From 8e0e17677afc1a93aa31b8b83849848b7bb52b9b Mon Sep 17 00:00:00 2001 From: "Vladimir N. Makarov" Date: Mon, 17 Mar 2025 15:21:46 -0400 Subject: [PATCH] [PR119285][IRA]: Use an additional way of reg equiv invariant substitution correctness Patch for PR114991 resulted in 5% decrease of SPEC2017 lbm performance on Zen2 and Zen4. For one RTL insn of lbm, LRA with PR114991 patch can not confirm that the equivalence insertion will create a valid RTL insn. This resulted in that the pseudo equiv was assumed costly and pseudo was assigned to hard reg (caller saved as the pseudo lives through calls) and some other pseudos did not get hard regs as it was before PR114991 patch. The insn in question is `pseudo1 = pseduo2 + pseudo3` where pseudo2 has equiv `hard_reg + const`. The old code recognized the insn after equiv substitution as LEA. The new code failed. The patch here makes to use two ways for equiv subsbtitution correctness, the old one and new one (mostly for memory addresses where the old code fails to find the substitution correctness). So given patch fixes lbm performance degradation and actually makes GCC to generate the same code as it was before PR114991 patch. gcc/ChangeLog: PR rtl-optimization/119285 * ira-costs.cc (equiv_can_be_consumed_p): Use 2 ways for recognizing a valid insn after equiv insertion. --- gcc/ira-costs.cc | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) diff --git a/gcc/ira-costs.cc b/gcc/ira-costs.cc index b568c7d0326..70cba942a7b 100644 --- a/gcc/ira-costs.cc +++ b/gcc/ira-costs.cc @@ -1794,21 +1794,6 @@ validate_autoinc_and_mem_addr_p (rtx x) static bool equiv_can_be_consumed_p (int regno, rtx to, rtx_insn *insn, bool invariant_p) { - if (invariant_p) - { - /* We use more expensive code for the invariant because we need to - simplify the result insn as the invariant can be arithmetic rtx - inserted into another arithmetic rtx. */ - rtx pat = PATTERN (insn); - int code = INSN_CODE (insn); - PATTERN (insn) = copy_rtx (pat); - PATTERN (insn) - = simplify_replace_rtx (PATTERN (insn), regno_reg_rtx[regno], to); - bool res = !insn_invalid_p (insn, false); - PATTERN (insn) = pat; - INSN_CODE (insn) = code; - return res; - } validate_replace_src_group (regno_reg_rtx[regno], to, insn); /* We can change register to equivalent memory in autoinc rtl. Some code including verify_changes assumes that autoinc contains only a register. @@ -1817,6 +1802,20 @@ equiv_can_be_consumed_p (int regno, rtx to, rtx_insn *insn, bool invariant_p) if (res) res = verify_changes (0); cancel_changes (0); + if (!res && invariant_p) + { + /* Here we use more expensive code for the invariant because we need to + simplify the result insn as the invariant can be arithmetic rtx + inserted into another arithmetic rtx, e.g. into memory address. */ + rtx pat = PATTERN (insn); + int code = INSN_CODE (insn); + PATTERN (insn) = copy_rtx (pat); + PATTERN (insn) + = simplify_replace_rtx (PATTERN (insn), regno_reg_rtx[regno], to); + res = !insn_invalid_p (insn, false); + PATTERN (insn) = pat; + INSN_CODE (insn) = code; + } return res; }