AMD news and milestones

Learn to capture thread traces with rocprofv3 and analyze instruction timing, stalls, utilization, and counters in ROCprof Compute Viewer.

Build high-performance BF16 GEMM kernels on Helios GPUs with HipKittens, from a naive baseline to optimized schedules.

Features hyper integration of fast memory, secure data, and adaptive compute for memory bound, compute intensive, high bandwidth applications.

Learn how to optimize LDS traffic in Gluon kernels on AMD Instinct MI450 GPUs using transposed loads and partition-conflict-free layouts.

Explore what

AMD reached an estimated 4x increase in AI energy efficiency from 2024 to 2026, building momentum toward its 2030 goal to deliver a 20x increase in…

Learn how fused Triton TLX kernels optimize GLU feed-forward networks, reducing memory bottlenecks and accelerating LLM training on AMD GPUs.

News Summary: Taalas' technology to further differentiate AMD's AI roadmap by delivering breakthrough inference performance and…...

AMD Instinct Coder is designed to help teams boost developer productivity while reducing reliance on unpredictable cloud model costs. Deploy a validated AI coding platform on pre…

Day 0 support for Kimi-K3 on AMD Instinct MI355X GPUs with validated TP8 setups.

Learn how to design a high-performance attention decode kernel on AMD MI450 GPUs using Gluon.

Explore Instella-MoE-16B-A3B, AMD's fully open 16B MoE LLM with 2.8B active params per token, trained on AMD Instinct MI300 & MI325 GPUs.

News Highlights Anthropic to deploy up to 2 gigawatts of MI450 Series GPUs in AMD Helios rack-scale solutions, with deployment of the first…...

Learn how SPIR-V brings compile-once, specialize-on-device portability to AMD GPUs - with a reproducible HIP benchmark, trade-off analysis, and quick-start guide.

Derive MI355X GPU (CDNA4) occupancy by hand: the four limiters, MXFP8 GEMM examples, and why matrix-bound kernels hit peak throughput at low occupancy.

Learn how FlyDSL low-latency GEMMs speed up LLM decode on AMD GPUs with Split-K, K-slice parallelism, and an LDS-based pipeline.

AMD-contributed HandBrake 1.11.0 fixes improve thread management and transcoding performance on high-core-count Threadripper systems.

Learn how to build high-performance FP8 GEMM kernels on AMD CDNA4 GPUs using MFMA, LDS swizzling, and double-buffering.

Learn how to build faster FP8 GEMM kernels on AMD CDNA4 using 4-wave interleaving to hide memory latency and maximize Matrix Core utilization.

Comes with preconfigured software to build, run, and scale AI locally. AMD Ryzen AI Halo delivers predictable cost per token, avoiding cloud cost uncertainty.

A technical walkthrough of ATOM on AMD Instinct GPUs, covering architecture, feature scope, model coverage, and practical benchmark dashboard usage.

AMD celebrates 10 years of AM4, extends AM5 through 2029 and expands RDNA 4 gaming with new Ryzen and Radeon launches.

Explore new AMD Vivado licensing options with flexible subscriptions and perpetual tiers. Find the right fit for your design needs with free and paid choices.

Explore what

Dan McNamara of AMD describes the changes enterprise IT leaders face as agentic AI rewrites the CPU-to-GPU ratio in the AI infrastructure equation.

Advanced Vector Extensions 512 (AVX-512) was introduced as a powerful tool to answer this question; it improves throughput without touching clock speed. Available on the latest A…