Hi Eljay, thank you very much for your response. > A quick Google search indicates that the Pentium 4 does not > natively support 128-bit floating point arithmetic. It does I'm sorry that I did not check more deeply, you are right. Pentium 4 (including Prescott) supports just SIMD on two doubles or 4 floats. However, what about Athlon64? On web page http://www.devx.com/amd/Article/17962 there is mentioned that "New native instructions for 64-bit integer and 128-bit floating- point arithmetic" On the other hand, I have checked the set of instructions for Athlon64 and it does not seem that it supports 128-bit floating point arithmetic. Any comments on this? Which processors supports 128-bit floating point arithmetic? I just know about sparc64, pa64, ia64-hpux and alpha-osf5. Thank you very much! Jirka
