CUDA 13.4 samples update - v13.4-public

Release 13.4 of the CUDA Samples supported by CUDA Toolkit 13.4.
See Changelog for more information.
This commit is contained in:
Dheemanth
2026-09-09 15:07:08 -07:00
committed by GitHub
parent b7c5481c55
commit 5443602d89
871 changed files with 6843 additions and 321849 deletions

View File

@@ -27,6 +27,21 @@ This sample is optionally built as part of the libnvvm samples from the CUDA
samples tree. Please see the README file at the root of the libnvvm samples
for build instructions.
It requires the LLVM development headers and libraries, version 7 or newer.
LLVM 15 and newer emit opaque pointers, which libNVVM accepts only for
Blackwell and later architectures, so such a build cannot run on an older GPU:
$ ./cuda-c-linking
Using CUDA Device [0]: NVIDIA L4
Device Compute Capability: 8.9
This sample was built against LLVM 18, which emits opaque pointers, but
libNVVM accepts only LLVM 7 IR for compute_89. Build against LLVM 14 or
older to run on this device, or run on a Blackwell or later device.
The sample exits with code 2 in that case, reporting an unmet requirement
rather than a failure. Building against LLVM 7 to 14 produces a binary that
runs on any device this sample supports.
Usage
-----