From e8b0edf1ee639b3d36a0e7ab8f480ed8436adef2 Mon Sep 17 00:00:00 2001 From: "Ralf W. Grosse-Kunstleve" Date: Thu, 8 Oct 2026 15:52:12 -0700 Subject: [PATCH] docs: refresh moved sample reference links (cherry picked from commit 30a628161c82d6dd6ef419b33d56290fce1d8dd5) --- .../3_CUDA_Features/globalToShmemAsyncCopy/README.md | 4 ++-- samples/cuda_core/binarySearch/README.md | 2 +- samples/cuda_core/cudaComputeLambdas/README.md | 2 +- samples/cuda_core/launchConfigTuning/README.md | 2 +- samples/cuda_core/pageRank/README.md | 2 +- samples/cuda_core/simplePrint/README.md | 2 +- samples/cuda_core/tmaTensorMap/README.md | 2 +- 7 files changed, 8 insertions(+), 8 deletions(-) diff --git a/samples/cuda_bindings/3_CUDA_Features/globalToShmemAsyncCopy/README.md b/samples/cuda_bindings/3_CUDA_Features/globalToShmemAsyncCopy/README.md index 0184db06812..8108cb6a154 100644 --- a/samples/cuda_bindings/3_CUDA_Features/globalToShmemAsyncCopy/README.md +++ b/samples/cuda_bindings/3_CUDA_Features/globalToShmemAsyncCopy/README.md @@ -113,5 +113,5 @@ Result = PASS - [CUDA Python Documentation](https://nvidia.github.io/cuda-python/) - [`samples/cuda_core/matrixMulSharedMem/`](../../../cuda_core/matrixMulSharedMem/) - basic tiled GEMM (no async copy) - [CUDA C++ Programming Guide — Asynchronous Data Copies](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#asynchronous-data-copies) -- [`libcudacxx` `cuda::memcpy_async`](https://nvidia.github.io/libcudacxx/extended_api/asynchronous_operations/memcpy_async.html) -- [`libcudacxx` `cuda::pipeline`](https://nvidia.github.io/libcudacxx/extended_api/synchronization_primitives/pipeline.html) +- [`libcudacxx` `cuda::memcpy_async`](https://nvidia.github.io/cccl/unstable/libcudacxx/extended_api/asynchronous_operations/memcpy_async.html) +- [`libcudacxx` `cuda::pipeline`](https://nvidia.github.io/cccl/unstable/libcudacxx/extended_api/synchronization_primitives/pipeline.html) diff --git a/samples/cuda_core/binarySearch/README.md b/samples/cuda_core/binarySearch/README.md index de03e8c652d..a9fa1876e96 100644 --- a/samples/cuda_core/binarySearch/README.md +++ b/samples/cuda_core/binarySearch/README.md @@ -29,7 +29,7 @@ diverge on present values). Results are verified against ## Key Libraries -- [`cuda.compute`](https://nvidia.github.io/cccl/python.html) (from the `cuda-cccl` package) - device algorithms +- [`cuda.compute`](https://nvidia.github.io/cccl/unstable/python/compute/index.html) (from the `cuda-cccl` package) - device algorithms - [`cuda.core`](https://nvidia.github.io/cuda-python/cuda-core/latest/) - device setup - `cupy` - device buffers - `numpy` - host-side reference via `numpy.searchsorted` diff --git a/samples/cuda_core/cudaComputeLambdas/README.md b/samples/cuda_core/cudaComputeLambdas/README.md index 120da5a780e..3ef683b353a 100644 --- a/samples/cuda_core/cudaComputeLambdas/README.md +++ b/samples/cuda_core/cudaComputeLambdas/README.md @@ -30,7 +30,7 @@ The sample exercises three algorithm families: ## Key Libraries -- [`cuda.compute`](https://nvidia.github.io/cccl/python.html) (from the `cuda-cccl` package) - device algorithms and JIT-compiled Python ops +- [`cuda.compute`](https://nvidia.github.io/cccl/unstable/python/compute/index.html) (from the `cuda-cccl` package) - device algorithms and JIT-compiled Python ops - [`cuda.core`](https://nvidia.github.io/cuda-python/cuda-core/latest/) - device setup - `cupy` - device buffers - `numpy` - scalar init values and host-side verification diff --git a/samples/cuda_core/launchConfigTuning/README.md b/samples/cuda_core/launchConfigTuning/README.md index f0590021860..849744d3a31 100644 --- a/samples/cuda_core/launchConfigTuning/README.md +++ b/samples/cuda_core/launchConfigTuning/README.md @@ -183,6 +183,6 @@ specific kernel characteristics. Always benchmark to find the best! - [cuda.core Documentation](https://nvidia.github.io/cuda-python/cuda-core/latest/) - [cuda.core.LaunchConfig](https://nvidia.github.io/cuda-python/cuda-core/latest/generated/cuda.core.LaunchConfig.html) -- [CUDA Occupancy Calculator](https://docs.nvidia.com/cuda/cuda-occupancy-calculator/) +- [Nsight Compute Occupancy Calculator](https://docs.nvidia.com/nsight-compute/NsightCompute/index.html#occupancy-calculator) - [CUDA Best Practices Guide - Execution Configuration](https://docs.nvidia.com/cuda/cuda-c-best-practices-guide/index.html#execution-configuration-optimizations) - [Nsight Compute Profiler](https://developer.nvidia.com/nsight-compute) diff --git a/samples/cuda_core/pageRank/README.md b/samples/cuda_core/pageRank/README.md index b37fc2a06d7..63ad39f8c4d 100644 --- a/samples/cuda_core/pageRank/README.md +++ b/samples/cuda_core/pageRank/README.md @@ -181,4 +181,4 @@ RAPIDS cuGraph provides production-grade, GPU-accelerated graph analytics: - [RAPIDS cuGraph Documentation](https://docs.rapids.ai/api/cugraph/stable/) - [cuGraph GitHub Repository](https://github.com/rapidsai/cugraph) -- [RAPIDS Installation Guide](https://rapids.ai/start.html) +- [RAPIDS Installation Guide](https://docs.nvidia.com/datascience/install/) diff --git a/samples/cuda_core/simplePrint/README.md b/samples/cuda_core/simplePrint/README.md index 3ff97645176..1e2550f1c66 100644 --- a/samples/cuda_core/simplePrint/README.md +++ b/samples/cuda_core/simplePrint/README.md @@ -260,4 +260,4 @@ Try modifying: ### CUDA References: - [CUDA C Programming Guide - Printf](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#formatted-output) -- [C++ simplePrintf Sample](https://github.com/NVIDIA/cuda-samples/tree/master/Samples/0_Introduction/simplePrintf) +- [C++ simplePrintf Sample](https://github.com/NVIDIA/cuda-samples/tree/master/cpp/0_Introduction/simplePrintf) diff --git a/samples/cuda_core/tmaTensorMap/README.md b/samples/cuda_core/tmaTensorMap/README.md index a5797b48c4a..6ab4be27ce3 100644 --- a/samples/cuda_core/tmaTensorMap/README.md +++ b/samples/cuda_core/tmaTensorMap/README.md @@ -135,4 +135,4 @@ replace_address verified: descriptor reused with new source tensor - [CUDA Python Documentation](https://nvidia.github.io/cuda-python/) - [TMA in the CUDA C++ Programming Guide](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#tensor-memory-accelerator) -- [`cuda::barrier` reference](https://nvidia.github.io/cccl/libcudacxx/extended_api/synchronization_primitives/barrier.html) +- [`cuda::barrier` reference](https://nvidia.github.io/cccl/unstable/libcudacxx/extended_api/synchronization_primitives/barrier.html)