From: Matthew Wahab Date: Fri, 23 Sep 2016 10:34:57 +0000 (+0000) Subject: [PATCH 12/17][ARM] Add builtins for NEON FP16 intrinsics. X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=0768b127e5ea675efb5377fc6bbd52e399a6f580;p=gcc.git [PATCH 12/17][ARM] Add builtins for NEON FP16 intrinsics. 2016-09-23 Matthew Wahab * config/arm/arm_neon_builtins.def (vadd): New (v8hf, v4hf variants). (vmulf): New (v8hf, v4hf variants). (vfma): New (v8hf, v4hf variants). (vfms): New (v8hf, v4hf variants). (vsub): New (v8hf, v4hf variants). (vcage): New (v8hf, v4hf variants). (vcagt): New (v8hf, v4hf variants). (vcale): New (v8hf, v4hf variants). (vcalt): New (v8hf, v4hf variants). (vceq): New (v8hf, v4hf variants). (vcgt): New (v8hf, v4hf variants). (vcge): New (v8hf, v4hf variants). (vcle): New (v8hf, v4hf variants). (vclt): New (v8hf, v4hf variants). (vceqz): New (v8hf, v4hf variants). (vcgez): New (v8hf, v4hf variants). (vcgtz): New (v8hf, v4hf variants). (vcltz): New (v8hf, v4hf variants). (vclez): New (v8hf, v4hf variants). (vabd): New (v8hf, v4hf variants). (vmaxf): New (v8hf, v4hf variants). (vmaxnm): New (v8hf, v4hf variants). (vminf): New (v8hf, v4hf variants). (vminnm): New (v8hf, v4hf variants). (vpmaxf): New (v4hf variant). (vpminf): New (v4hf variant). (vpadd): New (v4hf variant). (vrecps): New (v8hf, v4hf variants). (vrsqrts): New (v8hf, v4hf variants). (vabs): New (v8hf, v4hf variants). (vneg): New (v8hf, v4hf variants). (vrecpe): New (v8hf, v4hf variants). (vrnd): New (v8hf, v4hf variants). (vrnda): New (v8hf, v4hf variants). (vrndm): New (v8hf, v4hf variants). (vrndn): New (v8hf, v4hf variants). (vrndp): New (v8hf, v4hf variants). (vrndx): New (v8hf, v4hf variants). (vrsqrte): New (v8hf, v4hf variants). (vmul_lane): Add v4hf and v8hf variants. (vmul_n): Add v4hf and v8hf variants. (vext): New (v8hf, v4hf variants). (vcvts): New (v8hi, v4hi variants). (vcvts): New (v8hf, v4hf variants). (vcvtu): New (v8hi, v4hi variants). (vcvtu): New (v8hf, v4hf variants). (vcvts_n): New (v8hf, v4hf variants). (vcvtu_n): New (v8hi, v4hi variants). (vcvts_n): New (v8hi, v4hi variants). (vcvtu_n): New (v8hf, v4hf variants). (vbsl): New (v8hf, v4hf variants). (vcvtas): New (v8hf, v4hf variants). (vcvtau): New (v8hf, v4hf variants). (vcvtms): New (v8hf, v4hf variants). (vcvtmu): New (v8hf, v4hf variants). (vcvtns): New (v8hf, v4hf variants). (vcvtnu): New (v8hf, v4hf variants). (vcvtps): New (v8hf, v4hf variants). (vcvtpu): New (v8hf, v4hf variants). From-SVN: r240422 --- diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 9e76a72575e..9d306bd5104 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,66 @@ +2016-09-23 Matthew Wahab + + * config/arm/arm_neon_builtins.def (vadd): New (v8hf, v4hf + variants). + (vmulf): New (v8hf, v4hf variants). + (vfma): New (v8hf, v4hf variants). + (vfms): New (v8hf, v4hf variants). + (vsub): New (v8hf, v4hf variants). + (vcage): New (v8hf, v4hf variants). + (vcagt): New (v8hf, v4hf variants). + (vcale): New (v8hf, v4hf variants). + (vcalt): New (v8hf, v4hf variants). + (vceq): New (v8hf, v4hf variants). + (vcgt): New (v8hf, v4hf variants). + (vcge): New (v8hf, v4hf variants). + (vcle): New (v8hf, v4hf variants). + (vclt): New (v8hf, v4hf variants). + (vceqz): New (v8hf, v4hf variants). + (vcgez): New (v8hf, v4hf variants). + (vcgtz): New (v8hf, v4hf variants). + (vcltz): New (v8hf, v4hf variants). + (vclez): New (v8hf, v4hf variants). + (vabd): New (v8hf, v4hf variants). + (vmaxf): New (v8hf, v4hf variants). + (vmaxnm): New (v8hf, v4hf variants). + (vminf): New (v8hf, v4hf variants). + (vminnm): New (v8hf, v4hf variants). + (vpmaxf): New (v4hf variant). + (vpminf): New (v4hf variant). + (vpadd): New (v4hf variant). + (vrecps): New (v8hf, v4hf variants). + (vrsqrts): New (v8hf, v4hf variants). + (vabs): New (v8hf, v4hf variants). + (vneg): New (v8hf, v4hf variants). + (vrecpe): New (v8hf, v4hf variants). + (vrnd): New (v8hf, v4hf variants). + (vrnda): New (v8hf, v4hf variants). + (vrndm): New (v8hf, v4hf variants). + (vrndn): New (v8hf, v4hf variants). + (vrndp): New (v8hf, v4hf variants). + (vrndx): New (v8hf, v4hf variants). + (vrsqrte): New (v8hf, v4hf variants). + (vmul_lane): Add v4hf and v8hf variants. + (vmul_n): Add v4hf and v8hf variants. + (vext): New (v8hf, v4hf variants). + (vcvts): New (v8hi, v4hi variants). + (vcvts): New (v8hf, v4hf variants). + (vcvtu): New (v8hi, v4hi variants). + (vcvtu): New (v8hf, v4hf variants). + (vcvts_n): New (v8hf, v4hf variants). + (vcvtu_n): New (v8hi, v4hi variants). + (vcvts_n): New (v8hi, v4hi variants). + (vcvtu_n): New (v8hf, v4hf variants). + (vbsl): New (v8hf, v4hf variants). + (vcvtas): New (v8hf, v4hf variants). + (vcvtau): New (v8hf, v4hf variants). + (vcvtms): New (v8hf, v4hf variants). + (vcvtmu): New (v8hf, v4hf variants). + (vcvtns): New (v8hf, v4hf variants). + (vcvtnu): New (v8hf, v4hf variants). + (vcvtps): New (v8hf, v4hf variants). + (vcvtpu): New (v8hf, v4hf variants). + 2016-09-23 Matthew Wahab * config/arm/arm-builtins.c (hf_UP): New. diff --git a/gcc/config/arm/arm_neon_builtins.def b/gcc/config/arm/arm_neon_builtins.def index a4ba516209c..b29aa91a64e 100644 --- a/gcc/config/arm/arm_neon_builtins.def +++ b/gcc/config/arm/arm_neon_builtins.def @@ -19,6 +19,7 @@ . */ VAR2 (BINOP, vadd, v2sf, v4sf) +VAR2 (BINOP, vadd, v8hf, v4hf) VAR3 (BINOP, vaddls, v8qi, v4hi, v2si) VAR3 (BINOP, vaddlu, v8qi, v4hi, v2si) VAR3 (BINOP, vaddws, v8qi, v4hi, v2si) @@ -32,12 +33,15 @@ VAR8 (BINOP, vqaddu, v8qi, v4hi, v2si, di, v16qi, v8hi, v4si, v2di) VAR3 (BINOP, vaddhn, v8hi, v4si, v2di) VAR3 (BINOP, vraddhn, v8hi, v4si, v2di) VAR2 (BINOP, vmulf, v2sf, v4sf) +VAR2 (BINOP, vmulf, v8hf, v4hf) VAR2 (BINOP, vmulp, v8qi, v16qi) VAR8 (TERNOP, vmla, v8qi, v4hi, v2si, v2sf, v16qi, v8hi, v4si, v4sf) VAR3 (TERNOP, vmlals, v8qi, v4hi, v2si) VAR3 (TERNOP, vmlalu, v8qi, v4hi, v2si) VAR2 (TERNOP, vfma, v2sf, v4sf) +VAR2 (TERNOP, vfma, v4hf, v8hf) VAR2 (TERNOP, vfms, v2sf, v4sf) +VAR2 (TERNOP, vfms, v4hf, v8hf) VAR8 (TERNOP, vmls, v8qi, v4hi, v2si, v2sf, v16qi, v8hi, v4si, v4sf) VAR3 (TERNOP, vmlsls, v8qi, v4hi, v2si) VAR3 (TERNOP, vmlslu, v8qi, v4hi, v2si) @@ -94,6 +98,7 @@ VAR8 (TERNOP_IMM, vsrau_n, v8qi, v4hi, v2si, di, v16qi, v8hi, v4si, v2di) VAR8 (TERNOP_IMM, vrsras_n, v8qi, v4hi, v2si, di, v16qi, v8hi, v4si, v2di) VAR8 (TERNOP_IMM, vrsrau_n, v8qi, v4hi, v2si, di, v16qi, v8hi, v4si, v2di) VAR2 (BINOP, vsub, v2sf, v4sf) +VAR2 (BINOP, vsub, v8hf, v4hf) VAR3 (BINOP, vsubls, v8qi, v4hi, v2si) VAR3 (BINOP, vsublu, v8qi, v4hi, v2si) VAR3 (BINOP, vsubws, v8qi, v4hi, v2si) @@ -111,12 +116,27 @@ VAR8 (BINOP, vcgt, v8qi, v4hi, v2si, v2sf, v16qi, v8hi, v4si, v4sf) VAR6 (BINOP, vcgtu, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR2 (BINOP, vcage, v2sf, v4sf) VAR2 (BINOP, vcagt, v2sf, v4sf) +VAR2 (BINOP, vcage, v4hf, v8hf) +VAR2 (BINOP, vcagt, v4hf, v8hf) +VAR2 (BINOP, vcale, v4hf, v8hf) +VAR2 (BINOP, vcalt, v4hf, v8hf) +VAR2 (BINOP, vceq, v4hf, v8hf) +VAR2 (BINOP, vcge, v4hf, v8hf) +VAR2 (BINOP, vcgt, v4hf, v8hf) +VAR2 (BINOP, vcle, v4hf, v8hf) +VAR2 (BINOP, vclt, v4hf, v8hf) +VAR2 (UNOP, vceqz, v4hf, v8hf) +VAR2 (UNOP, vcgez, v4hf, v8hf) +VAR2 (UNOP, vcgtz, v4hf, v8hf) +VAR2 (UNOP, vclez, v4hf, v8hf) +VAR2 (UNOP, vcltz, v4hf, v8hf) VAR6 (BINOP, vtst, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR6 (BINOP, vabds, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR6 (BINOP, vabdu, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR2 (BINOP, vabdf, v2sf, v4sf) VAR3 (BINOP, vabdls, v8qi, v4hi, v2si) VAR3 (BINOP, vabdlu, v8qi, v4hi, v2si) +VAR2 (BINOP, vabd, v8hf, v4hf) VAR6 (TERNOP, vabas, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR6 (TERNOP, vabau, v8qi, v4hi, v2si, v16qi, v8hi, v4si) @@ -126,27 +146,38 @@ VAR3 (TERNOP, vabalu, v8qi, v4hi, v2si) VAR6 (BINOP, vmaxs, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR6 (BINOP, vmaxu, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR2 (BINOP, vmaxf, v2sf, v4sf) +VAR2 (BINOP, vmaxf, v8hf, v4hf) +VAR2 (BINOP, vmaxnm, v4hf, v8hf) VAR6 (BINOP, vmins, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR6 (BINOP, vminu, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR2 (BINOP, vminf, v2sf, v4sf) +VAR2 (BINOP, vminf, v4hf, v8hf) +VAR2 (BINOP, vminnm, v8hf, v4hf) VAR3 (BINOP, vpmaxs, v8qi, v4hi, v2si) VAR3 (BINOP, vpmaxu, v8qi, v4hi, v2si) VAR1 (BINOP, vpmaxf, v2sf) +VAR1 (BINOP, vpmaxf, v4hf) VAR3 (BINOP, vpmins, v8qi, v4hi, v2si) VAR3 (BINOP, vpminu, v8qi, v4hi, v2si) VAR1 (BINOP, vpminf, v2sf) +VAR1 (BINOP, vpminf, v4hf) VAR4 (BINOP, vpadd, v8qi, v4hi, v2si, v2sf) +VAR1 (BINOP, vpadd, v4hf) VAR6 (UNOP, vpaddls, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR6 (UNOP, vpaddlu, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR6 (BINOP, vpadals, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR6 (BINOP, vpadalu, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR2 (BINOP, vrecps, v2sf, v4sf) VAR2 (BINOP, vrsqrts, v2sf, v4sf) +VAR2 (BINOP, vrecps, v4hf, v8hf) +VAR2 (BINOP, vrsqrts, v4hf, v8hf) VAR8 (TERNOP_IMM, vsri_n, v8qi, v4hi, v2si, di, v16qi, v8hi, v4si, v2di) VAR8 (TERNOP_IMM, vsli_n, v8qi, v4hi, v2si, di, v16qi, v8hi, v4si, v2di) VAR8 (UNOP, vabs, v8qi, v4hi, v2si, v2sf, v16qi, v8hi, v4si, v4sf) +VAR2 (UNOP, vabs, v8hf, v4hf) +VAR2 (UNOP, vneg, v8hf, v4hf) VAR6 (UNOP, vqabs, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR8 (UNOP, vneg, v8qi, v4hi, v2si, v2sf, v16qi, v8hi, v4si, v4sf) VAR6 (UNOP, vqneg, v8qi, v4hi, v2si, v16qi, v8hi, v4si) @@ -155,8 +186,16 @@ VAR6 (UNOP, vclz, v8qi, v4hi, v2si, v16qi, v8hi, v4si) VAR5 (BSWAP, bswap, v4hi, v8hi, v2si, v4si, v2di) VAR2 (UNOP, vcnt, v8qi, v16qi) VAR4 (UNOP, vrecpe, v2si, v2sf, v4si, v4sf) +VAR2 (UNOP, vrecpe, v8hf, v4hf) VAR4 (UNOP, vrsqrte, v2si, v2sf, v4si, v4sf) +VAR2 (UNOP, vrsqrte, v4hf, v8hf) VAR6 (UNOP, vmvn, v8qi, v4hi, v2si, v16qi, v8hi, v4si) +VAR2 (UNOP, vrnd, v8hf, v4hf) +VAR2 (UNOP, vrnda, v8hf, v4hf) +VAR2 (UNOP, vrndm, v8hf, v4hf) +VAR2 (UNOP, vrndn, v8hf, v4hf) +VAR2 (UNOP, vrndp, v8hf, v4hf) +VAR2 (UNOP, vrndx, v8hf, v4hf) /* FIXME: vget_lane supports more variants than this! */ VAR10 (GETLANE, vget_lane, v8qi, v4hi, v2si, v2sf, di, v16qi, v8hi, v4si, v4sf, v2di) @@ -179,7 +218,7 @@ VAR3 (UNOP, vqmovnu, v8hi, v4si, v2di) VAR3 (UNOP, vqmovun, v8hi, v4si, v2di) VAR3 (UNOP, vmovls, v8qi, v4hi, v2si) VAR3 (UNOP, vmovlu, v8qi, v4hi, v2si) -VAR6 (SETLANE, vmul_lane, v4hi, v2si, v2sf, v8hi, v4si, v4sf) +VAR8 (SETLANE, vmul_lane, v4hi, v2si, v2sf, v8hi, v4si, v4sf, v4hf, v8hf) VAR6 (MAC_LANE, vmla_lane, v4hi, v2si, v2sf, v8hi, v4si, v4sf) VAR2 (MAC_LANE, vmlals_lane, v4hi, v2si) VAR2 (MAC_LANE, vmlalu_lane, v4hi, v2si) @@ -188,7 +227,7 @@ VAR6 (MAC_LANE, vmls_lane, v4hi, v2si, v2sf, v8hi, v4si, v4sf) VAR2 (MAC_LANE, vmlsls_lane, v4hi, v2si) VAR2 (MAC_LANE, vmlslu_lane, v4hi, v2si) VAR2 (MAC_LANE, vqdmlsl_lane, v4hi, v2si) -VAR6 (BINOP, vmul_n, v4hi, v2si, v2sf, v8hi, v4si, v4sf) +VAR8 (BINOP, vmul_n, v4hi, v2si, v2sf, v8hi, v4si, v4sf, v4hf, v8hf) VAR6 (MAC_N, vmla_n, v4hi, v2si, v2sf, v8hi, v4si, v4sf) VAR2 (MAC_N, vmlals_n, v4hi, v2si) VAR2 (MAC_N, vmlalu_n, v4hi, v2si) @@ -204,9 +243,17 @@ VAR8 (UNOP, vrev64, v8qi, v4hi, v2si, v2sf, v16qi, v8hi, v4si, v4sf) VAR4 (UNOP, vrev32, v8qi, v4hi, v16qi, v8hi) VAR2 (UNOP, vrev16, v8qi, v16qi) VAR4 (UNOP, vcvts, v2si, v2sf, v4si, v4sf) +VAR2 (UNOP, vcvts, v4hi, v8hi) +VAR2 (UNOP, vcvts, v4hf, v8hf) +VAR2 (UNOP, vcvtu, v4hi, v8hi) +VAR2 (UNOP, vcvtu, v4hf, v8hf) VAR4 (UNOP, vcvtu, v2si, v2sf, v4si, v4sf) VAR4 (BINOP, vcvts_n, v2si, v2sf, v4si, v4sf) VAR4 (BINOP, vcvtu_n, v2si, v2sf, v4si, v4sf) +VAR2 (BINOP, vcvts_n, v4hf, v8hf) +VAR2 (BINOP, vcvtu_n, v4hi, v8hi) +VAR2 (BINOP, vcvts_n, v4hi, v8hi) +VAR2 (BINOP, vcvtu_n, v4hf, v8hf) VAR1 (UNOP, vcvtv4sf, v4hf) VAR1 (UNOP, vcvtv4hf, v4sf) VAR10 (TERNOP, vbsl, @@ -223,6 +270,14 @@ VAR1 (UNOP, vcvtav2sf, v2si) VAR1 (UNOP, vcvtav4sf, v4si) VAR1 (UNOP, vcvtauv2sf, v2si) VAR1 (UNOP, vcvtauv4sf, v4si) +VAR2 (UNOP, vcvtas, v4hf, v8hf) +VAR2 (UNOP, vcvtau, v4hf, v8hf) +VAR2 (UNOP, vcvtms, v4hf, v8hf) +VAR2 (UNOP, vcvtmu, v4hf, v8hf) +VAR2 (UNOP, vcvtns, v4hf, v8hf) +VAR2 (UNOP, vcvtnu, v4hf, v8hf) +VAR2 (UNOP, vcvtps, v4hf, v8hf) +VAR2 (UNOP, vcvtpu, v4hf, v8hf) VAR1 (UNOP, vcvtpv2sf, v2si) VAR1 (UNOP, vcvtpv4sf, v4si) VAR1 (UNOP, vcvtpuv2sf, v2si)