Which gsdx to use

Ask Ubuntu is a question and answer site for Ubuntu users and developers. It only takes a minute to sign up. Connect and share knowledge within a single location that is structured and easy to search. In this case use the SSE2 flavor. Ubuntu Community Ask! Sign up to join this community. The best answers are voted up and rise to the top.

Stack Overflow for Teams — Collaborate and share knowledge with a private group. Create a free Team What is Teams? SSE4 is my favorite option. Most CPUs support it. Show 2 previous replies. I know how to do that with cmake add extra object file targets that reference the same files with extra definitions, link them all with the gsdx target but I don't know how to do this for msbuild Also you can't dynamically load GSVector or you'll be making one function call per instruction, and would be slower than just compiling for SSE2.

We dropped support of Win7 in 1. Show 4 previous replies. They are. The gain of AVX1 alone is not big so no need to bother 1. No, before. All will be handled before. All PRs listed in the first message have been delayed until the merge is done.

The GS merge is finally there: 1. Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment. Insert Link. Link Text. An error occurred while translating this comment. Try again. People with administrator rights can quickly scan and then clean a user's registry. Limitations: trial version offers an unlimited number of scans, backup, restore of your windows registry for FREE. Full version must be purchased. Home Gabest gsdx-sse2-r How to fix the Gsdx-sse2-r If you see these messages, you have some problems with Gsdx-sse2-r Try reinstalling the program to fix this problem.

Reinstalling the application may fix this problem. Copy the file to the program install directory after where it is missing the DLL file. Now you need to reboot the computer. Yes ssse3. Are you sure that bulldozer arch doesn't support avx? I think Phenom 2 is limited to sse2. I think most of the speed impact, if any, is in GSState. This part could be dynamic because handlers are function pointers. I know a lot of people use the FX chip which only supports ssse3, beyond that I'm not sure where the change is.

I quickly look at the code. Big changes are in gsvector h file. Sse code is inlined everywhere. It would be very hard to split the code. Maybe not that dominant anymore but most of older system have a Core2 installed. I could possibly benchmark ssse3 vs sse2 on such a system using games that are not that cpu hungry. Possibly ffx, ffxii, kh, kh2 and GoW. I think I don't need to check snowblind games and SotC. Not mentioned yet, but avx also has the vex encoding with arbitrary destination register, it is much less likely to spill data into temp registers on the stack.

That alone could help a lot in pcsx2's recompiler, too. Not sure if it's related to the AVX transition penalties or if there is another reason for it.

Most likely no penalties, because it's per thread, and pcsx2 runs gsdx on its own thread, memcpy may use sse instruction only. Or to avoid strange crash due to no stack alignment in the recompiler. Well, I meant that all the versions of the core executable are compiled with something like -mno-sse -mno-sse2, etc under windows which is sort of odd and explains why some of the assembly code claims 10x speedups which made no sense unless the MS libraries were totally broken at some point.

Well project is very old, it comes from a long journey. Various compiler options were not safe. Potentially sse can be enabled safely. This way we could remove the remaining memcmp and memset which is mostly removed anyway. An idea, the new instructions are mostly useful for the SW renderer. Other ideas perhaps. Anyway, I think the best start will be on the SW code generator. Overhead will be small. Old non-VEX encoded code have to be mixed with AVX to trigger it, but the compiler encodes intrinsics with VEX, the generated code is also done that way, and the GS runs on its own thread hopefully , so pcsx2 cannot interfere much.

So bulldozer and later are fine. Previous CPU was already limited to sse2. So in short the impact for the he renderer. Ah yes you're right, only the 65 nm version is impacted. Actually just checking the code again. But the gains seem to be small. It could still be bigger than 0 on some games.