| |keywords=NVIDIA, Jetson,Tegra, TX1,TX2, AI,Deep Learning, GStreamer,CUDA, CUDA optimisation, RidgeRun, NVIDIA CUDA, CUDA Optimisation guide, profiling, memory profiling, CUDA Memcheck, CUDA Profiler, GPU Architecture, Execution process, Memory hierarchy, Correct memory access patterns, Inter-thread communication, Increase arithmetic intensity, Function approximation, Condition and loops replacement, Inlining, Common pitfalls when optimising, Communication and Concurrency, NVIDIA Jetson, NVIDIA TX1, NVIDIA TX2, Xavier, NVIDIA Xavier, Jetson Nano, Jetson AGX Xavier, Jeston Xavier NX, Xavier NX, Jetson Xavier, NVIDIA Jetson Orin, Jetson Orin, Orin, {{{keywords|}}} | | |description={{{description|This guide from RidgeRun explains the GPU Architecture, a common workflow for optimisation, pitfalls when optimising and the case studies.}}} |
| <seo title="{{{title|RidgeRun CUDA Optimisation Guide - {{SUBPAGENAME}}}}}" titlemode="replace" metakeywords="NVIDIA, Jetson,Tegra, TX1,TX2, AI,Deep Learning, GStreamer,CUDA, CUDA optimisation, RidgeRun, NVIDIA CUDA, CUDA Optimisation guide, profiling, memory profiling, CUDA Memcheck, CUDA Profiler, GPU Architecture, Execution process, Memory hierarchy, Correct memory access patterns, Inter-thread communication, Increase arithmetic intensity, Function approximation, Condition and loops replacement, Inlining, Common pitfalls when optimising, Communication and Concurrency, NVIDIA Jetson, NVIDIA TX1, NVIDIA TX2, Xavier, NVIDIA Xavier, Jetson Nano, Jetson AGX Xavier, Jeston Xavier NX, Xavier NX, Jetson Xavier, NVIDIA Jetson Orin, Jetson Orin, Orin, {{{metakeywords|}}}" metadescription="{{{metadescription|RidgeRun CUDA Optimisation Guide.}}}"></seo>
| |
