I was following the instructions to use SVML here https://numba.readthedocs.io/en/stable/user/performance-tips.html#intel-svml, but cannot get SVML operational. Is there something I'm missing?
Steps:
# using uv 0.9.24 on a blank directory
uv init --python 3.13
uv add numba==0.63.1 intel-complr-lib-rt==2025.3.1 pip
# installs numba==0.63.1, llvmlite==0.46.0, numpy==2.3.5, intel-cmplr-lib-rt==2025.3.1
# pip is needed for `numba -s` to introspect the environment
uv run numba -s
Output (truncated)
__Hardware Information__
Machine : x86_64
CPU Name : tigerlake
__OS Information__
Platform Name : Linux-6.6.87.2-microsoft-standard-WSL2-x86_64-with-glibc2.39
Platform Release : 6.6.87.2-microsoft-standard-WSL2
OS Name : Linux
OS Version : #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025
OS Specific Version : ?
Libc Version : glibc 2.39
__Python Information__
Python Compiler : Clang 21.1.4
Python Implementation : CPython
Python Version : 3.13.11
Python Locale : C.UTF-8
__Numba Toolchain Versions__
Numba Version : 0.63.1
llvmlite Version : 0.46.0
__LLVM Information__
LLVM Version : 20.1.8
__SVML Information__
SVML State, config.USING_SVML : False
SVML Library Loaded : False
llvmlite Using SVML Patched LLVM : False
SVML Operational : False
__Numba Environment Variable Information__
None found.
__Conda Information__
Conda not available.
__Installed Packages__
Package Version
------------------ --------
intel-cmplr-lib-rt 2025.3.1
llvmlite 0.46.0
numba 0.63.1
numpy 2.3.5
pip 25.3
I was following the instructions to use SVML here https://numba.readthedocs.io/en/stable/user/performance-tips.html#intel-svml, but cannot get SVML operational. Is there something I'm missing?
Steps:
Output (truncated)