hot Chips 2025 is Google, who is at the show to talk about their latest tensor processing unit (TPU), codenamed Ironwood. Revealed by the company a few months ago, Ironwood is the first Google TPU that is explicitly designed for large-scale AI inference (rather than AI training). Paired […]

The post Google’s Ironwood TPU Swings for Reasoning Model Leadership at Hot Chips 2025 appeared first on ServeTheHome.

AMD Dives Deep on CDNA 4 Architecture and MI350 Accelerator at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/amd-dives-deep-on-cdna-4-architecture-and-mi350-accelerator-at-hot-chips-2025/

The second big machine learning accelerator talk of the afternoon belongs to AMD. The company’s chip architects are at this year’s show to tell the audience all about the CDNA 4 architecture, which is powering AMD’s new MI350 family of accelerators. Like it’s MI300 predecessor, AMD is using 3D die stacking to build up a […]

The post AMD Dives Deep on CDNA 4 Architecture and MI350 Accelerator at Hot Chips 2025 appeared first on ServeTheHome.

NVIDIA Outlines GB10 SoC Architecture at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/nvidia-outlines-gb10-soc-architecture-at-hot-chips-2025/

Back from our Hot Chips 2025 ice cream break, NVIDIA is starting off the second session of machine learning presentations. As with yesterday’s graphics presentation, NVIDIA isn’t so much showing off future hardware as much as they are offering a better lay of the land on their latest generation of hardware that is already on […]

The post NVIDIA Outlines GB10 SoC Architecture at Hot Chips 2025 appeared first on ServeTheHome.

Huawei Presents UB-Mesh Interconnect for Large AI SuperNodes at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/huawei-presents-ub-mesh-interconnect-for-large-ai-supernodes-at-hot-chips-2025/

The third and final machine learning presentation before the afternoon break comes from Huawei. Unlike many of the other ML vendors who are here to pitch products, Huawei’s presentation is more focused on fundamental technology. In this case, how to use efficiently use meshes to interconnect the chips within large AI systems. Eyeing so-called SuperNodes […]

The post Huawei Presents UB-Mesh Interconnect for Large AI SuperNodes at Hot Chips 2025 appeared first on ServeTheHome.

d-Matrix Presents Corsair, An In-Memory Computing Architecture For Inference, at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/d-matrix-presents-corsair-an-in-memory-computing-architecture-for-inference-at-hot-chips-2025/

The second machine learning presentation of the afternoon comes from d-Matrix. The company specializes in hardware for AI inference, and as of late has been tackling the matter of how to improve inference performance by using in-memory computing. Along those lines, the company is presenting their Corsair in-memory computing chiplet architecture at Hot Chips. Not […]

The post d-Matrix Presents Corsair, An In-Memory Computing Architecture For Inference, at Hot Chips 2025 appeared first on ServeTheHome.

Marvell Shows Dense SRAM Custom HBM and CXL with Arm Compute at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/marvell-shows-dense-sram-custom-hbm-and-cxl-with-arm-compute-at-hot-chips-2025/

Marvell showed its massively dense SRAM, its custom HBM solution, and how it is adding Arm cores to CXL memory controllers at Hot Chips 2025

The post Marvell Shows Dense SRAM Custom HBM and CXL with Arm Compute at Hot Chips 2025 appeared first on ServeTheHome.

Meta Talks World-Lock Rendering for AR/MR at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/meta-talks-world-lock-rendering-for-ar-mr-at-hot-chips-2025/

The final graphics-related talk of the day comes from Meta, who has perhaps the most novel presentation on the graphics track. Rather than talking about GPU architectures that have already been shipping to customers for several months, Meta’s ex-Oculus headset division is at the show to talk about using dedicated ICs for accelerating world-locked rendering […]

The post Meta Talks World-Lock Rendering for AR/MR at Hot Chips 2025 appeared first on ServeTheHome.

NVIDIA GeForce RTX 5090 and the Age of Neural Rendering at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/nvidia-geforce-rtx-5090-and-the-age-of-neural-rendering-at-hot-chips-2025/

The second presentation on today’s graphics track comes from NVIDIA. Like AMD, NVIDIA is mid-cycle on its current generation of graphics products, having launched the first of them back in late 2024. As a result, their Hot Chips presentation is more of a recap, with a focus on what the Blackwell architecture offers for graphics […]

The post NVIDIA GeForce RTX 5090 and the Age of Neural Rendering at Hot Chips 2025 appeared first on ServeTheHome.

AMD RDNA 4 GPU Architecture at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/amd-rdna-4-gpu-architecture-at-hot-chips-2025/

Kicking off this afternoon’s graphics track at Hot Chips 2025 is AMD. The company launched its RDNA 4 architecture and associated Radeon RX 9000 series video cards earlier this year, releasing two GPUs thus far. As AMD is now well into this generation of Radeon GPUs, the company doesn’t necessarily have any grand revelations to […]

The post AMD RDNA 4 GPU Architecture at Hot Chips 2025 appeared first on ServeTheHome.

Intel Xeon Clearwater Forest with 288 Cores on Intel 18A at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/intel-xeon-clearwater-forest-with-288-cores-on-intel-18a-at-hot-chips-2025/

At Hot Chips 2025, Intel went into its next-gen 288 core processor constructed on Intel 18A process and using 3D packaging technology

The post Intel Xeon Clearwater Forest with 288 Cores on Intel 18A at Hot Chips 2025 appeared first on ServeTheHome.

IBM’s Power11 Processor Architecture at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/ibms-power11-processor-architecture-at-hot-chips-2025/

Third up on today’s CPU track is IBM. Big Blue is at the conference to talk about its latest generation Power architecture chip, the Power11. IBM starts off by recapping Power. Why it exists, and what IBM’s goals are for the processor and architecture. IBM is very system-focused, rather than focusing on selling just CPUs. […]

The post IBM’s Power11 Processor Architecture at Hot Chips 2025 appeared first on ServeTheHome.

Pezy Computing’s PEZY-SC4s, A MIMD Many-Core Architecture at Hot Chips 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/pezy-computings-pezy-sc4s-a-mimd-many-core-architecture-at-hot-chips-2025/

Second on today’s Hot Chip 2025 CPU track is Pezy Computing, the quirky Japanese CPU development firm who specializes in Multiple Instructions Multiple Data (MIMD) CPU designs. MIMD is an old concept in CPU design, but it’s not a CPU design we see too much of in the real world. Most designs are variations on […]

The post Pezy Computing’s PEZY-SC4s, A MIMD Many-Core Architecture at Hot Chips 2025 appeared first on ServeTheHome.

Condor Computing’s Cuzco, a High-Perf RISC-V Design at Hot Chip 2025

Post Syndicated from Ryan Smith original https://www.servethehome.com/condor-computings-cuzco-a-high-perf-risc-v-design-at-hot-chip-2025/

Hot Chips, the semiconductor industry’s leading conferences on high-performance microprocessors and related integrated circuits is taking place this week. Living up to its name, the show offers a rather deep look at some of the latest and hottest chips in the industry, from smaller vendors specializing in RISC-V all the way up to the big […]

The post Condor Computing’s Cuzco, a High-Perf RISC-V Design at Hot Chip 2025 appeared first on ServeTheHome.