Parallel Thread Execution
PulseAugur coverage of Parallel Thread Execution — every cluster mentioning Parallel Thread Execution across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Hand-written PTX kernels show significant speedups for INT8/INT4 GEMM on NVIDIA L4 GPUs
A new research paper explores the performance benefits of using hand-written PTX (Parallel Thread Execution) kernels for GEMM (General Matrix Multiply) operations on NVIDIA L4 GPUs, compared to the standard WMMA (Warp M…
-
Tessera system unlocks heterogeneous GPUs for AI workloads
A new system called Tessera has been developed to improve the performance and cost-efficiency of running large AI models on heterogeneous GPU clusters. Unlike previous methods that operated at a coarse granularity, Tess…
-
Open-source Nvidia Vulkan driver NVK adds experimental DLSS support on Linux
The open-source Vulkan driver NVK, developed for Nvidia GPUs on Linux, has introduced experimental support for Nvidia's DLSS upscaling technology. This integration is achieved by loading pre-compiled CUDA binaries direc…
-
Ex-OpenAI Tech Lead Joins SemiAnalysis to Find GPU Compiler Bugs
Former OpenAI Tech Lead Justin Lebar has joined SemiAnalysis as a Visiting Fellow. In this role, he will focus on identifying bugs within AMDGPU LLVM, x86 LLVM, and NVPTX. The project aims to discover numerous vulnerabi…
-
WAVE project creates unified GPU ISA for cross-vendor compatibility
A new portable GPU instruction set architecture (ISA) called WAVE has been developed, aiming to unify programming across different hardware vendors. WAVE abstracts common functionalities found in NVIDIA, AMD, and Intel …
-
NVIDIA releases experimental Rust-to-CUDA compiler backend
NVIDIA AI researchers have introduced cuda-oxide, an experimental compiler that enables developers to write GPU kernels in Rust and compile them directly to PTX, NVIDIA's intermediate representation for GPUs. This new t…