Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Cell: fix some alignment issues by aligning commands to 8-byte boundaries | Brian | 2008-02-04 | 3 | -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 3.0 | Brian | 2008-02-04 | 1 | -3/+1 |
| | |||||
* | Cell: don't use VEC_LITERAL macro, doesn't work w/ SDK 3.0 | Brian | 2008-02-04 | 2 | -32/+33 |
| | |||||
* | Cell: move float4 typedef (temporary datatype) | Brian | 2008-02-04 | 2 | -7/+6 |
| | |||||
* | Cell: fix small sampling error in sample_texture_bilinear() | Brian | 2008-02-04 | 1 | -0/+2 |
| | |||||
* | Cell: texture sampler functions always return vector float now | Brian | 2008-02-04 | 4 | -32/+29 |
| | | | | Texture colors look the same now, regardless of X display/pixel format | ||||
* | Cell: added spu_unpack_A8R8G8B8() | Brian | 2008-02-04 | 1 | -0/+15 |
| | |||||
* | Cell: fix typo | Brian | 2008-02-04 | 1 | -1/+1 |
| | |||||
* | Cell: some basic blending code | Brian | 2008-02-04 | 4 | -0/+105 |
| | |||||
* | Cell: replace float 4 with vector float in eval_coeff() | Brian | 2008-02-04 | 1 | -16/+17 |
| | |||||
* | Cell: emit blend state to SPUs | Brian | 2008-02-04 | 2 | -0/+18 |
| | |||||
* | Cell: choose bilinear vs. nearest filtering according to sampler state | Brian | 2008-02-04 | 5 | -6/+12 |
| | |||||
* | Cell: improved bilinear filtering | Brian | 2008-02-04 | 1 | -8/+19 |
| | | | | avoid calling get_tex_tile() if all texels are in same tile | ||||
* | Cell: implement basic bilinear texture sampler | Brian | 2008-02-04 | 2 | -0/+71 |
| | |||||
* | Cell: added spu_unpack_color(), spu_pack_R8G8B8A8() | Brian | 2008-02-04 | 1 | -0/+25 |
| | |||||
* | Cell: SIMD-ize more of texture sampling | Brian | 2008-02-04 | 1 | -37/+29 |
| | |||||
* | Cell: checkpoint: start to SIMD-ize texture sampling | Brian | 2008-02-04 | 5 | -8/+33 |
| | |||||
* | Cell: move tile clear code to flush_spans() | Brian | 2008-02-04 | 1 | -23/+28 |
| | |||||
* | Cell: clamp txmax, tymax in tile_bounding_box() | Brian | 2008-02-04 | 1 | -0/+10 |
| | | | | Also, added some debug printfs | ||||
* | Cell: comment about emit_quad() mask | Brian | 2008-02-01 | 1 | -0/+3 |
| | |||||
* | Cell: move some tile get/clear code | Brian | 2008-02-01 | 1 | -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 stmnt | Brian | 2008-02-01 | 5 | -46/+56 |
| | |||||
* | Cell: New color packing functions (A8R8G8B8 and B8G8R8A8) | Brian | 2008-02-01 | 2 | -13/+69 |
| | |||||
* | Cell: rename/move global vars | Brian | 2008-02-01 | 6 | -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 ↵ | Brian | 2008-02-01 | 1 | -16/+4 |
| | | | | batch buffers | ||||
* | Cell: move ztest before color interp/packing | Brian | 2008-02-01 | 1 | -22/+21 |
| | |||||
* | Cell: rename fields of the tile_t union | Brian | 2008-02-01 | 5 | -22/+22 |
| | |||||
* | Cell: implement Z16 and Z32 testing with SIMD instructions. | Brian | 2008-02-01 | 3 | -197/+163 |
| | |||||
* | Cell: store current tile status in cur_tile_status_c/z, add TILE_STATUS_GETTING | Brian | 2008-02-01 | 5 | -22/+87 |
| | |||||
* | Cell: SIMD-ize const_coeff() | Brian | 2008-01-31 | 1 | -15/+9 |
| | |||||
* | I don't know why using uint64_t for "base" doesn't work. Ugh. | Ian Romanick | 2008-01-30 | 1 | -2/+2 |
| | |||||
* | Numerous small fixed to PPU-SPU vertex shader protocol | Ian Romanick | 2008-01-30 | 1 | -5/+22 |
| | |||||
* | Correctly read / write vertex header from / to main memory | Ian Romanick | 2008-01-30 | 1 | -8/+9 |
| | |||||
* | Handle CELL_CMD_VS_EXECUTE *only* outside batch commands. | Ian Romanick | 2008-01-30 | 1 | -5/+3 |
| | |||||
* | Set machine->Processor | Ian Romanick | 2008-01-30 | 1 | -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 command | Ian Romanick | 2008-01-30 | 1 | -12/+2 |
| | |||||
* | Implement micro_pow and micro_sqrt | Ian Romanick | 2008-01-30 | 1 | -12/+31 |
| | | | | Unimplemented micro ops get assertions for now. | ||||
* | Fix size calculation in attribute fetch. | Ian Romanick | 2008-01-30 | 1 | -4/+4 |
| | |||||
* | Fetch uniforms from main memory. | Ian Romanick | 2008-01-30 | 1 | -5/+16 |
| | |||||
* | Missing amperstand in previous commit. Oops. | Ian Romanick | 2008-01-30 | 1 | -1/+1 |
| | |||||
* | Pass ptr to local memory copy instead of main memory to exec_instruction | Ian Romanick | 2008-01-30 | 1 | -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-back | Ian Romanick | 2008-01-30 | 2 | -39/+55 |
| | |||||
* | Initial pass at instruction / declaration fetch | Ian Romanick | 2008-01-30 | 2 | -0/+23 |
| | |||||
* | Initial pass at vertex shader on SPU using TGSI VM | Ian Romanick | 2008-01-30 | 8 | -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 testing | Brian | 2008-01-30 | 2 | -34/+123 |
| | |||||
* | Cell: start to SIMD-ize triangle attribute interpolation | Brian | 2008-01-30 | 4 | -62/+79 |
| | | | | | Using the spu_add(), etc intrinsics. About a 15% speed-up with some tests. | ||||
* | Cell: fold setup_tri() into tri_draw() | Brian | 2008-01-30 | 1 | -43/+19 |
| | |||||
* | Cell: make 'setup' a regular var instead of passing around a pointer everywhere | Brian | 2008-01-30 | 1 | -210/+209 |
| | | | | | We'll never have more than one of these objects. Avoiding pointer deref improves performance a bit. | ||||
* | Cell: minor code refactoring, movement | Brian | 2008-01-30 | 1 | -30/+55 |
| | |||||
* | Cell: check tile status before wait_on_mask() | Brian | 2008-01-30 | 1 | -2/+2 |
| |