diff --git a/docs.it4i/cs/guides/grace.md b/docs.it4i/cs/guides/grace.md index 3266a505dcec5bab8483602ad3ce76d6f7e9fce7..8a9d694f87eeb45ecc0ec457924d70b6c342003f 100644 --- a/docs.it4i/cs/guides/grace.md +++ b/docs.it4i/cs/guides/grace.md @@ -23,7 +23,7 @@ The platform offers three toolchains: - [Clang for NVIDIA Grace](https://developer.nvidia.com/grace/clang) (installed in `/opt/nvidia/clang`) !!! note - The NVHPC toolchain showed strong results with minimal amount of tunning necessary in our initial evaluation. + The NVHPC toolchain showed strong results with minimal amount of tuning necessary in our initial evaluation. ### GCC Toolchain @@ -59,11 +59,11 @@ for(int i = 0; i < 1000000; ++i) { ``` !!! note - Our basic experiments show that fixed width vectorization (NEON) tends to perform better in the case of short (register-length) loops than SVE. In cases (like above), where specified `vectorize_width` is larger than avaliable vector unit width, Clang will emit multiple NEON instructions (eg. 4 instructions will be emitted to process 8 64-bit operations in 128-bit units of Grace). + Our basic experiments show that fixed width vectorization (NEON) tends to perform better in the case of short (register-length) loops than SVE. In cases (like above), where specified `vectorize_width` is larger than availiable vector unit width, Clang will emit multiple NEON instructions (eg. 4 instructions will be emitted to process 8 64-bit operations in 128-bit units of Grace). ### NVHPC Toolchain -The NVHPC toolchain handled aforementioned case without any additional tunning. Simple `-O3 -march=native -fast` should be therefore sufficient. +The NVHPC toolchain handled aforementioned case without any additional tuning. Simple `-O3 -march=native -fast` should be therefore sufficient. ## Basic Math Libraries @@ -84,7 +84,7 @@ The [NVPL](https://developer.nvidia.com/nvpl) package includes more extensive se - RAND: `-lnvpl_rand` or `-lnvpl_rand_mt` - SPARSE: `-lnvpl_sparse` -This package should be compatible with all avaliable toolchains and includes CMake module files for easy integration into CMake-based projects. For further documentation see also [NVPL](https://docs.nvidia.com/nvpl). +This package should be compatible with all availiable toolchains and includes CMake module files for easy integration into CMake-based projects. For further documentation see also [NVPL](https://docs.nvidia.com/nvpl). ## Basic Communication Libraries @@ -242,7 +242,7 @@ end program main ### Using NVHPC Toolchain -The C++ version of the example can be compiled with NVHPC and ran as folows +The C++ version of the example can be compiled with NVHPC and ran as follows ```console ml NVHPC