Age | Commit message (Collapse) | Author | |
---|---|---|---|
2009-03-13 | i965: move declarations before code | Brian Paul | |
2009-03-11 | i965: fix lock-ups when GLSL program wrote to gl_FragDepth | Brian Paul | |
It seems the code that set up the FB_WRITE message was incomplete in this case. The number of payload registers was wrong and that caused a hang. It would be good to have a second set of eyes take a look at this... | |||
2009-03-10 | i965: more code clean-ups, comments | Brian Paul | |
2009-03-10 | i965: minor code clean-ups, comments | Brian Paul | |
2009-03-06 | i965: check if we run out of GRF/temp registers | Brian Paul | |
Before this change we would up emitting instructions with invalid register numbers. This typically (but not always) hung the GPU. For now, just prevent emitting bad instructions to avoid hangs. Still need to do some kind of proper error recovery. | |||
2009-03-06 | i965: comments and minor clean-ups | Brian Paul | |
2009-03-05 | i965: comments and formatting fixes | Brian Paul | |
2009-03-05 | i965: fix emit_math1() function used for scalar instructions | Brian Paul | |
Instructions such as RCP, RSQ, LOG must smear the result of the function across the dest register's X, Y, Z and W channels (subject to write masking). Before this change, only the X component was getting written. Among other things, this fixes cube map texture sampling in GLSL shaders (since cube lookups involve normalizing the texcoord). | |||
2009-02-26 | mesa: replace old prog_instruction::Sampler field with Aux field | Brian Paul | |
The i965 driver needs an extra instruction field for color output information. It was using the Sampler field for this. Use the Aux field instead. This will probaby be revisited at some point... | |||
2009-02-20 | i965: additional debug output | Brian Paul | |
2009-02-13 | i965: rewrite the code for handling shader subroutine calls | Brian Paul | |
Previously, the prog_instruction::Data field was used to map original Mesa instructions to brw instructions in order to resolve subroutine calls. This was a rather tangled mess. Plus it's an obstacle to implementing dynamic allocation/growing of the instruction buffer (it's still a fixed size). Mesa's GLSL compiler emits a label for each subroutine and CAL instruction. Now we use those labels to patch the subroutine calls after code generation has been done. We just keep a list of all CAL instructions that needs patching and a list of all subroutine labels. It's a simple matter to resolve them. This also consolidates some redundant post-emit code between brw_vs_emit.c and brw_wm_glsl.c and removes some loops that cleared the prog_instruction::Data fields at the end. Plus, a bunch of new comments. | |||
2009-02-13 | i965: updated comments | Brian Paul | |
2009-02-13 | i965: more reformatting/clean-up | Brian Paul | |
2009-02-13 | i965: s/__inline/INLINE/ | Brian Paul | |
2009-02-13 | i965: formatting and indentation fixes | Brian Paul | |
2009-01-14 | i965: comment for emit_kil() | Brian Paul | |
2009-01-14 | i965: fix indentation | Brian Paul | |
2009-01-07 | i965: Fix GLSL FS DPH to return the right value instead of src0.w * src1.w. | Eric Anholt | |
2009-01-05 | i965: implement OPCODE_TRUNC (round toward zero) on vertex path. | Brian Paul | |
Also, fix some RNDD vs. RNDZ confusion elsewhere. | |||
2008-12-13 | i965: Finish OPCODE_NOISEn instructions. | Gary Wong | |
Added missing OPCODE_NOISE4, and use BRW_REGISTER_TYPE_D (instead of _UD) in the initial RNDD instructions (which avoids saturating negative inputs to 0). | |||
2008-11-06 | mesa: rename OPCODE_INT -> OPCODE_TRUNC | Brian Paul | |
Trunc is a more accurate description; there's no type conversion involved. | |||
2008-11-05 | i965: Implement missing OPCODE_NOISE3 instruction in fragment shaders. | Gary Wong | |
OPCODE_NOISE4 coming later. | |||
2008-10-31 | i965: implement the missing OPCODE_NOISE1 and OPCODE_NOISE2 instructions. | Gary Wong | |
(Only in fragment shaders, so far. Support for NOISE3 and NOISE4 to come.) | |||
2008-10-28 | i965: Allocate temporaries contiguously with other regs in fragment shaders. | Gary Wong | |
This is required for threads to be spawned with correctly sized GRF register blocks. | |||
2008-09-18 | mesa: added "main/" prefix to includes, remove some -I paths from ↵ | Brian Paul | |
Makefile.template | |||
2008-08-29 | i965: Push/pop instruction state. partial fix for #16882 | Xiang, Haihao | |
2008-08-05 | i965: Use program->SamplerUnits[] to get the appropriate texture unit. | Xiang, Haihao | |
inst->TexSrcUnit is used as an index into program->SamplerUnits[] since the commit ade508312c701ce89d3c2cd717994dbbabb4f207, and program->SamplerUnits is a sampler-to-texture-unit mapping. | |||
2008-06-10 | i965: apply commit 6c1a98e97affb2163e776551eb3a9e669ff99bbf to glsl | Xiang, Haihao | |
2008-03-17 | [i965] fix wpos height 1 pixel higher | Zou Nan hai | |
2008-03-13 | [i965] multiple rendering target support | Zou Nan hai | |
2008-02-28 | [965] Bug #9151: make fragment.position return window coords not screen coords. | Eric Anholt | |
2008-01-29 | i965: new integrated graphics chipset support | Xiang, Haihao | |
2007-12-14 | [intel] warnings cleanup | Eric Anholt | |
2007-11-30 | i965: if source depth to render target is set, | Xiang, Haihao | |
it should be handled in fb_write. | |||
2007-10-09 | fix for prev commit | Zou Nan hai | |
2007-10-09 | INT support | Zou Nan hai | |
2007-10-09 | shadow sampler fix. | Zou Nan hai | |
1. spec requite result (0, 0, 0, 1) instead of (0, 0, 0, 0) 2. support shadow sampler in simd8 | |||
2007-09-30 | fragment shader function call fix, gl_FragCoord fix | Zou Nan hai | |
2007-09-29 | support continue, fix conditional | Zou Nan hai | |
2007-09-28 | fix | Zou Nan hai | |
2007-09-28 | support nested function call in pixel shader | Zou Nan hai | |
2007-09-27 | handle INT op, still require high level handle of integer to be correct | Zou Nan hai | |
2007-09-18 | fix double free in 965-glsl branch | Zou Nan hai | |
2007-07-24 | DDX DDY support, not very accurate | Zou Nan hai | |
2007-07-17 | Fix SOP in fragment shader, brick is ok now. | Zou Nan hai | |
2007-07-05 | support "discard"; | Zou Nan hai | |
2007-06-21 | support branch and loop in pixel shader | Zou Nan hai | |
most of the sample working with some small modification |