extend.texi (PowerPC AltiVec/VSX Built-in Functions): Document new power8 builtins.
[gcc]
2013-06-06 Michael Meissner <meissner@linux.vnet.ibm.com>
Pat Haugen <pthaugen@us.ibm.com>
Peter Bergner <bergner@vnet.ibm.com>
* doc/extend.texi (PowerPC AltiVec/VSX Built-in Functions):
Document new power8 builtins.
* config/rs6000/vector.md (and<mode>3): Add a clobber/scratch of a
condition code register, to allow 128-bit logical operations to be
done in the VSX or GPR registers.
(nor<mode>3): Use the canonical form for nor.
(eqv<mode>3): Add expanders for power8 xxleqv, xxlnand, xxlorc,
vclz*, and vpopcnt* vector instructions.
(nand<mode>3): Likewise.
(orc<mode>3): Likewise.
(clz<mode>2): LIkewise.
(popcount<mode>2): Likewise.
* config/rs6000/predicates.md (int_reg_operand): Rework tests so
that only the GPRs are recognized.
* config/rs6000/rs6000-c.c (altivec_overloaded_builtins): Add
support for new power8 builtins.
* config/rs6000/rs6000.c (rs6000_option_override_internal): Only
allow power8 quad mode in 64-bit.
(rs6000_builtin_vectorized_function): Add support to vectorize
ISA 2.07 count leading zeros, population count builtins.
(rs6000_expand_vector_init): On ISA 2.07 use xscvdpspn to form
V4SF vectors instead of xscvdpsp to avoid IEEE related traps.
(builtin_function_type): Add vgbbd builtin function which takes an
unsigned argument.
(altivec_expand_vec_perm_const): Add support for new power8 merge
instructions.
* config/rs6000/vsx.md (VSX_L2): New iterator for 128-bit types,
that does not include TImdoe for use with 32-bit.
(UNSPEC_VSX_CVSPDPN): Support for power8 xscvdpspn and xscvspdpn
instructions.
(UNSPEC_VSX_CVDPSPN): Likewise.
(vsx_xscvdpspn): Likewise.
(vsx_xscvspdpn): Likewise.
(vsx_xscvdpspn_scalar): Likewise.
(vsx_xscvspdpn_directmove): Likewise.
(vsx_and<mode>3): Split logical operations into 32-bit and
64-bit. Add support to do logical operations on TImode as well as
VSX vector types. Allow logical operations to be done in either
VSX registers or in general purpose registers in 64-bit mode. Add
splitters if GPRs were used. For AND, add clobber of CCmode to
allow use of ANDI on GPRs. Rewrite nor to use the canonical RTL
encoding.
(vsx_and<mode>3_32bit): Likewise.
(vsx_and<mode>3_64bit): Likewise.
(vsx_ior<mode>3): Likewise.
(vsx_ior<mode>3_32bit): Likewise.
(vsx_ior<mode>3_64bit): Likewise.
(vsx_xor<mode>3): Likewise.
(vsx_xor<mode>3_32bit): Likewise.
(vsx_xor<mode>3_64bit): Likewise.
(vsx_one_cmpl<mode>2): Likewise.
(vsx_one_cmpl<mode>2_32bit): Likewise.
(vsx_one_cmpl<mode>2_64bit): Likewise.
(vsx_nor<mode>3): Likewise.
(vsx_nor<mode>3_32bit): Likewise.
(vsx_nor<mode>3_64bit): Likewise.
(vsx_andc<mode>3): Likewise.
(vsx_andc<mode>3_32bit): Likewise.
(vsx_andc<mode>3_64bit): Likewise.
(vsx_eqv<mode>3_32bit): Add support for power8 xxleqv, xxlnand,
and xxlorc instructions.
(vsx_eqv<mode>3_64bit): Likewise.
(vsx_nand<mode>3_32bit): Likewise.
(vsx_nand<mode>3_64bit): Likewise.
(vsx_orc<mode>3_32bit): Likewise.
(vsx_orc<mode>3_64bit): Likewise.
* config/rs6000/altivec.md (UNSPEC_VGBBD): Add power8 vgbbd
instruction.
(p8_vmrgew): Add power8 vmrgew and vmrgow instructions.
(p8_vmrgow): Likewise.
(altivec_and<mode>3): Add clobber of CCmode to allow AND using
GPRs to be split under VSX.
(p8v_clz<mode>2): Add power8 count leading zero support.
(p8v_popcount<mode>2): Add power8 population count support.
(p8v_vgbbd): Add power8 gather bits by bytes by doubleword
support.
* config/rs6000/rs6000.md (eqv<mode>3): Add support for powerp eqv
instruction.