Currently, when a function argument of type double gets loaded into a vector register on a 32-bit target, it is firstly reloaded into two general purpose registers, and then loaded into a vector register using two insert.w instructions.
This patch swaps the two insert.w instructions with one insve.d instruction, which operates on 64-bit floating point registers, so the value can be reloaded into a FPR. This is done by adding another alternative of constraints for msa_insert_<msafmt_f> pattern, which covers the case of a floating-point input value. gcc/ChangeLog: * config/mips/mips-msa.md (msa_insert_<msaftm_f>): Add an alternative which covers the floating-point input value. Also forbid the split of insert.d pattern for floating-point values. gcc/testsuite/ChangeLog: * gcc.target/mips/msa-insert-split.c: New test. --- gcc/config/mips/mips-msa.md | 11 ++++++++--- gcc/testsuite/gcc.target/mips/msa-insert-split.c | 16 ++++++++++++++++ 2 files changed, 24 insertions(+), 3 deletions(-) create mode 100644 gcc/testsuite/gcc.target/mips/msa-insert-split.c diff --git a/gcc/config/mips/mips-msa.md b/gcc/config/mips/mips-msa.md index 929646d..628423d 100644 --- a/gcc/config/mips/mips-msa.md +++ b/gcc/config/mips/mips-msa.md @@ -436,14 +436,17 @@ }) (define_insn "msa_insert_<msafmt_f>" - [(set (match_operand:MSA 0 "register_operand" "=f") + [(set (match_operand:MSA 0 "register_operand" "=f,f") (vec_merge:MSA (vec_duplicate:MSA - (match_operand:<UNITMODE> 1 "reg_or_0_operand" "dJ")) - (match_operand:MSA 2 "register_operand" "0") + (match_operand:<UNITMODE> 1 "reg_or_0_operand" "dJ,f")) + (match_operand:MSA 2 "register_operand" "0,0") (match_operand 3 "const_<bitmask>_operand" "")))] "ISA_HAS_MSA" { + if (which_alternative == 1) + return "insve.<msafmt>\t%w0[%y3],%w1[0]"; + if (!TARGET_64BIT && (<MODE>mode == V2DImode || <MODE>mode == V2DFmode)) return "#"; else @@ -462,6 +465,8 @@ "reload_completed && ISA_HAS_MSA && !TARGET_64BIT" [(const_int 0)] { + if (REG_P (operands[1]) && FP_REG_P (REGNO (operands[1]))) + FAIL; mips_split_msa_insert_d (operands[0], operands[2], operands[3], operands[1]); DONE; }) diff --git a/gcc/testsuite/gcc.target/mips/msa-insert-split.c b/gcc/testsuite/gcc.target/mips/msa-insert-split.c new file mode 100644 index 0000000..50f3b8a --- /dev/null +++ b/gcc/testsuite/gcc.target/mips/msa-insert-split.c @@ -0,0 +1,16 @@ +/* { dg-do compile } */ +/* { dg-options "-mfp64 -mhard-float -mmsa" } */ +/* { dg-skip-if "code quality test" { *-*-* } { "-O0" } { "" } } */ + +typedef double v2f64 __attribute__ ((vector_size (16))); + +void foo (double* arr, v2f64* vec) +{ + v2f64 v; + v[0] = arr[0]; + v[1] = arr[1]; + *vec = v; +} + +/* { dg-final { scan-assembler-not "insert.w" } } */ +/* { dg-final { scan-assembler-times "insve.d" 2 } } */ -- 2.7.4