[PATCH 08/34] rs6000: Add Power9 builtins
Bill Schmidt
wschmidt@linux.ibm.com
Thu Jul 29 13:30:55 GMT 2021
2021-06-15 Bill Schmidt <wschmidt@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin-new.def: Add power9-vector, power9,
and power9-64 stanzas.
---
gcc/config/rs6000/rs6000-builtin-new.def | 375 +++++++++++++++++++++++
1 file changed, 375 insertions(+)
diff --git a/gcc/config/rs6000/rs6000-builtin-new.def b/gcc/config/rs6000/rs6000-builtin-new.def
index f13fb13b0ad..8885df089a6 100644
--- a/gcc/config/rs6000/rs6000-builtin-new.def
+++ b/gcc/config/rs6000/rs6000-builtin-new.def
@@ -2434,3 +2434,378 @@
const double __builtin_vsx_xscvspdpn (vf);
XSCVSPDPN vsx_xscvspdpn {}
+
+
+; Power9 vector builtins.
+[power9-vector]
+ const vss __builtin_altivec_convert_4f32_8f16 (vf, vf);
+ CONVERT_4F32_8F16 convert_4f32_8f16 {}
+
+ const vss __builtin_altivec_convert_4f32_8i16 (vf, vf);
+ CONVERT_4F32_8I16 convert_4f32_8i16 {}
+
+ const signed int __builtin_altivec_first_match_index_v16qi (vsc, vsc);
+ VFIRSTMATCHINDEX_V16QI first_match_index_v16qi {}
+
+ const signed int __builtin_altivec_first_match_index_v8hi (vss, vss);
+ VFIRSTMATCHINDEX_V8HI first_match_index_v8hi {}
+
+ const signed int __builtin_altivec_first_match_index_v4si (vsi, vsi);
+ VFIRSTMATCHINDEX_V4SI first_match_index_v4si {}
+
+ const signed int __builtin_altivec_first_match_or_eos_index_v16qi (vsc, vsc);
+ VFIRSTMATCHOREOSINDEX_V16QI first_match_or_eos_index_v16qi {}
+
+ const signed int __builtin_altivec_first_match_or_eos_index_v8hi (vss, vss);
+ VFIRSTMATCHOREOSINDEX_V8HI first_match_or_eos_index_v8hi {}
+
+ const signed int __builtin_altivec_first_match_or_eos_index_v4si (vsi, vsi);
+ VFIRSTMATCHOREOSINDEX_V4SI first_match_or_eos_index_v4si {}
+
+ const signed int __builtin_altivec_first_mismatch_index_v16qi (vsc, vsc);
+ VFIRSTMISMATCHINDEX_V16QI first_mismatch_index_v16qi {}
+
+ const signed int __builtin_altivec_first_mismatch_index_v8hi (vss, vss);
+ VFIRSTMISMATCHINDEX_V8HI first_mismatch_index_v8hi {}
+
+ const signed int __builtin_altivec_first_mismatch_index_v4si (vsi, vsi);
+ VFIRSTMISMATCHINDEX_V4SI first_mismatch_index_v4si {}
+
+ const signed int __builtin_altivec_first_mismatch_or_eos_index_v16qi (vsc, vsc);
+ VFIRSTMISMATCHOREOSINDEX_V16QI first_mismatch_or_eos_index_v16qi {}
+
+ const signed int __builtin_altivec_first_mismatch_or_eos_index_v8hi (vss, vss);
+ VFIRSTMISMATCHOREOSINDEX_V8HI first_mismatch_or_eos_index_v8hi {}
+
+ const signed int __builtin_altivec_first_mismatch_or_eos_index_v4si (vsi, vsi);
+ VFIRSTMISMATCHOREOSINDEX_V4SI first_mismatch_or_eos_index_v4si {}
+
+ const vsc __builtin_altivec_vadub (vsc, vsc);
+ VADUB vaduv16qi3 {}
+
+ const vss __builtin_altivec_vaduh (vss, vss);
+ VADUH vaduv8hi3 {}
+
+ const vsi __builtin_altivec_vaduw (vsi, vsi);
+ VADUW vaduv4si3 {}
+
+ const vsll __builtin_altivec_vbpermd (vsll, vsc);
+ VBPERMD altivec_vbpermd {}
+
+ const signed int __builtin_altivec_vclzlsbb_v16qi (vsc);
+ VCLZLSBB_V16QI vclzlsbb_v16qi {}
+
+ const signed int __builtin_altivec_vclzlsbb_v4si (vsi);
+ VCLZLSBB_V4SI vclzlsbb_v4si {}
+
+ const signed int __builtin_altivec_vclzlsbb_v8hi (vss);
+ VCLZLSBB_V8HI vclzlsbb_v8hi {}
+
+ const vsc __builtin_altivec_vctzb (vsc);
+ VCTZB ctzv16qi2 {}
+
+ const vsll __builtin_altivec_vctzd (vsll);
+ VCTZD ctzv2di2 {}
+
+ const vss __builtin_altivec_vctzh (vss);
+ VCTZH ctzv8hi2 {}
+
+ const vsi __builtin_altivec_vctzw (vsi);
+ VCTZW ctzv4si2 {}
+
+ const signed int __builtin_altivec_vctzlsbb_v16qi (vsc);
+ VCTZLSBB_V16QI vctzlsbb_v16qi {}
+
+ const signed int __builtin_altivec_vctzlsbb_v4si (vsi);
+ VCTZLSBB_V4SI vctzlsbb_v4si {}
+
+ const signed int __builtin_altivec_vctzlsbb_v8hi (vss);
+ VCTZLSBB_V8HI vctzlsbb_v8hi {}
+
+ const signed int __builtin_altivec_vcmpaeb_p (vsc, vsc);
+ VCMPAEB_P vector_ae_v16qi_p {}
+
+ const signed int __builtin_altivec_vcmpaed_p (vsll, vsll);
+ VCMPAED_P vector_ae_v2di_p {}
+
+ const signed int __builtin_altivec_vcmpaedp_p (vd, vd);
+ VCMPAEDP_P vector_ae_v2df_p {}
+
+ const signed int __builtin_altivec_vcmpaefp_p (vf, vf);
+ VCMPAEFP_P vector_ae_v4sf_p {}
+
+ const signed int __builtin_altivec_vcmpaeh_p (vss, vss);
+ VCMPAEH_P vector_ae_v8hi_p {}
+
+ const signed int __builtin_altivec_vcmpaew_p (vsi, vsi);
+ VCMPAEW_P vector_ae_v4si_p {}
+
+ const vsc __builtin_altivec_vcmpneb (vsc, vsc);
+ VCMPNEB vcmpneb {}
+
+ const signed int __builtin_altivec_vcmpneb_p (vsc, vsc);
+ VCMPNEB_P vector_ne_v16qi_p {}
+
+ const signed int __builtin_altivec_vcmpned_p (vsll, vsll);
+ VCMPNED_P vector_ne_v2di_p {}
+
+ const signed int __builtin_altivec_vcmpnedp_p (vd, vd);
+ VCMPNEDP_P vector_ne_v2df_p {}
+
+ const signed int __builtin_altivec_vcmpnefp_p (vf, vf);
+ VCMPNEFP_P vector_ne_v4sf_p {}
+
+ const vss __builtin_altivec_vcmpneh (vss, vss);
+ VCMPNEH vcmpneh {}
+
+ const signed int __builtin_altivec_vcmpneh_p (vss, vss);
+ VCMPNEH_P vector_ne_v8hi_p {}
+
+ const vsi __builtin_altivec_vcmpnew (vsi, vsi);
+ VCMPNEW vcmpnew {}
+
+ const signed int __builtin_altivec_vcmpnew_p (vsi, vsi);
+ VCMPNEW_P vector_ne_v4si_p {}
+
+ const vsc __builtin_altivec_vcmpnezb (vsc, vsc);
+ CMPNEZB vcmpnezb {}
+
+ const signed int __builtin_altivec_vcmpnezb_p (signed int, vsc, vsc);
+ VCMPNEZB_P vector_nez_v16qi_p {pred}
+
+ const vss __builtin_altivec_vcmpnezh (vss, vss);
+ CMPNEZH vcmpnezh {}
+
+ const signed int __builtin_altivec_vcmpnezh_p (signed int, vss, vss);
+ VCMPNEZH_P vector_nez_v8hi_p {pred}
+
+ const vsi __builtin_altivec_vcmpnezw (vsi, vsi);
+ CMPNEZW vcmpnezw {}
+
+ const signed int __builtin_altivec_vcmpnezw_p (signed int, vsi, vsi);
+ VCMPNEZW_P vector_nez_v4si_p {pred}
+
+ const signed int __builtin_altivec_vextublx (signed int, vsc);
+ VEXTUBLX vextublx {}
+
+ const signed int __builtin_altivec_vextubrx (signed int, vsc);
+ VEXTUBRX vextubrx {}
+
+ const signed int __builtin_altivec_vextuhlx (signed int, vss);
+ VEXTUHLX vextuhlx {}
+
+ const signed int __builtin_altivec_vextuhrx (signed int, vss);
+ VEXTUHRX vextuhrx {}
+
+ const signed int __builtin_altivec_vextuwlx (signed int, vsi);
+ VEXTUWLX vextuwlx {}
+
+ const signed int __builtin_altivec_vextuwrx (signed int, vsi);
+ VEXTUWRX vextuwrx {}
+
+ const vsq __builtin_altivec_vmsumudm (vsll, vsll, vsq);
+ VMSUMUDM altivec_vmsumudm {}
+
+ const vsll __builtin_altivec_vprtybd (vsll);
+ VPRTYBD parityv2di2 {}
+
+ const vsq __builtin_altivec_vprtybq (vsq);
+ VPRTYBQ parityv1ti2 {}
+
+ const vsi __builtin_altivec_vprtybw (vsi);
+ VPRTYBW parityv4si2 {}
+
+ const vsll __builtin_altivec_vrldmi (vsll, vsll, vsll);
+ VRLDMI altivec_vrldmi {}
+
+ const vsll __builtin_altivec_vrldnm (vsll, vsll);
+ VRLDNM altivec_vrldnm {}
+
+ const vsi __builtin_altivec_vrlwmi (vsi, vsi, vsi);
+ VRLWMI altivec_vrlwmi {}
+
+ const vsi __builtin_altivec_vrlwnm (vsi, vsi);
+ VRLWNM altivec_vrlwnm {}
+
+ const vsll __builtin_altivec_vsignextsb2d (vsc);
+ VSIGNEXTSB2D vsignextend_qi_v2di {}
+
+ const vsi __builtin_altivec_vsignextsb2w (vsc);
+ VSIGNEXTSB2W vsignextend_qi_v4si {}
+
+ const vsll __builtin_altivec_visgnextsh2d (vss);
+ VSIGNEXTSH2D vsignextend_hi_v2di {}
+
+ const vsi __builtin_altivec_vsignextsh2w (vss);
+ VSIGNEXTSH2W vsignextend_hi_v4si {}
+
+ const vsll __builtin_altivec_vsignextsw2d (vsi);
+ VSIGNEXTSW2D vsignextend_si_v2di {}
+
+ const vsc __builtin_altivec_vslv (vsc, vsc);
+ VSLV vslv {}
+
+ const vsc __builtin_altivec_vsrv (vsc, vsc);
+ VSRV vsrv {}
+
+ const signed int __builtin_scalar_byte_in_range (signed int, signed int);
+ CMPRB cmprb {}
+
+ const signed int __builtin_scalar_byte_in_either_range (signed int, signed int);
+ CMPRB2 cmprb2 {}
+
+ const vsll __builtin_vsx_extract4b (vsc, const int[0,12]);
+ EXTRACT4B extract4b {}
+
+ const vd __builtin_vsx_extract_exp_dp (vd);
+ VEEDP xvxexpdp {}
+
+ const vf __builtin_vsx_extract_exp_sp (vf);
+ VEESP xvxexpsp {}
+
+ const vd __builtin_vsx_extract_sig_dp (vd);
+ VESDP xvxsigdp {}
+
+ const vf __builtin_vsx_extract_sig_sp (vf);
+ VESSP xvxsigsp {}
+
+ const vsc __builtin_vsx_insert4b (vsi, vsc, const int[0,12]);
+ INSERT4B insert4b {}
+
+ const vd __builtin_vsx_insert_exp_dp (vd, vd);
+ VIEDP xviexpdp {}
+
+ const vf __builtin_vsx_insert_exp_sp (vf, vf);
+ VIESP xviexpsp {}
+
+ const signed int __builtin_vsx_scalar_cmp_exp_dp_eq (double, double);
+ VSCEDPEQ xscmpexpdp_eq {}
+
+ const signed int __builtin_vsx_scalar_cmp_exp_dp_gt (double, double);
+ VSCEDPGT xscmpexpdp_gt {}
+
+ const signed int __builtin_vsx_scalar_cmp_exp_dp_lt (double, double);
+ VSCEDPLT xscmpexpdp_lt {}
+
+ const signed int __builtin_vsx_scalar_cmp_exp_dp_unordered (double, double);
+ VSCEDPUO xscmpexpdp_unordered {}
+
+ const signed int __builtin_vsx_scalar_test_data_class_dp (double, const int<7>);
+ VSTDCDP xststdcdp {}
+
+ const signed int __builtin_vsx_scalar_test_data_class_sp (float, const int<7>);
+ VSTDCSP xststdcsp {}
+
+ const signed int __builtin_vsx_scalar_test_neg_dp (double);
+ VSTDCNDP xststdcnegdp {}
+
+ const signed int __builtin_vsx_scalar_test_neg_sp (float);
+ VSTDCNSP xststdcnegsp {}
+
+ const vsll __builtin_vsx_test_data_class_dp (vd, const int<7>);
+ VTDCDP xvtstdcdp {}
+
+ const vsi __builtin_vsx_test_data_class_sp (vf, const int<7>);
+ VTDCSP xvtstdcsp {}
+
+ const vf __builtin_vsx_vextract_fp_from_shorth (vss);
+ VEXTRACT_FP_FROM_SHORTH vextract_fp_from_shorth {}
+
+ const vf __builtin_vsx_vextract_fp_from_shortl (vss);
+ VEXTRACT_FP_FROM_SHORTL vextract_fp_from_shortl {}
+
+ const vd __builtin_vsx_xxbrd_v2df (vd);
+ XXBRD_V2DF p9_xxbrd_v2df {}
+
+ const vsll __builtin_vsx_xxbrd_v2di (vsll);
+ XXBRD_V2DI p9_xxbrd_v2di {}
+
+ const vss __builtin_vsx_xxbrh_v8hi (vss);
+ XXBRH_V8HI p9_xxbrh_v8hi {}
+
+ const vsc __builtin_vsx_xxbrq_v16qi (vsc);
+ XXBRQ_V16QI p9_xxbrq_v16qi {}
+
+ const vsq __builtin_vsx_xxbrq_v1ti (vsq);
+ XXBRQ_V1TI p9_xxbrq_v1ti {}
+
+ const vf __builtin_vsx_xxbrw_v4sf (vf);
+ XXBRW_V4SF p9_xxbrw_v4sf {}
+
+ const vsi __builtin_vsx_xxbrw_v4si (vsi);
+ XXBRW_V4SI p9_xxbrw_v4si {}
+
+
+; Miscellaneous P9 functions
+[power9]
+ signed long long __builtin_darn ();
+ DARN darn {}
+
+ signed int __builtin_darn_32 ();
+ DARN_32 darn_32 {}
+
+ signed long long __builtin_darn_raw ();
+ DARN_RAW darn_raw {}
+
+ double __builtin_mffsl ();
+ MFFSL rs6000_mffsl {}
+
+ const signed int __builtin_dtstsfi_eq_dd (const int<6>, _Decimal64);
+ TSTSFI_EQ_DD dfptstsfi_eq_dd {}
+
+ const signed int __builtin_dtstsfi_eq_td (const int<6>, _Decimal128);
+ TSTSFI_EQ_TD dfptstsfi_eq_td {}
+
+ const signed int __builtin_dtstsfi_gt_dd (const int<6>, _Decimal64);
+ TSTSFI_GT_DD dfptstsfi_gt_dd {}
+
+ const signed int __builtin_dtstsfi_gt_td (const int<6>, _Decimal128);
+ TSTSFI_GT_TD dfptstsfi_gt_td {}
+
+ const signed int __builtin_dtstsfi_lt_dd (const int<6>, _Decimal64);
+ TSTSFI_LT_DD dfptstsfi_lt_dd {}
+
+ const signed int __builtin_dtstsfi_lt_td (const int<6>, _Decimal128);
+ TSTSFI_LT_TD dfptstsfi_lt_td {}
+
+ const signed int __builtin_dtstsfi_ov_dd (const int<6>, _Decimal64);
+ TSTSFI_OV_DD dfptstsfi_unordered_dd {}
+
+ const signed int __builtin_dtstsfi_ov_td (const int<6>, _Decimal128);
+ TSTSFI_OV_TD dfptstsfi_unordered_td {}
+
+
+; These things need some review to see whether they really require
+; MASK_POWERPC64. For xsxexpdp, this seems to be fine for 32-bit,
+; because the result will always fit in 32 bits and the return
+; value is SImode; but the pattern currently requires TARGET_64BIT.
+; On the other hand, xsxsigdp has a result that doesn't fit in
+; 32 bits, and the return value is DImode, so it seems that
+; TARGET_64BIT (actually TARGET_POWERPC64) is justified. TBD. ####
+[power9-64]
+ void __builtin_altivec_xst_len_r (vsc, void *, long);
+ XST_LEN_R xst_len_r {}
+
+ void __builtin_altivec_stxvl (vsc, void *, long);
+ STXVL stxvl {}
+
+ const signed int __builtin_scalar_byte_in_set (signed int, signed long long);
+ CMPEQB cmpeqb {}
+
+ pure vsc __builtin_vsx_lxvl (const void *, signed long);
+ LXVL lxvl {}
+
+ const signed long __builtin_vsx_scalar_extract_exp (double);
+ VSEEDP xsxexpdp {}
+
+ const signed long __builtin_vsx_scalar_extract_sig (double);
+ VSESDP xsxsigdp {}
+
+ const double __builtin_vsx_scalar_insert_exp (unsigned long long, unsigned long long);
+ VSIEDP xsiexpdp {}
+
+ const double __builtin_vsx_scalar_insert_exp_dp (double, unsigned long long);
+ VSIEDPF xsiexpdpf {}
+
+ pure vsc __builtin_vsx_xl_len_r (void *, signed long);
+ XL_LEN_R xl_len_r {}
--
2.27.0
More information about the Gcc-patches
mailing list