diff options
author | Jason Henline <jhen@google.com> | 2016-08-26 19:55:32 +0000 |
---|---|---|
committer | Jason Henline <jhen@google.com> | 2016-08-26 19:55:32 +0000 |
commit | f14306b01e505a7442257b2f3df5b86ebc69b69e (patch) | |
tree | 3bd9a752ea030a8771c4492f672e03ef668c1783 /parallel-libs | |
parent | 0e52c92e22eeb7d5b99bc711c467a129154ade09 (diff) |
[StreamExecutor] Fix KernelSpec Doxygen
Summary:
There was a typo where \endcode was spelled as \encode and it was
keeping the whole file document from rendering. I also added in some \c
annotations for inline code stuff to make it look nicer.
Reviewers: jprice
Subscribers: parallel_libs-commits
Differential Revision: https://reviews.llvm.org/D23941
llvm-svn: 279855
Diffstat (limited to 'parallel-libs')
-rw-r--r-- | parallel-libs/streamexecutor/include/streamexecutor/KernelSpec.h | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/parallel-libs/streamexecutor/include/streamexecutor/KernelSpec.h b/parallel-libs/streamexecutor/include/streamexecutor/KernelSpec.h index 110c803258f5..14c0c105c21f 100644 --- a/parallel-libs/streamexecutor/include/streamexecutor/KernelSpec.h +++ b/parallel-libs/streamexecutor/include/streamexecutor/KernelSpec.h @@ -31,9 +31,9 @@ /// the user. A simplified example workflow which a compiler might follow in the /// case of a CUDA kernel that is compiled to CUDA fatbin code is as follows: /// -/// 1. The user defines a kernel function called UserKernel. +/// 1. The user defines a kernel function called \c UserKernel. /// 2. The compiler compiles the kernel code into CUDA fatbin data and embeds -/// that data into the host code at address __UserKernelFatbinAddress. +/// that data into the host code at address \c __UserKernelFatbinAddress. /// 3. The compiler adds code at the beginning of the host code to instantiate a /// MultiKernelLoaderSpec: /// \code @@ -43,16 +43,16 @@ /// \endcode /// 4. The compiler then adds code to the host code to add the fatbin data to /// the new MultiKernelLoaderSpec, and to associate that data with the kernel -/// name "UserKernel": +/// name \c "UserKernel": /// \code /// namespace compiler_cuda_namespace { /// UserKernelLoaderSpec.addCUDAFatbinInMemory( /// __UserKernelFatbinAddress, "UserKernel"); /// } // namespace compiler_cuda_namespace -/// \encode +/// \endcode /// 5. The host code, having known beforehand that the compiler would initialize /// a MultiKernelLoaderSpec based on the name of the CUDA kernel, makes use -/// of the symbol cudanamespace::UserKernelLoaderSpec without defining it. +/// of the symbol \c cudanamespace::UserKernelLoaderSpec without defining it. /// /// In the example above, the MultiKernelLoaderSpec instance created by the /// compiler can be used by the host code to create StreamExecutor kernel |