From d038deaa400c819e5867d1e417849b124ccd07b3 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Alejandro=20Pi=C3=B1eiro?= Date: Sat, 1 Jul 2017 08:14:56 +0200 Subject: [PATCH] i965/fs: Add remove_extra_rounding_modes optimization MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Although from SPIR-V point of view, rounding modes are attached to the operation/destination, on i965 it is a status, so we don't need to explicitly set the rounding mode if the one we want is already set. Taking into account that the default mode is RTE, one possible optimization would be optimize out the first RTE set for each block. For in order to work, we would need to take into account block interrelationships. At this point, it is not worth to complicate the optimization for such small gain. v2: Use a single SHADER_OPCODE_RND_MODE opcode taking an immediate with the rounding mode (Curro) v3: Reset optimization for every block. (Jason Ekstrand) Signed-off-by: Jose Maria Casanova Crespo Signed-off-by: Alejandro Piñeiro Reviewed-by: Jason Ekstrand --- src/intel/compiler/brw_eu_defines.h | 1 + src/intel/compiler/brw_fs.cpp | 37 +++++++++++++++++++++++++++++ src/intel/compiler/brw_fs.h | 1 + 3 files changed, 39 insertions(+) diff --git a/src/intel/compiler/brw_eu_defines.h b/src/intel/compiler/brw_eu_defines.h index 8a8f36cbc11..9d5cf05c86e 100644 --- a/src/intel/compiler/brw_eu_defines.h +++ b/src/intel/compiler/brw_eu_defines.h @@ -1252,6 +1252,7 @@ enum PACKED brw_rnd_mode { BRW_RND_MODE_RU = 1, /* Round Up, toward +inf */ BRW_RND_MODE_RD = 2, /* Round Down, toward -inf */ BRW_RND_MODE_RTZ = 3, /* Round Toward Zero */ + BRW_RND_MODE_UNSPECIFIED, /* Unspecified rounding mode */ }; #endif /* BRW_EU_DEFINES_H */ diff --git a/src/intel/compiler/brw_fs.cpp b/src/intel/compiler/brw_fs.cpp index 6cdd2bd9f31..36fb337c620 100644 --- a/src/intel/compiler/brw_fs.cpp +++ b/src/intel/compiler/brw_fs.cpp @@ -3092,6 +3092,42 @@ fs_visitor::remove_duplicate_mrf_writes() return progress; } +/** + * Rounding modes for conversion instructions are included for each + * conversion, but right now it is a state. So once it is set, + * we don't need to call it again for subsequent calls. + * + * This is useful for vector/matrices conversions, as setting the + * mode once is enough for the full vector/matrix + */ +bool +fs_visitor::remove_extra_rounding_modes() +{ + bool progress = false; + + foreach_block (block, cfg) { + brw_rnd_mode prev_mode = BRW_RND_MODE_UNSPECIFIED; + + foreach_inst_in_block_safe (fs_inst, inst, block) { + if (inst->opcode == SHADER_OPCODE_RND_MODE) { + assert(inst->src[0].file == BRW_IMMEDIATE_VALUE); + const brw_rnd_mode mode = (brw_rnd_mode) inst->src[0].d; + if (mode == prev_mode) { + inst->remove(block); + progress = true; + } else { + prev_mode = mode; + } + } + } + } + + if (progress) + invalidate_live_intervals(); + + return progress; +} + static void clear_deps_for_inst_src(fs_inst *inst, bool *deps, int first_grf, int grf_len) { @@ -5808,6 +5844,7 @@ fs_visitor::optimize() int pass_num = 0; OPT(opt_drop_redundant_mov_to_flags); + OPT(remove_extra_rounding_modes); do { progress = false; diff --git a/src/intel/compiler/brw_fs.h b/src/intel/compiler/brw_fs.h index 40dd83f45e4..19b897e7a9f 100644 --- a/src/intel/compiler/brw_fs.h +++ b/src/intel/compiler/brw_fs.h @@ -150,6 +150,7 @@ public: bool eliminate_find_live_channel(); bool dead_code_eliminate(); bool remove_duplicate_mrf_writes(); + bool remove_extra_rounding_modes(); bool opt_sampler_eot(); bool virtual_grf_interferes(int a, int b); -- 2.30.2