summaryrefslogtreecommitdiff
path: root/src/gallium
AgeCommit message (Collapse)Author
2008-10-15cell: send rasterizer state to SPUs in proper way, remove front_winding hackBrian Paul
2008-10-15cell: query # cells tooBrian Paul
2008-10-15cell: query number SPUs with spe_cpu_info_get()Brian Paul
2008-10-15cell: use CELL_MAX_SPUS consistently.Brian Paul
2008-10-15cell: remove some old, pre-batchbuffer stuffBrian Paul
2008-10-15cell: move some CELL_MAX constantsBrian Paul
2008-10-15cell: remove obsolete spu_debug.h fileBrian Paul
2008-10-15cell: simplify spu debug codeBrian Paul
2008-10-15cell: propogate blend color to SPUs for the fallback fragment ops codeBrian Paul
2008-10-15gallium: fix the shader-rebind test in softpipe, as was done for the draw ↵Brian Paul
module.
2008-10-15gallium: fix the test in vs_exec_prepare() to avoid redundant bindingsBrian Paul
Fixes regressions seen in progs/samples/prim.c, progs/demos/ray.c
2008-10-15gallium: temporariliy revert softpipe shader optimizationBrian Paul
2008-10-15cell: updated vertex dump/debug codeBrian Paul
2008-10-15cell: additional debugBrian Paul
2008-10-15cell: fix/add some fallback blend casesBrian Paul
2008-10-15cell: need to flush draw module when constants changeBrian Paul
2008-10-15draw: don't assume output buffer pointer is alignedKeith Whitwell
(cherry picked from commit 23cc303994eb630c56b1224dfdac51dcea41ed03)
2008-10-14cell: initial bits for 3D texture supportBrian Paul
2008-10-14cell: replace FREE() with align_free()Brian Paul
2008-10-14cell: fix incorrect parameter typeBrian Paul
2008-10-14cell: support for cubemapsBrian Paul
Though, progs/demos/cubemap.c doesn't quite work right...
2008-10-14cell: fall-through case for TGSI_OPCODE_TXBBrian Paul
2008-10-14cell: support NPOT textures, clamp/repeat mode, normalized/unorm texcoordsBrian Paul
glDrawPixels works now.
2008-10-14cell: fix npot texture tiling bugsBrian Paul
2008-10-14cell: fix broken negative texcoord conversionBrian Paul
2008-10-14cell: use minify vs magnify filtersBrian Paul
2008-10-14cell: fix assertionsBrian Paul
2008-10-14cell: basic mipmap filtering works nowBrian Paul
Though, only GL_MIPMAP_NEAREST / GL_LINEAR works right now.
2008-10-14cell: fix tex image stride bugsBrian Paul
2008-10-14cell: now do texture twiddling in the right way, at the right time.Brian Paul
Also handles images smaller than 32x32 now.
2008-10-14cell: remove old code, clean-ups, etc.Brian Paul
2008-10-13cell: more clean-up in spu_tri.cBrian Paul
2008-10-13cell: remove dead code, clean-up, reformattingBrian Paul
2008-10-13cell: finish-up perspective-corrected interpolationBrian Paul
2008-10-13cell: initial work for mipmap texture filteringBrian Paul
2008-10-13cell: remove old texture-related fieldsBrian Paul
2008-10-13cell: use fewer memory references in sample_texture4_bilinear_2()Brian Paul
2008-10-13cell: remove more old texture codeBrian Paul
2008-10-13cell: bilinear texture filtering using integer arithmeticBrian Paul
Fewer float/int conversions involved.
2008-10-13cell: remove old texture codeBrian Paul
2008-10-13cell: do texture sampling/filtering for four pixels at a time.Brian Paul
2008-10-13cell: added spu_unpack_A8R8G8B8_transpose4()Brian Paul
Plus, clearer shuffle masks in other funcs.
2008-10-10cell: more instruction scheduling optimizations (MIN/MAX/LERP/etc)Brian Paul
Also, optimize register->memory stores.
2008-10-10cell: pass texture unit (sampler number) to txp() functionBrian Paul
The glsl/multitex demo runs now.
2008-10-10cell: add emit_RI10s() which does range checking on the 10-bit signed ↵Brian Paul
immediate field This type of checking should be expanded to cover more instructions...
2008-10-10cell: additional 'offset' checking in spe_lqd(), spe_stqd()Brian Paul
2008-10-10cell: fix assertions in spe_lqd(), spe_stqd()Brian Paul
2008-10-10cell: fix function prologue/epilogue code for large stack framesBrian Paul
The ai instruction is limited to a 10-bit signed immediate value.
2008-10-10CELL: fixing stencil bugsRobert Ellison
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.
2008-10-10cell: call cell_flush_int() at end of cell_create_context()Brian Paul
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.