Repository Issue Activity (beta)

#409 Potential bug in simpleVulkan example

#411 Improve matrixMul Tiling to support non-multiple BLOCK_SIZE dimensions in matrixMul.cu .

#413 Missing check for CUDA failure in example

#417 Request for Official CUDA support for Ubuntu 26.04 LTS (release timeline for native installer/apt repo)

#418 Sample proposal: persistent kernel for tiny-model autoregressive inference (microGPT, ~4k MACs/token)

#433 CUDA 13.2.1 libcudart causes SIGSEGV in cuInit on WSL2 (Driver 596.49, Blackwell)

#437 helloTile: per-sample build fails on Ubuntu/Debian/Fedora — _FORTIFY_SOURCE rewrites printf to a non-tile-callable __printf_chk (v13.3)

#438 4_CUDA_Libraries: cmake -S cpp fails — CUDA language not enabled for the subtree, so cuda_std_17 is unresolvable for 24 leaves (v13.3)

#439 CUDA Tile 1.3: store_masked crashes on element-wise-computed tiles

#442 Problem building deviceQuery with Ubuntu 26.04 package cuda-toolkit-13-1

#444 Suggestion: Add roofline/arithmetic-intensity analysis to matrixMul samples

#446 cmake add_custom_command() is not passing the ccbin flag to nvcc for the Fatbin and PTX cuda samples

#447 Question: readiness for Windows ARM?

#449 p2pBandwidthLatencyTest shows large run-to-run variance with P2P enabled due to low repeat count

#64 Why do the Vulkan interop examples not do ownership transfers?

#128 CUDA 11.7 support.

#129 Update solvers to use SpSv instead of other deprecated functions

#140 Vulkan Semaphores

#162 A bug of 3_CUDA_Features/cdpQuadtree

#249 Performance comparison in sample alignedTypes not significant

#240 Maybe there is an error in Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy.cu?

#230 What the meaning of 'CPU latency' in p2pBandwidthLatencyTest ?

#200 All Cuda samples vcxproj have the same ProjectGuid causing bad performance in VS IDE

#197 cufftXtMemcpy device to device would change data value(simpleCUFFT_2d_MGPU)?

#192 Cudla input Tensort, output Tensort data layout, quantization, and inverse quantization issues