Hi, Sergey,

thanks for the patch! LGTM with a minor comment.

I propose to add a small description to the comment. Something like this:

The test runs a part of the Lua version of SciMark 2.0a, which is a 
benchmark for scientific and numerical computing developed by 
programmers at the NIST (National Institute of Standards and 
Technology). This test is made up of  dense LU matrix factorization 
benchmarks.

Sergey

On 10/24/25 13:50, Sergey Kaplun wrote:
> This patch adjusts the aforementioned test to use the benchmark
> framework introduced before. The default arguments are adjusted
> according to the <PARAM_x86.txt> file. The arguments to the script still
> can be provided in the command line run.
>
> Checks are omitted since they were not present in the original suite,
> plus the precise result value depends on the input parameter.
> ---
>   perf/LuaJIT-benches/scimark-lu.lua | 20 +++++++++++++++++++-
>   1 file changed, 19 insertions(+), 1 deletion(-)
>
> diff --git a/perf/LuaJIT-benches/scimark-lu.lua b/perf/LuaJIT-benches/scimark-lu.lua
> index 7636d994..4f521e0b 100644
> --- a/perf/LuaJIT-benches/scimark-lu.lua
> +++ b/perf/LuaJIT-benches/scimark-lu.lua
> @@ -1 +1,19 @@
> -require("scimark_lib").LU(100)(tonumber(arg and arg[1]) or 5000)
> +local bench = require("bench").new(arg)
> +
> +local cycles = tonumber(arg and arg[1]) or 5000
> +
> +local benchmark
> +benchmark = {
> +  name = "scimark_lu",
> +  -- XXX: The description of tests for the function is too
> +  -- inconvenient.
> +  skip_check = true,
> +  payload = function()
> +    local flops = require("scimark_lib").LU(100)(cycles)
> +    benchmark.items = flops
> +  end,
> +}
> +
> +bench:add(benchmark)
> +
> +bench:run_and_report()