This is a collection of patches I've written and collected that aim to reduce the pain when dropping brw_do_channel_expressions() and brw_do_vector_splitting() two passes that combined take about 14% of the time it takes to run shader-db. This series includes Ken's move comparisions series with a couple of small changes.
V2: - first two clean-up patches added - added support for conditional helpers to expressions patch 3 (used by pathes 8 & 9) - small update to patch 4 - patch 7 no londer converts to ffma directly - some patches from last version pushed [PATCH 1/9] nir: tidy up swizzle handling in nir_search [PATCH 2/9] nir: stop passing swizzle to search condition [PATCH 3/9] nir/algebraic: add support for conditional helper [PATCH 4/9] nir: Introduce a nir_opt_move_comparisons() pass. [PATCH 5/9] i965: Move nir_lower_locals_to_regs a bit later. [PATCH 6/9] i965: Use the nir_move_comparisons pass. [PATCH 7/9] nir: add imprecise flrp optimisation [PATCH 8/9] nir: add late opt to turn inot/b2f combos back to bcsel [PATCH 9/9] nir: don't turn ieq/ine into inot if used by an if _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev
