Short WUs (20.40 credit sized) are being done in 2,972.94 with 4.17
Previously with 4.10 the best I got was 3,640.14
System is Pentium 4 2.66 (with sse2 capability) and 768 megs ram running Gentoo Linux 2.6.17-r4 and BOINC plus all deps, kernel etc have been compiled from source.
Cheers - Gray
PS: no errors due to the application thus far - and now I know how to change file ownership there should be no more human errors either (grin)
cruch times for a long WU went from about 9 hours (4.01) to about 8 hours with both 4.16 and 4.17 on an AMD Athlon(tm) XP 2000+, 256 mb memory, Linux fc3.
4.16 amd 4.17 results are all within a few minutes of each other.
Good morning everybody. Here are my first results obtained under beta 4.17
AuthenticAMD mobile AMD Athlon XP-M 2400+ Linux 2.6.8-24.24-default (Suse 9.2)
Computation times ( in seconds )
v4.01 average: 31881.45 v4.01 std dev: 775.56 [sample of 15 results]
v4.16 average: 27903.87 v4.16 std dev: 301.39 [sample of 5 results]
v4.17 average: 28109.39 v4.17 std dev: 185.97 [sample of 2 results]
Compare v4.16/v4.01 = 12.48% faster
Compare v4.17/v4.01 = 11.83% faster
Compare v4.17/v4.16 = -0.74% slower
Caution ! I need 1 more result before calculating acurate average time and std deviation.
However, first data ocuring for an Athlon 64 3500+ tends to show an even greater loss of speed of v4.17 vs 4.16 [about -2 %]
"Patience et longueur de temps font mieux que force et que rage"
La Fontaine
"Entia non sunt multiplicandam praeter necessitatem" (OKHAM)
Hello Short WUs (20.40
)
Hello
Short WUs (20.40 credit sized) are being done in 2,972.94 with 4.17
Previously with 4.10 the best I got was 3,640.14
System is Pentium 4 2.66 (with sse2 capability) and 768 megs ram running Gentoo Linux 2.6.17-r4 and BOINC plus all deps, kernel etc have been compiled from source.
Cheers - Gray
PS: no errors due to the application thus far - and now I know how to change file ownership there should be no more human errors either (grin)
Hi. Just finished my first
)
Hi.
Just finished my first result using v4.17.
37950001 CPU time: 23,695.24s (claim: 174.58)
The last result using v4.01
37663847 CPU time: 25,847.26s (claim: 172.32)
The speedup is approx. 9%. CPU is AMD X2 3800+.
Michael
Team Linux Users Everywhere
4.17 is about 5% slower than
)
4.17 is about 5% slower than 4.16 on my Pentium II, while 4.16 was 7% faster than 4.01. So I only gain 2%.
Tullio
8 results in and they are
)
8 results in and they are around 18,900 sec, about 17% faster than 4.01.
All still pending.
20-30 small x in each.
Opteron 170 @2.4gig.
cruch times for a long WU
)
cruch times for a long WU went from about 9 hours (4.01) to about 8 hours with both 4.16 and 4.17 on an AMD Athlon(tm) XP 2000+, 256 mb memory, Linux fc3.
4.16 amd 4.17 results are all within a few minutes of each other.
RE: 4.17 is about 5% slower
)
Latest result with 4.17 is even worse than with 4.01. I see 4.17 is using very little physical memory (1.8% of total). Can this be a clue?
For my 800 MHz P3
)
For my 800 MHz P3 processors:
v4.01 times: approx. 9,200 - 9,300 seconds
v4.16 times: approx. 8,900 - 9,000 seconds
v4.17 times: approx. 7,800 - 8,000 seconds
The computer only gets short runtime tasks.
Since S5 started it's never gotten a long one.
Nothing travels faster than the speed of light with the possible exception of bad news, which obeys its own special laws.
Douglas Adams (1952 - 2001)
Good morning everybody. Here
)
Good morning everybody. Here are my first results obtained under beta 4.17
AuthenticAMD mobile AMD Athlon XP-M 2400+ Linux 2.6.8-24.24-default (Suse 9.2)
Computation times ( in seconds )
v4.01 average: 31881.45 v4.01 std dev: 775.56 [sample of 15 results]
v4.16 average: 27903.87 v4.16 std dev: 301.39 [sample of 5 results]
v4.17 average: 28109.39 v4.17 std dev: 185.97 [sample of 2 results]
Compare v4.16/v4.01 = 12.48% faster
Compare v4.17/v4.01 = 11.83% faster
Compare v4.17/v4.16 = -0.74% slower
Caution ! I need 1 more result before calculating acurate average time and std deviation.
However, first data ocuring for an Athlon 64 3500+ tends to show an even greater loss of speed of v4.17 vs 4.16 [about -2 %]
"Patience et longueur de temps font mieux que force et que rage"
La Fontaine
"Entia non sunt multiplicandam praeter necessitatem"
(OKHAM)
Hi again :-) AuthenticAMD
)
Hi again :-)
AuthenticAMD AMD Athlon64 3500+ Linux 2.6.13-15.8-default (Suse 10.1)
Computation times ( in seconds )
v4.01 average: 55562,95 v4.01 std dev: 836.75 [sample of 15 results]
v4.16 average: 44060,07 v4.16 std dev: 56.75 [sample of 3 results]
v4.17 average: 44979,89 v4.17 std dev: 7.48 [sample of 2 results]
Compare v4.16/v4.01 = 20.70% faster
Compare v4.17/v4.01 = 19.05% faster
Compare v4.17/v4.16 = -2.09% slower
Am I the only one who believes that 4.17 is slower than 4.16 ? On AMD and non-Xeon Intel, anyway.
"Entia non sunt multiplicandam praeter necessitatem"
(OKHAM)
RE: Am I the only one who
)
On my Pentium II (no SSE) 4.17 is slower than 4.16 and also 4.01.
Tullio