tag:blogger.com,1999:blog-5052591504201077738.post201785675613719506..comments2023-05-18T03:53:07.304+12:00Comments on The Big E-UAE JIT blog: One small step for mankind, a giant leap for the projectÁlmos Rajnaihttp://www.blogger.com/profile/13385962754685794358noreply@blogger.comBlogger15125tag:blogger.com,1999:blog-5052591504201077738.post-58653819921883058002013-05-23T19:22:26.134+12:002013-05-23T19:22:26.134+12:00I am not sure I understood this correctly: you tri...I am not sure I understood this correctly: you tried to measure how the free time of your PPC processor changes? That is meaningless, because the JIT emulates a non-existing processor which is "much faster" than any real one. It adjusts the chipset timing balance to increase the load on the processor emulation against the custom chip emulation, to let the emulated processor execute more code. So, it skips more custom emulation in favor to the processor emulation.<br />The side effect of this might be that the free PPC processor time drops, but why would you measure that? Most of the cases (especially for the old demos and games) the processor is barely doing anything else, but waiting. In this case it is waiting more faster. :)<br /><br />What worth checking if the frame rate of a processor intense game is higher or some calculation takes less time when the emulation runs on maximum speed. For these tests you have to set up these configuration items:<br /><br />cpu_speed=max<br />cpu_compatible=false<br />cpu_cycle_exact=false<br /><br />Álmos Rajnaihttps://www.blogger.com/profile/13385962754685794358noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-80240217269451566712013-05-23T16:35:00.295+12:002013-05-23T16:35:00.295+12:00@Almos
Yep, it can be not faster, but it should...@Almos<br />Yep, it can be not faster, but it should't be slower with jit imho too ? I check the differences by just running cpu_metter on background, and i can see by it that with enabled jit cpu loading is more on 10% in compare with no enabled jit.<br /><br />At least in theory everything should be the same, and not slower (but i assume even in those old aga games which use chipset and so on, its still should speedup few parts a bit there and there , right ?)kas1ehttps://www.blogger.com/profile/06141071692883103173noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-58331580418585219682013-05-21T20:38:41.174+12:002013-05-21T20:38:41.174+12:00Um, no, that mail address is ancient. I put a cont...Um, no, that mail address is ancient. I put a contact field to the right column on this page, just send me a message and I will reply.<br /><br />I don't see any problem with my kickstart, probably you got a different version.<br /><br />From the log I don't see anything particular which might trigger this error. Unfortunately, it is hard to tell where this error is coming from exactly because it is printed by one of the most widely used functions.<br /><br />Maybe if you could send me the kick file I would be able to debug it.<br />Or you can also narrow it down by removing the supported instructions from the table68k_comp file until the error disappears. Just change the number '1' next to the instruction name to '0' and rebuild the code. Doing it one-by-one might take a while, but you can do this in bigger blocks, the refine it when the error disappears.Álmos Rajnaihttps://www.blogger.com/profile/13385962754685794358noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-71277975964634443132013-05-21T19:55:14.598+12:002013-05-21T19:55:14.598+12:00I had a look on the Technological Death: first of ...I had a look on the Technological Death: first of all, this is an OCS demo which is heavily using the chipset (the blitter mostly), but not the processor. The JIT won't help in this case, because the demo is slow due to the sluggish chipset emulation.<br />I am not sure how did you figure out that it is slower by 10%, I see no difference at all. And yes, it doesn't work fully, there are still bugs to be fixed.<br /><br />It is pretty easy to find out whether the processor emulation is the bottleneck or the chipset emulation: if on large movements on the screen the emulation slows down then it is the chipset emulation to blame. For these games/apps the JIT won't help much (or at all).<br /><br />I would suggest to test something where the processor emulation is more important, like some painter (Personal Paint for example) or ray tracer which is working on 68020 without FPU. Or maybe Quake1 which is compiled for 68020. Anything which is running on emulated graph card and not on ECS/AGA screens is going to gain more speedup mostly likely.Álmos Rajnaihttps://www.blogger.com/profile/13385962754685794358noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-72916325878640092542013-05-21T19:34:27.754+12:002013-05-21T19:34:27.754+12:00Okay. Do you still have this bfd... address?
I tri...Okay. Do you still have this bfd... address?<br />I tried it with gods, apidya, Siedler and Lotus2. But I don't think it's the games, but the kickstart itself. When I comment the adf section, the error also appears.<br />For Kick3.x the last lines are:<br />JIT: Compiled code start: 2dff3b58<br />JIT: Comp: 00f81a0e 4aaa 000a TST.L (A2,$000a) == $00c0005a<br />JIT: Comp: 00f81a12 67f4 BEQ.B #$fffffff4 == 00f81a08 (FALSE)<br />JIT: Done compiling<br />JIT: Init compiling<br />JIT: Compiled code start: 2dff3c6c<br />JIT: Comp: 00f81a14 206a 000a MOVEA.L (A2,$000a) == $00c0005a,A0<br />JIT: Comp: 00f81a18 2241 MOVEA.L D1,A1<br />JIT: Comp: 00f81a1a b308 CMPM.B (A0)+,(A1)+<br />JIT: Unsupported opcode: 0xb308<br />JIT: Comp: 00f81a1c 66ea BNE.B #$ffffffea == 00f81a08 (TRUE)<br /><br />Then the error message appears.<br /><br />For the CPU cache, it seems that the other processor types don't enable the cache by default.Thunderhttps://www.blogger.com/profile/15893092462978452048noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-17511378437384232132013-05-21T08:17:02.044+12:002013-05-21T08:17:02.044+12:00Ok, I will check the demo why is that slower than ...Ok, I will check the demo why is that slower than it should be. Although not all insturctions are done yet, but it should be at least the same speed as the interpreted.Álmos Rajnaihttps://www.blogger.com/profile/13385962754685794358noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-45476299765387648412013-05-21T01:41:12.782+12:002013-05-21T01:41:12.782+12:00@Almos
Its pretty much green all the time, mostly ...@Almos<br />Its pretty much green all the time, mostly "light green", like there is a lot of jit happenskas1ehttps://www.blogger.com/profile/06141071692883103173noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-48773920476388274442013-05-20T23:38:58.286+12:002013-05-20T23:38:58.286+12:00JIT is only working with CPU cache enabled. (See F...JIT is only working with CPU cache enabled. (See FAQ.)<br /><br />The other sounds like a bug in one of the new instructions. Could you please tell me which games are these? Or maybe run it while the comp_log=true is set and send me the logs?Álmos Rajnaihttps://www.blogger.com/profile/13385962754685794358noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-87245812276979206662013-05-20T23:36:33.690+12:002013-05-20T23:36:33.690+12:00Is the JIT led bright green while these are runnin...Is the JIT led bright green while these are running?Álmos Rajnaihttps://www.blogger.com/profile/13385962754685794358noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-60354712828777934742013-05-20T22:12:06.658+12:002013-05-20T22:12:06.658+12:00Thank you, sounds good. I tried it with MorphOS an...Thank you, sounds good. I tried it with MorphOS and here I have two issues:<br />1. It seems that only the 68020 will do JIT, no other processor<br />2. On _every_ game now I get the message "JIT temporary register '1' is not allocated, but mapping info is requested"<br />So I could not try it yet ;)Thunderhttps://www.blogger.com/profile/15893092462978452048noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-45321927155165307542013-05-20T17:12:38.567+12:002013-05-20T17:12:38.567+12:00@Almos
Do some tests and:
Aladdin and LionKing g...@Almos<br /><br />Do some tests and:<br /><br />Aladdin and LionKing games: with jit slower on 10%.<br /><br />Technological Death demo: start to works with jit, slower on 10% too, and freezes somewhere on third scene (about 20 seconds from run). I.e. bugs still here, but it start to works now.<br /><br />Whdload stuff: after few seconds of loading black screen and uae freezes.kas1ehttps://www.blogger.com/profile/06141071692883103173noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-43421398571891081972013-05-20T08:15:35.535+12:002013-05-20T08:15:35.535+12:00Thx almos! you rock Thx almos! you rock baranahttps://www.blogger.com/profile/06175896258606216409noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-91312200915637591042013-05-20T00:20:01.880+12:002013-05-20T00:20:01.880+12:00Where there is a will, there is a way. ;-)Where there is a will, there is a way. ;-)Dirk-Bhttps://www.blogger.com/profile/04992123363567510965noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-38041638856426411222013-05-19T23:01:36.715+12:002013-05-19T23:01:36.715+12:00Awesome, awesome work!Awesome, awesome work!Akariaioshttps://www.blogger.com/profile/17620276682531528583noreply@blogger.comtag:blogger.com,1999:blog-5052591504201077738.post-79451583034934527722013-05-19T22:24:21.734+12:002013-05-19T22:24:21.734+12:00Great!!!
Very great work!!!Great!!!<br /><br />Very great work!!!The Rainbow UIhttps://www.blogger.com/profile/02623708043087623495noreply@blogger.com