Hi,
is there an optimization for 64 bit CPUs in process?

Sorry for my bad english..

---

Hi,
is there an optimization for 64 bit CPUs in process?

Sorry for my bad english..

no-one answers my posts,
is my english so bad?^^

---

Hi,

I'm not a member of the project, but I don't think there will be a 64-bit version of most of the scientific projects, because all the "real work" is FLOATING POINT operations.

A much better options would be a SSE-enabled version of Rosetta, which should speed overall projects TeraFLOPS up by 3.5x - 4x times, as F@H experience has shown the last few years.

---

Hi,

I'm not a member of the project, but I don't think there will be a 64-bit version of most of the scientific projects, because all the "real work" is FLOATING POINT operations.

A much better options would be a SSE-enabled version of Rosetta, which should speed overall projects TeraFLOPS up by 3.5x - 4x times, as F@H experience has shown the last few years.

Assuming the type of coding is similar to F@H you may do, although over at FaD which was mainly single precision FP ops and was already optimised by intel at the initial stages, compiling for SSE or SSE2 gained little or no benefit. So SSE was always turned off (MMX may even have been turned off).

As for 64bit, well it would be a nice thing (as in run natively).
But you would think solaris and MAC-intel would come first as they are official BOINC platforms ;-)

... I think there is already this suggestion in Feedback as it's not a current test....

---

I don't know the application at all, but the AMD64 ABIs use the SSE registers to pass arguments around. Moreover, many math transcendentals are implemented in routines which are faster and more precise than the equivalent x87 instructions.

HTH

---

As for 64bit, well it would be a nice thing (as in run natively).
But you would think solaris and MAC-intel would come first as they are official BOINC platforms ;-)

... I think there is already this suggestion in Feedback as it's not a current test....

Things might begin to change next year, as it's already been mentioned that Conroe (Intel's to be replacement for the Pentium 4), not only will drop the whole net-burst arch, but will be a 64-bit x86 processor as well. Conroe will also be dual proc... Given the A64s/x2s, as well as Conroe supplying x86-64 procs from both Intel as well as AMD, I imagine a look at 64-bit software support will begin to increase. Afterall, when both PC proc manufacturers will be supporting it...

The only aside that leaves is the OS, and on the Windows sphere, and unlike winXP, Vista will be compiled with both 32-bit and 64-bit variants (which would run native 64-bit on both the A64s as well as the up-comming Conroe), right out the gate. Won't be like XP-64 which was made sometime latter...

I do suspect that after Conroe, as well as Vista make there appearance, we might begin to see a change here. In part, because people will probably start getting 64-bit systems straight from Dell and other OEMs...

---

I have my 64-bit Vista computer now, and no 64-bit boinc or 64-bit rosetta.

It's not like I am advocating that there would be a major decrease in completion times, I just like seeing one less task on my 32-bit Emulator.

I know it's a stupid reason.. but hey?

---