Hacker News with Generative AI: AMD

Tiny Corp Nearing "Completely Sovereign" Compute Stack for AMD GPUs with Tinygr (phoronix.com)
George Hotz' Tiny Corp that develops the Tinygrad neural network framework and sells the Tinybox NVIDIA and AMD powered AI workstations is nearing a "completely sovereign" software stack for GPU compute on AMD.
Apple joins UALink consortium with Intel and AMD to take on Nvidia AI dominance (9to5mac.com)
Apple has officially gained a board seat on the Ultra Accelerator Link Consortium, a group of more than 65 members developing next generation AI accelerator architecture.
AMD says Intel's 'horrible product' is causing Ryzen 7 9800X3D shortages (tomshardware.com)
AMD says Intel's 'horrible product' is causing Ryzen 7 9800X3D shortages (tomshardware.com)
TSMC Arizona allegedly now producing AMD's Ryzen 9000 and Apple's S9 processors (tomshardware.com)
AMD Ryzen 9 9950X3D and 9900X3D claims 20% faster gaming performance vs. Intel (tomshardware.com)
AMD 'Strix Halo' Ryzen AI Max+ Debuts with RDNA 3.5 Graphics and Zen 5 CPU Cores (tomshardware.com)
Agner Fog's Software Optimization Resources (agner.org)
This series of five manuals describes everything you need to know about optimizing code for x86 and x86-64 family microprocessors, including optimization advices for C++ and assembly language, details about the microarchitecture and instruction timings of most Intel, AMD and VIA processors, and details about different compilers and calling conventions.
Intel's Linux Performance Optimizations Continue Paying Off for AMD EPYC (phoronix.com)
As part of my end-of-year benchmarking and various historical comparisons, over the holidays I was curious to take a look at how the mature AMD EPYC 9004 "Genoa" performance has evolved over the past two years under Linux.
I helped fix sleep-wake hangs on Linux with AMD GPUs (gitlab.io)
I dual-boot my desktop between Windows and Linux. Over the past few years, Linux would often crash when I tried to sleep my computer with high RAM usage. Upon waking it would show a black screen with moving cursor, or enter a "vegetative" state with no image on-screen, only responding to magic SysRq or a hard reset. I traced this behavior to an amdgpu driver power/memory management bug, which took over a year to brainstorm and implement solutions for.
AMD Continued Ramping Up Their Linux and Open-Source Investments in 2024 (phoronix.com)
AMD's new products this year have not only been supported well on the server side with their new EPYC 9005 "Turin" processors but also on the consumer side with the Ryzen AI 300 series laptop and Ryzen 9000 series desktop Zen 5 processors.
UALink Consortium Led by AMD and Intel Poised to Compete with Nvidia's NVLink (tomshardware.com)
AMD 3D V-Cache teardown shows majority of the Ryzen 7 9800X3D is dummy silicon (tomshardware.com)
Framework 13 AMD Review on Linux: Almost Perfect (boilingsteam.com)
Following our review of the Framework Intel 12th gen laptop last year, we are giving a spin to the Framework Laptop AMD 13 that features one of the latest AMD processors, and a brand new screen as well, at 2.8K resolution and 120 Hz refresh rate. And it’s a matte display!
DOOM ported to run atop AMD ROCm + LLVM libc (phoronix.com)
An open-source developer at AMD has carried out a DOOM port that runs almost entirely atop AMD GPUs for rendering and the game logic.
Ask HN: How Are AMD GPUs/ROCm for Machine Learning in 2024? (ycombinator.com)
Ask HN: How Are AMD GPUs/ROCm for Machine Learning in 2024?
Instant macOS install on Proxmox including AMD patches (github.com/luchina-gabriel)
Voilà, install macOS on ANY Computer! This is really and magic easiest way!
How AMD Is Taking Standard C/C++ Code to Run Directly on GPUs (phoronix.com)
Back at the 2024 LLVM Developers' Meeting was an interesting presentation by AMD engineer Joseph Huber for how they have been exploring running common, standard C/C++ code directly on GPUs without having to be adapted for any GPU language / programming dialects or other adaptations.
AMD's trusted execution environment blown wide open by new BadRAM attack (arstechnica.com)
One of the oldest maxims in hacking is that once an attacker has physical access to a device, it’s game over for its security.
Pocket 4 with 8.8″ High-Refresh LTPS Screen, 64GB RAM, 2TB SSD, and 45Wh Battery (linuxgizmos.com)
Indiegogo recently introduced the GPD Pocket 4, a compact PC powered by AMD’s latest processors, including the Ryzen AI9 HX370. It features up to 64GB of LPDDR5x RAM, an M.2 NVMe port, Gigabit Ethernet, Wi-Fi 6E, Bluetooth 5.3, and more.
An EPYC Exclusive for Azure: AMD's MI300C – By George Cozma (chipsandcheese.com)
At SC24 we stopped by the Azure Booth to check out their new HBv5 VMs powered by the AMD EPYC 9v64H CPU.
Vulkan Video Now Enabled by Default for Radeon VCN2/VCN3 Hardware on Linux (phoronix.com)
An exciting merge today for the Radeon "RADV" Vulkan driver with next quarter's Mesa 25.0 is enabling Vulkan Video API support by default for AMD graphics having VCN 2.x and VCN 3.x hardware.
Scale (run CUDA on AMD GPUs without mods) supports gfx900 and gfx1102 (scale-lang.com)
AMD Disables Zen 4's Loop Buffer (chipsandcheese.com)
A loop buffer sits at a CPU's frontend, where it holds a small number of previously fetched instructions. Small loops can be contained within the loop buffer, after which they can be executed with some frontend stages shut off. That saves power, and can improve performance by bypassing any limitations present in prior frontend stages. It's an old but popular technique that has seen use by Intel, Arm, and AMD cores.
AMD Releases ROCm Version 6.3 (insidehpc.com)
Nov. 26, 2024: AMD today announced the release of ROCm Version 6.3 open-source platform, introducing tools and optimizations for AI, ML and HPC workloads on AMD Instinct GPU accelerators.
Pushing AMD's Infinity Fabric to Its Limits (chipsandcheese.com)
I recently wrote code to test memory latency under load, seeking to reproduce data in various presentations with bandwidth on the X axis and latency on the Y axis. Ampere pretty much described how that was done during their Hot Chips 2024 presentation. To achieve the same results in a semi-automated fashion, I run a latency test thread while also running a variable number of threads that generate bandwidth load.
Pushing AMD's Infinity Fabric to Its Limit (chipsandcheese.com)
I recently wrote code to test memory latency under load, seeking to reproduce data in various presentations with bandwidth on the X axis and latency on the Y axis. Ampere pretty much described how that was done during their Hot Chips 2024 presentation. To achieve the same results in a semi-automated fashion, I run a latency test thread while also running a variable number of threads that generate bandwidth load.
Ten best selling CPUs on Amazon are all AMD chips (pcgamer.com)
AMD crafts custom EPYC CPU with HBM3 for Azure: 88 Zen 4 cores and 450GB of HBM3 (tomshardware.com)
AMD now has more compute on the top 500 than Nvidia (nextplatform.com)
There has been a lot more churn on the November Top500 supercomputer rankings that is the talk of the SC24 conference in Atlanta this week than there was in the list that came out in June at the ISC24 conference in Hamburg, Germany back in May, and there are some interesting developments in the new machinery that is being installed.