Tensile¶
Tensile is a tool for creating benchmark-driven backend libraries for GEMMs, GEMM-like problems (such as batched GEMM), and general N-dimensional tensor contractions on a GPU. The Tensile library is mainly used as a backend library for rocBLAS. Tensile acts as the performance backbone for a wide variety of 'compute' applications running on AMD GPUs.
homepage: https://github.com/ROCm/Tensile
Available installations¶
| Tensile version | Supported CPU targets | Supported GPU targets | EESSI version | Module |
|---|---|---|---|---|
| 4.43.0 | generic: x86_64Arm: AMD: zen2, zen3, zen4, zen5Intel: haswell, skylake_avx512, sapphirerapids, icelake, cascadelake |
AMD: gfx1030, gfx1100, gfx1101, gfx1200, gfx1201, gfx908, gfx90a, gfx942 |
2025.06 | Tensile/4.43.0-rocm-compilers-19.0.0-ROCm-6.4.1 |
Extensions¶
Overview of extensions included in Tensile installations
joblib¶
joblib version |
Tensile modules that include it |
|---|---|
| 1.5.1 | Tensile/4.43.0-rocm-compilers-19.0.0-ROCm-6.4.1 |
msgpack¶
msgpack version |
Tensile modules that include it |
|---|---|
| 1.1.1 | Tensile/4.43.0-rocm-compilers-19.0.0-ROCm-6.4.1 |
rich¶
rich version |
Tensile modules that include it |
|---|---|
| 14.0.0 | Tensile/4.43.0-rocm-compilers-19.0.0-ROCm-6.4.1 |
Tensile¶
Tensile version |
Tensile modules that include it |
|---|---|
| 4.43.0 | Tensile/4.43.0-rocm-compilers-19.0.0-ROCm-6.4.1 |