From e8ac14527a2fd384c1f2cce56e44a9e93e0a13ec Mon Sep 17 00:00:00 2001 From: Rhys Perry Date: Thu, 6 Aug 2020 17:38:41 +0100 Subject: [PATCH] aco: keep loop live-through variables spilled MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit fossil-db (Navi): Totals from 3149 (2.32% of 135946) affected shaders: VGPRs: 280928 -> 280932 (+0.00%) SpillSGPRs: 51133 -> 30042 (-41.25%) CodeSize: 43063076 -> 41377252 (-3.91%); split: -3.92%, +0.00% Instrs: 8278435 -> 8037133 (-2.91%); split: -2.92%, +0.00% Cycles: 709575456 -> 683366172 (-3.69%); split: -3.69%, +0.00% VMEM: 542887 -> 542937 (+0.01%); split: +0.05%, -0.04% SMEM: 210255 -> 206368 (-1.85%); split: +0.12%, -1.97% SClause: 258847 -> 258019 (-0.32%); split: -0.52%, +0.20% Copies: 731836 -> 684784 (-6.43%); split: -6.44%, +0.01% Branches: 305422 -> 292844 (-4.12%); split: -4.12%, +0.00% PreSGPRs: 333103 -> 332701 (-0.12%) PreVGPRs: 280086 -> 280089 (+0.00%) Helps mostly Detroit: Become Human and the single spilling Doom Eternal shader. Signed-off-by: Rhys Perry Reviewed-by: Daniel Schürmann Cc: 20.2 Part-of: --- src/amd/compiler/aco_spill.cpp | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/src/amd/compiler/aco_spill.cpp b/src/amd/compiler/aco_spill.cpp index 94364bfa54e..7d3055e33e0 100644 --- a/src/amd/compiler/aco_spill.cpp +++ b/src/amd/compiler/aco_spill.cpp @@ -383,6 +383,20 @@ RegisterDemand init_live_in_vars(spill_ctx& ctx, Block* block, unsigned block_id } unsigned loop_end = i; + /* keep live-through spilled */ + for (std::pair> pair : ctx.next_use_distances_end[block_idx - 1]) { + if (pair.second.first < loop_end) + continue; + + Temp to_spill = pair.first; + auto it = ctx.spills_exit[block_idx - 1].find(to_spill); + if (it == ctx.spills_exit[block_idx - 1].end()) + continue; + + ctx.spills_entry[block_idx][to_spill] = it->second; + spilled_registers += to_spill; + } + /* select live-through vgpr variables */ while (new_demand.vgpr - spilled_registers.vgpr > ctx.target_pressure.vgpr) { unsigned distance = 0; -- 2.30.2