diff options
| author | Andrew Stubbs <ams@codesourcery.com> | 2020-02-10 13:23:29 +0000 |
|---|---|---|
| committer | Andrew Stubbs <ams@codesourcery.com> | 2020-07-03 11:00:28 +0100 |
| commit | bf628a97efaf11204ab02527b30ca71d7759ca37 (patch) | |
| tree | 5aab130b83bd083d48fa8b26aea9f6073e978556 | |
| parent | 9e5508c2d006f2d4f8670e6c3fed770ac1c85e64 (diff) | |
| download | gcc-bf628a97efaf11204ab02527b30ca71d7759ca37.zip gcc-bf628a97efaf11204ab02527b30ca71d7759ca37.tar.gz gcc-bf628a97efaf11204ab02527b30ca71d7759ca37.tar.bz2 | |
amdgcn: Add fold_left_plus vector reductions
These aren't real in-order instructions, because the ISA can't do that
quickly, but a means to allow regular out-of-order reductions when that's
good enough, but the middle-end doesn't know so.
gcc/
* config/gcn/gcn-valu.md (fold_left_plus_<mode>): New.
| -rw-r--r-- | gcc/config/gcn/gcn-valu.md | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/gcc/config/gcn/gcn-valu.md b/gcc/config/gcn/gcn-valu.md index 6d7feca..26559ff 100644 --- a/gcc/config/gcn/gcn-valu.md +++ b/gcc/config/gcn/gcn-valu.md @@ -3076,6 +3076,26 @@ DONE; }) +;; Warning: This "-ffast-math" implementation converts in-order reductions +;; into associative reductions. It's also used where OpenMP or +;; OpenACC paralellization has already broken the in-order semantics. +(define_expand "fold_left_plus_<mode>" + [(match_operand:<SCALAR_MODE> 0 "register_operand") + (match_operand:<SCALAR_MODE> 1 "gcn_alu_operand") + (match_operand:V_FP 2 "gcn_alu_operand")] + "can_create_pseudo_p () + && (flag_openacc || flag_openmp + || flag_associative_math)" + { + rtx dest = operands[0]; + rtx scalar = operands[1]; + rtx vector = operands[2]; + rtx tmp = gen_reg_rtx (<SCALAR_MODE>mode); + + emit_insn (gen_reduc_plus_scal_<mode> (tmp, vector)); + emit_insn (gen_add<scalar_mode>3 (dest, scalar, tmp)); + DONE; + }) (define_insn "*<reduc_op>_dpp_shr_<mode>" [(set (match_operand:V_1REG 0 "register_operand" "=v") |