Latest about CUDA
DeepSeek's AI breakthrough bypasses industry-standard CUDA for some functions, uses Nvidia's assembly-like PTX programming instead
DeepSeek used PTX ISA to fine-tune its AI model training.
CUDA-beating ZLUDA breathes new life with financial backing from unknown party — pivots to AI workloads across multiple GPU vendors
ZLUDA, a CUDA translation layer, gets new funding and therefore refocuses to AI software and multiple GPU vendors support.
AMD asks developer to take down open source ZLUDA, dev vows to rebuild his project
Developer of ZLUDA translation layer vows to rebuild the CUDA translation layer as AMD demands to take down open source code developed with its funding.
New SCALE tool enables CUDA applications to run on AMD GPUs
New SCALE software allows to run CUDA code on AMD processors.
Nvidia bans using translation layers for CUDA software to run on other chips
Nvidia doesn't allow running CUDA software with translation layers on other platforms with its licensing agreement. This move appears to specifically target ZLUDA along with some Chinese GPU makers.
Jim Keller criticizes Nvidia's CUDA and x86, calls both 'a swamp'
Legendary processor architecture designer criticizes CUDA and compares it to x86.
AMD-Friendly AI LLM Developer Jokes About Nvidia GPU Shortages
Nvidia’s GPU oven is too slow, but there are fresh AMD GPUs on the grill.
Nvidia to Reportedly Triple Output of Compute GPUs in 2024: Up to 2 Million H100s
Nvidia to massively increase production of compute GPUs for AI and HPC applications in 2024, a report claims.
