Arm Targets Server AI Bottlenecks with Custom Architecture Benchmarks
Arm claims its upcoming AGI CPU design nearly doubles rack-level throughput against AMD's flagship Turin chip in complex agentic workloads.
David Park 3 min read
Tag
#amd
All stories tagged amd on The Silicon Valley News.
Stories tagged amd
AMD's EPYC Verano CPUs to Feature New SB1 Socket for AI Server Architectures
AMD's forthcoming EPYC 'Verano' AI host CPUs, based on the Zen 6 architecture, are reportedly adopting a new SB1 socket, signaling a significant platform shift for high-performance computing and AI server designs.
David Park 2 min read
AMD EPYC 'Venice' CPUs Target Nvidia Vera with Double Performance Claims
AMD has released initial performance benchmarks for its upcoming EPYC 'Venice' CPUs, positioning its high-core-count processors as a direct challenge to Nvidia's Vera server offerings, particularly in compute-intensive workloads.
David Park 3 min read
Optimizing FidelityFX on Legacy Silicon: The BC-250 Modding Breakthrough
Community-driven optimization of FSR 4 on AMD's BC-250 mining APU highlights the latent performance potential in repurposed, PS5-derived silicon through software-level efficiency gains.
David Park 3 min read
AMD's Ryzen AI Halo Platform Demands Extreme Memory Bandwidth for Project Zenith
Microsoft's Project Zenith, a specialized Windows 11 build for AI developers, will debut on AMD's Ryzen AI Halo platform, setting a new benchmark with requirements for 64GB RAM and 250 GB/s memory bandwidth.
David Park 2 min read
AMD Threadripper Halo Station Signals Shift Toward Desktop-Scale AI Inference
AMD's new Threadripper Halo Station pushes the boundaries of local compute, integrating dual MI350P accelerators and massive memory bandwidth to enable trillion-parameter model inference on a workstation.
David Park 3 min read
AMD's Desktop Gains Mask Structural Shifts in x86 Processor Consumption
Despite a 20% contraction in the desktop CPU market, AMD has hit record market share, signaling a fundamental divergence in how Intel and AMD are navigating the current silicon glut.
David Park 3 min read
Xen Project Targets Safety-Critical Silicon to Partition Mixed-Criticality Workloads
With backing from AMD, Renesas, and Boeing, the Xen Project is pursuing safety-critical certifications to enable secure hardware virtualization in automotive and aerospace systems.
David Park 2 min read
Google and AMD Partner on Hybrid TPU Architecture to Accelerate Agentic AI
Google is reportedly collaborating with AMD to develop a next-generation Tensor Processing Unit that integrates custom CPU cores on-package to handle the complex, sequential logic required for reinforcement learning and agentic AI workloads.
David Park 3 min read
MIT's TONTOU Exploit Bypasses Modern Spectre Defenses via Timer Interrupts
Researchers at MIT have uncovered TONTOU, a microarchitectural attack that leverages hardware timer interrupts to bypass existing Spectre mitigations on modern Intel and AMD processors.
David Park 3 min read
AMD and Cerebras Unveil Helios AI Rack-Scale Platform Combining EPYC CPUs and Wafer-Scale Engines
AMD and Cerebras collaborate to integrate EPYC processors with Cerebras' wafer-scale AI engines in the Helios platform, targeting low-latency, high-throughput AI inference workloads for data centers.
David Park 2 min read
AMD’s $5 Billion Commitment to Anthropic Signals Scale-Up in AI Infrastructure
AMD’s multi-billion dollar investment in Anthropic aims to expand AI computing capacity with up to 2 gigawatts of new Instinct MI450 GPUs, highlighting the growing demand for specialized hardware in large-scale AI model deployment.
Maya Chen 2 min read
AMD’s 10-Core Medusa Point APU Sets New Single-Core Performance Benchmark
AMD’s upcoming 10-core Medusa Point mobile APU achieves its highest Geekbench single-core score yet, surpassing all other x86 mobile chips and signaling a major leap in mobile CPU performance.
David Park 2 min read