gemm_strided: error: always_inline function '_mm256_setzero_pd' requires target feature 'xsave'

[timotheecour]

import pkg/laser/primitives/matrix_multiplication/gemm

#[
error:
/tmp/nim/nimcache/laser_gemm_ukernel_avx.c:416:10: error: always_inline function '_mm256_setzero_pd' requires target feature 'xsave', but would be inlined into function 'gebb_ukernel_float64_x86_AVX_Ecs27YPxbc6EG9arud9a0ZTQ' that is compiled without support for 'xsave'
        AB0_0 = _mm256_setzero_pd();
]#
proc test =
  let a = [[1.0, 2, 3],
           [1.0, 1, 1],
           [1.0, 1, 1]]

  let b = [[1.0, 1],
           [1.0, 1],
           [1.0, 1]]

  let ab = [[6.0, 6],
            [3.0, 3],
            [3.0, 3]]

  var res_ab: array[3, array[2, float]]
  gemm_strided(
    3, 2, 3,
    1.0,  a[0][0].unsafeAddr, 3, 1,
          b[0][0].unsafeAddr, 2, 1,
    0.0,  res_ab[0][0].addr,  2, 1
    )

when defined(case1):
  proc test =
    # todo: different numbers
    let p1 = 3
    let p2 = p1
    let p3 = p1

    type T = float

    var a = newSeq[T](p1 * p2)
    for i in 0..<a.len: a[i] = 1.0
    var b = newSeq[T](p2 * p3)
    for i in 0..<b.len: b[i] = 1.0
    var c = newSeq[T](p1 * p3)

    gemm_strided(
      p1, p2, p3, # CHECKME ; not sure if order correct, would be nice to document M,N,K in `gemm_strided`

      1.0,
      a[0].addr, p1, 1,
      b[0].addr, p2, 1,

      0.0,
      c[0].addr, p1, 1,
    )
    echo c

test()

[timotheecour]

workaround: use https://github.com/numforge/laser/blob/master/nim.cfg