Information on SSE4 including some whitepapers is available at www.intel.com/software/avx while SSE3 and SSE4 are both documented in the software developer manuals http://www.intel.com/products/processor/manuals/- I'd recommend you look mainly at volumes 2a and 2b for details of the instructions. Can you speak more of the problem you're trying to solve?
Thanks for your information.
Untill now, I am not use SSE3 and SSe4 in my application. I just want to have some knowledge about them. Whem I have further tests of them, maybe I will have some problems to share with you.
- Intel C++ Intrinsic Reference Document
-Intel C++ Compiler for Linux Systems User's Guide (search SSE/SSE2)
- Intel Pentium 4 & Xeon Processor Optimization Manual http://www.cs.grinnell.edu/~walker/courses/211.fa01/pentium-4-optimization.pdf Chapter 3 onwards.
- Refer Apple SIMD/Altivec website http://developer.apple.com/hardwaredrivers/ve/sse.html but don't get confused with SIMD & Altivec way of writing SSE programming.
I think abovefour should be sufficient to guide you in writing small SSE2 examples program and than latter move to Intel Vol-I & II Instructions Manual for better understanding OR try referring in between for any doubts related to definition of any instructions.
Perform google search too if needed apart from above 4 helps.