summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* i965/fs_nir: Handle coarse/fine derivativesJason Ekstrand2015-01-151-0/+18
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir/glsl: Add support for coarse and fine derivativesJason Ekstrand2015-01-151-2/+6
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir: Add fine and coarse derivative opcodesJason Ekstrand2015-01-151-0/+4
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir/glsl: Add support for saturateJason Ekstrand2015-01-151-0/+5
| | | | Reviewed-by: Connor Abbott <[email protected]>
* i965/fs_nir: Add support for sample_pos and sample_idJason Ekstrand2015-01-151-3/+14
|
* Fix up varying pull constantsJason Ekstrand2015-01-151-1/+1
| | | | Reviewed-by: Connor Abbott <[email protected]>
* Fix what I think are a few NIR typosJason Ekstrand2015-01-151-3/+3
| | | | Reviewed-by: Connor Abbott <[email protected]>
* i965/fs_nir: Use the correct texture offset immediateJason Ekstrand2015-01-151-4/+3
| | | | Reviewed-by: Connor Abbott <[email protected]>
* i965/fs_nir: Use the correct types for texture inputsJason Ekstrand2015-01-151-7/+25
| | | | Reviewed-by: Connor Abbott <[email protected]>
* i965/fs_nir: Make the sampler register always unsignedJason Ekstrand2015-01-151-2/+2
| | | | Reviewed-by: Connor Abbott <[email protected]>
* i965/fs: Only use nir for 8-wide non-fast-clear shaders.Jason Ekstrand2015-01-151-1/+2
| | | | Reviewed-by: Connor Abbott <[email protected]>
* i965/fs: add a NIR frontendConnor Abbott2015-01-155-4/+1756
| | | | | | | | | | This is similar to the GLSL IR frontend, except consuming NIR. This lets us test NIR as part of an actual compiler. v2: Jason Ekstrand <[email protected]>: Make brw_fs_nir build again Only use NIR of INTEL_USE_NIR is set whitespace fixes
* i965/fs: Don't pass through the coordinate typeConnor Abbott2015-01-153-22/+21
| | | | All we really need is the number of components.
* i965/fs: make emit_fragcoord_interpolation() not take an ir_variableConnor Abbott2015-01-154-9/+14
|
* nir: add an SSA-based dead code elimination passConnor Abbott2015-01-153-0/+191
| | | | | v2: Jason Ekstrand <[email protected]>: whitespace fixes
* nir: add an SSA-based copy propagation passConnor Abbott2015-01-153-0/+317
|
* nir: add a pass to convert to SSAConnor Abbott2015-01-153-0/+686
| | | | | v2: Jason Ekstrand <[email protected]>: whitespace fixes
* nir: calculate dominance informationConnor Abbott2015-01-154-1/+337
|
* nir: add an optimization to turn global registers into local registersConnor Abbott2015-01-153-0/+106
| | | | | After linking and inlining, this allows us to convert these registers into SSA values and optimise more code.
* nir: add a pass to lower atomicsConnor Abbott2015-01-153-0/+130
| | | | | v2: Jason Ekstrand <[email protected]> whitespace fixes
* nir: add a pass to lower system value readsConnor Abbott2015-01-153-0/+109
| | | | | v2: Jason Ekstrand <[email protected]>: whitespace fixes
* nir: add a pass to lower sampler instructionsConnor Abbott2015-01-153-0/+176
|
* nir: add a pass to remove unused variablesConnor Abbott2015-01-153-0/+141
| | | | | | | | After we lower variables, we want to delete them in order to free up some memory. v2: Jason Ekstrand <[email protected]>: whitespace fixes
* nir: keep track of the number of input, output, and uniform slotsConnor Abbott2015-01-153-4/+16
|
* nir: add a pass to lower variables for scalar backendsConnor Abbott2015-01-153-0/+1237
|
* nir: add a glsl-to-nir passConnor Abbott2015-01-153-1/+1797
| | | | | | v2: Jason Ekstrand <[email protected]>: Make glsl_to_nir build again fix whitespace
* nir: add a validation passConnor Abbott2015-01-153-0/+793
| | | | | | | This is similar to ir_validate.cpp. v2: Jason Ekstrand <[email protected]>: whitespace fixes
* nir: add a printerConnor Abbott2015-01-153-0/+915
| | | | | | | This is similar to ir_print_visitor.cpp. v2: Jason Ekstrand <[email protected]>: whitespace fixes
* SQUASH: Fix comments from ericJason Ekstrand2015-01-151-0/+3
| | | | Reviewed-by: Eric Anholt <[email protected]>
* SQUASH: Add an assertJason Ekstrand2015-01-151-0/+1
|
* nir: add core helper functionsConnor Abbott2015-01-153-3/+1815
| | | | | | | | | These include functions for adding and removing various bits of IR and helpers for iterating over all the sources and destinations of an instruction. This is similar to ir.cpp. v2: Jason Ekstrand <[email protected]>: whitespace and automake fixes
* SQUASH: Use the enum for the variable modeJason Ekstrand2015-01-151-1/+1
|
* nir: add the core datastructuresConnor Abbott2015-01-156-0/+1751
| | | | | | | | | | | | | This includes all the instructions, ifs, loops, functions, etc. This is similar to the information in ir.h. v2: Jason Ekstrand <[email protected]>: Include ralloc and hash_table from the util directory whitespace fixes Signed-off-by: Jason Ekstrand <[email protected]> Reviewed-by: Eric Anholt <[email protected]> Reviewed-By glenn.kennard <[email protected]>
* nir: add a simple C wrapper around glsl_types.hConnor Abbott2015-01-154-1/+238
| | | | | | | v2: Jason Ekstrand <[email protected]>: whitespace and automake fixes Reviewed-by: Eric Anholt <[email protected]>
* nir: add initial READMEConnor Abbott2015-01-151-0/+118
| | | | Reviewed-by: Eric Anholt <[email protected]>
* exec_list: add a list_foreach_typed_reverse() macroConnor Abbott2015-01-151-0/+6
| | | | Reviewed-by: Eric Anholt <[email protected]>
* vc4: Add some dumping for STORE_TILE_BUFFER_GENERAL.Eric Anholt2015-01-151-1/+79
|
* vc4: Add dumping for the TILE_RENDERING_MODE_CONFIG packet.Eric Anholt2015-01-151-1/+70
| | | | I wanted to read it, so I wrote parsing.
* vc4: Fix CL dumping trying to dump too far.Eric Anholt2015-01-151-2/+2
| | | | | Execution will end at the cl->next, because that's what ct0ea/ct1ea get programmed to.
* vc4: Fix texture type masking.Eric Anholt2015-01-151-1/+1
| | | | | Everything from ETC1 to RGBA64 was getting its top bit dropped, but we didn't use any of those formats.
* vc4: Colormask should apply after all other fragment ops (like logic op).Eric Anholt2015-01-151-9/+18
| | | | | Theoretically it should apply after dithering as well, but ditehring for 565 happens in fixed function in the TLB store.
* vc4: No turning unpack arguments into small immediates.Eric Anholt2015-01-151-0/+3
| | | | | Since unpack only happens on things read from the A register file, we have to leave them as something that can be allocated to A (temp or uniform).
* vc4: Move the tests for src needing to be an A register to vc4_qir.c.Eric Anholt2015-01-153-17/+28
| | | | I want it from another location.
* vc4: Don't swap the raddr on instructions doing unpacks.Eric Anholt2015-01-151-0/+5
| | | | | It would mean different unpacking behavior, since only the A file does unpack (with PM==0).
* vc4: Don't let pairing happen with badly mismatched unpack flags.Eric Anholt2015-01-151-0/+39
| | | | | No difference on shader-db, but prevents definite regressions in the blending changes.
* vc4: Don't let pairing happen with badly mismatched pack flags.Eric Anholt2015-01-151-0/+39
| | | | | No difference on shader-db, but will become more important as I introduce more use of pack flags with the blending changes.
* vc4: Fix early Z behavior on hardware.Eric Anholt2015-01-151-2/+1
| | | | | | It turns out the simulator was not treating this bit the same as the RPi, and I'd forgotten to remove it when turning on early Z. The result was that you'd get big chunks of your rendering missing.
* Revert "radeonsi: only set BC_OPTIMIZE_DISABLE when necessary"Michel Dänzer2015-01-152-15/+6
| | | | | | | | | | | | | | | | This reverts commit 0543630d0b0d9d9f6eefbc14fbd3385d4de37ba0. It caused flickering artifacts in Steam games such as Team Fortress 2 or Left 4 Dead 2. We could probably only enable this optimization by also making sure the shader code only uses either SI_PARAM_LINEAR_CENTROID or SI_PARAM_LINEAR_CENTER, not both. This would probably require a shader variant. Sorry I didn't remember this when reviewing the reverted change. Reviewed-by: Marek Olšák <[email protected]>
* st/clover: Adapt to TargetLibraryInfo.h move in LLVM SVN r226078Michel Dänzer2015-01-151-0/+4
| | | | Trivial.
* mesa: Micro-optimize _mesa_is_valid_prim_modeIan Romanick2015-01-141-18/+12
| | | | | | | | | | | | | | | | | | | You would not believe the mess GCC 4.8.3 generated for the old switch-statement. On Bay Trail-D using Fedora 20 compile flags (-m64 -O2 -mtune=generic for 64-bit and -m32 -march=i686 -mtune=atom for 32-bit), affects Gl32Batch7: 32-bit: Difference at 95.0% confidence -0.37374% +/- 0.184057% (n=40) 64-bit: Difference at 95.0% confidence 0.966722% +/- 0.338442% (n=40) The regression on 32-bit is odd. Callgrind says the caller, _mesa_is_valid_prim_mode is faster. Before it says 2,293,760 cycles, and after it says 917,504. Signed-off-by: Ian Romanick <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-22 05:31:24 +0000