CUDA: Is It Possible to Use All of 48KB of On-Die Memory As Shared Memory?...

Performance of atomic operations on shared memory...

Shared memory bandwidth Fermi vs Kepler GPU...

GPU Shared Memory Bank Conflict...

Can I use in my code shared memory for nVidia Quadro KxxxxM (MXM) mobile GPUs?...

How to efficiently perform load and bitwise operation using GPGPU?...

Are needless write operations in multi-thread kernels in CUDA inefficient?...

Does CUDA broadcast shared memory to all threads in a block without a bank conflict?...

CUDA Driver API vs. CUDA runtime...

Can I use a single address space for the GPU, CPU and FPGA look like to CUDA UVA?...

CUDA placement new and virtual functions...

Disassemble an OpenCL kernel?...

Blockwise/Strided reduction using CUDA...

Nsight Compute says: "Profiling is not supported on this device" - why?...

Aberth–Ehrlich method GPU implementation...

Error compiling Cuda - expected primary-expression...

Is there a way to block and unblock a CUDA stream arbitrarily?...

Is it possible to execute more than one CUDA graph's host execution node in different streams co...

Atomic swap on more than one number in an HLSL Compute Shader?...

How are registers allocated to threads inside a GPU?...

Do integrated GPUs in CPUs have the overhead of transferring data over the PCIe bus just like transf...

How to get instruction cost in NVIDIA GPU？...

Retaining dot product on GPGPU using CUBLAS routine...

Optimising Monte-Carlo algorithm | Reduce operation on GPU & Eigenvalues problem | Many-body pro...

A single GPU thread is faster than running the same on CPU?...

What is the context switching mechanism in GPU?...

Memory issue in running multiple processes on GPU...

Time-sliced GPU scheduler...

SyCL ComputeCpp: how to support both SPIR and PTX bitcode at runtime...

Why do CUDA kernels have to check `if (index < n)` before doing anything?...