![]() |
|
|
#12 |
|
Sep 2002
66210 Posts |
Wow, under 1 day 2^67 TF is already being done !
I thought it needed about a 3.6 GHz but the SSE2 instructions on a P4 must be quite efficient. A friend who is also doing TF is going to build a new machine this may influence what chip/speed he gets. I have been very curious about TF speeds and which CPU's are best, but I don't have access to any PCs with SSE2. All the posts have given really good information and insight. Thanks I wonder if the Opteron/Athlon64 will be this quick or if raw clock speed will dominate ? |
|
|
|
|
|
#13 |
|
Sep 2002
2·331 Posts |
What are the facts on integer / FP x87 / int x87 / FP SSE2 / int SSE2 ?
I noticed the x87 has a 64 bit signed integer format and the SSE2 has 64 and 128 integer support. What is used at what levels ? Does it start as 64 bit integer up to 2^62 using 2 32 bit registers ? Switch to x87 then at 2^64 or 2^65 go to SSE2 if available ? Is the SSE2 using integer or floating point ? Would a Prime95 lite ( just the TF code, interface could remain the same ) be more efficient ? ( a much smaller exe that could remain in the cache ) Or is the code for TF small enough that the section that does the TF can stay in the cache L1, L2 ? |
|
|
|
![]() |
| Thread Tools | |
Similar Threads
|
||||
| Thread | Thread Starter | Forum | Replies | Last Post |
| Trial Factor Assignment Time Limits | Judge Hale | Information & Answers | 12 | 2015-07-11 23:48 |
| How many bits does/did the server trial factor to? | Jayder | Information & Answers | 6 | 2015-01-25 03:29 |
| Trial Factor Bit Depth | lavalamp | Operation Billion Digits | 8 | 2010-08-02 18:49 |
| trial division over a factor base | Peter Hackman | Factoring | 7 | 2009-10-26 18:27 |
| P95 Trial Factor speeds 40M vs 100M | harlee | Software | 3 | 2006-10-15 04:38 |