What was the first version of zdoom to use sse2 for sw mode?

[invictius]

I can tell by the window color and shape that it is indeed Windows XP, but Graf's right - it must be an old version, because...

Code: Select all

CMakeCache.txt:CMAKE_GENERATOR_TOOLSET:INTERNAL=v140_xp

That's what it was compiled with.

I trust dpJudas's numbers even if they came from a more modern processor. I've made the builds as you asked but honestly this issue is not worth that much effort for me - if you get it working, great, if not, I am not making any special effort to get that working on any pre-SP3 system, it's really not that important to me. Even on your more modern system you've shown that SSE2 builds are faster - case closed.

That's not to say the non-SSE code can't be optimized - I am sure there's a few tricks that can be done to make it run faster - but I don't think it's worth it, at this point anyhow, I don't think there is much gain to be had in doing so. The code is there for readability and understandability of what it's actually doing - not for being actually used in a real-world scenario where time is critical in these steps.

If you want to use your own compiler, simply insert "#define NO_SSE" at the top of the files "src/swrenderer/r_all.cpp" and "src/polyrenderer/poly_all.cpp" - that's exactly how the no-sse build was compiled in both cases.

Oh, sse is meant to speed up loading as well? I've just been concentrating on timedemo fps. Startup speed doesn't interest me that much.

[Rachael]

No... that has nothing to do with how it loads. If there's any SSE code in the loading code, it would be MSVC's optimization passes, not from the source.

[invictius]

No... that has nothing to do with how it loads. If there's any SSE code in the loading code, it would be MSVC's optimization passes, not from the source.

I'm just confused with dpJudas' result that has a measurement in ms. I only get gametics, realtics and fps in my results.

[Rachael]

That's milliseconds per frame and that's a more accurate way to measure how long it actually takes to draw a single frame. Frames per second (FPS) the most common measurement is not as accurate because it is an inverse measurement of speed and performance, and can be a bit misleading.

[invictius]

That's milliseconds per frame and that's a more accurate way to measure how long it actually takes to draw a single frame. Frames per second (FPS) the most common measurement is not as accurate because it is an inverse measurement of speed and performance, and can be a bit misleading.

I'm not getting a ms readout in my timedemo playback for some reason.

[Rachael]

Try vid_fps true.

[invictius]

Try vid_fps true.

I enter it, confirm it's on-screen then quit and play my demo from the command line, but it disappears/isn't included in the readout at the end.

[dpJudas]

You can calculate the ms value from the fps by doing 1000 / fps. I.e. 185 fps is 1000 / 185 = 5.4ms.

[invictius]

You can calculate the ms value from the fps by doing 1000 / fps. I.e. 185 fps is 1000 / 185 = 5.4ms.

Any way to force software mode on startup, before you get into the game? Trying to compare on a system that's giving me "gl driver not accelerated" and trying to verify a timedemo that, on zdoom, is 17.6ms on a p3-1ghz and 7.8 on a p4-2.6. I'm trying to figure out whether a) sse2 is causing the better performance, or b) the higher clockrate, or c) both.

[_mental_]

Any way to force software mode on startup, before you get into the game?

Use +vid_renderer 0 command line.