#gpu
-
SpaceX locks in $40B to buy AI chips
The company disclosed what it calls a record-setting GPU leasing arrangement with Apollo to fund chips and data center gear.
-
Intel Unveils GPU D Series, Formerly Known as Crescent Island
Intel has announced its GPU D Series — enterprise-focused accelerators optimized for inference workloads. The products were previously known under the Crescent Island codename.
-
How a Valve Engineer Breathed New Life Into Old AMD GPUs on Linux
Over the past year Timur Kristóf of Valve's Linux graphics team has improved support for AMD's decade-old GCN 1.0/1.1 GPUs in the AMDGPU driver. He recounted the work at the XDC2026 conference in Toronto.
-
Qualcomm Keeps Expanding Its Open-Source Linux GPU Drivers
At XDC 2026 in Toronto, Rob Clark outlined Qualcomm's latest work on the upstream open-source graphics driver stack for Linux.
-
Bend: The Language That Blocks AI Errors with Mathematical Proofs
Bend promises the speed of C, parallelism across CPU and GPU, and code verification through formal proofs — so that an AI agent physically cannot commit a violation of the rules you set.
-
A Linux GPU Driver for the M4 Mac mini Was Written in a Month with AI
Cody Ho and Niklas Sheth put together a driver fully compliant with OpenGL ES 3.0 for the Apple Silicon GPU in a little over a month—where it usually takes years. AI agents wrote the bulk of the code.
-
Nvidia's Advantage Is Moving Beyond the GPU
After the quarterly report, investors came to see that Nvidia's strength lies not just in the accelerators themselves, but in orchestrating the data around them. As data centers scale up to the gigawatt level, it's the management of traffic that becomes decisive.
-
Nvidia is closing in on a $100 billion revenue quarter
The chipmaker expects revenue of $108 billion within the coming months, and last quarter brought in a record $96.2 billion — almost entirely thanks to data centers.
-
GPUThor: New Rowhammer Attack Defeats ECC Protection on NVIDIA GPUs
Researchers at the University of Toronto have demonstrated an attack that bypasses memory error correction on NVIDIA's Ampere-family GPUs, enabling both denial of service and privilege escalation to root.
-
Nvidia is building CUDA support for RISC-V — but the requirements are steep
At Hot Chips 2026, Nvidia laid out what a RISC-V processor needs to look like in order to work with CUDA. The list of conditions rules out almost all existing hardware.
-
AMD Uploads RDNA 4m Firmware to linux-firmware Ahead of GPU Announcement
The company has published all the binary firmware files the open-source driver needs to initialize the upcoming RDNA 4m “GFX 11.7” graphics — well before the hardware ships.
-
Intel's Jay Shader Compiler Passes the Vulkan CTS on Xe2 and Xe3
Intel's new SSA-based shader compiler Jay, developed under the leadership of Alyssa Rosenzweig, has passed the Vulkan conformance tests on Xe2 and Xe3 graphics cards for the first time.
-
Mesa 26.2 Released: Mesh Shaders in NVK and a Host of Vulkan Improvements
The latest quarterly release of the open-source OpenGL and Vulkan driver stack for Linux is out. The focus is once again on Vulkan, but Zink, Rusticl and even the old Radeon drivers got some attention too.
-
AMD Unveils Instinct MI455X Accelerator and Helios Rack for AI
At the Advancing AI 2026 conference, Lisa Su announced the Instinct MI455X accelerator with 432 GB of HBM4 memory and the production-ready Helios platform.
-
AMD to invest up to $5 billion in Anthropic and supply it with computing power
AMD and Anthropic have announced a partnership: the chipmaker will invest up to $5 billion, while the maker of Claude will deploy up to 2 gigawatts of Instinct MI450 accelerators.
-
Bit2Watt: How a Cloud Tenant Can Rock the Power Grid Using GPUs
Researchers from Zhejiang University have shown that a cloud tenant, using nothing but ordinary GPU access, can modulate a data center's power draw and, in theory, destabilize the grid that feeds it — with no exploits and no hacking.
-
Moonshot AI Pauses New Subscriptions Amid Demand for Kimi K3
Chinese company Moonshot AI has temporarily halted new sign-ups: demand for its Kimi K3 model has run up against the limits of its computing capacity.
-
Microsoft Adds Hardware AV1 Encoding to Mesa via DirectX 12
Microsoft engineers have contributed support for hardware-accelerated AV1 video encoding on the GPU to the Mesa codebase. The implementation pairs DirectX 12 with the Hardware Media Foundation Transform (HMFT) from the Windows Media Foundation layer.