From 2b3027bea3f218599d36379d3d593841df7a1559 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Mon, 8 Jul 2024 20:47:52 +0200 Subject: [PATCH] i386: Promote {QI,HI}mode x86_movcc_0_m1_neg to SImode Promote HImode x86_movcc_0_m1_neg insn to SImode to avoid redundant prefixes. Also promote QImode insn when TARGET_PROMOTE_QImode is set. This is similar to promotable_binary_operator splitter, where we promote the result to SImode. Also correct insn condition for splitters to SImode of NEG and NOT instructions. The sizes of QImode and SImode instructions are always the same, so there is no need for optimize_insn_for_size bypass. gcc/ChangeLog: * config/i386/i386.md (x86_movcc_0_m1_neg splitter to SImode): New splitter. (NEG and NOT splitter to SImode): Remove optimize_insn_for_size_p predicate from insn condition. --- gcc/config/i386/i386.md | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md index b24c4fe5875..214cb2e239a 100644 --- a/gcc/config/i386/i386.md +++ b/gcc/config/i386/i386.md @@ -26576,9 +26576,7 @@ (clobber (reg:CC FLAGS_REG))] "! TARGET_PARTIAL_REG_STALL && reload_completed && (GET_MODE (operands[0]) == HImode - || (GET_MODE (operands[0]) == QImode - && (TARGET_PROMOTE_QImode - || optimize_insn_for_size_p ())))" + || (GET_MODE (operands[0]) == QImode && TARGET_PROMOTE_QImode))" [(parallel [(set (match_dup 0) (neg:SI (match_dup 1))) (clobber (reg:CC FLAGS_REG))])] @@ -26593,15 +26591,30 @@ (not (match_operand 1 "general_reg_operand")))] "! TARGET_PARTIAL_REG_STALL && reload_completed && (GET_MODE (operands[0]) == HImode - || (GET_MODE (operands[0]) == QImode - && (TARGET_PROMOTE_QImode - || optimize_insn_for_size_p ())))" + || (GET_MODE (operands[0]) == QImode && TARGET_PROMOTE_QImode))" [(set (match_dup 0) (not:SI (match_dup 1)))] { operands[0] = gen_lowpart (SImode, operands[0]); operands[1] = gen_lowpart (SImode, operands[1]); }) + +(define_split + [(set (match_operand 0 "general_reg_operand") + (neg (match_operator 1 "ix86_carry_flag_operator" + [(reg FLAGS_REG) (const_int 0)]))) + (clobber (reg:CC FLAGS_REG))] + "! TARGET_PARTIAL_REG_STALL && reload_completed + && (GET_MODE (operands[0]) == HImode + || (GET_MODE (operands[0]) == QImode && TARGET_PROMOTE_QImode))" + [(parallel [(set (match_dup 0) + (neg:SI (match_dup 1))) + (clobber (reg:CC FLAGS_REG))])] +{ + operands[0] = gen_lowpart (SImode, operands[0]); + operands[1] = shallow_copy_rtx (operands[1]); + PUT_MODE (operands[1], SImode); +}) ;; RTL Peephole optimizations, run before sched2. These primarily look to ;; transform a complex memory operation into two memory to register operations. -- 2.47.3