Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | cell: simplify spu debug code | Brian Paul | 2008-10-15 | 7 | -48/+41 |
| | |||||
* | cell: propogate blend color to SPUs for the fallback fragment ops code | Brian Paul | 2008-10-15 | 6 | -9/+74 |
| | |||||
* | gallium: fix the shader-rebind test in softpipe, as was done for the draw ↵ | Brian Paul | 2008-10-15 | 1 | -4/+1 |
| | | | | module. | ||||
* | gallium: fix the test in vs_exec_prepare() to avoid redundant bindings | Brian Paul | 2008-10-15 | 1 | -3/+1 |
| | | | | Fixes regressions seen in progs/samples/prim.c, progs/demos/ray.c | ||||
* | gallium: temporariliy revert softpipe shader optimization | Brian Paul | 2008-10-15 | 1 | -1/+2 |
| | |||||
* | cell: updated vertex dump/debug code | Brian Paul | 2008-10-15 | 1 | -9/+14 |
| | |||||
* | cell: additional debug | Brian Paul | 2008-10-15 | 1 | -0/+1 |
| | |||||
* | cell: fix/add some fallback blend cases | Brian Paul | 2008-10-15 | 1 | -3/+46 |
| | |||||
* | cell: need to flush draw module when constants change | Brian Paul | 2008-10-15 | 1 | -0/+2 |
| | |||||
* | draw: don't assume output buffer pointer is aligned | Keith Whitwell | 2008-10-15 | 1 | -1/+1 |
| | | | | (cherry picked from commit 23cc303994eb630c56b1224dfdac51dcea41ed03) | ||||
* | cell: initial bits for 3D texture support | Brian Paul | 2008-10-14 | 5 | -6/+20 |
| | |||||
* | cell: replace FREE() with align_free() | Brian Paul | 2008-10-14 | 1 | -1/+1 |
| | |||||
* | cell: fix incorrect parameter type | Brian Paul | 2008-10-14 | 2 | -2/+2 |
| | |||||
* | cell: support for cubemaps | Brian Paul | 2008-10-14 | 8 | -41/+214 |
| | | | | Though, progs/demos/cubemap.c doesn't quite work right... | ||||
* | cell: fall-through case for TGSI_OPCODE_TXB | Brian Paul | 2008-10-14 | 1 | -0/+2 |
| | |||||
* | cell: support NPOT textures, clamp/repeat mode, normalized/unorm texcoords | Brian Paul | 2008-10-14 | 3 | -42/+117 |
| | | | | glDrawPixels works now. | ||||
* | cell: fix npot texture tiling bugs | Brian Paul | 2008-10-14 | 1 | -4/+12 |
| | |||||
* | cell: fix broken negative texcoord conversion | Brian Paul | 2008-10-14 | 1 | -4/+4 |
| | |||||
* | cell: use minify vs magnify filters | Brian Paul | 2008-10-14 | 3 | -21/+53 |
| | |||||
* | cell: fix assertions | Brian Paul | 2008-10-14 | 1 | -5/+5 |
| | |||||
* | cell: basic mipmap filtering works now | Brian Paul | 2008-10-14 | 5 | -61/+79 |
| | | | | Though, only GL_MIPMAP_NEAREST / GL_LINEAR works right now. | ||||
* | cell: fix tex image stride bugs | Brian Paul | 2008-10-14 | 1 | -5/+9 |
| | |||||
* | cell: now do texture twiddling in the right way, at the right time. | Brian Paul | 2008-10-14 | 4 | -148/+83 |
| | | | | Also handles images smaller than 32x32 now. | ||||
* | cell: remove old code, clean-ups, etc. | Brian Paul | 2008-10-14 | 4 | -44/+35 |
| | |||||
* | cell: more clean-up in spu_tri.c | Brian Paul | 2008-10-13 | 1 | -84/+16 |
| | |||||
* | cell: remove dead code, clean-up, reformatting | Brian Paul | 2008-10-13 | 1 | -90/+24 |
| | |||||
* | cell: finish-up perspective-corrected interpolation | Brian Paul | 2008-10-13 | 1 | -45/+82 |
| | |||||
* | cell: initial work for mipmap texture filtering | Brian Paul | 2008-10-13 | 10 | -77/+176 |
| | |||||
* | cell: remove old texture-related fields | Brian Paul | 2008-10-13 | 2 | -5/+0 |
| | |||||
* | cell: use fewer memory references in sample_texture4_bilinear_2() | Brian Paul | 2008-10-13 | 1 | -25/+31 |
| | |||||
* | cell: remove more old texture code | Brian Paul | 2008-10-13 | 1 | -26/+0 |
| | |||||
* | cell: bilinear texture filtering using integer arithmetic | Brian Paul | 2008-10-13 | 2 | -0/+149 |
| | | | | Fewer float/int conversions involved. | ||||
* | cell: remove old texture code | Brian Paul | 2008-10-13 | 6 | -181/+7 |
| | |||||
* | cell: do texture sampling/filtering for four pixels at a time. | Brian Paul | 2008-10-13 | 5 | -10/+161 |
| | |||||
* | cell: added spu_unpack_A8R8G8B8_transpose4() | Brian Paul | 2008-10-13 | 1 | -7/+42 |
| | | | | Plus, clearer shuffle masks in other funcs. | ||||
* | cell: more instruction scheduling optimizations (MIN/MAX/LERP/etc) | Brian Paul | 2008-10-10 | 1 | -61/+140 |
| | | | | Also, optimize register->memory stores. | ||||
* | cell: pass texture unit (sampler number) to txp() function | Brian Paul | 2008-10-10 | 2 | -2/+7 |
| | | | | The glsl/multitex demo runs now. | ||||
* | cell: add emit_RI10s() which does range checking on the 10-bit signed ↵ | Brian Paul | 2008-10-10 | 2 | -10/+30 |
| | | | | | | immediate field This type of checking should be expanded to cover more instructions... | ||||
* | cell: additional 'offset' checking in spe_lqd(), spe_stqd() | Brian Paul | 2008-10-10 | 1 | -4/+14 |
| | |||||
* | cell: fix assertions in spe_lqd(), spe_stqd() | Brian Paul | 2008-10-10 | 1 | -2/+2 |
| | |||||
* | cell: fix function prologue/epilogue code for large stack frames | Brian Paul | 2008-10-10 | 1 | -7/+37 |
| | | | | The ai instruction is limited to a 10-bit signed immediate value. | ||||
* | CELL: fixing stencil bugs | Robert Ellison | 2008-10-10 | 2 | -20/+72 |
| | | | | | | | | | | | | | | | | | | | | | | | | These are the defects found and fixed so far. Several more have been observed; I'm working on them. - Fixed an error in spe_load_uint() that caused incorrect values to be loaded if the given unsigned value had the low 18 bits as 0, and that caused inefficient code to be emitted if the given value had the high 14 bits as 0. - Fixed a problem in stencil code generation where optional registers weren't tracked correctly. - Fixed a problem that the stencil function NEVER was acting as ALWAYS. - Fixed several problems that could occur if stenciling were enabled but depth was disabled. - Fixed a problem with two-sided stencil writemask handling that could cause a stencil writemask to not be applied. - Fixed several state permutations that were incorrectly flagged as not requiring stencil values to be calculated. | ||||
* | cell: call cell_flush_int() at end of cell_create_context() | Brian Paul | 2008-10-10 | 1 | -0/+3 |
| | | | | | | Ensures that SPUs are initialized/ready before proceeding. This fixes a spurious assertion failure when the SPU-side shader function info hasn't been returned to the PPU before shader codegen. | ||||
* | cell: fix LERP when dst reg is a src reg | Brian Paul | 2008-10-10 | 1 | -5/+7 |
| | | | | Also, bump up frame size and fix some assertions. | ||||
* | cell: fix fm/fs copy & paste bug from a few commits ago | Brian Paul | 2008-10-10 | 1 | -1/+1 |
| | |||||
* | cell: fix bug in emit_FLR() when src reg == dst reg | Brian Paul | 2008-10-10 | 1 | -7/+6 |
| | |||||
* | cell: fix bug in emit_FRC() when src register == dst register. | Brian Paul | 2008-10-10 | 1 | -7/+7 |
| | | | | With this fix, the glsl/brick demo runs. | ||||
* | cell: updates in response to draw's struct vertex_info changes | Brian Paul | 2008-10-10 | 1 | -2/+2 |
| | |||||
* | Merge commit 'origin/gallium-0.1' into gallium-0.2 | Keith Whitwell | 2008-10-10 | 16 | -49/+112 |
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: src/gallium/auxiliary/gallivm/instructionssoa.cpp src/gallium/auxiliary/gallivm/soabuiltins.c src/gallium/auxiliary/rtasm/rtasm_x86sse.c src/gallium/auxiliary/rtasm/rtasm_x86sse.h src/mesa/main/texenvprogram.c src/mesa/shader/arbprogparse.c src/mesa/shader/prog_statevars.c src/mesa/state_tracker/st_draw.c src/mesa/vbo/vbo_exec_draw.c | ||||
| * | draw: don't assume output buffer pointer is aligned | Keith Whitwell | 2008-10-07 | 1 | -1/+1 |
| | |