How can I implement a custom atomic function involving several variables?...

CUDA ptxas Error "function uses too much shared data"...

OpenCL including header causes ptxas fatal: Unresolved extern function...

How to overcome Stack size warning?...

How can I disable the ptxas warning about indeterminable stack size?...

What is the correct way to support `__shfl()` and `__shfl_sync()` instructions?...

What does the --abi-compile=yes option of CUDA ptxas do (which costs registers)?...

CUDA: --ptxas-options=-v shared memory and cudaFuncAttributes.sharedSizeBytes do not match...

NVCC separate compilation with PTX output...

Function properties for __internal_trig_reduction_slowpathd...

Debugging inline PTX in Parallel Nsight...

OpenCL: State space mismatch between instruction and address...

Avoiding unnecessary mov operations in inline PTX...

Strange results for profiled executed instructions and issued instructions in Fermi GPU (GTX 580)...