aboutsummaryrefslogtreecommitdiffstats
path: root/src/mesa/pipe/cell/spu
Commit message (Collapse)AuthorAgeFilesLines
* Cell: fix some alignment issues by aligning commands to 8-byte boundariesBrian2008-02-043-38/+29
| | | | | | Contributed by Ian Romanick. Also, temporarily disable inlined vertex buffers. They need to be 16-byte aligned...
* Cell: don't use VEC_LITERAL macro, doesn't work w/ SDK 3.0Brian2008-02-041-3/+1
|
* Cell: don't use VEC_LITERAL macro, doesn't work w/ SDK 3.0Brian2008-02-042-32/+33
|
* Cell: move float4 typedef (temporary datatype)Brian2008-02-042-7/+6
|
* Cell: fix small sampling error in sample_texture_bilinear()Brian2008-02-041-0/+2
|
* Cell: texture sampler functions always return vector float nowBrian2008-02-044-32/+29
| | | | Texture colors look the same now, regardless of X display/pixel format
* Cell: added spu_unpack_A8R8G8B8()Brian2008-02-041-0/+15
|
* Cell: fix typoBrian2008-02-041-1/+1
|
* Cell: some basic blending codeBrian2008-02-044-0/+105
|
* Cell: replace float 4 with vector float in eval_coeff()Brian2008-02-041-16/+17
|
* Cell: emit blend state to SPUsBrian2008-02-042-0/+18
|
* Cell: choose bilinear vs. nearest filtering according to sampler stateBrian2008-02-045-6/+12
|
* Cell: improved bilinear filteringBrian2008-02-041-8/+19
| | | | avoid calling get_tex_tile() if all texels are in same tile
* Cell: implement basic bilinear texture samplerBrian2008-02-042-0/+71
|
* Cell: added spu_unpack_color(), spu_pack_R8G8B8A8()Brian2008-02-041-0/+25
|
* Cell: SIMD-ize more of texture samplingBrian2008-02-041-37/+29
|
* Cell: checkpoint: start to SIMD-ize texture samplingBrian2008-02-045-8/+33
|
* Cell: move tile clear code to flush_spans()Brian2008-02-041-23/+28
|
* Cell: clamp txmax, tymax in tile_bounding_box()Brian2008-02-041-0/+10
| | | | Also, added some debug printfs
* Cell: comment about emit_quad() maskBrian2008-02-011-0/+3
|
* Cell: move some tile get/clear codeBrian2008-02-011-11/+16
| | | | Also, we weren't marking the ztile as dirty after ztesting, fixes gears glitches.
* Cell: use global color_shuffle to remove a switch stmntBrian2008-02-015-46/+56
|
* Cell: New color packing functions (A8R8G8B8 and B8G8R8A8)Brian2008-02-012-13/+69
|
* Cell: rename/move global varsBrian2008-02-016-90/+86
| | | | | Put tile-related globals into spu_global struct. Rename c/ztile fields to be more consistant.
* Cell: remove commands from top-level while loop which should only appear in ↵Brian2008-02-011-16/+4
| | | | batch buffers
* Cell: move ztest before color interp/packingBrian2008-02-011-22/+21
|
* Cell: rename fields of the tile_t unionBrian2008-02-015-22/+22
|
* Cell: implement Z16 and Z32 testing with SIMD instructions.Brian2008-02-013-197/+163
|
* Cell: store current tile status in cur_tile_status_c/z, add TILE_STATUS_GETTINGBrian2008-02-015-22/+87
|
* Cell: SIMD-ize const_coeff()Brian2008-01-311-15/+9
|
* I don't know why using uint64_t for "base" doesn't work. Ugh.Ian Romanick2008-01-301-2/+2
|
* Numerous small fixed to PPU-SPU vertex shader protocolIan Romanick2008-01-301-5/+22
|
* Correctly read / write vertex header from / to main memoryIan Romanick2008-01-301-8/+9
|
* Handle CELL_CMD_VS_EXECUTE *only* outside batch commands.Ian Romanick2008-01-301-5/+3
|
* Set machine->ProcessorIan Romanick2008-01-301-1/+2
| | | | | The default value is 0, which is TGSI_PROCESSOR_FRAGMENT...not correct for a vertex shader!
* Elts are always ints, pass vOut pointers in-line in commandIan Romanick2008-01-301-12/+2
|
* Implement micro_pow and micro_sqrtIan Romanick2008-01-301-12/+31
| | | | Unimplemented micro ops get assertions for now.
* Fix size calculation in attribute fetch.Ian Romanick2008-01-301-4/+4
|
* Fetch uniforms from main memory.Ian Romanick2008-01-301-5/+16
|
* Missing amperstand in previous commit. Oops.Ian Romanick2008-01-301-1/+1
|
* Pass ptr to local memory copy instead of main memory to exec_instructionIan Romanick2008-01-301-10/+12
| | | | | | This was essentially a cut-and-paste bug when the instruction fetcher was added. Also, the test for TGSI_PROCESSOR_FRAGMENT was moved outside the loop for exec_declaration.
* Implement vertex fetch / vertex shader output write-backIan Romanick2008-01-302-39/+55
|
* Initial pass at instruction / declaration fetchIan Romanick2008-01-302-0/+23
|
* Initial pass at vertex shader on SPU using TGSI VMIan Romanick2008-01-308-1/+3502
| | | | | | All of the code is wired in on the SPU side, but it is not called from the PPU yet. Instruction / declaration fetch still needs to be implemented in spu_exec.c.
* Cell: prototype SIMD code for z testingBrian2008-01-302-34/+123
|
* Cell: start to SIMD-ize triangle attribute interpolationBrian2008-01-304-62/+79
| | | | | Using the spu_add(), etc intrinsics. About a 15% speed-up with some tests.
* Cell: fold setup_tri() into tri_draw()Brian2008-01-301-43/+19
|
* Cell: make 'setup' a regular var instead of passing around a pointer everywhereBrian2008-01-301-210/+209
| | | | | We'll never have more than one of these objects. Avoiding pointer deref improves performance a bit.
* Cell: minor code refactoring, movementBrian2008-01-301-30/+55
|
* Cell: check tile status before wait_on_mask()Brian2008-01-301-2/+2
|