diff options
Diffstat (limited to 'libraries/libxsmm/README')
| -rw-r--r-- | libraries/libxsmm/README | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/libraries/libxsmm/README b/libraries/libxsmm/README new file mode 100644 index 0000000000..cda6921175 --- /dev/null +++ b/libraries/libxsmm/README @@ -0,0 +1,15 @@ + LIBXSMM is a library for specialized dense and sparse matrix +operations as well as for deep learning primitives such as small +convolutions. The library is targeting Intel Architecture with +Intel SSE, Intel AVX, Intel AVX2, Intel AVX512 (with VNNI and +Bfloat16), and Intel AMX (Advanced Matrix Extensions) supported by +future Intel processor code-named Sapphire Rapids. Code generation +is mainly based on Just-In-Time (JIT) code specialization for +compiler-independent performance (matrix multiplications, matrix +transpose/copy, sparse functionality, and deep learning). +LIBXSMM is suitable for "build once and deploy everywhere", +i.e., no special target flags are needed to exploit the available +performance. Supported GEMM datatypes are: FP64, FP32, bfloat16, +int16, and int8. + +NOTE: the library does not support 32-bit architecture (64-bit only) |