Commit message (Collapse) | Author | Files | Lines | ||
---|---|---|---|---|---|
2022-04-23 | general: Convert source file copyright comments over to SPDX | Morph | 1 | -3/+2 | |
This formats all copyright comments according to SPDX formatting guidelines. Additionally, this resolves the remaining GPLv2 only licensed files by relicensing them to GPLv2.0-or-later. | |||||
2022-03-20 | shader_recompiler: Reduce unused includes | ameerj | 1 | -1/+0 | |
2021-12-30 | shader: Add integer attribute get optimization pass | ameerj | 1 | -0/+23 | |
Works around an nvidia driver bug, where casting the integer attributes to float and back to an integer always returned 0. | |||||
2021-07-30 | shader: Fold UnpackFloat2x16 and PackFloat2x16 | ReinUsesLisp | 1 | -0/+4 | |
Simplifies the code a bit when possible. These instructions should be no-ops codegen wise. | |||||
2021-07-26 | shader: Fold integer FMA from Nvidia's pattern | ReinUsesLisp | 1 | -0/+175 | |
Fold shaders doing "a * b + c" on integers from the pattern generated by Nvidia's GL compiler. On a somewhat complex compute shader it reduces the code size by 16 instructions from 2 matches on Turing GPUs. On Intel as extracted from KHR_pipeline_executable_properties: Before the optimization: ``` Instruction Count: 2057 Basic Block Count: 45 Scratch Memory Size: 14752 Spill Count: 232 Fill Count: 261 SEND Count: 610 Cycle Count: 11325 ``` After the optimization: ``` Instruction Count: 2046 Basic Block Count: 44 Scratch Memory Size: 13728 Spill Count: 219 Fill Count: 268 SEND Count: 604 Cycle Count: 11367 ``` | |||||
2021-07-26 | shader: Use TryInstRecursive on XMAD multiply folding | ReinUsesLisp | 1 | -14/+12 | |
Simplify a bit the logic. | |||||
2021-07-23 | shader: Avoid usage of C++20 ranges to build in clang | ReinUsesLisp | 1 | -2/+3 | |
2021-07-23 | shader: Add constant propagation to integer vectors | ReinUsesLisp | 1 | -0/+9 | |
2021-07-23 | shader: Fix FSwizzleAdd folding when going through phi nodes | ReinUsesLisp | 1 | -2/+2 | |
2021-07-23 | glasm: Rework control flow introducing a syntax list | ReinUsesLisp | 1 | -20/+0 | |
This commit regresses VertexA shaders, their transformation pass has to be adapted to the new control flow. | |||||
2021-07-23 | shader: Fix BFE s32 undefined check | ameerj | 1 | -1/+1 | |
Our unit tests were hitting this exception. | |||||
2021-07-23 | shader: Fix error checking in bitfieldExtract and implement bitfieldInsert folding | ReinUsesLisp | 1 | -5/+14 | |
2021-07-23 | shader: Move microinstruction header to the value header | ReinUsesLisp | 1 | -1/+1 | |
2021-07-23 | shader: Add constant propagation for arithmetic right shifts | ReinUsesLisp | 1 | -0/+3 | |
2021-07-23 | shader: Add coarse derivatives | FernandoS27 | 1 | -8/+0 | |
2021-07-23 | shader: Implement fine derivates constant propagation | FernandoS27 | 1 | -0/+67 | |
2021-07-23 | shader: Add constant propagation for *&^| binary operations | ReinUsesLisp | 1 | -0/+12 | |
2021-07-23 | shader_recompiler,video_core: Cleanup some GCC and Clang errors | lat9nq | 1 | -23/+26 | |
Mostly fixing unused *, implicit conversion, braced scalar init, fpermissive, and some others. Some Clang errors likely remain in video_core, and std::ranges is still a pertinent issue in shader_recompiler shader_recompiler: cmake: Force bracket depth to 1024 on Clang Increases the maximum fold expression depth thread_worker: Include condition_variable Don't use list initializers in control flow Co-authored-by: ReinUsesLisp <reinuseslisp@airmail.cc> | |||||
2021-07-23 | shader: Address Feedback | FernandoS27 | 1 | -6/+3 | |
2021-07-23 | shader: Fold composite extract | FernandoS27 | 1 | -0/+62 | |
2021-07-23 | shader: Fold comparisons and Pack/Unpack16 | FernandoS27 | 1 | -1/+41 | |
2021-07-23 | shader: Fix constant propagation to use reverse post order | ReinUsesLisp | 1 | -1/+2 | |
2021-07-23 | shader: Refactor PTP and other minor changes | ReinUsesLisp | 1 | -20/+2 | |
2021-07-23 | shader: Implement TLD4.PTP | FernandoS27 | 1 | -0/+18 | |
2021-07-23 | shader: Implement TLD4 and TLD4_B | FernandoS27 | 1 | -0/+12 | |
2021-07-23 | shader: Fold interpolation multiplications | ReinUsesLisp | 1 | -0/+34 | |
2021-07-23 | shader: Implement DMNMX, DSET, DSETP | ameerj | 1 | -2/+8 | |
2021-07-23 | shader: Implement CAL inlining function calls | ReinUsesLisp | 1 | -3/+5 | |
2021-07-23 | shader: Partial implementation of LDC | ReinUsesLisp | 1 | -6/+16 | |
2021-07-23 | shader: FMUL, select, RRO, and MUFU fixes | ReinUsesLisp | 1 | -1/+1 | |
2021-07-23 | spirv: Add lower fp16 to fp32 pass | ReinUsesLisp | 1 | -6/+6 | |
2021-07-23 | shader: Add XMAD multiplication folding optimization | ReinUsesLisp | 1 | -5/+77 | |
2021-07-23 | spirv: Initial bindings support | ReinUsesLisp | 1 | -12/+64 | |
2021-07-23 | shader: Misc fixes | ReinUsesLisp | 1 | -16/+11 | |
2021-07-23 | shader: Initial implementation of an AST | ReinUsesLisp | 1 | -0/+50 | |
2021-07-23 | shader: Better constant folding | ReinUsesLisp | 1 | -12/+47 | |
2021-07-23 | shader: Make typed IR | ReinUsesLisp | 1 | -0/+20 | |
2021-07-23 | shader: Constant propagation and global memory to storage buffer | ReinUsesLisp | 1 | -0/+146 | |