From 37703040a142da6bc7c458479a70e35118e10e6b Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Mon, 23 Mar 2015 15:08:31 -0700 Subject: [PATCH] i965/nir: Run the ffma peephole after the rest of the optimizations The idea here is that fusing multiply-add combinations too early can reduce our ability to perform CSE and value-numbering. Instead, we split ffma opcodes up-front, hope CSE cleans up, and then fuse after-the-fact. Unless an algebraic pass does something silly where it inserts something between the multiply and the add, splitting and re-fusing should never cause a problem. We run the late algebraic optimizations after this so that things like compare-with-zero don't hurt our ability to fuse things. shader-db results for fragment shaders on Haswell: total instructions in shared programs: 4390538 -> 4379236 (-0.26%) instructions in affected programs: 989359 -> 978057 (-1.14%) helped: 5308 HURT: 97 GAINED: 78 LOST: 5 This does, unfortunately, cause some substantial hurt to a shader in Kerbal Space Program. However, the damage is caused by changing a single instruction from a ffma to an add. This, in turn, *decreases* register pressure in one part of the program causing it to fail to register allocate and spill. Given the overwhelmingly positive results in other shaders and the fact that the NIR for the Kerbal shaders is actually better, this should be considered a positive. Reviewed-by: Matt Turner --- src/mesa/drivers/dri/i965/brw_context.c | 5 +++++ src/mesa/drivers/dri/i965/brw_fs_nir.cpp | 8 ++++++-- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/src/mesa/drivers/dri/i965/brw_context.c b/src/mesa/drivers/dri/i965/brw_context.c index ed6fdffd265..21c8bd331b5 100644 --- a/src/mesa/drivers/dri/i965/brw_context.c +++ b/src/mesa/drivers/dri/i965/brw_context.c @@ -558,6 +558,11 @@ brw_initialize_context_constants(struct brw_context *brw) static const nir_shader_compiler_options gen6_nir_options = { .native_integers = true, + /* In order to help allow for better CSE at the NIR level we tell NIR + * to split all ffma instructions during opt_algebraic and we then + * re-combine them as a later step. + */ + .lower_ffma = true, }; /* We want the GLSL compiler to emit code that uses condition codes */ diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp index 4f4b74620fe..94641cf2ec1 100644 --- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp +++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp @@ -52,8 +52,6 @@ nir_optimize(nir_shader *nir) nir_validate_shader(nir); progress |= nir_opt_algebraic(nir); nir_validate_shader(nir); - progress |= nir_opt_peephole_ffma(nir); - nir_validate_shader(nir); progress |= nir_opt_constant_folding(nir); nir_validate_shader(nir); progress |= nir_opt_remove_phis(nir); @@ -149,6 +147,12 @@ fs_visitor::emit_nir_code() nir_optimize(nir); + if (brw->gen >= 6) { + /* Try and fuse multiply-adds */ + nir_opt_peephole_ffma(nir); + nir_validate_shader(nir); + } + nir_opt_algebraic_late(nir); nir_validate_shader(nir); -- 2.30.2