Hi all

Intel is releasing Core i7 and I am curious if this has any effect on Manta development.

It is heralded that the SSE 4.2 instruction set is great for media transcoding and 3D graphics:

(http://www.extremetech.com/article2/0,2845,2333766,00.asp)

But it seems among those instructions (taken from Wikipedia)

CRC32  Accumulate CRC32C value using the polynomial 0x11EDC6F41 (or, without the high order bit, 0x1EDC6F41).[5]

PCMPESTRI     Packed Compare Explicit Length Strings, Return Index

PCMPESTRM    Packed Compare Explicit Length Strings, Return Mask

PCMPISTRI      Packed Compare Implicit Length Strings, Return Index

PCMPISTRM     Packed Compare Implicit Length String, Return Mask

PCMPGTQ        Compare Packed Data For Greater Than

POPCNT           Population count (count number of bits set to 1) - bit manipulation; shares the same opcode for JMPE, the instruction used in Itanium CPUs to escape from IA-32 mode. POPCNT instruction may also be implemented in some processors that do not support the other SSE4 instructions and a separate bit can be tested to confirm POPCNT presence.

Most are related to string manipulation. Of course, being not an expert on SSE instructions I may not be seeing the direct applications.

It seems in this new CPU we do not need to align on cache boundaries. I wonder if it is worth to #ifdef out the current cache boundary check everywhere where SSE is present.

Also, it seems the new CPU handles hyperthreading to initiate multiple threads on one CPU. Does this mean these threads are really executing in parallel rather than the cpu constantly hopping from one to the other? Perhaps it is not very relevant to our purposes?

In general, I would be interested to know if and how we can utilize any new features to accelerate Manta further, the approximate gains we can expect, and if the core team has any plans to make the relevant changes.

Thanks

Bo