Przemyslaw Wirkus <przemyslaw.wir...@arm.com> writes: > @@ -5234,21 +5234,21 @@ (define_insn_and_rewrite "*cond_sub<mode>_3_const" > > ;; Predicated floating-point subtraction from a constant, merging with an > ;; independent value. > -(define_insn_and_rewrite "*cond_sub<mode>_any_const" > +;; The subtraction predicate and the merge predicate are allowed to be > +;; different.
Sorry for the micromanagement, but I think this is easier to read if it flows as a single paragraph: ;; Predicated floating-point subtraction from a constant, merging with an ;; independent value. The subtraction predicate and the merge predicate are ;; allowed to be different. or is written as two separate paragraphs: ;; Predicated floating-point subtraction from a constant, merging with an ;; independent value. ;; ;; The subtraction predicate and the merge predicate are allowed to be ;; different. Same for the second comment. > @@ -5271,6 +5271,41 @@ (define_insn_and_rewrite "*cond_sub<mode>_any_const" > [(set_attr "movprfx" "yes")] > ) > > +;; Predicated floating-point subtraction from a constant, merging with an > +;; independent value. > +;; The subtraction predicate and the merge predicate must be the same. > +(define_insn_and_rewrite "*cond_sub<mode>_strict_const" > + [(set (match_operand:SVE_FULL_F 0 "register_operand" "=w, w, ?w") > + (unspec:SVE_FULL_F > + [(match_operand:<VPRED> 1 "register_operand" "Upl, Upl, Upl") > + (unspec:SVE_FULL_F > + [(match_dup 1) > + (const_int SVE_STRICT_GP) > + (match_operand:SVE_FULL_F 2 "aarch64_sve_float_arith_immediate") > + (match_operand:SVE_FULL_F 3 "register_operand" "w, w, w")] > + UNSPEC_COND_FSUB) > + (match_operand:SVE_FULL_F 4 "aarch64_simd_reg_or_zero" "Dz, 0, w")] > + UNSPEC_SEL))] > + "TARGET_SVE && !rtx_equal_p (operands[3], operands[4])" > + "@ > + movprfx\t%0.<Vetype>, %1/z, %3.<Vetype>\;fsubr\t%0.<Vetype>, %1/m, > %0.<Vetype>, #%2 > + movprfx\t%0.<Vetype>, %1/m, %3.<Vetype>\;fsubr\t%0.<Vetype>, %1/m, > %0.<Vetype>, #%2 > + #" > + "&& 1" > + { > + if (reload_completed > + && register_operand (operands[4], <MODE>mode) > + && !rtx_equal_p (operands[0], operands[4])) > + { > + emit_insn (gen_vcond_mask_<mode><vpred> (operands[0], operands[3], > + operands[4], operands[1])); > + operands[4] = operands[3] = operands[0]; > + } > + else > + FAIL; I should have realised this would be the case, sorry, but now that there's only one rewrite, this should simply be: "&& reload_completed && register_operand (operands[4], <MODE>mode) && !rtx_equal_p (operands[0], operands[4]))" { emit_insn (gen_vcond_mask_<mode><vpred> (operands[0], operands[3], operands[4], operands[1])); operands[4] = operands[3] = operands[0]; } OK with those changes, thanks. Richard