summaryrefslogtreecommitdiffstats
path: root/src
Commit message (Collapse)AuthorAgeFilesLines
* gallium: added ppc_vzero()Brian Paul2008-10-222-0/+13
|
* gallium: GALLIUM_NOPPC debug var to disable PPC codegenBrian Paul2008-10-221-2/+10
|
* gallium: PPC LIT instruction (not quite complete yet)Brian Paul2008-10-221-4/+85
|
* gallium: var renaming in tgsi_ppc.cBrian Paul2008-10-221-18/+18
|
* gallium: remove SSE remnants from tgsi_ppc.cBrian Paul2008-10-221-2153/+0
|
* cell: turn on PPC assembly vertex transformBrian Paul2008-10-221-4/+1
| | | | gears runs with it now (3x faster FPS than before).
* cell: TGSI->PPC for RSQ, RCP and src register sign modesBrian Paul2008-10-221-46/+116
|
* gallium: TGSI->PPC inequality operatorsBrian Paul2008-10-221-0/+70
|
* gallium: added ppc_vload_float(), for limited casesBrian Paul2008-10-222-0/+22
|
* gallium: fix broken TGSI_FILE_CONSTANT case, use ppc_reserver_register()Brian Paul2008-10-221-8/+13
|
* gallium: fix-up confusing register allocation masks in rtasm_ppc.cBrian Paul2008-10-222-21/+36
| | | | Plus, add ppc_reserve_register() func.
* gallium: temporarily disable PPC vertex shader until more things runBrian Paul2008-10-221-0/+3
|
* gallium: PPC vertex shader supportBrian Paul2008-10-224-1/+279
| | | | Works, but dead code lingering, debug code present, etc.
* gallium: TGSI to PPC code generationBrian Paul2008-10-223-0/+2830
| | | | | | Based on the TGSIto SSE2 code generator. Incomplete and lots of SSE stuff still hanging around but the basic dozen or so TGSI opcodes are functioning.
* gallium: added ppc_lvewx()Brian Paul2008-10-222-0/+11
|
* cell: include pthread.hBrian Paul2008-10-221-0/+1
|
* cell: implement many more PPC instructions for code genBrian Paul2008-10-223-41/+704
|
* cell: implement fencing for texture buffersBrian Paul2008-10-2213-19/+367
| | | | | | | If we delete a texture, we need to keep the underlying tiled data buffer around until any rendering that references it has completed. Keep a list of buffers referenced by a rendering batch. Unref/free them when the associated batch's fence is executed/signalled.
* cell: set cell->num_texturesBrian Paul2008-10-221-0/+2
|
* cell: note that dst reg writing needs clampingBrian Paul2008-10-221-0/+16
|
* gallium: implement tests for PPC/PPC64Brian Paul2008-10-211-1/+4
|
* gallium: remove unused varBrian Paul2008-10-211-3/+0
|
* cell: minor improvements to batch buffer functionsBrian Paul2008-10-201-4/+7
|
* cell: temporarily disable freeing of tiled texture memoryBrian Paul2008-10-201-0/+6
| | | | Allows glDrawPixels to work for now...
* cell: use an approximation in compute_lambda_2d() to avoid sqrtBrian Paul2008-10-171-2/+12
| | | | Though, the logf() call still needs attention.
* cell: add new debug flag (cache) to report texture cache stats on exitBrian Paul2008-10-174-2/+7
|
* cell: more efficient state emit for textures/samplersBrian Paul2008-10-173-45/+58
|
* cell: use 7-bit weights in sample_texture_2d_bilinear_int()Brian Paul2008-10-171-31/+31
| | | | | This allows us to use 16-bit signed mul/add instructions. Had to used unsigned mul before and there's no unsigned mul/add instruction.
* Merge commit 'origin/gallium-0.1' into gallium-0.2Brian Paul2008-10-171-2/+2
|\ | | | | | | | | | | Conflicts: progs/trivial/tri.c
| * gallium: fix mis-matched malloc/free vs. aligned malloc/freeBrian Paul2008-10-171-2/+2
| | | | | | | | | | Use aligned malloc/free for teximage data everywhere to be consistant. The mismatch didn't make any difference when HAVE_POSIX_MEMALIGN was defined.
* | cell: pass spu_texture_level ptr to get_four_texels()Brian Paul2008-10-161-11/+11
| |
* | cell: implement KIL instructionBrian Paul2008-10-163-4/+87
| |
* | cell: CELL_NUM_SPUS env varBrian Paul2008-10-161-0/+4
| |
* | cell: trilinear mipmap interpolationBrian Paul2008-10-161-9/+46
| |
* | cell: update commentsBrian Paul2008-10-161-5/+2
| |
* | cell: call proper sampler function in sample_texture_cube()Brian Paul2008-10-161-4/+4
| |
* | cell: clean up various texture-related thingsBrian Paul2008-10-166-80/+107
| | | | | | | | | | Distinguish among texture targets in codegen. progs/demos/cubemap.c runs correctly now too.
* | cell: start some performance measurementsBrian Paul2008-10-154-1/+55
| | | | | | | | | | Use the spu_write_decrementer() and spu_read_decrementer() functions to measure time. Convert to milliseconds according to the system timebase value.
* | cell: updated debug codeBrian Paul2008-10-151-19/+7
| |
* | cell: get rid of last usage of float4 union/typedefBrian Paul2008-10-151-34/+29
| | | | | | | | Results in slightly tighter code.
* | cell: simplify triangle front/back face determinationBrian Paul2008-10-151-46/+23
| |
* | cell: send rasterizer state to SPUs in proper way, remove front_winding hackBrian Paul2008-10-158-9/+34
| |
* | cell: query # cells tooBrian Paul2008-10-152-3/+5
| |
* | cell: query number SPUs with spe_cpu_info_get()Brian Paul2008-10-151-3/+4
| |
* | cell: use CELL_MAX_SPUS consistently.Brian Paul2008-10-153-7/+5
| |
* | cell: remove some old, pre-batchbuffer stuffBrian Paul2008-10-154-39/+2
| |
* | cell: move some CELL_MAX constantsBrian Paul2008-10-152-10/+7
| |
* | cell: remove obsolete spu_debug.h fileBrian Paul2008-10-151-51/+0
| |
* | cell: simplify spu debug codeBrian Paul2008-10-157-48/+41
| |
* | cell: propogate blend color to SPUs for the fallback fragment ops codeBrian Paul2008-10-156-9/+74
| |