This patch makes the floating-point conditional FMA patterns provide the same /z alternatives as the integer patterns added by a previous patch. We can handle cases in which individual inputs are allocated to the same register as the output, so we don't need to force all registers to be different.
Tested on aarch64-linux-gnu (with and without SVE) and aarch64_be-elf. Applied as r274516. Richard 2019-08-15 Richard Sandiford <richard.sandif...@arm.com> Kugan Vivekanandarajah <kugan.vivekanandara...@linaro.org> gcc/ * config/aarch64/aarch64-sve.md (*cond_<SVE_COND_FP_TERNARY:optab><SVE_F:mode>_any): Add /z alternatives in which one of the inputs is in the same register as the output. gcc/testsuite/ * gcc.target/aarch64/sve/cond_mla_5.c: Allow FMAD as well as FMLA and FMSB as well as FMLS. Index: gcc/config/aarch64/aarch64-sve.md =================================================================== --- gcc/config/aarch64/aarch64-sve.md 2019-08-15 09:37:10.528856480 +0100 +++ gcc/config/aarch64/aarch64-sve.md 2019-08-15 09:38:53.656095524 +0100 @@ -3844,17 +3844,17 @@ (define_insn_and_rewrite "*cond_<optab>< ;; Predicated floating-point ternary operations, merging with an ;; independent value. (define_insn_and_rewrite "*cond_<optab><mode>_any" - [(set (match_operand:SVE_F 0 "register_operand" "=&w, &w, ?&w") + [(set (match_operand:SVE_F 0 "register_operand" "=&w, &w, &w, &w, &w, ?&w") (unspec:SVE_F - [(match_operand:<VPRED> 1 "register_operand" "Upl, Upl, Upl") + [(match_operand:<VPRED> 1 "register_operand" "Upl, Upl, Upl, Upl, Upl, Upl") (unspec:SVE_F [(match_operand 6) (match_operand:SI 7 "aarch64_sve_gp_strictness") - (match_operand:SVE_F 2 "register_operand" "w, w, w") - (match_operand:SVE_F 3 "register_operand" "w, w, w") - (match_operand:SVE_F 4 "register_operand" "w, w, w")] + (match_operand:SVE_F 2 "register_operand" "w, w, 0, w, w, w") + (match_operand:SVE_F 3 "register_operand" "w, w, w, 0, w, w") + (match_operand:SVE_F 4 "register_operand" "w, 0, w, w, w, w")] SVE_COND_FP_TERNARY) - (match_operand:SVE_F 5 "aarch64_simd_reg_or_zero" "Dz, 0, w")] + (match_operand:SVE_F 5 "aarch64_simd_reg_or_zero" "Dz, Dz, Dz, Dz, 0, w")] UNSPEC_SEL))] "TARGET_SVE && !rtx_equal_p (operands[2], operands[5]) @@ -3863,6 +3863,9 @@ (define_insn_and_rewrite "*cond_<optab>< && aarch64_sve_pred_dominates_p (&operands[6], operands[1])" "@ movprfx\t%0.<Vetype>, %1/z, %4.<Vetype>\;<sve_fmla_op>\t%0.<Vetype>, %1/m, %2.<Vetype>, %3.<Vetype> + movprfx\t%0.<Vetype>, %1/z, %0.<Vetype>\;<sve_fmla_op>\t%0.<Vetype>, %1/m, %2.<Vetype>, %3.<Vetype> + movprfx\t%0.<Vetype>, %1/z, %0.<Vetype>\;<sve_fmad_op>\t%0.<Vetype>, %1/m, %3.<Vetype>, %4.<Vetype> + movprfx\t%0.<Vetype>, %1/z, %0.<Vetype>\;<sve_fmad_op>\t%0.<Vetype>, %1/m, %2.<Vetype>, %4.<Vetype> movprfx\t%0.<Vetype>, %1/m, %4.<Vetype>\;<sve_fmla_op>\t%0.<Vetype>, %1/m, %2.<Vetype>, %3.<Vetype> #" "&& 1" Index: gcc/testsuite/gcc.target/aarch64/sve/cond_mla_5.c =================================================================== --- gcc/testsuite/gcc.target/aarch64/sve/cond_mla_5.c 2019-08-15 09:22:03.047558159 +0100 +++ gcc/testsuite/gcc.target/aarch64/sve/cond_mla_5.c 2019-08-15 09:38:53.656095524 +0100 @@ -39,13 +39,13 @@ TEST_ALL (DEF_LOOP) /* { dg-final { scan-assembler-times {\t(?:mls|msb)\tz[0-9]+\.s, p[0-7]/m,} 1 } } */ /* { dg-final { scan-assembler-times {\t(?:mls|msb)\tz[0-9]+\.d, p[0-7]/m,} 1 } } */ -/* { dg-final { scan-assembler-times {\tfmla\tz[0-9]+\.h, p[0-7]/m,} 1 } } */ -/* { dg-final { scan-assembler-times {\tfmla\tz[0-9]+\.s, p[0-7]/m,} 1 } } */ -/* { dg-final { scan-assembler-times {\tfmla\tz[0-9]+\.d, p[0-7]/m,} 1 } } */ +/* { dg-final { scan-assembler-times {\t(?:fmla|fmad)\tz[0-9]+\.h, p[0-7]/m,} 1 } } */ +/* { dg-final { scan-assembler-times {\t(?:fmla|fmad)\tz[0-9]+\.s, p[0-7]/m,} 1 } } */ +/* { dg-final { scan-assembler-times {\t(?:fmla|fmad)\tz[0-9]+\.d, p[0-7]/m,} 1 } } */ -/* { dg-final { scan-assembler-times {\tfmls\tz[0-9]+\.h, p[0-7]/m,} 1 } } */ -/* { dg-final { scan-assembler-times {\tfmls\tz[0-9]+\.s, p[0-7]/m,} 1 } } */ -/* { dg-final { scan-assembler-times {\tfmls\tz[0-9]+\.d, p[0-7]/m,} 1 } } */ +/* { dg-final { scan-assembler-times {\t(?:fmls|fmsb)\tz[0-9]+\.h, p[0-7]/m,} 1 } } */ +/* { dg-final { scan-assembler-times {\t(?:fmls|fmsb)\tz[0-9]+\.s, p[0-7]/m,} 1 } } */ +/* { dg-final { scan-assembler-times {\t(?:fmls|fmsb)\tz[0-9]+\.d, p[0-7]/m,} 1 } } */ /* { dg-final { scan-assembler-times {\tmovprfx\tz[0-9]+\.b, p[0-7]/z,} 2 } } */ /* { dg-final { scan-assembler-times {\tmovprfx\tz[0-9]+\.h, p[0-7]/z,} 4 } } */