From dfd878f2badac012a1ccdec28da9795d893d337c Mon Sep 17 00:00:00 2001 From: Samuel Pitoiset Date: Tue, 10 Nov 2020 11:20:18 +0100 Subject: [PATCH] aco: combine more s_add+s_lshl to s_lshl_add by ignoring uses Even if the s_lshl is used more that once, it can still be combined. fossils-db (Vega10): Totals from 771 (0.55% of 139517) affected shaders: SGPRs: 46216 -> 46304 (+0.19%); split: -0.02%, +0.21% VGPRs: 38488 -> 38464 (-0.06%) SpillSGPRs: 1894 -> 1875 (-1.00%); split: -3.12%, +2.11% CodeSize: 5681856 -> 5679844 (-0.04%); split: -0.07%, +0.03% MaxWaves: 5320 -> 5323 (+0.06%) Instrs: 1093960 -> 1093474 (-0.04%); split: -0.09%, +0.05% Cycles: 47198380 -> 47258872 (+0.13%); split: -0.06%, +0.19% VMEM: 176036 -> 176283 (+0.14%); split: +0.16%, -0.02% SMEM: 53397 -> 53255 (-0.27%); split: +0.03%, -0.30% VClause: 23156 -> 23152 (-0.02%); split: -0.03%, +0.01% SClause: 35716 -> 35726 (+0.03%); split: -0.00%, +0.03% Copies: 139395 -> 139871 (+0.34%); split: -0.04%, +0.39% Branches: 33808 -> 33798 (-0.03%); split: -0.04%, +0.01% PreSGPRs: 35381 -> 35331 (-0.14%); split: -0.20%, +0.06% Signed-off-by: Samuel Pitoiset Reviewed-by: Rhys Perry Part-of: --- src/amd/compiler/aco_optimizer.cpp | 2 +- src/amd/compiler/tests/test_optimizer.cpp | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/src/amd/compiler/aco_optimizer.cpp b/src/amd/compiler/aco_optimizer.cpp index 9d6219037de..89fcdee261e 100644 --- a/src/amd/compiler/aco_optimizer.cpp +++ b/src/amd/compiler/aco_optimizer.cpp @@ -2207,7 +2207,7 @@ bool combine_salu_lshl_add(opt_ctx& ctx, aco_ptr& instr) return false; for (unsigned i = 0; i < 2; i++) { - Instruction *op2_instr = follow_operand(ctx, instr->operands[i]); + Instruction *op2_instr = follow_operand(ctx, instr->operands[i], true); if (!op2_instr || op2_instr->opcode != aco_opcode::s_lshl_b32 || ctx.uses[op2_instr->definitions[1].tempId()]) continue; diff --git a/src/amd/compiler/tests/test_optimizer.cpp b/src/amd/compiler/tests/test_optimizer.cpp index 00e4cdef6dd..4be2f6226ae 100644 --- a/src/amd/compiler/tests/test_optimizer.cpp +++ b/src/amd/compiler/tests/test_optimizer.cpp @@ -143,9 +143,9 @@ BEGIN_TEST(optimize.add_lshl) Operand(inputs[0]), Operand(3u)); writeout(0, bld.sop2(aco_opcode::s_add_u32, bld.def(s1), bld.def(s1, scc), shift, Operand(4u))); - //! s1: %lshl, s1: %_:scc = s_lshl_b32 %a, 3 - //! v1: %add = v_add_u32 %lshl, %b - //! v1: %res1 = v_add3_u32 %add, %lshl, 4 + //! s1: %lshl1, s1: %_:scc = s_lshl3_add_u32 %a, 4 + //! v1: %lshl_add = v_lshl_add_u32 %a, 3, %b + //! v1: %res1 = v_add_u32 %lshl1, %lshl_add //! p_unit_test 1, %res1 shift = bld.sop2(aco_opcode::s_lshl_b32, bld.def(s1), bld.def(s1, scc), Operand(inputs[0]), Operand(3u));