SoftGPU - successor to VBEMP with 2d/3d (software) acceleration

[SweetLow]

14 minutes ago, reboot12 said:

cause Windows Protection Error on VMware Workstation 8 and on real iGPU Haswell

Check your Windows installation then and get BOOTLOG.TXT for the usual first step of course.  And may be it is Windows 95 related problem. The last working case I checked - iGPU on Intel Core Gen 8.

[reboot12]

On other old laptop Lenovo IdeaPad S10e driver 2D works OK, after run tray3d.exe, detect modes then possible set native resolution 1024x576 :-)

[Guest the solutor]

3 hours ago, SweetLow said:

It is only YOUR model of using this software. Bare 2D vmdisp9x in VESA mode now works better than VBEMP on the real hardware for example. Not ideally of course, some bugs exist still.

Obviously is MY mode of doing things and not Mikey Mouse's one, and my mode told me that the 2D VGA support was good enough in VMware since when I rewiewed it in august 2000, I generally care relatively little of VBox that has been always behind and only recently started to be usable (especially on Linux hosts).

Perhaps it's called SoftGPU and not SoftVGA for a reason. 3D is the focus, then if it's brings 2D advantages as a byproduct they are welcome.

Assuming that talking of 2D only makes sense today like it did in '98, given a lot of modern "2D" features are really rendered as a flat 3D surfaces (the optput settings of MPC-HC exposes a real world example of that)

 

 

[Guest the solutor]

2 hours ago, reboot12 said:

Both 2D (vmdisp9x-1.2025.0.119b-driver-2d) and 3D (vmdisp9x-1.2025.0.119b-driver-3d-win95-min) versions cause Windows Protection Error on VMware Workstation 8 and on real iGPU Haswell

You need at least VMware 15.x.x or VBox 7.xx to use the driver at its best, older versions may work or not with progressive lack of functionality

[reboot12]

58 minutes ago, the solutor said:

You need at least VMware 15.x.x or VBox 7.xx to use the driver at its best, older versions may work or not with progressive lack of functionality

I don't want to use it in a virtual machine, but on a real PC with a Haswell iGPU.

[Guest the solutor]

3 hours ago, reboot12 said:

I don't want to use it in a virtual machine, but on a real PC with a Haswell iGPU.

Ok but you mentioned VMware 8, I didn't dream about it.

 

About real HW, I guess it all depends on the vesa implementation in the BIOS.

 

Perhaps the author of SoftGPU seem vanished since July or so, I hope he is well.

 

[awkduck]

On 8/12/2025 at 4:02 AM, FantasyAcquiesce said:

This honestly sounds perfect for those old 915 and 945 chipset machines

I offered MMX, SSE, SSE2 optimized opengl32, for machines like this. The softgpu only offers mmx (win95), with the other supplied opengl option requiring features not available on these older CPUs. But, the performance wasn't wonderful.

There is a better option, and I'm sure some at MSFN have heard of it before. TitaniumGL doubles the performance of older Mesa OpenGL releases [6.5.4-7] (asm optimized for MMX, SSE, and SSE2). This is also true, if not more true, when using the SoftGPU provided opengl.

TitaniumGL is meant to provide a conversion of opengl to direct3d, on machine that have hardware acceleration. But, when no hardware accel exists, it falls back on its own software rendering. I've tested its software rending, and it does double the performance. It can also be paired with Wine3d, like the Mesa opengl, included with softgpu.

In the TitaniumGL download, it includes supporting files for Modern Windows, Win9x, and ReactOS. The modern release does not work with Win9x (even with KernelEx). The Win9x version works great. The ReactOS version works in Win9x, with KernelEx (maybe without it, as well), with a potential minuscule increase in performance (not verified, and hardly detectable; if real).

Be sure to get the modern release of TitaniumGL, as the older ones floating around are half the performance.

Also, be warned, don't get too excited. While the performance is doubled, that might not mean much in a less powerful machine. My Pentium-M 1.2Ghz machine still did not achieve real playable results with "Unreal Tournament GOTY Edition". At windowed 400x300, it really came close (Titanium -> Wine3d [haven't to tested opengl patches for UT]). But PSCXR went from unusable to usable windowed @640x480 (better @600x440) with graphics performance settings enabled, on the opengl plugin.

For those using multiple core supporting versions of windows, the software (and hardware) renderer supports using these other cores. I assume, for hardware accelerated systems, the extra cores are utilized to increase performance of the opengl > direct3d translations. It has been noted, on machines with weaker GPUs, that the software renderer can outperform hardware "opengl (maybe not with wine3d)" acceleration (providing enough cores are available [support for 32 cores]).

Again, it would be nice if a hack could achieve access to other cores, on bare metal Win9x installs.

SIMD95 might improve performance, on CPUs that provide AVX (SSE/AVX for Win95) however it is intended for Virtual Machines.

Not an excellent update, but I thought it worth mentioning. A nicely capable Core Solo (bare metal Win9x install) would probably provide a low expectation, but usable, software rendering experience. This might pair well the the emerging potential for HDA audio support (un-accelerated [emulated], like AC97).

Edited February 14 by awkduck