I want to optimize a computationally intensive loop using SIMD instructions on an Intel Core i7 `12700K` processor and 32GB of DDR4 `3200` memory , to boost the performance for a double precision floating point vector addition operation within a larger scientific computation

section .data
data_array: dq 1.0, 2.0, 3.0, 4.0, ..., 1000000.0  ; Array of 1 million double-precision values

section .text
global my_function

my_function:
  mov rcx, 1000000 / 4  ; Loop counter (number of 128-bit chunks)
  mov rsi, data_array

loop_start:
  movups xmm0, [rsi]
  movups xmm1, [rsi + 16]
  addps xmm0, xmm1
  movups [rsi], xmm0
  add rsi, 32
  dec rcx
  jnz loop_start
  ret