Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | llvmpipe: Fake missing SSSE3 when simulation less capabable machines. | José Fonseca | 2009-11-26 | 1 | -0/+1 |
| | | | | SSE3 != SSSE3 and so far we only use the later. | ||||
* | llvmpipe: Use assert instead of abort. Only verify functions on debug builds. | José Fonseca | 2009-11-24 | 1 | -1/+1 |
| | |||||
* | llvmpipe: Make sure the JIT engine and X86 target are linked on MSVC build. | José Fonseca | 2009-10-28 | 1 | -2/+1 |
| | | | | | Basically mimic the llvm 2.6 way of linking execution engines and targets. | ||||
* | llvmpipe: Workaround for bug in llvm 2.5. | José Fonseca | 2009-09-29 | 1 | -1/+14 |
| | | | | | | | | The combination of fptosi and sitofp (necessary for trunc/floor/ceil/round implementation) somehow becomes invalid code. Skip the instruction combining pass when SSE4.1 is not available. | ||||
* | llvmpipe: Emit SSE intrinsics based on runtime cpu capability check. | José Fonseca | 2009-09-29 | 1 | -0/+3 |
| | | | | | | | Note that llvmpipe still doesn't run on any processor yet: if you don't have a recent processor with SSE4.1 you will still likely end up hitting a code path for which a generic non-sse4 version is not implemented yet. | ||||
* | llvmpipe: Allow building with LLVM 2.6 too. | José Fonseca | 2009-09-26 | 1 | -0/+5 |
| | |||||
* | llvmpipe: Make the code portable for MinGW. | José Fonseca | 2009-09-16 | 1 | -1/+1 |
| | |||||
* | llvmpipe: Code generate the texture sampling inside the shader. | José Fonseca | 2009-09-07 | 1 | -1/+36 |
| | | | | | | | | | | Finally a substantial performance improvement: framerates of apps using texturing tripled, and furthermore, enabling/disabling texturing only affects around 15% of the framerate, which means the bottleneck is now somewhere else. Generated texture sampling code is not complete though -- we always sample from the base level -- so final figures will be different. | ||||
* | llvmpipe: Isolate sampling from TGSI translation. | José Fonseca | 2009-08-29 | 1 | -2/+1 |
| | |||||
* | llvmpipe: Pre-declare fetch_texel. | José Fonseca | 2009-08-29 | 1 | -2/+22 |
| | |||||
* | llvmpipe: Pass the alpha ref value and blend color in the jit context. | José Fonseca | 2009-08-29 | 1 | -1/+7 |
| | |||||
* | llvmpipe: Pass fragment context to generated function in a single structure. | José Fonseca | 2009-08-29 | 1 | -1/+37 |
| | |||||
* | llvmpipe: Centralize the C <-> JIT interfaces in one place. | José Fonseca | 2009-08-29 | 1 | -0/+77 |