Latest track on soundcloud: Farewell - to a better Place (piano improvisation)
New to Xonotic? Check out my Newbie Corner! <ZeRoQL> i think i got 1 proper quad and that cunt halogen fuck me over with a laser
Thank you, thank you. The replacement for my old broken GPU (gtx 560) really gave the thing a boost. Now if I only would play some pimped graphic-stunning commercial games...
Latest track on soundcloud: Farewell - to a better Place (piano improvisation)
New to Xonotic? Check out my Newbie Corner! <ZeRoQL> i think i got 1 proper quad and that cunt halogen fuck me over with a laser
(08-31-2013, 08:35 PM)Acidphase Wrote: I want to see how it fairs in Windows when I get chance.
That would be interesting, as on my machine Windows performs SIGNIFICANTLY worse than linux. I recently ran a benchmark again but it was so bad results that I am convinced I must tweak something before I run that again.
Latest track on soundcloud: Farewell - to a better Place (piano improvisation)
New to Xonotic? Check out my Newbie Corner! <ZeRoQL> i think i got 1 proper quad and that cunt halogen fuck me over with a laser
(08-31-2013, 08:35 PM)Acidphase Wrote: The Big Benchmark
Wiki updated. Acidphase, there is some info on the driver version etc. missing, could you post the benchmark logfile here? (You're supposed to do that anyway )
Username: Karamel
System name: karamel-desktop
CPU: Intel® Core i3-3220 CPU @ 3.30GHz
GHz: 1.60GHz
Cores: 2
RAM: 1.4GB free (of 4GB)
Vendor: ATI Technologies Inc.
Card: AMD Radeon HD 7700 Series
Driver: 4.2.11762 Compatibility Profile Context
OS: Linux
Arch: x64
Note: Graphic card Saphire Radeon HD 7750 1GB. Debian 7 (Wheezy), Linux 3.2.0-4-amd64
I'm not a CPU expert, it looks like the i3 is a 2 physical cores of twice 1.6GHz "subcores" (I have 4 entries in /proc/cpuinfo but only 2 core id and other i3 are listed as 2 cores).
CPU: Intel® Core™ i5-4570 CPU
GHz: 3.20GHz
Cores: 4
RAM: 8GB
Card: Gainward Geforce GTX 750 Ti
Driver: 335.23 WHQL
OS: Windows 7 64bit
<Samual> I am the most unprofessional developer ever
<bluez> halogene, you make awesome music, but you have no clue about ctf.
<Halogene> I didn't know mappers include some mysterious waypoints so members of the BOT clan can navigate a map?
<divVerent> if you don't pay for a premium account, your movement speed is limited to 100qu/s
Latest track on soundcloud: Farewell - to a better Place (piano improvisation)
New to Xonotic? Check out my Newbie Corner! <ZeRoQL> i think i got 1 proper quad and that cunt halogen fuck me over with a laser
BTW: my logfile is 850MB, since it's text only I zipped it to below 7MB. But I wonder if it is normal to have that many "Attempted division by zero" messages in the log...
Latest track on soundcloud: Farewell - to a better Place (piano improvisation)
New to Xonotic? Check out my Newbie Corner! <ZeRoQL> i think i got 1 proper quad and that cunt halogen fuck me over with a laser
well i have some concerns with this benchmarking design..
1: Platform (x86/x64/PPC) restrictions - only X86/X86_64/PPC?
Darkplaces/Xonotic is compatible on all linux platforms that have a gnu compiler set. including ARM/HPA/IA64/MIPS-a.
I have a RPI-2 testbed, that i run hosting testing on often. ARM7 is a rather decent platform for low-powered >30 client, dedicated server.(when compiled with optimizations)
2: Client-only design - This benchmark focuses on framerate, which is mostly GPU rendering speed by design. instead of measuring all portions of the game. (execution time, physics rendering speed, frame loss due to audio/video/texture loading/etc, gpu usage, cpu usage). Alot of those options are great at detecting ways to optimize/improve both the engine and the game.
3: non-uniform script - The script used for testing is platform dependent. but you can run batch scripts on other platforms(wine) and bash is available for windows(gnuwin/cygwin/msys). this along with the update script, would be much nicer if it was written in a non-bias manner(win/*nix/osx/bsd/hpux/solaris/etc) so that running it unattended would be much easier and capable of being ran on a cluster easily.
-----------
There my concerns... Will post my results from my platforms later.
So I build a new system.
USER: edh
SYSTEM: metis
CPU: Core i5 6400
RAM: 8Gb
GPU: GTX 950 2Gb
OS: Arch Linux
Driver: NIVDIA 355.11
Big benchmark for some reason stops working when it gets to Ultra but the following results are given first:
Benchmarking on omg
MED: 10510 frames 24.0513053 seconds 436.9825206 fps, one-second fps min/avg/max: 266 458 1171 (336 seconds)
Benchmarking on low
MED: 10510 frames 23.8759197 seconds 440.1924675 fps, one-second fps min/avg/max: 181 466 1235 (336 seconds)
Benchmarking on med
MED: 10510 frames 25.5375133 seconds 411.5514259 fps, one-second fps min/avg/max: 220 439 1188 (336 seconds)
Benchmarking on normal
MED: 10510 frames 26.9150207 seconds 390.4882749 fps, one-second fps min/avg/max: 224 418 1119 (336 seconds)
Benchmarking on high
MED: 10510 frames 28.2539935 seconds 371.9828134 fps, one-second fps min/avg/max: 209 397 1060 (336 seconds)
No log file as it stops working before doing the logfile dump but I will see about trying to get around this issue, do some system tweaking then rerun. I think right now I have the record for high quality! More to follow.
I'm at least a reasonably tolerable person to be around - Narcopic