Store 128-bits (composed of 4 packed single-precision (32-bit) floating-point elements) from
as into memory using a non-temporal memory hint. mem_addr must be aligned on a 16-byte
boundary or a general-protection exception may be generated.
Note: non-temporal stores should be followed by _mm_sfence() for reader threads.
Store 128-bits (composed of 4 packed single-precision (32-bit) floating-point elements) from as into memory using a non-temporal memory hint. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated. Note: non-temporal stores should be followed by _mm_sfence() for reader threads.