fn compute_rhs_inplace(
chi: &[f32],
w: &[Complex32],
b0: &[Complex32],
d_kernel: &[f32],
mx: &[f32],
my: &[f32],
mz: &[f32],
vr: &[f32],
lambda: f32,
rhs: &mut [f32],
ws: &mut MediWorkspace,
)Expand description
Compute RHS in-place using workspace buffers (f32) Uses per-direction gradient masks (mx, my, mz) matching MATLAB MEDI SIMD-accelerated for element-wise operations