/* https://cirosantilli.com/linux-kernel-module-cheat#x86-sse-packed-arithmetic-instructions */ #include LKMC_PROLOGUE .data /* Unlike MOVAPS, we don't need to align memory here. */ input: .float 1.5, 2.5, 3.5, 4.5 .bss output: .skip 16 .text movups input, %xmm0 movups %xmm0, %xmm1 movups %xmm1, output LKMC_ASSERT_MEMCMP(input, output, $16) LKMC_EPILOGUE