+2009-11-04 Harsha Jagasia <harsha.jagasia@amd.com>
+ Dwarakanath Rajagopal <dwarak.rajagopal@amd.com>
+
+ * config.gcc (i[34567]86-*-*): Include xopintrin.h.
+ (x86_64-*-*): Ditto.
+ * config/i386/xopintrin.h: New file, provide common x86 compiler
+ intrinisics for XOP.
+ * config/i386/cpuid.h (bit_XOP): Define XOP bit.
+ * config/i386/x86intrin.h: Add XOP check and xopintrin.h.
+ * config/i386/i386-c.c(ix86_target_macros_internal): Check
+ ISA_FLAG for XOP.
+ * config/i386/i386.h(TARGET_XOP): New macro for XOP.
+ * config/i386/i386.opt (-mxop): New switch for XOP support.
+ * config/i386/i386.md (UNSPEC_XOP_UNSIGNED_CMP)
+ (UNSPEC_XOP_TRUEFALSE)
+ (UNSPEC_XOP_PERMUTE)
+ (UNSPEC_FRCZ): Add new UNSPEC for XOP support.
+ (PPERM_*): New constants for vpperm instruction.
+ (xop_pcmov_<mode>): Add XOP conditional mov instructions.
+ * config/i386/i386.c (OPTION_MASK_ISA_XOP_SET): New.
+ (OPTION_MASK_ISA_XOP_UNSET): New.
+ (OPTION_MASK_ISA_XOP_UNSET): Change definition to
+ depend on XOP.
+ (ix86_handle_option): Handle -mxop.
+ (isa_opts): Handle -mxop.
+ (enum pta_flags): Add PTA_XOP.
+ (override_options): Add XOP support.
+ (print_operand): Add code for XOP compare instructions.
+ (ix86_expand_sse_movcc): Extend for XOP conditional move instruction.
+ (ix86_expand_int_vcond): Extend for XOP compare instruction.
+
+ (IX86_BUILTIN_VPCMOV): New for XOP intrinsic.
+ (IX86_BUILTIN_VPCMOV_V2DI): Ditto.
+ (IX86_BUILTIN_VPCMOV_V4SI): Ditto.
+ (IX86_BUILTIN_VPCMOV_V8HI): Ditto.
+ (IX86_BUILTIN_VPCMOV_V16QI): Ditto.
+ (IX86_BUILTIN_VPCMOV_V4SF): Ditto.
+ (IX86_BUILTIN_VPCMOV_V2DF): Ditto.
+
+ (IX86_BUILTIN_VPCMOV256): Ditto.
+ (IX86_BUILTIN_VPCMOV_V4DI256): Ditto.
+ (IX86_BUILTIN_VPCMOV_V8SI256): Ditto.
+ (IX86_BUILTIN_VPCMOV_V16HI256): Ditto.
+ (IX86_BUILTIN_VPCMOV_V32QI256): Ditto.
+ (IX86_BUILTIN_VPCMOV_V8SF256): Ditto.
+ (IX86_BUILTIN_VPCMOV_V4DF256): Ditto.
+
+ (IX86_BUILTIN_VPPERM): Ditto.
+
+ (IX86_BUILTIN_VPMACSSWW): Ditto.
+ (IX86_BUILTIN_VPMACSWW): Ditto.
+ (IX86_BUILTIN_VPMACSSWD): Ditto.
+ (IX86_BUILTIN_VPMACSWD): Ditto.
+ (IX86_BUILTIN_VPMACSSDD): Ditto.
+ (IX86_BUILTIN_VPMACSDD): Ditto.
+ (IX86_BUILTIN_VPMACSSDQL): Ditto.
+ (IX86_BUILTIN_VPMACSSDQH): Ditto.
+ (IX86_BUILTIN_VPMACSDQL): Ditto.
+ (IX86_BUILTIN_VPMACSDQH): Ditto.
+ (IX86_BUILTIN_VPMADCSSWD): Ditto.
+ (IX86_BUILTIN_VPMADCSWD): Ditto.
+
+ (IX86_BUILTIN_VPHADDBW): Ditto.
+ (IX86_BUILTIN_VPHADDBD): Ditto.
+ (IX86_BUILTIN_VPHADDBQ): Ditto.
+ (IX86_BUILTIN_VPHADDWD): Ditto.
+ (IX86_BUILTIN_VPHADDWQ): Ditto.
+ (IX86_BUILTIN_VPHADDDQ): Ditto.
+ (IX86_BUILTIN_VPHADDUBW): Ditto.
+ (IX86_BUILTIN_VPHADDUBD): Ditto.
+ (IX86_BUILTIN_VPHADDUBQ): Ditto.
+ (IX86_BUILTIN_VPHADDUWD): Ditto.
+ (IX86_BUILTIN_VPHADDUWQ): Ditto.
+ (IX86_BUILTIN_VPHADDUDQ): Ditto.
+ (IX86_BUILTIN_VPHSUBBW): Ditto.
+ (IX86_BUILTIN_VPHSUBWD): Ditto.
+ (IX86_BUILTIN_VPHSUBDQ): Ditto.
+
+ (IX86_BUILTIN_VPROTB): Ditto.
+ (IX86_BUILTIN_VPROTW): Ditto.
+ (IX86_BUILTIN_VPROTD): Ditto.
+ (IX86_BUILTIN_VPROTQ): Ditto.
+ (IX86_BUILTIN_VPROTB_IMM): Ditto.
+ (IX86_BUILTIN_VPROTW_IMM): Ditto.
+ (IX86_BUILTIN_VPROTD_IMM): Ditto.
+ (IX86_BUILTIN_VPROTQ_IMM): Ditto.
+
+ (IX86_BUILTIN_VPSHLB): Ditto.
+ (IX86_BUILTIN_VPSHLW): Ditto.
+ (IX86_BUILTIN_VPSHLD): Ditto.
+ (IX86_BUILTIN_VPSHLQ): Ditto.
+ (IX86_BUILTIN_VPSHAB): Ditto.
+ (IX86_BUILTIN_VPSHAW): Ditto.
+ (IX86_BUILTIN_VPSHAD): Ditto.
+ (IX86_BUILTIN_VPSHAQ): Ditto.
+
+ (IX86_BUILTIN_VFRCZSS): Ditto.
+ (IX86_BUILTIN_VFRCZSD): Ditto.
+ (IX86_BUILTIN_VFRCZPS): Ditto.
+ (IX86_BUILTIN_VFRCZPD): Ditto.
+ (IX86_BUILTIN_VFRCZPS256): Ditto.
+ (IX86_BUILTIN_VFRCZPD256): Ditto.
+
+ (IX86_BUILTIN_VPCOMEQUB): Ditto.
+ (IX86_BUILTIN_VPCOMNEUB): Ditto.
+ (IX86_BUILTIN_VPCOMLTUB): Ditto.
+ (IX86_BUILTIN_VPCOMLEUB): Ditto.
+ (IX86_BUILTIN_VPCOMGTUB): Ditto.
+ (IX86_BUILTIN_VPCOMGEUB): Ditto.
+ (IX86_BUILTIN_VPCOMFALSEUB): Ditto.
+ (IX86_BUILTIN_VPCOMTRUEUB): Ditto.
+
+ (IX86_BUILTIN_VPCOMEQUW): Ditto.
+ (IX86_BUILTIN_VPCOMNEUW): Ditto.
+ (IX86_BUILTIN_VPCOMLTUW): Ditto.
+ (IX86_BUILTIN_VPCOMLEUW): Ditto.
+ (IX86_BUILTIN_VPCOMGTUW): Ditto.
+ (IX86_BUILTIN_VPCOMGEUW): Ditto.
+ (IX86_BUILTIN_VPCOMFALSEUW): Ditto.
+ (IX86_BUILTIN_VPCOMTRUEUW): Ditto.
+
+ (IX86_BUILTIN_VPCOMEQUD): Ditto.
+ (IX86_BUILTIN_VPCOMNEUD): Ditto.
+ (IX86_BUILTIN_VPCOMLTUD): Ditto.
+ (IX86_BUILTIN_VPCOMLEUD): Ditto.
+ (IX86_BUILTIN_VPCOMGTUD): Ditto.
+ (IX86_BUILTIN_VPCOMGEUD): Ditto.
+ (IX86_BUILTIN_VPCOMFALSEUD): Ditto.
+ (IX86_BUILTIN_VPCOMTRUEUD): Ditto.
+
+ (IX86_BUILTIN_VPCOMEQUQ): Ditto.
+ (IX86_BUILTIN_VPCOMNEUQ): Ditto.
+ (IX86_BUILTIN_VPCOMLTUQ): Ditto.
+ (IX86_BUILTIN_VPCOMLEUQ): Ditto.
+ (IX86_BUILTIN_VPCOMGTUQ): Ditto.
+ (IX86_BUILTIN_VPCOMGEUQ): Ditto.
+ (IX86_BUILTIN_VPCOMFALSEUQ): Ditto.
+ (IX86_BUILTIN_VPCOMTRUEUQ): Ditto.
+
+ (IX86_BUILTIN_VPCOMEQB): Ditto.
+ (IX86_BUILTIN_VPCOMNEB): Ditto.
+ (IX86_BUILTIN_VPCOMLTB): Ditto.
+ (IX86_BUILTIN_VPCOMLEB): Ditto.
+ (IX86_BUILTIN_VPCOMGTB): Ditto.
+ (IX86_BUILTIN_VPCOMGEB): Ditto.
+ (IX86_BUILTIN_VPCOMFALSEB): Ditto.
+ (IX86_BUILTIN_VPCOMTRUEB): Ditto.
+
+ (IX86_BUILTIN_VPCOMEQW): Ditto.
+ (IX86_BUILTIN_VPCOMNEW): Ditto.
+ (IX86_BUILTIN_VPCOMLTW): Ditto.
+ (IX86_BUILTIN_VPCOMLEW): Ditto.
+ (IX86_BUILTIN_VPCOMGTW): Ditto.
+ (IX86_BUILTIN_VPCOMGEW): Ditto.
+ (IX86_BUILTIN_VPCOMFALSEW): Ditto.
+ (IX86_BUILTIN_VPCOMTRUEW): Ditto.
+
+ (IX86_BUILTIN_VPCOMEQD): Ditto.
+ (IX86_BUILTIN_VPCOMNED): Ditto.
+ (IX86_BUILTIN_VPCOMLTD): Ditto.
+ (IX86_BUILTIN_VPCOMLED): Ditto.
+ (IX86_BUILTIN_VPCOMGTD): Ditto.
+ (IX86_BUILTIN_VPCOMGED): Ditto.
+ (IX86_BUILTIN_VPCOMFALSED): Ditto.
+ (IX86_BUILTIN_VPCOMTRUED): Ditto.
+
+ (IX86_BUILTIN_VPCOMEQQ): Ditto.
+ (IX86_BUILTIN_VPCOMNEQ): Ditto.
+ (IX86_BUILTIN_VPCOMLTQ): Ditto.
+ (IX86_BUILTIN_VPCOMLEQ): Ditto.
+ (IX86_BUILTIN_VPCOMGTQ): Ditto.
+ (IX86_BUILTIN_VPCOMGEQ): Ditto.
+ (IX86_BUILTIN_VPCOMFALSEQ): Ditto.
+ (IX86_BUILTIN_VPCOMTRUEQ): Ditto.
+
+ (enum multi_arg_type): New enum for describing the various XOP
+ intrinsic argument types.
+ (bdesc_multi_arg): New table for XOP intrinsics.
+ (ix86_init_mmx_sse_builtins): Add XOP intrinsic support.
+ (ix86_expand_multi_arg_builtin): New function for creating XOP
+ intrinsics.
+
+ * config/i386/sse.md (sserotatemax): New mode attribute for XOP.
+ (xop_pmacsww): Ditto.
+ (xop_pmacssww): Ditto.
+ (xop_pmacsdd): Ditto.
+ (xop_pmacssdd): Ditto.
+ (xop_pmacssdql): Ditto.
+ (xop_pmacssdqh): Ditto.
+ (xop_pmacsdql): Ditto.
+ (xop_pmacsdql_mem): Ditto.
+ (xop_mulv2div2di3_low): Ditto.
+ (xop_pmacsdqh): Ditto.
+ (xop_pmacsdqh_mem): Ditto.
+ (xop_mulv2div2di3_high): Ditto.
+ (xop_pmacsswd): Ditto.
+ (xop_pmacswd): Ditto.
+ (xop_pmadcsswd): Ditto.
+ (xop_pmadcswd): Ditto.
+ (xop_pcmov_<mode>): Ditto.
+ (xop_pcmov_<mode>)256: Ditto.
+ (xop_phaddbw): Ditto.
+ (xop_phaddbd): Ditto.
+ (xop_phaddbq): Ditto.
+ (xop_phaddwd): Ditto.
+ (xop_phaddwq): Ditto.
+ (xop_phadddq): Ditto.
+ (xop_phaddubw): Ditto.
+ (xop_phaddubd): Ditto.
+ (xop_phaddubq): Ditto.
+ (xop_phadduwd): Ditto.
+ (xop_phadduwq): Ditto.
+ (xop_phaddudq): Ditto.
+ (xop_phsubbw): Ditto.
+ (xop_phsubwd): Ditto.
+ (xop_phsubdq): Ditto.
+ (xop_pperm): Ditto.
+ (rotl<mode>3): Ditto.
+ (rotr<mode>3): Ditto.
+ (xop_rotl<mode>3): Ditto.
+ (xop_rotr<mode>3): Ditto.
+ (vrotr<mode>3): Ditto.
+ (vrotl<mode>3): Ditto.
+ (xop_vrotl<mode>3): Ditto.
+ (vlshr<mode>3): Ditto.
+ (vashr<mode>3): Ditto.
+ (vashl<mode>3
+ (xop_ashl<mode>3): Ditto.
+ (xop_lshl<mode>3): Ditto.
+ (ashlv16qi3): Ditto.
+ (lshlv16qi3): Ditto.
+ (ashrv16qi3): Ditto.
+ (ashrv2di3): Ditto.
+ (xop_frcz<mode>2): Ditto.
+ (xop_vmfrcz<mode>2): Ditto.
+ (xop_frcz<mode>2256): Ditto.
+ (xop_maskcmp<mode>3): Ditto.
+ (xop_maskcmp_uns<mode>3): Ditto.
+ (xop_maskcmp_uns2<mode>3): Ditto.
+ (xop_pcom_tf<mode>3): Ditto.
+
+ * doc/invoke.texi (-mxop): Add documentation.
+ * doc/extend.texi (x86 intrinsics): Add XOP intrinsics.
+
2009-11-03 Mark Mitchell <mark@codesourcery.com>
PR driver/11810
extra_headers="cpuid.h mmintrin.h mm3dnow.h xmmintrin.h emmintrin.h
pmmintrin.h tmmintrin.h ammintrin.h smmintrin.h
nmmintrin.h bmmintrin.h fma4intrin.h wmmintrin.h
- immintrin.h x86intrin.h avxintrin.h
+ immintrin.h x86intrin.h avxintrin.h xopintrin.h
ia32intrin.h cross-stdarg.h"
;;
x86_64-*-*)
extra_headers="cpuid.h mmintrin.h mm3dnow.h xmmintrin.h emmintrin.h
pmmintrin.h tmmintrin.h ammintrin.h smmintrin.h
nmmintrin.h bmmintrin.h fma4intrin.h wmmintrin.h
- immintrin.h x86intrin.h avxintrin.h
+ immintrin.h x86intrin.h avxintrin.h xopintrin.h
ia32intrin.h cross-stdarg.h"
need_64bit_hwint=yes
;;
/* Extended Features */
/* %ecx */
+#define bit_FMA4 (1 << 16)
#define bit_LAHF_LM (1 << 0)
#define bit_SSE4a (1 << 6)
-#define bit_FMA4 (1 << 16)
+#define bit_XOP (1 << 11)
/* %edx */
#define bit_LM (1 << 29)
def_or_undef (parse_in, "__SSE4A__");
if (isa_flag & OPTION_MASK_ISA_FMA4)
def_or_undef (parse_in, "__FMA4__");
+ if (isa_flag & OPTION_MASK_ISA_XOP)
+ def_or_undef (parse_in, "__XOP__");
if ((fpmath & FPMATH_SSE) && (isa_flag & OPTION_MASK_ISA_SSE))
def_or_undef (parse_in, "__SSE_MATH__");
if ((fpmath & FPMATH_SSE) && (isa_flag & OPTION_MASK_ISA_SSE2))
#define OPTION_MASK_ISA_FMA4_SET \
(OPTION_MASK_ISA_FMA4 | OPTION_MASK_ISA_SSE4A_SET \
| OPTION_MASK_ISA_AVX_SET)
+#define OPTION_MASK_ISA_XOP_SET \
+ (OPTION_MASK_ISA_XOP | OPTION_MASK_ISA_FMA4_SET)
/* AES and PCLMUL need SSE2 because they use xmm registers */
#define OPTION_MASK_ISA_AES_SET \
#define OPTION_MASK_ISA_SSE4A_UNSET \
(OPTION_MASK_ISA_SSE4A | OPTION_MASK_ISA_FMA4_UNSET)
-#define OPTION_MASK_ISA_FMA4_UNSET OPTION_MASK_ISA_FMA4
+#define OPTION_MASK_ISA_FMA4_UNSET \
+ (OPTION_MASK_ISA_FMA4 | OPTION_MASK_ISA_XOP_UNSET)
+#define OPTION_MASK_ISA_XOP_UNSET OPTION_MASK_ISA_XOP
#define OPTION_MASK_ISA_AES_UNSET OPTION_MASK_ISA_AES
#define OPTION_MASK_ISA_PCLMUL_UNSET OPTION_MASK_ISA_PCLMUL
}
return true;
+ case OPT_mxop:
+ if (value)
+ {
+ ix86_isa_flags |= OPTION_MASK_ISA_XOP_SET;
+ ix86_isa_flags_explicit |= OPTION_MASK_ISA_XOP_SET;
+ }
+ else
+ {
+ ix86_isa_flags &= ~OPTION_MASK_ISA_XOP_UNSET;
+ ix86_isa_flags_explicit |= OPTION_MASK_ISA_XOP_UNSET;
+ }
+ return true;
+
case OPT_mabm:
if (value)
{
{
{ "-m64", OPTION_MASK_ISA_64BIT },
{ "-mfma4", OPTION_MASK_ISA_FMA4 },
+ { "-mxop", OPTION_MASK_ISA_XOP },
{ "-msse4a", OPTION_MASK_ISA_SSE4A },
{ "-msse4.2", OPTION_MASK_ISA_SSE4_2 },
{ "-msse4.1", OPTION_MASK_ISA_SSE4_1 },
PTA_AVX = 1 << 18,
PTA_FMA = 1 << 19,
PTA_MOVBE = 1 << 20,
- PTA_FMA4 = 1 << 21
+ PTA_FMA4 = 1 << 21,
+ PTA_XOP = 1 << 22
};
static struct pta
if (processor_alias_table[i].flags & PTA_FMA4
&& !(ix86_isa_flags_explicit & OPTION_MASK_ISA_FMA4))
ix86_isa_flags |= OPTION_MASK_ISA_FMA4;
+ if (processor_alias_table[i].flags & PTA_XOP
+ && !(ix86_isa_flags_explicit & OPTION_MASK_ISA_XOP))
+ ix86_isa_flags |= OPTION_MASK_ISA_XOP;
if (processor_alias_table[i].flags & PTA_ABM
&& !(ix86_isa_flags_explicit & OPTION_MASK_ISA_ABM))
ix86_isa_flags |= OPTION_MASK_ISA_ABM;
IX86_ATTR_ISA ("sse4a", OPT_msse4a),
IX86_ATTR_ISA ("ssse3", OPT_mssse3),
IX86_ATTR_ISA ("fma4", OPT_mfma4),
+ IX86_ATTR_ISA ("xop", OPT_mxop),
/* string options */
IX86_ATTR_STR ("arch=", IX86_FUNCTION_SPECIFIC_ARCH),
X -- don't print any sort of PIC '@' suffix for a symbol.
& -- print some in-use local-dynamic symbol name.
H -- print a memory address offset by 8; used for sse high-parts
+ Y -- print condition for XOP pcom* instruction.
+ -- print a branch hint as 'cs' or 'ds' prefix
; -- print a semicolon (after prefixes due to bug in older gas).
*/
return;
}
+ case 'Y':
+ switch (GET_CODE (x))
+ {
+ case NE:
+ fputs ("neq", file);
+ break;
+ case EQ:
+ fputs ("eq", file);
+ break;
+ case GE:
+ case GEU:
+ fputs (INTEGRAL_MODE_P (GET_MODE (x)) ? "ge" : "unlt", file);
+ break;
+ case GT:
+ case GTU:
+ fputs (INTEGRAL_MODE_P (GET_MODE (x)) ? "gt" : "unle", file);
+ break;
+ case LE:
+ case LEU:
+ fputs ("le", file);
+ break;
+ case LT:
+ case LTU:
+ fputs ("lt", file);
+ break;
+ case UNORDERED:
+ fputs ("unord", file);
+ break;
+ case ORDERED:
+ fputs ("ord", file);
+ break;
+ case UNEQ:
+ fputs ("ueq", file);
+ break;
+ case UNGE:
+ fputs ("nlt", file);
+ break;
+ case UNGT:
+ fputs ("nle", file);
+ break;
+ case UNLE:
+ fputs ("ule", file);
+ break;
+ case UNLT:
+ fputs ("ult", file);
+ break;
+ case LTGT:
+ fputs ("une", file);
+ break;
+ default:
+ output_operand_lossage ("operand is not a condition code, invalid operand code 'D'");
+ return;
+ }
+ return;
+
case ';':
#if TARGET_MACHO
fputs (" ; ", file);
x = gen_rtx_AND (mode, x, op_false);
emit_insn (gen_rtx_SET (VOIDmode, dest, x));
}
+ else if (TARGET_XOP)
+ {
+ rtx pcmov = gen_rtx_SET (mode, dest,
+ gen_rtx_IF_THEN_ELSE (mode, cmp,
+ op_true,
+ op_false));
+ emit_insn (pcmov);
+ }
else
{
op_true = force_reg (mode, op_true);
cop0 = operands[4];
cop1 = operands[5];
+ /* XOP supports all of the comparisons on all vector int types. */
+ if (!TARGET_XOP)
+ {
/* Canonicalize the comparison to EQ, GT, GTU. */
switch (code)
{
cop0 = x;
cop1 = CONST0_RTX (mode);
}
+ }
x = ix86_expand_sse_cmp (operands[0], code, cop0, cop1,
operands[1+negate], operands[2-negate]);
IX86_BUILTIN_VFNMADDPD256,
IX86_BUILTIN_VFNMSUBPS256,
IX86_BUILTIN_VFNMSUBPD256,
+
+ IX86_BUILTIN_VPCMOV,
+ IX86_BUILTIN_VPCMOV_V2DI,
+ IX86_BUILTIN_VPCMOV_V4SI,
+ IX86_BUILTIN_VPCMOV_V8HI,
+ IX86_BUILTIN_VPCMOV_V16QI,
+ IX86_BUILTIN_VPCMOV_V4SF,
+ IX86_BUILTIN_VPCMOV_V2DF,
+ IX86_BUILTIN_VPCMOV256,
+ IX86_BUILTIN_VPCMOV_V4DI256,
+ IX86_BUILTIN_VPCMOV_V8SI256,
+ IX86_BUILTIN_VPCMOV_V16HI256,
+ IX86_BUILTIN_VPCMOV_V32QI256,
+ IX86_BUILTIN_VPCMOV_V8SF256,
+ IX86_BUILTIN_VPCMOV_V4DF256,
+
+ IX86_BUILTIN_VPPERM,
+
+ IX86_BUILTIN_VPMACSSWW,
+ IX86_BUILTIN_VPMACSWW,
+ IX86_BUILTIN_VPMACSSWD,
+ IX86_BUILTIN_VPMACSWD,
+ IX86_BUILTIN_VPMACSSDD,
+ IX86_BUILTIN_VPMACSDD,
+ IX86_BUILTIN_VPMACSSDQL,
+ IX86_BUILTIN_VPMACSSDQH,
+ IX86_BUILTIN_VPMACSDQL,
+ IX86_BUILTIN_VPMACSDQH,
+ IX86_BUILTIN_VPMADCSSWD,
+ IX86_BUILTIN_VPMADCSWD,
+
+ IX86_BUILTIN_VPHADDBW,
+ IX86_BUILTIN_VPHADDBD,
+ IX86_BUILTIN_VPHADDBQ,
+ IX86_BUILTIN_VPHADDWD,
+ IX86_BUILTIN_VPHADDWQ,
+ IX86_BUILTIN_VPHADDDQ,
+ IX86_BUILTIN_VPHADDUBW,
+ IX86_BUILTIN_VPHADDUBD,
+ IX86_BUILTIN_VPHADDUBQ,
+ IX86_BUILTIN_VPHADDUWD,
+ IX86_BUILTIN_VPHADDUWQ,
+ IX86_BUILTIN_VPHADDUDQ,
+ IX86_BUILTIN_VPHSUBBW,
+ IX86_BUILTIN_VPHSUBWD,
+ IX86_BUILTIN_VPHSUBDQ,
+
+ IX86_BUILTIN_VPROTB,
+ IX86_BUILTIN_VPROTW,
+ IX86_BUILTIN_VPROTD,
+ IX86_BUILTIN_VPROTQ,
+ IX86_BUILTIN_VPROTB_IMM,
+ IX86_BUILTIN_VPROTW_IMM,
+ IX86_BUILTIN_VPROTD_IMM,
+ IX86_BUILTIN_VPROTQ_IMM,
+
+ IX86_BUILTIN_VPSHLB,
+ IX86_BUILTIN_VPSHLW,
+ IX86_BUILTIN_VPSHLD,
+ IX86_BUILTIN_VPSHLQ,
+ IX86_BUILTIN_VPSHAB,
+ IX86_BUILTIN_VPSHAW,
+ IX86_BUILTIN_VPSHAD,
+ IX86_BUILTIN_VPSHAQ,
+
+ IX86_BUILTIN_VFRCZSS,
+ IX86_BUILTIN_VFRCZSD,
+ IX86_BUILTIN_VFRCZPS,
+ IX86_BUILTIN_VFRCZPD,
+ IX86_BUILTIN_VFRCZPS256,
+ IX86_BUILTIN_VFRCZPD256,
+
+ IX86_BUILTIN_VPCOMEQUB,
+ IX86_BUILTIN_VPCOMNEUB,
+ IX86_BUILTIN_VPCOMLTUB,
+ IX86_BUILTIN_VPCOMLEUB,
+ IX86_BUILTIN_VPCOMGTUB,
+ IX86_BUILTIN_VPCOMGEUB,
+ IX86_BUILTIN_VPCOMFALSEUB,
+ IX86_BUILTIN_VPCOMTRUEUB,
+
+ IX86_BUILTIN_VPCOMEQUW,
+ IX86_BUILTIN_VPCOMNEUW,
+ IX86_BUILTIN_VPCOMLTUW,
+ IX86_BUILTIN_VPCOMLEUW,
+ IX86_BUILTIN_VPCOMGTUW,
+ IX86_BUILTIN_VPCOMGEUW,
+ IX86_BUILTIN_VPCOMFALSEUW,
+ IX86_BUILTIN_VPCOMTRUEUW,
+
+ IX86_BUILTIN_VPCOMEQUD,
+ IX86_BUILTIN_VPCOMNEUD,
+ IX86_BUILTIN_VPCOMLTUD,
+ IX86_BUILTIN_VPCOMLEUD,
+ IX86_BUILTIN_VPCOMGTUD,
+ IX86_BUILTIN_VPCOMGEUD,
+ IX86_BUILTIN_VPCOMFALSEUD,
+ IX86_BUILTIN_VPCOMTRUEUD,
+
+ IX86_BUILTIN_VPCOMEQUQ,
+ IX86_BUILTIN_VPCOMNEUQ,
+ IX86_BUILTIN_VPCOMLTUQ,
+ IX86_BUILTIN_VPCOMLEUQ,
+ IX86_BUILTIN_VPCOMGTUQ,
+ IX86_BUILTIN_VPCOMGEUQ,
+ IX86_BUILTIN_VPCOMFALSEUQ,
+ IX86_BUILTIN_VPCOMTRUEUQ,
+
+ IX86_BUILTIN_VPCOMEQB,
+ IX86_BUILTIN_VPCOMNEB,
+ IX86_BUILTIN_VPCOMLTB,
+ IX86_BUILTIN_VPCOMLEB,
+ IX86_BUILTIN_VPCOMGTB,
+ IX86_BUILTIN_VPCOMGEB,
+ IX86_BUILTIN_VPCOMFALSEB,
+ IX86_BUILTIN_VPCOMTRUEB,
+
+ IX86_BUILTIN_VPCOMEQW,
+ IX86_BUILTIN_VPCOMNEW,
+ IX86_BUILTIN_VPCOMLTW,
+ IX86_BUILTIN_VPCOMLEW,
+ IX86_BUILTIN_VPCOMGTW,
+ IX86_BUILTIN_VPCOMGEW,
+ IX86_BUILTIN_VPCOMFALSEW,
+ IX86_BUILTIN_VPCOMTRUEW,
+
+ IX86_BUILTIN_VPCOMEQD,
+ IX86_BUILTIN_VPCOMNED,
+ IX86_BUILTIN_VPCOMLTD,
+ IX86_BUILTIN_VPCOMLED,
+ IX86_BUILTIN_VPCOMGTD,
+ IX86_BUILTIN_VPCOMGED,
+ IX86_BUILTIN_VPCOMFALSED,
+ IX86_BUILTIN_VPCOMTRUED,
+
+ IX86_BUILTIN_VPCOMEQQ,
+ IX86_BUILTIN_VPCOMNEQ,
+ IX86_BUILTIN_VPCOMLTQ,
+ IX86_BUILTIN_VPCOMLEQ,
+ IX86_BUILTIN_VPCOMGTQ,
+ IX86_BUILTIN_VPCOMGEQ,
+ IX86_BUILTIN_VPCOMFALSEQ,
+ IX86_BUILTIN_VPCOMTRUEQ,
+
IX86_BUILTIN_MAX
};
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_movmskps256, "__builtin_ia32_movmskps256", IX86_BUILTIN_MOVMSKPS256, UNKNOWN, (int) INT_FTYPE_V8SF },
};
-/* FMA4. */
+/* FMA4 and XOP. */
enum multi_arg_type {
MULTI_ARG_UNKNOWN,
MULTI_ARG_3_SF,
MULTI_ARG_3_DF,
MULTI_ARG_3_SF2,
- MULTI_ARG_3_DF2
+ MULTI_ARG_3_DF2,
+ MULTI_ARG_3_DI,
+ MULTI_ARG_3_SI,
+ MULTI_ARG_3_SI_DI,
+ MULTI_ARG_3_HI,
+ MULTI_ARG_3_HI_SI,
+ MULTI_ARG_3_QI,
+ MULTI_ARG_3_DI2,
+ MULTI_ARG_3_SI2,
+ MULTI_ARG_3_HI2,
+ MULTI_ARG_3_QI2,
+ MULTI_ARG_2_SF,
+ MULTI_ARG_2_DF,
+ MULTI_ARG_2_DI,
+ MULTI_ARG_2_SI,
+ MULTI_ARG_2_HI,
+ MULTI_ARG_2_QI,
+ MULTI_ARG_2_DI_IMM,
+ MULTI_ARG_2_SI_IMM,
+ MULTI_ARG_2_HI_IMM,
+ MULTI_ARG_2_QI_IMM,
+ MULTI_ARG_2_DI_CMP,
+ MULTI_ARG_2_SI_CMP,
+ MULTI_ARG_2_HI_CMP,
+ MULTI_ARG_2_QI_CMP,
+ MULTI_ARG_2_DI_TF,
+ MULTI_ARG_2_SI_TF,
+ MULTI_ARG_2_HI_TF,
+ MULTI_ARG_2_QI_TF,
+ MULTI_ARG_2_SF_TF,
+ MULTI_ARG_2_DF_TF,
+ MULTI_ARG_1_SF,
+ MULTI_ARG_1_DF,
+ MULTI_ARG_1_SF2,
+ MULTI_ARG_1_DF2,
+ MULTI_ARG_1_DI,
+ MULTI_ARG_1_SI,
+ MULTI_ARG_1_HI,
+ MULTI_ARG_1_QI,
+ MULTI_ARG_1_SI_DI,
+ MULTI_ARG_1_HI_DI,
+ MULTI_ARG_1_HI_SI,
+ MULTI_ARG_1_QI_DI,
+ MULTI_ARG_1_QI_SI,
+ MULTI_ARG_1_QI_HI
+
};
static const struct builtin_description bdesc_multi_arg[] =
{ OPTION_MASK_ISA_FMA4, CODE_FOR_fma4i_fmaddsubv8sf4, "__builtin_ia32_vfmaddsubps256", IX86_BUILTIN_VFMADDSUBPS256, UNKNOWN, (int)MULTI_ARG_3_SF2 },
{ OPTION_MASK_ISA_FMA4, CODE_FOR_fma4i_fmaddsubv4df4, "__builtin_ia32_vfmaddsubpd256", IX86_BUILTIN_VFMADDSUBPD256, UNKNOWN, (int)MULTI_ARG_3_DF2 },
{ OPTION_MASK_ISA_FMA4, CODE_FOR_fma4i_fmsubaddv8sf4, "__builtin_ia32_vfmsubaddps256", IX86_BUILTIN_VFMSUBADDPS256, UNKNOWN, (int)MULTI_ARG_3_SF2 },
- { OPTION_MASK_ISA_FMA4, CODE_FOR_fma4i_fmsubaddv4df4, "__builtin_ia32_vfmsubaddpd256", IX86_BUILTIN_VFMSUBADDPD256, UNKNOWN, (int)MULTI_ARG_3_DF2 }
+ { OPTION_MASK_ISA_FMA4, CODE_FOR_fma4i_fmsubaddv4df4, "__builtin_ia32_vfmsubaddpd256", IX86_BUILTIN_VFMSUBADDPD256, UNKNOWN, (int)MULTI_ARG_3_DF2 },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v2di, "__builtin_ia32_vpcmov", IX86_BUILTIN_VPCMOV, UNKNOWN, (int)MULTI_ARG_3_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v2di, "__builtin_ia32_vpcmov_v2di", IX86_BUILTIN_VPCMOV_V2DI, UNKNOWN, (int)MULTI_ARG_3_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v4si, "__builtin_ia32_vpcmov_v4si", IX86_BUILTIN_VPCMOV_V4SI, UNKNOWN, (int)MULTI_ARG_3_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v8hi, "__builtin_ia32_vpcmov_v8hi", IX86_BUILTIN_VPCMOV_V8HI, UNKNOWN, (int)MULTI_ARG_3_HI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v16qi, "__builtin_ia32_vpcmov_v16qi",IX86_BUILTIN_VPCMOV_V16QI,UNKNOWN, (int)MULTI_ARG_3_QI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v2df, "__builtin_ia32_vpcmov_v2df", IX86_BUILTIN_VPCMOV_V2DF, UNKNOWN, (int)MULTI_ARG_3_DF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v4sf, "__builtin_ia32_vpcmov_v4sf", IX86_BUILTIN_VPCMOV_V4SF, UNKNOWN, (int)MULTI_ARG_3_SF },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v4di256, "__builtin_ia32_vpcmov256", IX86_BUILTIN_VPCMOV256, UNKNOWN, (int)MULTI_ARG_3_DI2 },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v4di256, "__builtin_ia32_vpcmov_v4di256", IX86_BUILTIN_VPCMOV_V4DI256, UNKNOWN, (int)MULTI_ARG_3_DI2 },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v8si256, "__builtin_ia32_vpcmov_v8si256", IX86_BUILTIN_VPCMOV_V8SI256, UNKNOWN, (int)MULTI_ARG_3_SI2 },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v16hi256, "__builtin_ia32_vpcmov_v16hi256", IX86_BUILTIN_VPCMOV_V16HI256, UNKNOWN, (int)MULTI_ARG_3_HI2 },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v32qi256, "__builtin_ia32_vpcmov_v32qi256", IX86_BUILTIN_VPCMOV_V32QI256, UNKNOWN, (int)MULTI_ARG_3_QI2 },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v4df256, "__builtin_ia32_vpcmov_v4df256", IX86_BUILTIN_VPCMOV_V4DF256, UNKNOWN, (int)MULTI_ARG_3_DF2 },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcmov_v8sf256, "__builtin_ia32_vpcmov_v8sf256", IX86_BUILTIN_VPCMOV_V8SF256, UNKNOWN, (int)MULTI_ARG_3_SF2 },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pperm, "__builtin_ia32_vpperm", IX86_BUILTIN_VPPERM, UNKNOWN, (int)MULTI_ARG_3_QI },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmacssww, "__builtin_ia32_vpmacssww", IX86_BUILTIN_VPMACSSWW, UNKNOWN, (int)MULTI_ARG_3_HI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmacsww, "__builtin_ia32_vpmacsww", IX86_BUILTIN_VPMACSWW, UNKNOWN, (int)MULTI_ARG_3_HI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmacsswd, "__builtin_ia32_vpmacsswd", IX86_BUILTIN_VPMACSSWD, UNKNOWN, (int)MULTI_ARG_3_HI_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmacswd, "__builtin_ia32_vpmacswd", IX86_BUILTIN_VPMACSWD, UNKNOWN, (int)MULTI_ARG_3_HI_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmacssdd, "__builtin_ia32_vpmacssdd", IX86_BUILTIN_VPMACSSDD, UNKNOWN, (int)MULTI_ARG_3_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmacsdd, "__builtin_ia32_vpmacsdd", IX86_BUILTIN_VPMACSDD, UNKNOWN, (int)MULTI_ARG_3_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmacssdql, "__builtin_ia32_vpmacssdql", IX86_BUILTIN_VPMACSSDQL, UNKNOWN, (int)MULTI_ARG_3_SI_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmacssdqh, "__builtin_ia32_vpmacssdqh", IX86_BUILTIN_VPMACSSDQH, UNKNOWN, (int)MULTI_ARG_3_SI_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmacsdql, "__builtin_ia32_vpmacsdql", IX86_BUILTIN_VPMACSDQL, UNKNOWN, (int)MULTI_ARG_3_SI_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmacsdqh, "__builtin_ia32_vpmacsdqh", IX86_BUILTIN_VPMACSDQH, UNKNOWN, (int)MULTI_ARG_3_SI_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmadcsswd, "__builtin_ia32_vpmadcsswd", IX86_BUILTIN_VPMADCSSWD, UNKNOWN, (int)MULTI_ARG_3_HI_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pmadcswd, "__builtin_ia32_vpmadcswd", IX86_BUILTIN_VPMADCSWD, UNKNOWN, (int)MULTI_ARG_3_HI_SI },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_vrotlv2di3, "__builtin_ia32_vprotq", IX86_BUILTIN_VPROTQ, UNKNOWN, (int)MULTI_ARG_2_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_vrotlv4si3, "__builtin_ia32_vprotd", IX86_BUILTIN_VPROTD, UNKNOWN, (int)MULTI_ARG_2_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_vrotlv8hi3, "__builtin_ia32_vprotw", IX86_BUILTIN_VPROTW, UNKNOWN, (int)MULTI_ARG_2_HI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_vrotlv16qi3, "__builtin_ia32_vprotb", IX86_BUILTIN_VPROTB, UNKNOWN, (int)MULTI_ARG_2_QI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_rotlv2di3, "__builtin_ia32_vprotqi", IX86_BUILTIN_VPROTQ_IMM, UNKNOWN, (int)MULTI_ARG_2_DI_IMM },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_rotlv4si3, "__builtin_ia32_vprotdi", IX86_BUILTIN_VPROTD_IMM, UNKNOWN, (int)MULTI_ARG_2_SI_IMM },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_rotlv8hi3, "__builtin_ia32_vprotwi", IX86_BUILTIN_VPROTW_IMM, UNKNOWN, (int)MULTI_ARG_2_HI_IMM },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_rotlv16qi3, "__builtin_ia32_vprotbi", IX86_BUILTIN_VPROTB_IMM, UNKNOWN, (int)MULTI_ARG_2_QI_IMM },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_ashlv2di3, "__builtin_ia32_vpshaq", IX86_BUILTIN_VPSHAQ, UNKNOWN, (int)MULTI_ARG_2_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_ashlv4si3, "__builtin_ia32_vpshad", IX86_BUILTIN_VPSHAD, UNKNOWN, (int)MULTI_ARG_2_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_ashlv8hi3, "__builtin_ia32_vpshaw", IX86_BUILTIN_VPSHAW, UNKNOWN, (int)MULTI_ARG_2_HI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_ashlv16qi3, "__builtin_ia32_vpshab", IX86_BUILTIN_VPSHAB, UNKNOWN, (int)MULTI_ARG_2_QI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_lshlv2di3, "__builtin_ia32_vpshlq", IX86_BUILTIN_VPSHLQ, UNKNOWN, (int)MULTI_ARG_2_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_lshlv4si3, "__builtin_ia32_vpshld", IX86_BUILTIN_VPSHLD, UNKNOWN, (int)MULTI_ARG_2_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_lshlv8hi3, "__builtin_ia32_vpshlw", IX86_BUILTIN_VPSHLW, UNKNOWN, (int)MULTI_ARG_2_HI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_lshlv16qi3, "__builtin_ia32_vpshlb", IX86_BUILTIN_VPSHLB, UNKNOWN, (int)MULTI_ARG_2_QI },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_vmfrczv4sf2, "__builtin_ia32_vfrczss", IX86_BUILTIN_VFRCZSS, UNKNOWN, (int)MULTI_ARG_2_SF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_vmfrczv2df2, "__builtin_ia32_vfrczsd", IX86_BUILTIN_VFRCZSD, UNKNOWN, (int)MULTI_ARG_2_DF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_frczv4sf2, "__builtin_ia32_vfrczps", IX86_BUILTIN_VFRCZPS, UNKNOWN, (int)MULTI_ARG_1_SF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_frczv2df2, "__builtin_ia32_vfrczpd", IX86_BUILTIN_VFRCZPD, UNKNOWN, (int)MULTI_ARG_1_DF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_frczv8sf2256, "__builtin_ia32_vfrczps256", IX86_BUILTIN_VFRCZPS256, UNKNOWN, (int)MULTI_ARG_1_SF2 },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_frczv4df2256, "__builtin_ia32_vfrczpd256", IX86_BUILTIN_VFRCZPD256, UNKNOWN, (int)MULTI_ARG_1_DF2 },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phaddbw, "__builtin_ia32_vphaddbw", IX86_BUILTIN_VPHADDBW, UNKNOWN, (int)MULTI_ARG_1_QI_HI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phaddbd, "__builtin_ia32_vphaddbd", IX86_BUILTIN_VPHADDBD, UNKNOWN, (int)MULTI_ARG_1_QI_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phaddbq, "__builtin_ia32_vphaddbq", IX86_BUILTIN_VPHADDBQ, UNKNOWN, (int)MULTI_ARG_1_QI_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phaddwd, "__builtin_ia32_vphaddwd", IX86_BUILTIN_VPHADDWD, UNKNOWN, (int)MULTI_ARG_1_HI_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phaddwq, "__builtin_ia32_vphaddwq", IX86_BUILTIN_VPHADDWQ, UNKNOWN, (int)MULTI_ARG_1_HI_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phadddq, "__builtin_ia32_vphadddq", IX86_BUILTIN_VPHADDDQ, UNKNOWN, (int)MULTI_ARG_1_SI_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phaddubw, "__builtin_ia32_vphaddubw", IX86_BUILTIN_VPHADDUBW, UNKNOWN, (int)MULTI_ARG_1_QI_HI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phaddubd, "__builtin_ia32_vphaddubd", IX86_BUILTIN_VPHADDUBD, UNKNOWN, (int)MULTI_ARG_1_QI_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phaddubq, "__builtin_ia32_vphaddubq", IX86_BUILTIN_VPHADDUBQ, UNKNOWN, (int)MULTI_ARG_1_QI_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phadduwd, "__builtin_ia32_vphadduwd", IX86_BUILTIN_VPHADDUWD, UNKNOWN, (int)MULTI_ARG_1_HI_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phadduwq, "__builtin_ia32_vphadduwq", IX86_BUILTIN_VPHADDUWQ, UNKNOWN, (int)MULTI_ARG_1_HI_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phaddudq, "__builtin_ia32_vphaddudq", IX86_BUILTIN_VPHADDUDQ, UNKNOWN, (int)MULTI_ARG_1_SI_DI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phsubbw, "__builtin_ia32_vphsubbw", IX86_BUILTIN_VPHSUBBW, UNKNOWN, (int)MULTI_ARG_1_QI_HI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phsubwd, "__builtin_ia32_vphsubwd", IX86_BUILTIN_VPHSUBWD, UNKNOWN, (int)MULTI_ARG_1_HI_SI },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_phsubdq, "__builtin_ia32_vphsubdq", IX86_BUILTIN_VPHSUBDQ, UNKNOWN, (int)MULTI_ARG_1_SI_DI },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv16qi3, "__builtin_ia32_vpcomeqb", IX86_BUILTIN_VPCOMEQB, EQ, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv16qi3, "__builtin_ia32_vpcomneb", IX86_BUILTIN_VPCOMNEB, NE, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv16qi3, "__builtin_ia32_vpcomneqb", IX86_BUILTIN_VPCOMNEB, NE, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv16qi3, "__builtin_ia32_vpcomltb", IX86_BUILTIN_VPCOMLTB, LT, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv16qi3, "__builtin_ia32_vpcomleb", IX86_BUILTIN_VPCOMLEB, LE, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv16qi3, "__builtin_ia32_vpcomgtb", IX86_BUILTIN_VPCOMGTB, GT, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv16qi3, "__builtin_ia32_vpcomgeb", IX86_BUILTIN_VPCOMGEB, GE, (int)MULTI_ARG_2_QI_CMP },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv8hi3, "__builtin_ia32_vpcomeqw", IX86_BUILTIN_VPCOMEQW, EQ, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv8hi3, "__builtin_ia32_vpcomnew", IX86_BUILTIN_VPCOMNEW, NE, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv8hi3, "__builtin_ia32_vpcomneqw", IX86_BUILTIN_VPCOMNEW, NE, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv8hi3, "__builtin_ia32_vpcomltw", IX86_BUILTIN_VPCOMLTW, LT, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv8hi3, "__builtin_ia32_vpcomlew", IX86_BUILTIN_VPCOMLEW, LE, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv8hi3, "__builtin_ia32_vpcomgtw", IX86_BUILTIN_VPCOMGTW, GT, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv8hi3, "__builtin_ia32_vpcomgew", IX86_BUILTIN_VPCOMGEW, GE, (int)MULTI_ARG_2_HI_CMP },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv4si3, "__builtin_ia32_vpcomeqd", IX86_BUILTIN_VPCOMEQD, EQ, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv4si3, "__builtin_ia32_vpcomned", IX86_BUILTIN_VPCOMNED, NE, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv4si3, "__builtin_ia32_vpcomneqd", IX86_BUILTIN_VPCOMNED, NE, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv4si3, "__builtin_ia32_vpcomltd", IX86_BUILTIN_VPCOMLTD, LT, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv4si3, "__builtin_ia32_vpcomled", IX86_BUILTIN_VPCOMLED, LE, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv4si3, "__builtin_ia32_vpcomgtd", IX86_BUILTIN_VPCOMGTD, GT, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv4si3, "__builtin_ia32_vpcomged", IX86_BUILTIN_VPCOMGED, GE, (int)MULTI_ARG_2_SI_CMP },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv2di3, "__builtin_ia32_vpcomeqq", IX86_BUILTIN_VPCOMEQQ, EQ, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv2di3, "__builtin_ia32_vpcomneq", IX86_BUILTIN_VPCOMNEQ, NE, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv2di3, "__builtin_ia32_vpcomneqq", IX86_BUILTIN_VPCOMNEQ, NE, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv2di3, "__builtin_ia32_vpcomltq", IX86_BUILTIN_VPCOMLTQ, LT, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv2di3, "__builtin_ia32_vpcomleq", IX86_BUILTIN_VPCOMLEQ, LE, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv2di3, "__builtin_ia32_vpcomgtq", IX86_BUILTIN_VPCOMGTQ, GT, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmpv2di3, "__builtin_ia32_vpcomgeq", IX86_BUILTIN_VPCOMGEQ, GE, (int)MULTI_ARG_2_DI_CMP },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v16qi3,"__builtin_ia32_vpcomequb", IX86_BUILTIN_VPCOMEQUB, EQ, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v16qi3,"__builtin_ia32_vpcomneub", IX86_BUILTIN_VPCOMNEUB, NE, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v16qi3,"__builtin_ia32_vpcomnequb", IX86_BUILTIN_VPCOMNEUB, NE, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv16qi3, "__builtin_ia32_vpcomltub", IX86_BUILTIN_VPCOMLTUB, LTU, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv16qi3, "__builtin_ia32_vpcomleub", IX86_BUILTIN_VPCOMLEUB, LEU, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv16qi3, "__builtin_ia32_vpcomgtub", IX86_BUILTIN_VPCOMGTUB, GTU, (int)MULTI_ARG_2_QI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv16qi3, "__builtin_ia32_vpcomgeub", IX86_BUILTIN_VPCOMGEUB, GEU, (int)MULTI_ARG_2_QI_CMP },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v8hi3, "__builtin_ia32_vpcomequw", IX86_BUILTIN_VPCOMEQUW, EQ, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v8hi3, "__builtin_ia32_vpcomneuw", IX86_BUILTIN_VPCOMNEUW, NE, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v8hi3, "__builtin_ia32_vpcomnequw", IX86_BUILTIN_VPCOMNEUW, NE, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv8hi3, "__builtin_ia32_vpcomltuw", IX86_BUILTIN_VPCOMLTUW, LTU, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv8hi3, "__builtin_ia32_vpcomleuw", IX86_BUILTIN_VPCOMLEUW, LEU, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv8hi3, "__builtin_ia32_vpcomgtuw", IX86_BUILTIN_VPCOMGTUW, GTU, (int)MULTI_ARG_2_HI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv8hi3, "__builtin_ia32_vpcomgeuw", IX86_BUILTIN_VPCOMGEUW, GEU, (int)MULTI_ARG_2_HI_CMP },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v4si3, "__builtin_ia32_vpcomequd", IX86_BUILTIN_VPCOMEQUD, EQ, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v4si3, "__builtin_ia32_vpcomneud", IX86_BUILTIN_VPCOMNEUD, NE, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v4si3, "__builtin_ia32_vpcomnequd", IX86_BUILTIN_VPCOMNEUD, NE, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv4si3, "__builtin_ia32_vpcomltud", IX86_BUILTIN_VPCOMLTUD, LTU, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv4si3, "__builtin_ia32_vpcomleud", IX86_BUILTIN_VPCOMLEUD, LEU, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv4si3, "__builtin_ia32_vpcomgtud", IX86_BUILTIN_VPCOMGTUD, GTU, (int)MULTI_ARG_2_SI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv4si3, "__builtin_ia32_vpcomgeud", IX86_BUILTIN_VPCOMGEUD, GEU, (int)MULTI_ARG_2_SI_CMP },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v2di3, "__builtin_ia32_vpcomequq", IX86_BUILTIN_VPCOMEQUQ, EQ, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v2di3, "__builtin_ia32_vpcomneuq", IX86_BUILTIN_VPCOMNEUQ, NE, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_uns2v2di3, "__builtin_ia32_vpcomnequq", IX86_BUILTIN_VPCOMNEUQ, NE, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv2di3, "__builtin_ia32_vpcomltuq", IX86_BUILTIN_VPCOMLTUQ, LTU, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv2di3, "__builtin_ia32_vpcomleuq", IX86_BUILTIN_VPCOMLEUQ, LEU, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv2di3, "__builtin_ia32_vpcomgtuq", IX86_BUILTIN_VPCOMGTUQ, GTU, (int)MULTI_ARG_2_DI_CMP },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_maskcmp_unsv2di3, "__builtin_ia32_vpcomgeuq", IX86_BUILTIN_VPCOMGEUQ, GEU, (int)MULTI_ARG_2_DI_CMP },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv16qi3, "__builtin_ia32_vpcomfalseb", IX86_BUILTIN_VPCOMFALSEB, (enum rtx_code) PCOM_FALSE, (int)MULTI_ARG_2_QI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv8hi3, "__builtin_ia32_vpcomfalsew", IX86_BUILTIN_VPCOMFALSEW, (enum rtx_code) PCOM_FALSE, (int)MULTI_ARG_2_HI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv4si3, "__builtin_ia32_vpcomfalsed", IX86_BUILTIN_VPCOMFALSED, (enum rtx_code) PCOM_FALSE, (int)MULTI_ARG_2_SI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv2di3, "__builtin_ia32_vpcomfalseq", IX86_BUILTIN_VPCOMFALSEQ, (enum rtx_code) PCOM_FALSE, (int)MULTI_ARG_2_DI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv16qi3, "__builtin_ia32_vpcomfalseub",IX86_BUILTIN_VPCOMFALSEUB,(enum rtx_code) PCOM_FALSE, (int)MULTI_ARG_2_QI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv8hi3, "__builtin_ia32_vpcomfalseuw",IX86_BUILTIN_VPCOMFALSEUW,(enum rtx_code) PCOM_FALSE, (int)MULTI_ARG_2_HI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv4si3, "__builtin_ia32_vpcomfalseud",IX86_BUILTIN_VPCOMFALSEUD,(enum rtx_code) PCOM_FALSE, (int)MULTI_ARG_2_SI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv2di3, "__builtin_ia32_vpcomfalseuq",IX86_BUILTIN_VPCOMFALSEUQ,(enum rtx_code) PCOM_FALSE, (int)MULTI_ARG_2_DI_TF },
+
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv16qi3, "__builtin_ia32_vpcomtrueb", IX86_BUILTIN_VPCOMTRUEB, (enum rtx_code) PCOM_TRUE, (int)MULTI_ARG_2_QI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv8hi3, "__builtin_ia32_vpcomtruew", IX86_BUILTIN_VPCOMTRUEW, (enum rtx_code) PCOM_TRUE, (int)MULTI_ARG_2_HI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv4si3, "__builtin_ia32_vpcomtrued", IX86_BUILTIN_VPCOMTRUED, (enum rtx_code) PCOM_TRUE, (int)MULTI_ARG_2_SI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv2di3, "__builtin_ia32_vpcomtrueq", IX86_BUILTIN_VPCOMTRUEQ, (enum rtx_code) PCOM_TRUE, (int)MULTI_ARG_2_DI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv16qi3, "__builtin_ia32_vpcomtrueub", IX86_BUILTIN_VPCOMTRUEUB, (enum rtx_code) PCOM_TRUE, (int)MULTI_ARG_2_QI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv8hi3, "__builtin_ia32_vpcomtrueuw", IX86_BUILTIN_VPCOMTRUEUW, (enum rtx_code) PCOM_TRUE, (int)MULTI_ARG_2_HI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv4si3, "__builtin_ia32_vpcomtrueud", IX86_BUILTIN_VPCOMTRUEUD, (enum rtx_code) PCOM_TRUE, (int)MULTI_ARG_2_SI_TF },
+ { OPTION_MASK_ISA_XOP, CODE_FOR_xop_pcom_tfv2di3, "__builtin_ia32_vpcomtrueuq", IX86_BUILTIN_VPCOMTRUEUQ, (enum rtx_code) PCOM_TRUE, (int)MULTI_ARG_2_DI_TF },
};
integer_type_node,
NULL_TREE);
-
- tree v2di_ftype_v2di
- = build_function_type_list (V2DI_type_node, V2DI_type_node, NULL_TREE);
-
- tree v16qi_ftype_v8hi_v8hi
- = build_function_type_list (V16QI_type_node,
- V8HI_type_node, V8HI_type_node,
- NULL_TREE);
- tree v8hi_ftype_v4si_v4si
- = build_function_type_list (V8HI_type_node,
- V4SI_type_node, V4SI_type_node,
- NULL_TREE);
- tree v8hi_ftype_v16qi_v16qi
- = build_function_type_list (V8HI_type_node,
- V16QI_type_node, V16QI_type_node,
- NULL_TREE);
- tree v4hi_ftype_v8qi_v8qi
- = build_function_type_list (V4HI_type_node,
- V8QI_type_node, V8QI_type_node,
- NULL_TREE);
- tree unsigned_ftype_unsigned_uchar
- = build_function_type_list (unsigned_type_node,
- unsigned_type_node,
- unsigned_char_type_node,
- NULL_TREE);
- tree unsigned_ftype_unsigned_ushort
- = build_function_type_list (unsigned_type_node,
- unsigned_type_node,
- short_unsigned_type_node,
- NULL_TREE);
- tree unsigned_ftype_unsigned_unsigned
- = build_function_type_list (unsigned_type_node,
- unsigned_type_node,
- unsigned_type_node,
- NULL_TREE);
- tree uint64_ftype_uint64_uint64
- = build_function_type_list (long_long_unsigned_type_node,
- long_long_unsigned_type_node,
- long_long_unsigned_type_node,
- NULL_TREE);
- tree float_ftype_float
- = build_function_type_list (float_type_node,
- float_type_node,
- NULL_TREE);
-
/* AVX builtins */
tree V32QI_type_node = build_vector_type_for_mode (char_type_node,
V32QImode);
V4DImode);
tree V4DF_type_node = build_vector_type_for_mode (double_type_node,
V4DFmode);
+ tree V16HI_type_node = build_vector_type_for_mode (intHI_type_node,
+ V16HImode);
tree v8sf_ftype_v8sf
= build_function_type_list (V8SF_type_node,
V8SF_type_node,
= build_function_type_list (V2DF_type_node,
V2DF_type_node, V2DI_type_node, NULL_TREE);
+ /* XOP instructions */
+ tree v2di_ftype_v2di_v2di_v2di
+ = build_function_type_list (V2DI_type_node,
+ V2DI_type_node,
+ V2DI_type_node,
+ V2DI_type_node,
+ NULL_TREE);
+
+ tree v4di_ftype_v4di_v4di_v4di
+ = build_function_type_list (V4DI_type_node,
+ V4DI_type_node,
+ V4DI_type_node,
+ V4DI_type_node,
+ NULL_TREE);
+
+ tree v4si_ftype_v4si_v4si_v4si
+ = build_function_type_list (V4SI_type_node,
+ V4SI_type_node,
+ V4SI_type_node,
+ V4SI_type_node,
+ NULL_TREE);
+
+ tree v8si_ftype_v8si_v8si_v8si
+ = build_function_type_list (V8SI_type_node,
+ V8SI_type_node,
+ V8SI_type_node,
+ V8SI_type_node,
+ NULL_TREE);
+
+ tree v32qi_ftype_v32qi_v32qi_v32qi
+ = build_function_type_list (V32QI_type_node,
+ V32QI_type_node,
+ V32QI_type_node,
+ V32QI_type_node,
+ NULL_TREE);
+
+ tree v4si_ftype_v4si_v4si_v2di
+ = build_function_type_list (V4SI_type_node,
+ V4SI_type_node,
+ V4SI_type_node,
+ V2DI_type_node,
+ NULL_TREE);
+
+ tree v8hi_ftype_v8hi_v8hi_v8hi
+ = build_function_type_list (V8HI_type_node,
+ V8HI_type_node,
+ V8HI_type_node,
+ V8HI_type_node,
+ NULL_TREE);
+
+ tree v16hi_ftype_v16hi_v16hi_v16hi
+ = build_function_type_list (V16HI_type_node,
+ V16HI_type_node,
+ V16HI_type_node,
+ V16HI_type_node,
+ NULL_TREE);
+
+ tree v8hi_ftype_v8hi_v8hi_v4si
+ = build_function_type_list (V8HI_type_node,
+ V8HI_type_node,
+ V8HI_type_node,
+ V4SI_type_node,
+ NULL_TREE);
+
+ tree v2di_ftype_v2di_si
+ = build_function_type_list (V2DI_type_node,
+ V2DI_type_node,
+ integer_type_node,
+ NULL_TREE);
+
+ tree v4si_ftype_v4si_si
+ = build_function_type_list (V4SI_type_node,
+ V4SI_type_node,
+ integer_type_node,
+ NULL_TREE);
+
+ tree v8hi_ftype_v8hi_si
+ = build_function_type_list (V8HI_type_node,
+ V8HI_type_node,
+ integer_type_node,
+ NULL_TREE);
+
+ tree v16qi_ftype_v16qi_si
+ = build_function_type_list (V16QI_type_node,
+ V16QI_type_node,
+ integer_type_node,
+ NULL_TREE);
+
+ tree v2di_ftype_v2di
+ = build_function_type_list (V2DI_type_node, V2DI_type_node, NULL_TREE);
+
+ tree v16qi_ftype_v8hi_v8hi
+ = build_function_type_list (V16QI_type_node,
+ V8HI_type_node, V8HI_type_node,
+ NULL_TREE);
+ tree v8hi_ftype_v4si_v4si
+ = build_function_type_list (V8HI_type_node,
+ V4SI_type_node, V4SI_type_node,
+ NULL_TREE);
+ tree v8hi_ftype_v16qi_v16qi
+ = build_function_type_list (V8HI_type_node,
+ V16QI_type_node, V16QI_type_node,
+ NULL_TREE);
+ tree v4hi_ftype_v8qi_v8qi
+ = build_function_type_list (V4HI_type_node,
+ V8QI_type_node, V8QI_type_node,
+ NULL_TREE);
+ tree unsigned_ftype_unsigned_uchar
+ = build_function_type_list (unsigned_type_node,
+ unsigned_type_node,
+ unsigned_char_type_node,
+ NULL_TREE);
+ tree unsigned_ftype_unsigned_ushort
+ = build_function_type_list (unsigned_type_node,
+ unsigned_type_node,
+ short_unsigned_type_node,
+ NULL_TREE);
+ tree unsigned_ftype_unsigned_unsigned
+ = build_function_type_list (unsigned_type_node,
+ unsigned_type_node,
+ unsigned_type_node,
+ NULL_TREE);
+ tree uint64_ftype_uint64_uint64
+ = build_function_type_list (long_long_unsigned_type_node,
+ long_long_unsigned_type_node,
+ long_long_unsigned_type_node,
+ NULL_TREE);
+ tree float_ftype_float
+ = build_function_type_list (float_type_node,
+ float_type_node,
+ NULL_TREE);
+
/* Integer intrinsics. */
tree uint64_ftype_void
= build_function_type (long_long_unsigned_type_node,
case MULTI_ARG_3_DF: mtype = v2df_ftype_v2df_v2df_v2df; break;
case MULTI_ARG_3_SF2: mtype = v8sf_ftype_v8sf_v8sf_v8sf; break;
case MULTI_ARG_3_DF2: mtype = v4df_ftype_v4df_v4df_v4df; break;
+ case MULTI_ARG_3_DI: mtype = v2di_ftype_v2di_v2di_v2di; break;
+ case MULTI_ARG_3_SI: mtype = v4si_ftype_v4si_v4si_v4si; break;
+ case MULTI_ARG_3_SI_DI: mtype = v4si_ftype_v4si_v4si_v2di; break;
+ case MULTI_ARG_3_HI: mtype = v8hi_ftype_v8hi_v8hi_v8hi; break;
+ case MULTI_ARG_3_HI_SI: mtype = v8hi_ftype_v8hi_v8hi_v4si; break;
+ case MULTI_ARG_3_QI: mtype = v16qi_ftype_v16qi_v16qi_v16qi; break;
+ case MULTI_ARG_3_DI2: mtype = v4di_ftype_v4di_v4di_v4di; break;
+ case MULTI_ARG_3_SI2: mtype = v8si_ftype_v8si_v8si_v8si; break;
+ case MULTI_ARG_3_HI2: mtype = v16hi_ftype_v16hi_v16hi_v16hi; break;
+ case MULTI_ARG_3_QI2: mtype = v32qi_ftype_v32qi_v32qi_v32qi; break;
+ case MULTI_ARG_2_SF: mtype = v4sf_ftype_v4sf_v4sf; break;
+ case MULTI_ARG_2_DF: mtype = v2df_ftype_v2df_v2df; break;
+ case MULTI_ARG_2_DI: mtype = v2di_ftype_v2di_v2di; break;
+ case MULTI_ARG_2_SI: mtype = v4si_ftype_v4si_v4si; break;
+ case MULTI_ARG_2_HI: mtype = v8hi_ftype_v8hi_v8hi; break;
+ case MULTI_ARG_2_QI: mtype = v16qi_ftype_v16qi_v16qi; break;
+ case MULTI_ARG_2_DI_IMM: mtype = v2di_ftype_v2di_si; break;
+ case MULTI_ARG_2_SI_IMM: mtype = v4si_ftype_v4si_si; break;
+ case MULTI_ARG_2_HI_IMM: mtype = v8hi_ftype_v8hi_si; break;
+ case MULTI_ARG_2_QI_IMM: mtype = v16qi_ftype_v16qi_si; break;
+ case MULTI_ARG_2_DI_CMP: mtype = v2di_ftype_v2di_v2di; break;
+ case MULTI_ARG_2_SI_CMP: mtype = v4si_ftype_v4si_v4si; break;
+ case MULTI_ARG_2_HI_CMP: mtype = v8hi_ftype_v8hi_v8hi; break;
+ case MULTI_ARG_2_QI_CMP: mtype = v16qi_ftype_v16qi_v16qi; break;
+ case MULTI_ARG_2_SF_TF: mtype = v4sf_ftype_v4sf_v4sf; break;
+ case MULTI_ARG_2_DF_TF: mtype = v2df_ftype_v2df_v2df; break;
+ case MULTI_ARG_2_DI_TF: mtype = v2di_ftype_v2di_v2di; break;
+ case MULTI_ARG_2_SI_TF: mtype = v4si_ftype_v4si_v4si; break;
+ case MULTI_ARG_2_HI_TF: mtype = v8hi_ftype_v8hi_v8hi; break;
+ case MULTI_ARG_2_QI_TF: mtype = v16qi_ftype_v16qi_v16qi; break;
+ case MULTI_ARG_1_SF: mtype = v4sf_ftype_v4sf; break;
+ case MULTI_ARG_1_DF: mtype = v2df_ftype_v2df; break;
+ case MULTI_ARG_1_SF2: mtype = v8sf_ftype_v8sf; break;
+ case MULTI_ARG_1_DF2: mtype = v4df_ftype_v4df; break;
+ case MULTI_ARG_1_DI: mtype = v2di_ftype_v2di; break;
+ case MULTI_ARG_1_SI: mtype = v4si_ftype_v4si; break;
+ case MULTI_ARG_1_HI: mtype = v8hi_ftype_v8hi; break;
+ case MULTI_ARG_1_QI: mtype = v16qi_ftype_v16qi; break;
+ case MULTI_ARG_1_SI_DI: mtype = v2di_ftype_v4si; break;
+ case MULTI_ARG_1_HI_DI: mtype = v2di_ftype_v8hi; break;
+ case MULTI_ARG_1_HI_SI: mtype = v4si_ftype_v8hi; break;
+ case MULTI_ARG_1_QI_DI: mtype = v2di_ftype_v16qi; break;
+ case MULTI_ARG_1_QI_SI: mtype = v4si_ftype_v16qi; break;
+ case MULTI_ARG_1_QI_HI: mtype = v8hi_ftype_v16qi; break;
case MULTI_ARG_UNKNOWN:
default:
case MULTI_ARG_3_DF:
case MULTI_ARG_3_SF2:
case MULTI_ARG_3_DF2:
+ case MULTI_ARG_3_DI:
+ case MULTI_ARG_3_SI:
+ case MULTI_ARG_3_SI_DI:
+ case MULTI_ARG_3_HI:
+ case MULTI_ARG_3_HI_SI:
+ case MULTI_ARG_3_QI:
+ case MULTI_ARG_3_DI2:
+ case MULTI_ARG_3_SI2:
+ case MULTI_ARG_3_HI2:
+ case MULTI_ARG_3_QI2:
nargs = 3;
break;
+ case MULTI_ARG_2_SF:
+ case MULTI_ARG_2_DF:
+ case MULTI_ARG_2_DI:
+ case MULTI_ARG_2_SI:
+ case MULTI_ARG_2_HI:
+ case MULTI_ARG_2_QI:
+ nargs = 2;
+ break;
+
+ case MULTI_ARG_2_DI_IMM:
+ case MULTI_ARG_2_SI_IMM:
+ case MULTI_ARG_2_HI_IMM:
+ case MULTI_ARG_2_QI_IMM:
+ nargs = 2;
+ last_arg_constant = true;
+ break;
+
+ case MULTI_ARG_1_SF:
+ case MULTI_ARG_1_DF:
+ case MULTI_ARG_1_SF2:
+ case MULTI_ARG_1_DF2:
+ case MULTI_ARG_1_DI:
+ case MULTI_ARG_1_SI:
+ case MULTI_ARG_1_HI:
+ case MULTI_ARG_1_QI:
+ case MULTI_ARG_1_SI_DI:
+ case MULTI_ARG_1_HI_DI:
+ case MULTI_ARG_1_HI_SI:
+ case MULTI_ARG_1_QI_DI:
+ case MULTI_ARG_1_QI_SI:
+ case MULTI_ARG_1_QI_HI:
+ nargs = 1;
+ break;
+
+ case MULTI_ARG_2_DI_CMP:
+ case MULTI_ARG_2_SI_CMP:
+ case MULTI_ARG_2_HI_CMP:
+ case MULTI_ARG_2_QI_CMP:
+ nargs = 2;
+ comparison_p = true;
+ break;
+
+ case MULTI_ARG_2_SF_TF:
+ case MULTI_ARG_2_DF_TF:
+ case MULTI_ARG_2_DI_TF:
+ case MULTI_ARG_2_SI_TF:
+ case MULTI_ARG_2_HI_TF:
+ case MULTI_ARG_2_QI_TF:
+ nargs = 2;
+ tf_p = true;
+ break;
+
case MULTI_ARG_UNKNOWN:
default:
gcc_unreachable ();
#define TARGET_FMA OPTION_ISA_FMA
#define TARGET_SSE4A OPTION_ISA_SSE4A
#define TARGET_FMA4 OPTION_ISA_FMA4
+#define TARGET_XOP OPTION_ISA_XOP
#define TARGET_ROUND OPTION_ISA_ROUND
#define TARGET_ABM OPTION_ISA_ABM
#define TARGET_POPCNT OPTION_ISA_POPCNT
;; X -- don't print any sort of PIC '@' suffix for a symbol.
;; & -- print some in-use local-dynamic symbol name.
;; H -- print a memory address offset by 8; used for sse high-parts
+;; Y -- print condition for XOP pcom* instruction.
;; + -- print a branch hint as 'cs' or 'ds' prefix
;; ; -- print a semicolon (after prefixes due to bug in older gas).
(UNSPEC_FMA4_INTRINSIC 150)
(UNSPEC_FMA4_FMADDSUB 151)
(UNSPEC_FMA4_FMSUBADD 152)
+ (UNSPEC_XOP_UNSIGNED_CMP 151)
+ (UNSPEC_XOP_TRUEFALSE 152)
+ (UNSPEC_XOP_PERMUTE 153)
+ (UNSPEC_FRCZ 154)
+
; For AES support
(UNSPEC_AESENC 159)
(UNSPEC_AESENCLAST 160)
(COM_TRUE_P 5)
])
+;; Constants used in the XOP pperm instruction
+(define_constants
+ [(PPERM_SRC 0x00) /* copy source */
+ (PPERM_INVERT 0x20) /* invert source */
+ (PPERM_REVERSE 0x40) /* bit reverse source */
+ (PPERM_REV_INV 0x60) /* bit reverse & invert src */
+ (PPERM_ZERO 0x80) /* all 0's */
+ (PPERM_ONES 0xa0) /* all 1's */
+ (PPERM_SIGN 0xc0) /* propagate sign bit */
+ (PPERM_INV_SIGN 0xe0) /* invert & propagate sign */
+ (PPERM_SRC1 0x00) /* use first source byte */
+ (PPERM_SRC2 0x10) /* use second source byte */
+ ])
+
;; Registers by name.
(define_constants
[(AX_REG 0)
[(set_attr "type" "fcmov")
(set_attr "mode" "XF")])
+;; All moves in XOP pcmov instructions are 128 bits and hence we restrict
+;; the scalar versions to have only XMM registers as operands.
+
+;; XOP conditional move
+(define_insn "*xop_pcmov_<mode>"
+ [(set (match_operand:MODEF 0 "register_operand" "=x")
+ (if_then_else:MODEF
+ (match_operand:MODEF 1 "register_operand" "x")
+ (match_operand:MODEF 2 "register_operand" "x")
+ (match_operand:MODEF 3 "register_operand" "x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, true, 1, false)"
+ "vpcmov\t{%1, %3, %2, %0|%0, %2, %3, %1}"
+ [(set_attr "type" "sse4arg")])
+
;; These versions of the min/max patterns are intentionally ignorant of
;; their behavior wrt -0.0 and NaN (via the commutative operand mark).
;; Since both the tree-level MAX_EXPR and the rtl-level SMAX operator
Target Report Mask(ISA_FMA4) Var(ix86_isa_flags) VarExists Save
Support FMA4 built-in functions and code generation
+mxop
+Target Report Mask(ISA_XOP) Var(ix86_isa_flags) VarExists Save
+Support XOP built-in functions and code generation
+
mabm
Target Report Mask(ISA_ABM) Var(ix86_isa_flags) VarExists Save
Support code generation of Advanced Bit Manipulation (ABM) instructions.
(define_mode_attr ssemodesuffixf2c [(V4SF "s") (V2DF "d")])
+;; Mapping of the max integer size for xop rotate immediate constraint
+(define_mode_attr sserotatemax [(V16QI "7") (V8HI "15") (V4SI "31") (V2DI "63")])
+
;; Mapping of vector modes back to the scalar modes
(define_mode_attr ssescalarmode [(V4SF "SF") (V2DF "DF")
(V16QI "QI") (V8HI "HI")
(match_operator:SSEMODEF4 3 "sse_comparison_operator"
[(match_operand:SSEMODEF4 1 "register_operand" "0")
(match_operand:SSEMODEF4 2 "nonimmediate_operand" "xm")]))]
- "(SSE_FLOAT_MODE_P (<MODE>mode) || SSE_VEC_FLOAT_MODE_P (<MODE>mode))"
+ "!TARGET_XOP
+ && (SSE_FLOAT_MODE_P (<MODE>mode) || SSE_VEC_FLOAT_MODE_P (<MODE>mode))"
"cmp%D3<ssemodesuffixf4>\t{%2, %0|%0, %2}"
[(set_attr "type" "ssecmp")
(set_attr "length_immediate" "1")
(match_operand:V4SI 2 "register_operand" "")))]
"TARGET_SSE2"
{
- if (TARGET_SSE4_1)
+ if (TARGET_SSE4_1 || TARGET_XOP)
ix86_fixup_binary_operands_no_copy (MULT, V4SImode, operands);
})
[(set (match_operand:V4SI 0 "register_operand" "")
(mult:V4SI (match_operand:V4SI 1 "register_operand" "")
(match_operand:V4SI 2 "register_operand" "")))]
- "TARGET_SSE2 && !TARGET_SSE4_1
+ "TARGET_SSE2 && !TARGET_SSE4_1 && !TARGET_XOP
&& can_create_pseudo_p ()"
"#"
"&& 1"
rtx t1, t2, t3, t4, t5, t6, thirtytwo;
rtx op0, op1, op2;
+ if (TARGET_XOP)
+ {
+ /* op1: A,B,C,D, op2: E,F,G,H */
+ op0 = operands[0];
+ op1 = gen_lowpart (V4SImode, operands[1]);
+ op2 = gen_lowpart (V4SImode, operands[2]);
+ t1 = gen_reg_rtx (V4SImode);
+ t2 = gen_reg_rtx (V4SImode);
+ t3 = gen_reg_rtx (V4SImode);
+ t4 = gen_reg_rtx (V2DImode);
+ t5 = gen_reg_rtx (V2DImode);
+
+ /* t1: B,A,D,C */
+ emit_insn (gen_sse2_pshufd_1 (t1, op1,
+ GEN_INT (1),
+ GEN_INT (0),
+ GEN_INT (3),
+ GEN_INT (2)));
+
+ /* t2: 0 */
+ emit_move_insn (t2, CONST0_RTX (V4SImode));
+
+ /* t3: (B*E),(A*F),(D*G),(C*H) */
+ emit_insn (gen_xop_pmacsdd (t3, t1, op2, t2));
+
+ /* t4: (B*E)+(A*F), (D*G)+(C*H) */
+ emit_insn (gen_xop_phadddq (t4, t3));
+
+ /* t5: ((B*E)+(A*F))<<32, ((D*G)+(C*H))<<32 */
+ emit_insn (gen_ashlv2di3 (t5, t4, GEN_INT (32)));
+
+ /* op0: (((B*E)+(A*F))<<32)+(B*F), (((D*G)+(C*H))<<32)+(D*H) */
+ emit_insn (gen_xop_pmacsdql (op0, op1, op2, t5));
+ DONE;
+ }
+
op0 = operands[0];
op1 = operands[1];
op2 = operands[2];
DONE;
})
+(define_expand "vec_widen_smult_hi_v4si"
+ [(match_operand:V2DI 0 "register_operand" "")
+ (match_operand:V4SI 1 "register_operand" "")
+ (match_operand:V4SI 2 "register_operand" "")]
+ "TARGET_XOP"
+{
+ rtx t1, t2;
+
+ t1 = gen_reg_rtx (V4SImode);
+ t2 = gen_reg_rtx (V4SImode);
+
+ emit_insn (gen_sse2_pshufd_1 (t1, operands[1],
+ GEN_INT (0),
+ GEN_INT (2),
+ GEN_INT (1),
+ GEN_INT (3)));
+ emit_insn (gen_sse2_pshufd_1 (t2, operands[2],
+ GEN_INT (0),
+ GEN_INT (2),
+ GEN_INT (1),
+ GEN_INT (3)));
+ emit_insn (gen_xop_mulv2div2di3_high (operands[0], t1, t2));
+ DONE;
+})
+
+(define_expand "vec_widen_smult_lo_v4si"
+ [(match_operand:V2DI 0 "register_operand" "")
+ (match_operand:V4SI 1 "register_operand" "")
+ (match_operand:V4SI 2 "register_operand" "")]
+ "TARGET_XOP"
+{
+ rtx t1, t2;
+
+ t1 = gen_reg_rtx (V4SImode);
+ t2 = gen_reg_rtx (V4SImode);
+
+ emit_insn (gen_sse2_pshufd_1 (t1, operands[1],
+ GEN_INT (0),
+ GEN_INT (2),
+ GEN_INT (1),
+ GEN_INT (3)));
+ emit_insn (gen_sse2_pshufd_1 (t2, operands[2],
+ GEN_INT (0),
+ GEN_INT (2),
+ GEN_INT (1),
+ GEN_INT (3)));
+ emit_insn (gen_xop_mulv2div2di3_low (operands[0], t1, t2));
+ DONE;
+})
+
(define_expand "vec_widen_umult_hi_v4si"
[(match_operand:V2DI 0 "register_operand" "")
(match_operand:V4SI 1 "register_operand" "")
(eq:SSEMODE124
(match_operand:SSEMODE124 1 "nonimmediate_operand" "")
(match_operand:SSEMODE124 2 "nonimmediate_operand" "")))]
- "TARGET_SSE2"
+ "TARGET_SSE2 && !TARGET_XOP "
"ix86_fixup_binary_operands_no_copy (EQ, <MODE>mode, operands);")
(define_insn "*avx_eq<mode>3"
(eq:SSEMODE124
(match_operand:SSEMODE124 1 "nonimmediate_operand" "%0")
(match_operand:SSEMODE124 2 "nonimmediate_operand" "xm")))]
- "TARGET_SSE2
+ "TARGET_SSE2 && !TARGET_XOP
&& ix86_binary_operator_ok (EQ, <MODE>mode, operands)"
"pcmpeq<ssevecsize>\t{%2, %0|%0, %2}"
[(set_attr "type" "ssecmp")
(gt:SSEMODE124
(match_operand:SSEMODE124 1 "register_operand" "0")
(match_operand:SSEMODE124 2 "nonimmediate_operand" "xm")))]
- "TARGET_SSE2"
+ "TARGET_SSE2 && !TARGET_XOP"
"pcmpgt<ssevecsize>\t{%2, %0|%0, %2}"
[(set_attr "type" "ssecmp")
(set_attr "prefix_data16" "1")
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "TI")])
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;
+;; XOP instructions
+;;
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+;; XOP parallel integer multiply/add instructions.
+;; Note the instruction does not allow the value being added to be a memory
+;; operation. However by pretending via the nonimmediate_operand predicate
+;; that it does and splitting it later allows the following to be recognized:
+;; a[i] = b[i] * c[i] + d[i];
+(define_insn "xop_pmacsww"
+ [(set (match_operand:V8HI 0 "register_operand" "=x,x,x")
+ (plus:V8HI
+ (mult:V8HI
+ (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,xm")
+ (match_operand:V8HI 2 "nonimmediate_operand" "x,xm,x"))
+ (match_operand:V8HI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 2, true)"
+ "@
+ vpmacsww\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacsww\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacsww\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+;; Split pmacsww with two memory operands into a load and the pmacsww.
+(define_split
+ [(set (match_operand:V8HI 0 "register_operand" "")
+ (plus:V8HI
+ (mult:V8HI (match_operand:V8HI 1 "nonimmediate_operand" "")
+ (match_operand:V8HI 2 "nonimmediate_operand" ""))
+ (match_operand:V8HI 3 "nonimmediate_operand" "")))]
+ "TARGET_XOP
+ && !ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)
+ && ix86_fma4_valid_op_p (operands, insn, 4, false, 2, true)
+ && !reg_mentioned_p (operands[0], operands[1])
+ && !reg_mentioned_p (operands[0], operands[2])
+ && !reg_mentioned_p (operands[0], operands[3])"
+ [(const_int 0)]
+{
+ ix86_expand_fma4_multiple_memory (operands, 4, V8HImode);
+ emit_insn (gen_xop_pmacsww (operands[0], operands[1], operands[2],
+ operands[3]));
+ DONE;
+})
+
+(define_insn "xop_pmacssww"
+ [(set (match_operand:V8HI 0 "register_operand" "=x,x,x")
+ (ss_plus:V8HI
+ (mult:V8HI (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,m")
+ (match_operand:V8HI 2 "nonimmediate_operand" "x,m,x"))
+ (match_operand:V8HI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)"
+ "@
+ vpmacssww\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacssww\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacssww\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+;; Note the instruction does not allow the value being added to be a memory
+;; operation. However by pretending via the nonimmediate_operand predicate
+;; that it does and splitting it later allows the following to be recognized:
+;; a[i] = b[i] * c[i] + d[i];
+(define_insn "xop_pmacsdd"
+ [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
+ (plus:V4SI
+ (mult:V4SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
+ (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x"))
+ (match_operand:V4SI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 2, true)"
+ "@
+ vpmacsdd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacsdd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacsdd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+;; Split pmacsdd with two memory operands into a load and the pmacsdd.
+(define_split
+ [(set (match_operand:V4SI 0 "register_operand" "")
+ (plus:V4SI
+ (mult:V4SI (match_operand:V4SI 1 "nonimmediate_operand" "")
+ (match_operand:V4SI 2 "nonimmediate_operand" ""))
+ (match_operand:V4SI 3 "nonimmediate_operand" "")))]
+ "TARGET_XOP
+ && !ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)
+ && ix86_fma4_valid_op_p (operands, insn, 4, false, 2, true)
+ && !reg_mentioned_p (operands[0], operands[1])
+ && !reg_mentioned_p (operands[0], operands[2])
+ && !reg_mentioned_p (operands[0], operands[3])"
+ [(const_int 0)]
+{
+ ix86_expand_fma4_multiple_memory (operands, 4, V4SImode);
+ emit_insn (gen_xop_pmacsdd (operands[0], operands[1], operands[2],
+ operands[3]));
+ DONE;
+})
+
+(define_insn "xop_pmacssdd"
+ [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
+ (ss_plus:V4SI
+ (mult:V4SI (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
+ (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x"))
+ (match_operand:V4SI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)"
+ "@
+ vpmacssdd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacssdd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacssdd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_pmacssdql"
+ [(set (match_operand:V2DI 0 "register_operand" "=x,x,x")
+ (ss_plus:V2DI
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
+ (parallel [(const_int 1)
+ (const_int 3)])))
+ (vec_select:V2SI
+ (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
+ (parallel [(const_int 1)
+ (const_int 3)])))
+ (match_operand:V2DI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)"
+ "@
+ vpmacssdql\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacssdql\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacssdql\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_pmacssdqh"
+ [(set (match_operand:V2DI 0 "register_operand" "=x,x,x")
+ (ss_plus:V2DI
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
+ (parallel [(const_int 0)
+ (const_int 2)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
+ (parallel [(const_int 0)
+ (const_int 2)]))))
+ (match_operand:V2DI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)"
+ "@
+ vpmacssdqh\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacssdqh\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacssdqh\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_pmacsdql"
+ [(set (match_operand:V2DI 0 "register_operand" "=x,x,x")
+ (plus:V2DI
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
+ (parallel [(const_int 1)
+ (const_int 3)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
+ (parallel [(const_int 1)
+ (const_int 3)]))))
+ (match_operand:V2DI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)"
+ "@
+ vpmacsdql\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacsdql\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacsdql\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+(define_insn_and_split "*xop_pmacsdql_mem"
+ [(set (match_operand:V2DI 0 "register_operand" "=&x,&x,&x")
+ (plus:V2DI
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
+ (parallel [(const_int 1)
+ (const_int 3)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
+ (parallel [(const_int 1)
+ (const_int 3)]))))
+ (match_operand:V2DI 3 "memory_operand" "m,m,m")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, -1, true)"
+ "#"
+ "&& (reload_completed
+ || (!reg_mentioned_p (operands[0], operands[1])
+ && !reg_mentioned_p (operands[0], operands[2])))"
+ [(set (match_dup 0)
+ (match_dup 3))
+ (set (match_dup 0)
+ (plus:V2DI
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_dup 2)
+ (parallel [(const_int 1)
+ (const_int 3)]))))
+ (match_dup 0)))])
+
+;; We don't have a straight 32-bit parallel multiply and extend on XOP, so
+;; fake it with a multiply/add. In general, we expect the define_split to
+;; occur before register allocation, so we have to handle the corner case where
+;; the target is the same as operands 1/2
+(define_insn_and_split "xop_mulv2div2di3_low"
+ [(set (match_operand:V2DI 0 "register_operand" "=&x")
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "%x")
+ (parallel [(const_int 1)
+ (const_int 3)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 2 "nonimmediate_operand" "xm")
+ (parallel [(const_int 1)
+ (const_int 3)])))))]
+ "TARGET_XOP"
+ "#"
+ "&& (reload_completed
+ || (!reg_mentioned_p (operands[0], operands[1])
+ && !reg_mentioned_p (operands[0], operands[2])))"
+ [(set (match_dup 0)
+ (match_dup 3))
+ (set (match_dup 0)
+ (plus:V2DI
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_dup 2)
+ (parallel [(const_int 1)
+ (const_int 3)]))))
+ (match_dup 0)))]
+{
+ operands[3] = CONST0_RTX (V2DImode);
+}
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_pmacsdqh"
+ [(set (match_operand:V2DI 0 "register_operand" "=x,x,x")
+ (plus:V2DI
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
+ (parallel [(const_int 0)
+ (const_int 2)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
+ (parallel [(const_int 0)
+ (const_int 2)]))))
+ (match_operand:V2DI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)"
+ "@
+ vpmacsdqh\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacsdqh\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacsdqh\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+(define_insn_and_split "*xop_pmacsdqh_mem"
+ [(set (match_operand:V2DI 0 "register_operand" "=&x,&x,&x")
+ (plus:V2DI
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "%x,x,m")
+ (parallel [(const_int 0)
+ (const_int 2)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 2 "nonimmediate_operand" "x,m,x")
+ (parallel [(const_int 0)
+ (const_int 2)]))))
+ (match_operand:V2DI 3 "memory_operand" "m,m,m")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, -1, true)"
+ "#"
+ "&& (reload_completed
+ || (!reg_mentioned_p (operands[0], operands[1])
+ && !reg_mentioned_p (operands[0], operands[2])))"
+ [(set (match_dup 0)
+ (match_dup 3))
+ (set (match_dup 0)
+ (plus:V2DI
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_dup 1)
+ (parallel [(const_int 0)
+ (const_int 2)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_dup 2)
+ (parallel [(const_int 0)
+ (const_int 2)]))))
+ (match_dup 0)))])
+
+;; We don't have a straight 32-bit parallel multiply and extend on XOP, so
+;; fake it with a multiply/add. In general, we expect the define_split to
+;; occur before register allocation, so we have to handle the corner case where
+;; the target is the same as either operands[1] or operands[2]
+(define_insn_and_split "xop_mulv2div2di3_high"
+ [(set (match_operand:V2DI 0 "register_operand" "=&x")
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "%x")
+ (parallel [(const_int 0)
+ (const_int 2)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 2 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 2)])))))]
+ "TARGET_XOP"
+ "#"
+ "&& (reload_completed
+ || (!reg_mentioned_p (operands[0], operands[1])
+ && !reg_mentioned_p (operands[0], operands[2])))"
+ [(set (match_dup 0)
+ (match_dup 3))
+ (set (match_dup 0)
+ (plus:V2DI
+ (mult:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_dup 1)
+ (parallel [(const_int 0)
+ (const_int 2)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_dup 2)
+ (parallel [(const_int 0)
+ (const_int 2)]))))
+ (match_dup 0)))]
+{
+ operands[3] = CONST0_RTX (V2DImode);
+}
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+;; XOP parallel integer multiply/add instructions for the intrinisics
+(define_insn "xop_pmacsswd"
+ [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
+ (ss_plus:V4SI
+ (mult:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,m")
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)])))
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 2 "nonimmediate_operand" "x,m,x")
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)]))))
+ (match_operand:V4SI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)"
+ "@
+ vpmacsswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacsswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacsswd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_pmacswd"
+ [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
+ (plus:V4SI
+ (mult:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,m")
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)])))
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 2 "nonimmediate_operand" "x,m,x")
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)]))))
+ (match_operand:V4SI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)"
+ "@
+ vpmacswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmacswd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_pmadcsswd"
+ [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
+ (ss_plus:V4SI
+ (plus:V4SI
+ (mult:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,m")
+ (parallel [(const_int 0)
+ (const_int 2)
+ (const_int 4)
+ (const_int 6)])))
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 2 "nonimmediate_operand" "x,m,x")
+ (parallel [(const_int 0)
+ (const_int 2)
+ (const_int 4)
+ (const_int 6)]))))
+ (mult:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)])))
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_dup 2)
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)])))))
+ (match_operand:V4SI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)"
+ "@
+ vpmadcsswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmadcsswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmadcsswd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_pmadcswd"
+ [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
+ (plus:V4SI
+ (plus:V4SI
+ (mult:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 1 "nonimmediate_operand" "%x,x,m")
+ (parallel [(const_int 0)
+ (const_int 2)
+ (const_int 4)
+ (const_int 6)])))
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 2 "nonimmediate_operand" "x,m,x")
+ (parallel [(const_int 0)
+ (const_int 2)
+ (const_int 4)
+ (const_int 6)]))))
+ (mult:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)])))
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_dup 2)
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)])))))
+ (match_operand:V4SI 3 "register_operand" "x,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, false, 1, true)"
+ "@
+ vpmadcswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmadcswd\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpmadcswd\t{%3, %1, %2, %0|%0, %2, %1, %3}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "TI")])
+
+;; XOP parallel XMM conditional moves
+(define_insn "xop_pcmov_<mode>"
+ [(set (match_operand:SSEMODE 0 "register_operand" "=x,x,x")
+ (if_then_else:SSEMODE
+ (match_operand:SSEMODE 3 "nonimmediate_operand" "x,x,xm")
+ (match_operand:SSEMODE 1 "vector_move_operand" "x,xm,x")
+ (match_operand:SSEMODE 2 "vector_move_operand" "xm,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, true, 1, false)"
+ "@
+ vpcmov\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpcmov\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpcmov\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "sse4arg")])
+
+(define_insn "xop_pcmov_<mode>256"
+ [(set (match_operand:AVX256MODE 0 "register_operand" "=x,x,x")
+ (if_then_else:AVX256MODE
+ (match_operand:AVX256MODE 3 "nonimmediate_operand" "x,x,xm")
+ (match_operand:AVX256MODE 1 "vector_move_operand" "x,xm,x")
+ (match_operand:AVX256MODE 2 "vector_move_operand" "xm,x,x")))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, true, 1, false)"
+ "@
+ vpcmov\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpcmov\t{%3, %2, %1, %0|%0, %1, %2, %3}
+ vpcmov\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "sse4arg")])
+
+;; XOP horizontal add/subtract instructions
+(define_insn "xop_phaddbw"
+ [(set (match_operand:V8HI 0 "register_operand" "=x")
+ (plus:V8HI
+ (sign_extend:V8HI
+ (vec_select:V8QI
+ (match_operand:V16QI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 2)
+ (const_int 4)
+ (const_int 6)
+ (const_int 8)
+ (const_int 10)
+ (const_int 12)
+ (const_int 14)])))
+ (sign_extend:V8HI
+ (vec_select:V8QI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)
+ (const_int 9)
+ (const_int 11)
+ (const_int 13)
+ (const_int 15)])))))]
+ "TARGET_XOP"
+ "vphaddbw\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phaddbd"
+ [(set (match_operand:V4SI 0 "register_operand" "=x")
+ (plus:V4SI
+ (plus:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4QI
+ (match_operand:V16QI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 4)
+ (const_int 8)
+ (const_int 12)])))
+ (sign_extend:V4SI
+ (vec_select:V4QI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 5)
+ (const_int 9)
+ (const_int 13)]))))
+ (plus:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4QI
+ (match_dup 1)
+ (parallel [(const_int 2)
+ (const_int 6)
+ (const_int 10)
+ (const_int 14)])))
+ (sign_extend:V4SI
+ (vec_select:V4QI
+ (match_dup 1)
+ (parallel [(const_int 3)
+ (const_int 7)
+ (const_int 11)
+ (const_int 15)]))))))]
+ "TARGET_XOP"
+ "vphaddbd\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phaddbq"
+ [(set (match_operand:V2DI 0 "register_operand" "=x")
+ (plus:V2DI
+ (plus:V2DI
+ (plus:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2QI
+ (match_operand:V16QI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 4)])))
+ (sign_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 5)]))))
+ (plus:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 2)
+ (const_int 6)])))
+ (sign_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 3)
+ (const_int 7)])))))
+ (plus:V2DI
+ (plus:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 8)
+ (const_int 12)])))
+ (sign_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 9)
+ (const_int 13)]))))
+ (plus:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 10)
+ (const_int 14)])))
+ (sign_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 11)
+ (const_int 15)])))))))]
+ "TARGET_XOP"
+ "vphaddbq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phaddwd"
+ [(set (match_operand:V4SI 0 "register_operand" "=x")
+ (plus:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 2)
+ (const_int 4)
+ (const_int 6)])))
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)])))))]
+ "TARGET_XOP"
+ "vphaddwd\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phaddwq"
+ [(set (match_operand:V2DI 0 "register_operand" "=x")
+ (plus:V2DI
+ (plus:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2HI
+ (match_operand:V8HI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 4)])))
+ (sign_extend:V2DI
+ (vec_select:V2HI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 5)]))))
+ (plus:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2HI
+ (match_dup 1)
+ (parallel [(const_int 2)
+ (const_int 6)])))
+ (sign_extend:V2DI
+ (vec_select:V2HI
+ (match_dup 1)
+ (parallel [(const_int 3)
+ (const_int 7)]))))))]
+ "TARGET_XOP"
+ "vphaddwq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phadddq"
+ [(set (match_operand:V2DI 0 "register_operand" "=x")
+ (plus:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 2)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)])))))]
+ "TARGET_XOP"
+ "vphadddq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phaddubw"
+ [(set (match_operand:V8HI 0 "register_operand" "=x")
+ (plus:V8HI
+ (zero_extend:V8HI
+ (vec_select:V8QI
+ (match_operand:V16QI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 2)
+ (const_int 4)
+ (const_int 6)
+ (const_int 8)
+ (const_int 10)
+ (const_int 12)
+ (const_int 14)])))
+ (zero_extend:V8HI
+ (vec_select:V8QI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)
+ (const_int 9)
+ (const_int 11)
+ (const_int 13)
+ (const_int 15)])))))]
+ "TARGET_XOP"
+ "vphaddubw\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phaddubd"
+ [(set (match_operand:V4SI 0 "register_operand" "=x")
+ (plus:V4SI
+ (plus:V4SI
+ (zero_extend:V4SI
+ (vec_select:V4QI
+ (match_operand:V16QI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 4)
+ (const_int 8)
+ (const_int 12)])))
+ (zero_extend:V4SI
+ (vec_select:V4QI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 5)
+ (const_int 9)
+ (const_int 13)]))))
+ (plus:V4SI
+ (zero_extend:V4SI
+ (vec_select:V4QI
+ (match_dup 1)
+ (parallel [(const_int 2)
+ (const_int 6)
+ (const_int 10)
+ (const_int 14)])))
+ (zero_extend:V4SI
+ (vec_select:V4QI
+ (match_dup 1)
+ (parallel [(const_int 3)
+ (const_int 7)
+ (const_int 11)
+ (const_int 15)]))))))]
+ "TARGET_XOP"
+ "vphaddubd\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phaddubq"
+ [(set (match_operand:V2DI 0 "register_operand" "=x")
+ (plus:V2DI
+ (plus:V2DI
+ (plus:V2DI
+ (zero_extend:V2DI
+ (vec_select:V2QI
+ (match_operand:V16QI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 4)])))
+ (sign_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 5)]))))
+ (plus:V2DI
+ (zero_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 2)
+ (const_int 6)])))
+ (zero_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 3)
+ (const_int 7)])))))
+ (plus:V2DI
+ (plus:V2DI
+ (zero_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 8)
+ (const_int 12)])))
+ (sign_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 9)
+ (const_int 13)]))))
+ (plus:V2DI
+ (zero_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 10)
+ (const_int 14)])))
+ (zero_extend:V2DI
+ (vec_select:V2QI
+ (match_dup 1)
+ (parallel [(const_int 11)
+ (const_int 15)])))))))]
+ "TARGET_XOP"
+ "vphaddubq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phadduwd"
+ [(set (match_operand:V4SI 0 "register_operand" "=x")
+ (plus:V4SI
+ (zero_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 2)
+ (const_int 4)
+ (const_int 6)])))
+ (zero_extend:V4SI
+ (vec_select:V4HI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)])))))]
+ "TARGET_XOP"
+ "vphadduwd\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phadduwq"
+ [(set (match_operand:V2DI 0 "register_operand" "=x")
+ (plus:V2DI
+ (plus:V2DI
+ (zero_extend:V2DI
+ (vec_select:V2HI
+ (match_operand:V8HI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 4)])))
+ (zero_extend:V2DI
+ (vec_select:V2HI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 5)]))))
+ (plus:V2DI
+ (zero_extend:V2DI
+ (vec_select:V2HI
+ (match_dup 1)
+ (parallel [(const_int 2)
+ (const_int 6)])))
+ (zero_extend:V2DI
+ (vec_select:V2HI
+ (match_dup 1)
+ (parallel [(const_int 3)
+ (const_int 7)]))))))]
+ "TARGET_XOP"
+ "vphadduwq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phaddudq"
+ [(set (match_operand:V2DI 0 "register_operand" "=x")
+ (plus:V2DI
+ (zero_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 2)])))
+ (zero_extend:V2DI
+ (vec_select:V2SI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)])))))]
+ "TARGET_XOP"
+ "vphaddudq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phsubbw"
+ [(set (match_operand:V8HI 0 "register_operand" "=x")
+ (minus:V8HI
+ (sign_extend:V8HI
+ (vec_select:V8QI
+ (match_operand:V16QI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 2)
+ (const_int 4)
+ (const_int 6)
+ (const_int 8)
+ (const_int 10)
+ (const_int 12)
+ (const_int 14)])))
+ (sign_extend:V8HI
+ (vec_select:V8QI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)
+ (const_int 9)
+ (const_int 11)
+ (const_int 13)
+ (const_int 15)])))))]
+ "TARGET_XOP"
+ "vphsubbw\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phsubwd"
+ [(set (match_operand:V4SI 0 "register_operand" "=x")
+ (minus:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 2)
+ (const_int 4)
+ (const_int 6)])))
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)
+ (const_int 5)
+ (const_int 7)])))))]
+ "TARGET_XOP"
+ "vphsubwd\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+(define_insn "xop_phsubdq"
+ [(set (match_operand:V2DI 0 "register_operand" "=x")
+ (minus:V2DI
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_operand:V4SI 1 "nonimmediate_operand" "xm")
+ (parallel [(const_int 0)
+ (const_int 2)])))
+ (sign_extend:V2DI
+ (vec_select:V2SI
+ (match_dup 1)
+ (parallel [(const_int 1)
+ (const_int 3)])))))]
+ "TARGET_XOP"
+ "vphsubdq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseiadd1")])
+
+;; XOP permute instructions
+(define_insn "xop_pperm"
+ [(set (match_operand:V16QI 0 "register_operand" "=x,x,x")
+ (unspec:V16QI
+ [(match_operand:V16QI 1 "nonimmediate_operand" "x,x,xm")
+ (match_operand:V16QI 2 "nonimmediate_operand" "x,xm,x")
+ (match_operand:V16QI 3 "nonimmediate_operand" "xm,x,x")]
+ UNSPEC_XOP_PERMUTE))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, true, 1, false)"
+ "vpperm\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "sse4arg")
+ (set_attr "mode" "TI")])
+
+;; XOP pack instructions that combine two vectors into a smaller vector
+(define_insn "xop_pperm_pack_v2di_v4si"
+ [(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
+ (vec_concat:V4SI
+ (truncate:V2SI
+ (match_operand:V2DI 1 "nonimmediate_operand" "x,x,xm"))
+ (truncate:V2SI
+ (match_operand:V2DI 2 "nonimmediate_operand" "x,xm,x"))))
+ (use (match_operand:V16QI 3 "nonimmediate_operand" "xm,x,x"))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, true, 1, false)"
+ "vpperm\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "sse4arg")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_pperm_pack_v4si_v8hi"
+ [(set (match_operand:V8HI 0 "register_operand" "=x,x,x")
+ (vec_concat:V8HI
+ (truncate:V4HI
+ (match_operand:V4SI 1 "nonimmediate_operand" "x,x,xm"))
+ (truncate:V4HI
+ (match_operand:V4SI 2 "nonimmediate_operand" "x,xm,x"))))
+ (use (match_operand:V16QI 3 "nonimmediate_operand" "xm,x,x"))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, true, 1, false)"
+ "vpperm\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "sse4arg")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_pperm_pack_v8hi_v16qi"
+ [(set (match_operand:V16QI 0 "register_operand" "=x,x,x")
+ (vec_concat:V16QI
+ (truncate:V8QI
+ (match_operand:V8HI 1 "nonimmediate_operand" "x,x,xm"))
+ (truncate:V8QI
+ (match_operand:V8HI 2 "nonimmediate_operand" "x,xm,x"))))
+ (use (match_operand:V16QI 3 "nonimmediate_operand" "xm,x,x"))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 4, true, 1, false)"
+ "vpperm\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "sse4arg")
+ (set_attr "mode" "TI")])
+
+;; XOP packed rotate instructions
+(define_expand "rotl<mode>3"
+ [(set (match_operand:SSEMODE1248 0 "register_operand" "")
+ (rotate:SSEMODE1248
+ (match_operand:SSEMODE1248 1 "nonimmediate_operand" "")
+ (match_operand:SI 2 "general_operand")))]
+ "TARGET_XOP"
+{
+ /* If we were given a scalar, convert it to parallel */
+ if (! const_0_to_<sserotatemax>_operand (operands[2], SImode))
+ {
+ rtvec vs = rtvec_alloc (<ssescalarnum>);
+ rtx par = gen_rtx_PARALLEL (<MODE>mode, vs);
+ rtx reg = gen_reg_rtx (<MODE>mode);
+ rtx op2 = operands[2];
+ int i;
+
+ if (GET_MODE (op2) != <ssescalarmode>mode)
+ {
+ op2 = gen_reg_rtx (<ssescalarmode>mode);
+ convert_move (op2, operands[2], false);
+ }
+
+ for (i = 0; i < <ssescalarnum>; i++)
+ RTVEC_ELT (vs, i) = op2;
+
+ emit_insn (gen_vec_init<mode> (reg, par));
+ emit_insn (gen_xop_vrotl<mode>3 (operands[0], operands[1], reg));
+ DONE;
+ }
+})
+
+(define_expand "rotr<mode>3"
+ [(set (match_operand:SSEMODE1248 0 "register_operand" "")
+ (rotatert:SSEMODE1248
+ (match_operand:SSEMODE1248 1 "nonimmediate_operand" "")
+ (match_operand:SI 2 "general_operand")))]
+ "TARGET_XOP"
+{
+ /* If we were given a scalar, convert it to parallel */
+ if (! const_0_to_<sserotatemax>_operand (operands[2], SImode))
+ {
+ rtvec vs = rtvec_alloc (<ssescalarnum>);
+ rtx par = gen_rtx_PARALLEL (<MODE>mode, vs);
+ rtx neg = gen_reg_rtx (<MODE>mode);
+ rtx reg = gen_reg_rtx (<MODE>mode);
+ rtx op2 = operands[2];
+ int i;
+
+ if (GET_MODE (op2) != <ssescalarmode>mode)
+ {
+ op2 = gen_reg_rtx (<ssescalarmode>mode);
+ convert_move (op2, operands[2], false);
+ }
+
+ for (i = 0; i < <ssescalarnum>; i++)
+ RTVEC_ELT (vs, i) = op2;
+
+ emit_insn (gen_vec_init<mode> (reg, par));
+ emit_insn (gen_neg<mode>2 (neg, reg));
+ emit_insn (gen_xop_vrotl<mode>3 (operands[0], operands[1], neg));
+ DONE;
+ }
+})
+
+(define_insn "xop_rotl<mode>3"
+ [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
+ (rotate:SSEMODE1248
+ (match_operand:SSEMODE1248 1 "nonimmediate_operand" "xm")
+ (match_operand:SI 2 "const_0_to_<sserotatemax>_operand" "n")))]
+ "TARGET_XOP"
+ "vprot<ssevecsize>\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sseishft")
+ (set_attr "length_immediate" "1")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_rotr<mode>3"
+ [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
+ (rotatert:SSEMODE1248
+ (match_operand:SSEMODE1248 1 "nonimmediate_operand" "xm")
+ (match_operand:SI 2 "const_0_to_<sserotatemax>_operand" "n")))]
+ "TARGET_XOP"
+{
+ operands[3] = GEN_INT ((<ssescalarnum> * 8) - INTVAL (operands[2]));
+ return \"vprot<ssevecsize>\t{%3, %1, %0|%0, %1, %3}\";
+}
+ [(set_attr "type" "sseishft")
+ (set_attr "length_immediate" "1")
+ (set_attr "mode" "TI")])
+
+(define_expand "vrotr<mode>3"
+ [(match_operand:SSEMODE1248 0 "register_operand" "")
+ (match_operand:SSEMODE1248 1 "register_operand" "")
+ (match_operand:SSEMODE1248 2 "register_operand" "")]
+ "TARGET_XOP"
+{
+ rtx reg = gen_reg_rtx (<MODE>mode);
+ emit_insn (gen_neg<mode>2 (reg, operands[2]));
+ emit_insn (gen_xop_vrotl<mode>3 (operands[0], operands[1], reg));
+ DONE;
+})
+
+(define_expand "vrotl<mode>3"
+ [(match_operand:SSEMODE1248 0 "register_operand" "")
+ (match_operand:SSEMODE1248 1 "register_operand" "")
+ (match_operand:SSEMODE1248 2 "register_operand" "")]
+ "TARGET_XOP"
+{
+ emit_insn (gen_xop_vrotl<mode>3 (operands[0], operands[1], operands[2]));
+ DONE;
+})
+
+(define_insn "xop_vrotl<mode>3"
+ [(set (match_operand:SSEMODE1248 0 "register_operand" "=x,x")
+ (if_then_else:SSEMODE1248
+ (ge:SSEMODE1248
+ (match_operand:SSEMODE1248 2 "nonimmediate_operand" "xm,x")
+ (const_int 0))
+ (rotate:SSEMODE1248
+ (match_operand:SSEMODE1248 1 "nonimmediate_operand" "x,xm")
+ (match_dup 2))
+ (rotatert:SSEMODE1248
+ (match_dup 1)
+ (neg:SSEMODE1248 (match_dup 2)))))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 3, true, 1, false)"
+ "vprot<ssevecsize>\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sseishft")
+ (set_attr "prefix_data16" "0")
+ (set_attr "prefix_extra" "2")
+ (set_attr "mode" "TI")])
+
+;; XOP packed shift instructions.
+;; FIXME: add V2DI back in
+(define_expand "vlshr<mode>3"
+ [(match_operand:SSEMODE124 0 "register_operand" "")
+ (match_operand:SSEMODE124 1 "register_operand" "")
+ (match_operand:SSEMODE124 2 "register_operand" "")]
+ "TARGET_XOP"
+{
+ rtx neg = gen_reg_rtx (<MODE>mode);
+ emit_insn (gen_neg<mode>2 (neg, operands[2]));
+ emit_insn (gen_xop_lshl<mode>3 (operands[0], operands[1], neg));
+ DONE;
+})
+
+(define_expand "vashr<mode>3"
+ [(match_operand:SSEMODE124 0 "register_operand" "")
+ (match_operand:SSEMODE124 1 "register_operand" "")
+ (match_operand:SSEMODE124 2 "register_operand" "")]
+ "TARGET_XOP"
+{
+ rtx neg = gen_reg_rtx (<MODE>mode);
+ emit_insn (gen_neg<mode>2 (neg, operands[2]));
+ emit_insn (gen_xop_ashl<mode>3 (operands[0], operands[1], neg));
+ DONE;
+})
+
+(define_expand "vashl<mode>3"
+ [(match_operand:SSEMODE124 0 "register_operand" "")
+ (match_operand:SSEMODE124 1 "register_operand" "")
+ (match_operand:SSEMODE124 2 "register_operand" "")]
+ "TARGET_XOP"
+{
+ emit_insn (gen_xop_ashl<mode>3 (operands[0], operands[1], operands[2]));
+ DONE;
+})
+
+(define_insn "xop_ashl<mode>3"
+ [(set (match_operand:SSEMODE1248 0 "register_operand" "=x,x")
+ (if_then_else:SSEMODE1248
+ (ge:SSEMODE1248
+ (match_operand:SSEMODE1248 2 "nonimmediate_operand" "xm,x")
+ (const_int 0))
+ (ashift:SSEMODE1248
+ (match_operand:SSEMODE1248 1 "nonimmediate_operand" "x,xm")
+ (match_dup 2))
+ (ashiftrt:SSEMODE1248
+ (match_dup 1)
+ (neg:SSEMODE1248 (match_dup 2)))))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 3, true, 1, false)"
+ "vpsha<ssevecsize>\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sseishft")
+ (set_attr "prefix_data16" "0")
+ (set_attr "prefix_extra" "2")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_lshl<mode>3"
+ [(set (match_operand:SSEMODE1248 0 "register_operand" "=x,x")
+ (if_then_else:SSEMODE1248
+ (ge:SSEMODE1248
+ (match_operand:SSEMODE1248 2 "nonimmediate_operand" "xm,x")
+ (const_int 0))
+ (ashift:SSEMODE1248
+ (match_operand:SSEMODE1248 1 "nonimmediate_operand" "x,xm")
+ (match_dup 2))
+ (lshiftrt:SSEMODE1248
+ (match_dup 1)
+ (neg:SSEMODE1248 (match_dup 2)))))]
+ "TARGET_XOP && ix86_fma4_valid_op_p (operands, insn, 3, true, 1, false)"
+ "vpshl<ssevecsize>\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sseishft")
+ (set_attr "prefix_data16" "0")
+ (set_attr "prefix_extra" "2")
+ (set_attr "mode" "TI")])
+
+;; SSE2 doesn't have some shift varients, so define versions for XOP
+(define_expand "ashlv16qi3"
+ [(match_operand:V16QI 0 "register_operand" "")
+ (match_operand:V16QI 1 "register_operand" "")
+ (match_operand:SI 2 "nonmemory_operand" "")]
+ "TARGET_XOP"
+{
+ rtvec vs = rtvec_alloc (16);
+ rtx par = gen_rtx_PARALLEL (V16QImode, vs);
+ rtx reg = gen_reg_rtx (V16QImode);
+ int i;
+ for (i = 0; i < 16; i++)
+ RTVEC_ELT (vs, i) = operands[2];
+
+ emit_insn (gen_vec_initv16qi (reg, par));
+ emit_insn (gen_xop_ashlv16qi3 (operands[0], operands[1], reg));
+ DONE;
+})
+
+(define_expand "lshlv16qi3"
+ [(match_operand:V16QI 0 "register_operand" "")
+ (match_operand:V16QI 1 "register_operand" "")
+ (match_operand:SI 2 "nonmemory_operand" "")]
+ "TARGET_XOP"
+{
+ rtvec vs = rtvec_alloc (16);
+ rtx par = gen_rtx_PARALLEL (V16QImode, vs);
+ rtx reg = gen_reg_rtx (V16QImode);
+ int i;
+ for (i = 0; i < 16; i++)
+ RTVEC_ELT (vs, i) = operands[2];
+
+ emit_insn (gen_vec_initv16qi (reg, par));
+ emit_insn (gen_xop_lshlv16qi3 (operands[0], operands[1], reg));
+ DONE;
+})
+
+(define_expand "ashrv16qi3"
+ [(match_operand:V16QI 0 "register_operand" "")
+ (match_operand:V16QI 1 "register_operand" "")
+ (match_operand:SI 2 "nonmemory_operand" "")]
+ "TARGET_XOP"
+{
+ rtvec vs = rtvec_alloc (16);
+ rtx par = gen_rtx_PARALLEL (V16QImode, vs);
+ rtx reg = gen_reg_rtx (V16QImode);
+ int i;
+ rtx ele = ((CONST_INT_P (operands[2]))
+ ? GEN_INT (- INTVAL (operands[2]))
+ : operands[2]);
+
+ for (i = 0; i < 16; i++)
+ RTVEC_ELT (vs, i) = ele;
+
+ emit_insn (gen_vec_initv16qi (reg, par));
+
+ if (!CONST_INT_P (operands[2]))
+ {
+ rtx neg = gen_reg_rtx (V16QImode);
+ emit_insn (gen_negv16qi2 (neg, reg));
+ emit_insn (gen_xop_ashlv16qi3 (operands[0], operands[1], neg));
+ }
+ else
+ emit_insn (gen_xop_ashlv16qi3 (operands[0], operands[1], reg));
+
+ DONE;
+})
+
+(define_expand "ashrv2di3"
+ [(match_operand:V2DI 0 "register_operand" "")
+ (match_operand:V2DI 1 "register_operand" "")
+ (match_operand:DI 2 "nonmemory_operand" "")]
+ "TARGET_XOP"
+{
+ rtvec vs = rtvec_alloc (2);
+ rtx par = gen_rtx_PARALLEL (V2DImode, vs);
+ rtx reg = gen_reg_rtx (V2DImode);
+ rtx ele;
+
+ if (CONST_INT_P (operands[2]))
+ ele = GEN_INT (- INTVAL (operands[2]));
+ else if (GET_MODE (operands[2]) != DImode)
+ {
+ rtx move = gen_reg_rtx (DImode);
+ ele = gen_reg_rtx (DImode);
+ convert_move (move, operands[2], false);
+ emit_insn (gen_negdi2 (ele, move));
+ }
+ else
+ {
+ ele = gen_reg_rtx (DImode);
+ emit_insn (gen_negdi2 (ele, operands[2]));
+ }
+
+ RTVEC_ELT (vs, 0) = ele;
+ RTVEC_ELT (vs, 1) = ele;
+ emit_insn (gen_vec_initv2di (reg, par));
+ emit_insn (gen_xop_ashlv2di3 (operands[0], operands[1], reg));
+ DONE;
+})
+
+;; XOP FRCZ support
+;; parallel insns
+(define_insn "xop_frcz<mode>2"
+ [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x")
+ (unspec:SSEMODEF2P
+ [(match_operand:SSEMODEF2P 1 "nonimmediate_operand" "xm")]
+ UNSPEC_FRCZ))]
+ "TARGET_XOP"
+ "vfrcz<ssemodesuffixf4>\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssecvt1")
+ (set_attr "mode" "<MODE>")])
+
+;; scalar insns
+(define_insn "xop_vmfrcz<mode>2"
+ [(set (match_operand:SSEMODEF2P 0 "register_operand" "=x")
+ (vec_merge:SSEMODEF2P
+ (unspec:SSEMODEF2P
+ [(match_operand:SSEMODEF2P 2 "nonimmediate_operand" "xm")]
+ UNSPEC_FRCZ)
+ (match_operand:SSEMODEF2P 1 "register_operand" "0")
+ (const_int 1)))]
+ "TARGET_XOP"
+ "vfrcz<ssemodesuffixf2s>\t{%2, %0|%0, %2}"
+ [(set_attr "type" "ssecvt1")
+ (set_attr "mode" "<MODE>")])
+
+(define_insn "xop_frcz<mode>2256"
+ [(set (match_operand:FMA4MODEF4 0 "register_operand" "=x")
+ (unspec:FMA4MODEF4
+ [(match_operand:FMA4MODEF4 1 "nonimmediate_operand" "xm")]
+ UNSPEC_FRCZ))]
+ "TARGET_XOP"
+ "vfrcz<fma4modesuffixf4>\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssecvt1")
+ (set_attr "mode" "<MODE>")])
+
+(define_insn "xop_maskcmp<mode>3"
+ [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
+ (match_operator:SSEMODE1248 1 "ix86_comparison_int_operator"
+ [(match_operand:SSEMODE1248 2 "register_operand" "x")
+ (match_operand:SSEMODE1248 3 "nonimmediate_operand" "xm")]))]
+ "TARGET_XOP"
+ "vpcom%Y1<ssevecsize>\t{%3, %2, %0|%0, %2, %3}"
+ [(set_attr "type" "sse4arg")
+ (set_attr "prefix_data16" "0")
+ (set_attr "prefix_rep" "0")
+ (set_attr "prefix_extra" "2")
+ (set_attr "length_immediate" "1")
+ (set_attr "mode" "TI")])
+
+(define_insn "xop_maskcmp_uns<mode>3"
+ [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
+ (match_operator:SSEMODE1248 1 "ix86_comparison_uns_operator"
+ [(match_operand:SSEMODE1248 2 "register_operand" "x")
+ (match_operand:SSEMODE1248 3 "nonimmediate_operand" "xm")]))]
+ "TARGET_XOP"
+ "vpcom%Y1u<ssevecsize>\t{%3, %2, %0|%0, %2, %3}"
+ [(set_attr "type" "ssecmp")
+ (set_attr "prefix_data16" "0")
+ (set_attr "prefix_rep" "0")
+ (set_attr "prefix_extra" "2")
+ (set_attr "length_immediate" "1")
+ (set_attr "mode" "TI")])
+
+;; Version of pcom*u* that is called from the intrinsics that allows pcomequ*
+;; and pcomneu* not to be converted to the signed ones in case somebody needs
+;; the exact instruction generated for the intrinsic.
+(define_insn "xop_maskcmp_uns2<mode>3"
+ [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
+ (unspec:SSEMODE1248
+ [(match_operator:SSEMODE1248 1 "ix86_comparison_uns_operator"
+ [(match_operand:SSEMODE1248 2 "register_operand" "x")
+ (match_operand:SSEMODE1248 3 "nonimmediate_operand" "xm")])]
+ UNSPEC_XOP_UNSIGNED_CMP))]
+ "TARGET_XOP"
+ "vpcom%Y1u<ssevecsize>\t{%3, %2, %0|%0, %2, %3}"
+ [(set_attr "type" "ssecmp")
+ (set_attr "prefix_data16" "0")
+ (set_attr "prefix_extra" "2")
+ (set_attr "length_immediate" "1")
+ (set_attr "mode" "TI")])
+
+;; Pcomtrue and pcomfalse support. These are useless instructions, but are
+;; being added here to be complete.
+(define_insn "xop_pcom_tf<mode>3"
+ [(set (match_operand:SSEMODE1248 0 "register_operand" "=x")
+ (unspec:SSEMODE1248
+ [(match_operand:SSEMODE1248 1 "register_operand" "x")
+ (match_operand:SSEMODE1248 2 "nonimmediate_operand" "xm")
+ (match_operand:SI 3 "const_int_operand" "n")]
+ UNSPEC_XOP_TRUEFALSE))]
+ "TARGET_XOP"
+{
+ return ((INTVAL (operands[3]) != 0)
+ ? "vpcomtrue<ssevecsize>\t{%2, %1, %0|%0, %1, %2}"
+ : "vpcomfalse<ssevecsize>\t{%2, %1, %0|%0, %1, %2}");
+}
+ [(set_attr "type" "ssecmp")
+ (set_attr "prefix_data16" "0")
+ (set_attr "prefix_extra" "2")
+ (set_attr "length_immediate" "1")
+ (set_attr "mode" "TI")])
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
(define_insn "*avx_aesenc"
[(set (match_operand:V2DI 0 "register_operand" "=x")
(unspec:V2DI [(match_operand:V2DI 1 "register_operand" "x")
#include <fma4intrin.h>
#endif
+#ifdef __XOP__
+#include <xopintrin.h>
+#endif
+
#if defined (__AES__) || defined (__PCLMUL__)
#include <wmmintrin.h>
#endif
--- /dev/null
+/* Copyright (C) 2007, 2008, 2009 Free Software Foundation, Inc.
+
+ This file is part of GCC.
+
+ GCC is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3, or (at your option)
+ any later version.
+
+ GCC is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ Under Section 7 of GPL version 3, you are granted additional
+ permissions described in the GCC Runtime Library Exception, version
+ 3.1, as published by the Free Software Foundation.
+
+ You should have received a copy of the GNU General Public License and
+ a copy of the GCC Runtime Library Exception along with this program;
+ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ <http://www.gnu.org/licenses/>. */
+
+#ifndef _X86INTRIN_H_INCLUDED
+# error "Never use <xopintrin.h> directly; include <x86intrin.h> instead."
+#endif
+
+#ifndef _XOPMMINTRIN_H_INCLUDED
+#define _XOPMMINTRIN_H_INCLUDED
+
+#ifndef __XOP__
+# error "XOP instruction set not enabled"
+#else
+
+#include <fma4intrin.h>
+
+/* Integer multiply/add intructions. */
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maccs_epi16(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmacssww ((__v8hi)__A,(__v8hi)__B, (__v8hi)__C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_macc_epi16(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmacsww ((__v8hi)__A, (__v8hi)__B, (__v8hi)__C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maccsd_epi16(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmacsswd ((__v8hi)__A, (__v8hi)__B, (__v4si)__C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maccd_epi16(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmacswd ((__v8hi)__A, (__v8hi)__B, (__v4si)__C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maccs_epi32(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmacssdd ((__v4si)__A, (__v4si)__B, (__v4si)__C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_macc_epi32(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmacsdd ((__v4si)__A, (__v4si)__B, (__v4si)__C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maccslo_epi32(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmacssdql ((__v4si)__A, (__v4si)__B, (__v2di)__C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_macclo_epi32(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmacsdql ((__v4si)__A, (__v4si)__B, (__v2di)__C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maccshi_epi32(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmacssdqh ((__v4si)__A, (__v4si)__B, (__v2di)__C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_macchi_epi32(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmacsdqh ((__v4si)__A, (__v4si)__B, (__v2di)__C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maddsd_epi16(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmadcsswd ((__v8hi)__A,(__v8hi)__B,(__v4si)__C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maddd_epi16(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpmadcswd ((__v8hi)__A,(__v8hi)__B,(__v4si)__C);
+}
+
+/* Packed Integer Horizontal Add and Subtract */
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddw_epi8(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphaddbw ((__v16qi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddd_epi8(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphaddbd ((__v16qi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddq_epi8(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphaddbq ((__v16qi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddd_epi16(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphaddwd ((__v8hi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddq_epi16(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphaddwq ((__v8hi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddq_epi32(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphadddq ((__v4si)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddw_epu8(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphaddubw ((__v16qi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddd_epu8(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphaddubd ((__v16qi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddq_epu8(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphaddubq ((__v16qi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddd_epu16(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphadduwd ((__v8hi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddq_epu16(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphadduwq ((__v8hi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_haddq_epu32(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphaddudq ((__v4si)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_hsubw_epi8(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphsubbw ((__v16qi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_hsubd_epi16(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphsubwd ((__v8hi)__A);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_hsubq_epi32(__m128i __A)
+{
+ return (__m128i) __builtin_ia32_vphsubdq ((__v4si)__A);
+}
+
+/* Vector conditional move and permute */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmov_si128(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpcmov (__A, __B, __C);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_perm_epi8(__m128i __A, __m128i __B, __m128i __C)
+{
+ return (__m128i) __builtin_ia32_vpperm ((__v16qi)__A, (__v16qi)__B, (__v16qi)__C);
+}
+
+/* Packed Integer Rotates and Shifts
+ Rotates - Non-Immediate form */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_rot_epi8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vprotb ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_rot_epi16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vprotw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_rot_epi32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vprotd ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_rot_epi64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vprotq ((__v2di)__A, (__v2di)__B);
+}
+
+/* Rotates - Immediate form */
+
+#ifdef __OPTIMIZE__
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_roti_epi8(__m128i __A, const int __B)
+{
+ return (__m128i) __builtin_ia32_vprotbi ((__v16qi)__A, __B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_roti_epi16(__m128i __A, const int __B)
+{
+ return (__m128i) __builtin_ia32_vprotwi ((__v8hi)__A, __B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_roti_epi32(__m128i __A, const int __B)
+{
+ return (__m128i) __builtin_ia32_vprotdi ((__v4si)__A, __B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_roti_epi64(__m128i __A, const int __B)
+{
+ return (__m128i) __builtin_ia32_vprotqi ((__v2di)__A, __B);
+}
+#else
+#define _mm_roti_epi8(A, N) \
+ ((__m128i) __builtin_ia32_vprotbi ((__v16qi)(__m128i)(A), (int)(N)))
+#define _mm_roti_epi16(A, N) \
+ ((__m128i) __builtin_ia32_vprotwi ((__v8hi)(__m128i)(A), (int)(N)))
+#define _mm_roti_epi32(A, N) \
+ ((__m128i) __builtin_ia32_vprotdi ((__v4si)(__m128i)(A), (int)(N)))
+#define _mm_roti_epi64(A, N) \
+ ((__m128i) __builtin_ia32_vprotqi ((__v2di)(__m128i)(A), (int)(N)))
+#endif
+
+/* Shifts */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_shl_epi8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpshlb ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_shl_epi16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpshlw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_shl_epi32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpshld ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_shl_epi64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpshlq ((__v2di)__A, (__v2di)__B);
+}
+
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sha_epi8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpshab ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sha_epi16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpshaw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sha_epi32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpshad ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_sha_epi64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpshaq ((__v2di)__A, (__v2di)__B);
+}
+
+/* Compare and Predicate Generation
+ pcom (integer, unsinged bytes) */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comlt_epu8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomltub ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comle_epu8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomleub ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comgt_epu8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgtub ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comge_epu8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgeub ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comeq_epu8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomequb ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comneq_epu8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomnequb ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comfalse_epu8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomfalseub ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comtrue_epu8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomtrueub ((__v16qi)__A, (__v16qi)__B);
+}
+
+/*pcom (integer, unsinged words) */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comlt_epu16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomltuw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comle_epu16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomleuw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comgt_epu16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgtuw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comge_epu16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgeuw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comeq_epu16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomequw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comneq_epu16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomnequw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comfalse_epu16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomfalseuw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comtrue_epu16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomtrueuw ((__v8hi)__A, (__v8hi)__B);
+}
+
+/*pcom (integer, unsinged double words) */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comlt_epu32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomltud ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comle_epu32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomleud ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comgt_epu32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgtud ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comge_epu32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgeud ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comeq_epu32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomequd ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comneq_epu32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomnequd ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comfalse_epu32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomfalseud ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comtrue_epu32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomtrueud ((__v4si)__A, (__v4si)__B);
+}
+
+/*pcom (integer, unsinged quad words) */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comlt_epu64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomltuq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comle_epu64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomleuq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comgt_epu64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgtuq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comge_epu64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgeuq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comeq_epu64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomequq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comneq_epu64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomnequq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comfalse_epu64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomfalseuq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comtrue_epu64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomtrueuq ((__v2di)__A, (__v2di)__B);
+}
+
+/*pcom (integer, signed bytes) */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comlt_epi8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomltb ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comle_epi8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomleb ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comgt_epi8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgtb ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comge_epi8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgeb ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comeq_epi8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomeqb ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comneq_epi8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomneqb ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comfalse_epi8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomfalseb ((__v16qi)__A, (__v16qi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comtrue_epi8(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomtrueb ((__v16qi)__A, (__v16qi)__B);
+}
+
+/*pcom (integer, signed words) */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comlt_epi16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomltw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comle_epi16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomlew ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comgt_epi16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgtw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comge_epi16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgew ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comeq_epi16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomeqw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comneq_epi16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomneqw ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comfalse_epi16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomfalsew ((__v8hi)__A, (__v8hi)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comtrue_epi16(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomtruew ((__v8hi)__A, (__v8hi)__B);
+}
+
+/*pcom (integer, signed double words) */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comlt_epi32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomltd ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comle_epi32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomled ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comgt_epi32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgtd ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comge_epi32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomged ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comeq_epi32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomeqd ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comneq_epi32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomneqd ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comfalse_epi32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomfalsed ((__v4si)__A, (__v4si)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comtrue_epi32(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomtrued ((__v4si)__A, (__v4si)__B);
+}
+
+/*pcom (integer, signed quad words) */
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comlt_epi64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomltq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comle_epi64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomleq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comgt_epi64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgtq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comge_epi64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomgeq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comeq_epi64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomeqq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comneq_epi64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomneqq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comfalse_epi64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomfalseq ((__v2di)__A, (__v2di)__B);
+}
+
+extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comtrue_epi64(__m128i __A, __m128i __B)
+{
+ return (__m128i) __builtin_ia32_vpcomtrueq ((__v2di)__A, (__v2di)__B);
+}
+
+/* FRCZ */
+
+extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_frcz_ps (__m128 __A)
+{
+ return (__m128) __builtin_ia32_vfrczps ((__v4sf)__A);
+}
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_frcz_pd (__m128d __A)
+{
+ return (__m128d) __builtin_ia32_vfrczpd ((__v2df)__A);
+}
+
+extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_frcz_ss (__m128 __A, __m128 __B)
+{
+ return (__m128) __builtin_ia32_vfrczss ((__v4sf)__A, (__v4sf)__B);
+}
+
+extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_frcz_sd (__m128d __A, __m128d __B)
+{
+ return (__m128d) __builtin_ia32_vfrczsd ((__v2df)__A, (__v2df)__B);
+}
+
+extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_frcz_ps (__m256 __A)
+{
+ return (__m256) __builtin_ia32_vfrczps256 ((__v8sf)__A);
+}
+
+extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_frcz_pd (__m256d __A)
+{
+ return (__m256d) __builtin_ia32_vfrczpd256 ((__v4df)__A);
+}
+
+#endif /* __XOP__ */
+
+#endif /* _XOPMMINTRIN_H_INCLUDED */
@cindex @code{target("fma4")} attribute
Enable/disable the generation of the FMA4 instructions.
+@item xop
+@itemx no-xop
+@cindex @code{target("xop")} attribute
+Enable/disable the generation of the XOP instructions.
+
@item ssse3
@itemx no-ssse3
@cindex @code{target("ssse3")} attribute
v2di __builtin_ia32_insertqi (v2di, v2di, const unsigned int, const unsigned int)
@end smallexample
+The following built-in functions are available when @option{-mxop} is used.
+@smallexample
+v2df __builtin_ia32_vfrczpd (v2df)
+v4sf __builtin_ia32_vfrczps (v4sf)
+v2df __builtin_ia32_vfrczsd (v2df, v2df)
+v4sf __builtin_ia32_vfrczss (v4sf, v4sf)
+v4df __builtin_ia32_vfrczpd256 (v4df)
+v8sf __builtin_ia32_vfrczps256 (v8sf)
+v2di __builtin_ia32_vpcmov (v2di, v2di, v2di)
+v2di __builtin_ia32_vpcmov_v2di (v2di, v2di, v2di)
+v4si __builtin_ia32_vpcmov_v4si (v4si, v4si, v4si)
+v8hi __builtin_ia32_vpcmov_v8hi (v8hi, v8hi, v8hi)
+v16qi __builtin_ia32_vpcmov_v16qi (v16qi, v16qi, v16qi)
+v2df __builtin_ia32_vpcmov_v2df (v2df, v2df, v2df)
+v4sf __builtin_ia32_vpcmov_v4sf (v4sf, v4sf, v4sf)
+v4di __builtin_ia32_vpcmov_v4di256 (v4di, v4di, v4di)
+v8si __builtin_ia32_vpcmov_v8si256 (v8si, v8si, v8si)
+v16hi __builtin_ia32_vpcmov_v16hi256 (v16hi, v16hi, v16hi)
+v32qi __builtin_ia32_vpcmov_v32qi256 (v32qi, v32qi, v32qi)
+v4df __builtin_ia32_vpcmov_v4df256 (v4df, v4df, v4df)
+v8sf __builtin_ia32_vpcmov_v8sf256 (v8sf, v8sf, v8sf)
+v16qi __builtin_ia32_vpcomeqb (v16qi, v16qi)
+v8hi __builtin_ia32_vpcomeqw (v8hi, v8hi)
+v4si __builtin_ia32_vpcomeqd (v4si, v4si)
+v2di __builtin_ia32_vpcomeqq (v2di, v2di)
+v16qi __builtin_ia32_vpcomequb (v16qi, v16qi)
+v4si __builtin_ia32_vpcomequd (v4si, v4si)
+v2di __builtin_ia32_vpcomequq (v2di, v2di)
+v8hi __builtin_ia32_vpcomequw (v8hi, v8hi)
+v8hi __builtin_ia32_vpcomeqw (v8hi, v8hi)
+v16qi __builtin_ia32_vpcomfalseb (v16qi, v16qi)
+v4si __builtin_ia32_vpcomfalsed (v4si, v4si)
+v2di __builtin_ia32_vpcomfalseq (v2di, v2di)
+v16qi __builtin_ia32_vpcomfalseub (v16qi, v16qi)
+v4si __builtin_ia32_vpcomfalseud (v4si, v4si)
+v2di __builtin_ia32_vpcomfalseuq (v2di, v2di)
+v8hi __builtin_ia32_vpcomfalseuw (v8hi, v8hi)
+v8hi __builtin_ia32_vpcomfalsew (v8hi, v8hi)
+v16qi __builtin_ia32_vpcomgeb (v16qi, v16qi)
+v4si __builtin_ia32_vpcomged (v4si, v4si)
+v2di __builtin_ia32_vpcomgeq (v2di, v2di)
+v16qi __builtin_ia32_vpcomgeub (v16qi, v16qi)
+v4si __builtin_ia32_vpcomgeud (v4si, v4si)
+v2di __builtin_ia32_vpcomgeuq (v2di, v2di)
+v8hi __builtin_ia32_vpcomgeuw (v8hi, v8hi)
+v8hi __builtin_ia32_vpcomgew (v8hi, v8hi)
+v16qi __builtin_ia32_vpcomgtb (v16qi, v16qi)
+v4si __builtin_ia32_vpcomgtd (v4si, v4si)
+v2di __builtin_ia32_vpcomgtq (v2di, v2di)
+v16qi __builtin_ia32_vpcomgtub (v16qi, v16qi)
+v4si __builtin_ia32_vpcomgtud (v4si, v4si)
+v2di __builtin_ia32_vpcomgtuq (v2di, v2di)
+v8hi __builtin_ia32_vpcomgtuw (v8hi, v8hi)
+v8hi __builtin_ia32_vpcomgtw (v8hi, v8hi)
+v16qi __builtin_ia32_vpcomleb (v16qi, v16qi)
+v4si __builtin_ia32_vpcomled (v4si, v4si)
+v2di __builtin_ia32_vpcomleq (v2di, v2di)
+v16qi __builtin_ia32_vpcomleub (v16qi, v16qi)
+v4si __builtin_ia32_vpcomleud (v4si, v4si)
+v2di __builtin_ia32_vpcomleuq (v2di, v2di)
+v8hi __builtin_ia32_vpcomleuw (v8hi, v8hi)
+v8hi __builtin_ia32_vpcomlew (v8hi, v8hi)
+v16qi __builtin_ia32_vpcomltb (v16qi, v16qi)
+v4si __builtin_ia32_vpcomltd (v4si, v4si)
+v2di __builtin_ia32_vpcomltq (v2di, v2di)
+v16qi __builtin_ia32_vpcomltub (v16qi, v16qi)
+v4si __builtin_ia32_vpcomltud (v4si, v4si)
+v2di __builtin_ia32_vpcomltuq (v2di, v2di)
+v8hi __builtin_ia32_vpcomltuw (v8hi, v8hi)
+v8hi __builtin_ia32_vpcomltw (v8hi, v8hi)
+v16qi __builtin_ia32_vpcomneb (v16qi, v16qi)
+v4si __builtin_ia32_vpcomned (v4si, v4si)
+v2di __builtin_ia32_vpcomneq (v2di, v2di)
+v16qi __builtin_ia32_vpcomneub (v16qi, v16qi)
+v4si __builtin_ia32_vpcomneud (v4si, v4si)
+v2di __builtin_ia32_vpcomneuq (v2di, v2di)
+v8hi __builtin_ia32_vpcomneuw (v8hi, v8hi)
+v8hi __builtin_ia32_vpcomnew (v8hi, v8hi)
+v16qi __builtin_ia32_vpcomtrueb (v16qi, v16qi)
+v4si __builtin_ia32_vpcomtrued (v4si, v4si)
+v2di __builtin_ia32_vpcomtrueq (v2di, v2di)
+v16qi __builtin_ia32_vpcomtrueub (v16qi, v16qi)
+v4si __builtin_ia32_vpcomtrueud (v4si, v4si)
+v2di __builtin_ia32_vpcomtrueuq (v2di, v2di)
+v8hi __builtin_ia32_vpcomtrueuw (v8hi, v8hi)
+v8hi __builtin_ia32_vpcomtruew (v8hi, v8hi)
+v4si __builtin_ia32_vphaddbd (v16qi)
+v2di __builtin_ia32_vphaddbq (v16qi)
+v8hi __builtin_ia32_vphaddbw (v16qi)
+v2di __builtin_ia32_vphadddq (v4si)
+v4si __builtin_ia32_vphaddubd (v16qi)
+v2di __builtin_ia32_vphaddubq (v16qi)
+v8hi __builtin_ia32_vphaddubw (v16qi)
+v2di __builtin_ia32_vphaddudq (v4si)
+v4si __builtin_ia32_vphadduwd (v8hi)
+v2di __builtin_ia32_vphadduwq (v8hi)
+v4si __builtin_ia32_vphaddwd (v8hi)
+v2di __builtin_ia32_vphaddwq (v8hi)
+v8hi __builtin_ia32_vphsubbw (v16qi)
+v2di __builtin_ia32_vphsubdq (v4si)
+v4si __builtin_ia32_vphsubwd (v8hi)
+v4si __builtin_ia32_vpmacsdd (v4si, v4si, v4si)
+v2di __builtin_ia32_vpmacsdqh (v4si, v4si, v2di)
+v2di __builtin_ia32_vpmacsdql (v4si, v4si, v2di)
+v4si __builtin_ia32_vpmacssdd (v4si, v4si, v4si)
+v2di __builtin_ia32_vpmacssdqh (v4si, v4si, v2di)
+v2di __builtin_ia32_vpmacssdql (v4si, v4si, v2di)
+v4si __builtin_ia32_vpmacsswd (v8hi, v8hi, v4si)
+v8hi __builtin_ia32_vpmacssww (v8hi, v8hi, v8hi)
+v4si __builtin_ia32_vpmacswd (v8hi, v8hi, v4si)
+v8hi __builtin_ia32_vpmacsww (v8hi, v8hi, v8hi)
+v4si __builtin_ia32_vpmadcsswd (v8hi, v8hi, v4si)
+v4si __builtin_ia32_vpmadcswd (v8hi, v8hi, v4si)
+v16qi __builtin_ia32_vpperm (v16qi, v16qi, v16qi)
+v16qi __builtin_ia32_vprotb (v16qi, v16qi)
+v4si __builtin_ia32_vprotd (v4si, v4si)
+v2di __builtin_ia32_vprotq (v2di, v2di)
+v8hi __builtin_ia32_vprotw (v8hi, v8hi)
+v16qi __builtin_ia32_vpshab (v16qi, v16qi)
+v4si __builtin_ia32_vpshad (v4si, v4si)
+v2di __builtin_ia32_vpshaq (v2di, v2di)
+v8hi __builtin_ia32_vpshaw (v8hi, v8hi)
+v16qi __builtin_ia32_vpshlb (v16qi, v16qi)
+v4si __builtin_ia32_vpshld (v4si, v4si)
+v2di __builtin_ia32_vpshlq (v2di, v2di)
+v8hi __builtin_ia32_vpshlw (v8hi, v8hi)
+@end smallexample
+
The following built-in functions are available when @option{-mfma4} is used.
All of them generate the machine instruction that is part of the name
with MMX registers.
-mcld -mcx16 -msahf -mmovbe -mcrc32 -mrecip @gol
-mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4 -mavx @gol
-maes -mpclmul @gol
--msse4a -m3dnow -mpopcnt -mabm -mfma4 @gol
+-msse4a -m3dnow -mpopcnt -mabm -mfma4 -mxop @gol
-mthreads -mno-align-stringops -minline-all-stringops @gol
-minline-stringops-dynamically -mstringop-strategy=@var{alg} @gol
-mpush-args -maccumulate-outgoing-args -m128bit-long-double @gol
@itemx -mno-sse4a
@itemx -mfma4
@itemx -mno-fma4
+@itemx -mxop
+@itemx -mno-xop
@itemx -m3dnow
@itemx -mno-3dnow
@itemx -mpopcnt
@opindex m3dnow
@opindex mno-3dnow
These switches enable or disable the use of instructions in the MMX,
-SSE, SSE2, SSE3, SSSE3, SSE4.1, AVX, AES, PCLMUL, SSE4A, FMA4, ABM or
-3DNow!@: extended instruction sets.
+SSE, SSE2, SSE3, SSSE3, SSE4.1, AVX, AES, PCLMUL, SSE4A, FMA4, XOP,
+ABM or 3DNow!@: extended instruction sets.
These extensions are also available as built-in functions: see
@ref{X86 Built-in Functions}, for details of the functions enabled and
disabled by these switches.
+2009-11-04 Harsha Jagasia <harsha.jagasia@amd.com>
+ Dwarakanath Rajagopal <dwarak.rajagopal@amd.com>
+
+ * gcc.target/i386/xop-check.h: New file.
+ * gcc.target/i386/xop-hadduX.c: Ditto.
+ * gcc.target/i386/xop-haddX.c: Ditto.
+ * gcc.target/i386/xop-hsubX.c: Ditto.
+ * gcc.target/i386/xop-imul32widen-vector.c: Ditto.
+ * gcc.target/i386/xop-imul32widen-vector.c: Ditto.
+ * gcc.target/i386/xop-pcmov2.c: Ditto.
+ * gcc.target/i386/xop-pcmov.c: Ditto.
+ * gcc.target/i386/xop-rotate1-vector.c: Ditto.
+ * gcc.target/i386/xop-rotate2-vector.c: Ditto.
+ * gcc.target/i386/xop-rotate3-vector.c: Ditto.
+ * gcc.target/i386/xop-shift1-vector.c: Ditto.
+ * gcc.target/i386/xop-shift2-vector.c: Ditto.
+ * gcc.target/i386/xop-shift3-vector.c: Ditto.
+ * gcc.target/i386/i386.exp: Add check_effective_target_xop.
+ * gcc.target/i386/sse-12.c: Update with new compile options to
+ activate and check xopintrin.h intrinsic file.
+ * gcc.target/i386/sse-13.c: Ditto.
+ * gcc.target/i386/sse-14.c: Ditto.
+ * gcc.target/i386/sse-22.c: Ditto.
+ * gcc.target/i386/sse-23.c: Ditto.
+ * g++.dg/other/i386-2.C: Ditto.
+ * g++.dg/other/i386-3.C: Ditto.
+ * g++.dg/other/i386-5.C: Ditto.
+ * g++.dg/other/i386-6.C: Ditto.
+
2009-11-04 Wei Guozhi <carrot@google.com>
PR target/40835
-/* Test that {,x,e,p,t,s,w,a,i}mmintrin.h, fma4intrin.h, mm3dnow.h and
+/* Test that {,x,e,p,t,s,w,a,i}mmintrin.h, fma4intrin.h, xopintrin.h, mm3dnow.h and
mm_malloc.h are usable with -O -pedantic-errors. */
/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -pedantic-errors -march=k8 -m3dnow -mavx -msse4a -mfma4 -maes -mpclmul" } */
+/* { dg-options "-O -pedantic-errors -march=k8 -m3dnow -mavx -msse4a -mfma4 -mxop -maes -mpclmul" } */
#include <x86intrin.h>
int dummy;
+
-/* Test that {,x,e,p,t,s,w,a,i}mmintrin.h, fma4intrin.h, mm3dnow.h and
+/* Test that {,x,e,p,t,s,w,a,i}mmintrin.h, fma4intrin.h, mm3dnow.h, xopintrin.h and
mm_malloc.h are usable with -O -fkeep-inline-functions. */
/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -fkeep-inline-functions -march=k8 -m3dnow -mavx -msse4a -mfma4 -maes -mpclmul" } */
+/* { dg-options "-O -fkeep-inline-functions -march=k8 -m3dnow -mavx -msse4a -mfma4 -mxop -maes -mpclmul" } */
#include <x86intrin.h>
-/* Test that {,x,e,p,t,s,w,a,i}mmintrin.h, fma4intrin.h, mm3dnow.h and
+/* Test that {,x,e,p,t,s,w,a,i}mmintrin.h, fma4intrin.h, xopintrin.h, mm3dnow.h and
mm_malloc.h are usable with -O -fkeep-inline-functions. */
/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -fkeep-inline-functions -march=k8 -m3dnow -mavx -msse4a -mfma4 -maes -mpclmul" } */
+/* { dg-options "-O -fkeep-inline-functions -march=k8 -m3dnow -mavx -msse4a -mfma4 -mxop -maes -mpclmul" } */
#include <x86intrin.h>
-/* Test that {,x,e,p,t,s,w,a,i}mmintrin.h, fma4intrin.h, mm3dnow.h and
+/* Test that {,x,e,p,t,s,w,a,i}mmintrin.h, fma4intrin.h, xopintrin.h, mm3dnow.h and
mm_malloc.h are usable with -O -pedantic-errors. */
/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -pedantic-errors -march=k8 -m3dnow -mavx -msse4a -mfma4 -maes -mpclmul" } */
+/* { dg-options "-O -pedantic-errors -march=k8 -m3dnow -mavx -msse4a -mfma4 -mxop -maes -mpclmul" } */
#include <x86intrin.h>
} "-O2 -mfma4" ]
}
+# Return 1 if xop instructions can be compiled.
+proc check_effective_target_xop { } {
+ return [check_no_compiler_messages xop object {
+ typedef long long __m128i __attribute__ ((__vector_size__ (16), __may_alias__));
+ typedef short __v8hi __attribute__ ((__vector_size__ (16)));
+ __m128i _mm_maccs_epi16(__m128i __A, __m128i __B, __m128i __C)
+ {
+ return (__m128i) __builtin_ia32_pmacssww ((__v8hi)__A,
+ (__v8hi)__B,
+ (__v8hi)__C);
+ }
+ } "-O2 -mxop" ]
+}
+
# If a testcase doesn't have special options, use these.
global DEFAULT_CFLAGS
if ![info exists DEFAULT_CFLAGS] then {
-/* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h and mm_malloc.h are
+/* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, xopintrin.h, mm3dnow.h and mm_malloc.h are
usable with -O -std=c89 -pedantic-errors. */
/* { dg-do compile } */
-/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -m3dnow -mavx -mfma4 -maes -mpclmul" } */
+/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -m3dnow -mavx -mfma4 -mxop -maes -mpclmul" } */
#include <x86intrin.h>
/* { dg-do compile } */
-/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8 -m3dnow -mavx -maes -mpclmul" } */
+/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8 -m3dnow -mavx -mxop -maes -mpclmul" } */
#include <mm_malloc.h>
/* Test that the intrinsics compile with optimization. All of them are
- defined as inline functions in {,x,e,p,t,s,w,a,b,i}mmintrin.h and mm3dnow.h
+ defined as inline functions in {,x,e,p,t,s,w,a,b,i}mmintrin.h, xopintrin.h and mm3dnow.h
that reference the proper builtin functions. Defining away "extern" and
"__inline" results in all of them being compiled as proper functions. */
#define __builtin_ia32_vec_ext_v4hi(A, N) __builtin_ia32_vec_ext_v4hi(A, 0)
#define __builtin_ia32_shufps(A, B, N) __builtin_ia32_shufps(A, B, 0)
+/* xopintrin.h */
+#define __builtin_ia32_vprotbi(A, N) __builtin_ia32_vprotbi (A,1)
+#define __builtin_ia32_vprotwi(A, N) __builtin_ia32_vprotwi (A,1)
+#define __builtin_ia32_vprotdi(A, N) __builtin_ia32_vprotdi (A,1)
+#define __builtin_ia32_vprotqi(A, N) __builtin_ia32_vprotqi (A,1)
+
#include <x86intrin.h>
/* { dg-do compile } */
-/* { dg-options "-O0 -Werror-implicit-function-declaration -march=k8 -m3dnow -mavx -msse4a -maes -mpclmul" } */
+/* { dg-options "-O0 -Werror-implicit-function-declaration -march=k8 -m3dnow -mavx -mxop -msse4a -maes -mpclmul" } */
#include <mm_malloc.h>
/* Test that the intrinsics compile without optimization. All of them are
- defined as inline functions in {,x,e,p,t,s,w,a}mmintrin.h and mm3dnow.h
+ defined as inline functions in {,x,e,p,t,s,w,a}mmintrin.h, xopintrin.h and mm3dnow.h
that reference the proper builtin functions. Defining away "extern" and
"__inline" results in all of them being compiled as proper functions. */
test_1 (_mm_shuffle_pi16, __m64, __m64, 1)
test_1 (_m_pshufw, __m64, __m64, 1)
test_1 (_mm_prefetch, void, void *, _MM_HINT_NTA)
+
+/* xopintrin.h */
+test_1 ( _mm_roti_epi8, __m128i, __m128i, 1)
+test_1 ( _mm_roti_epi16, __m128i, __m128i, 1)
+test_1 ( _mm_roti_epi32, __m128i, __m128i, 1)
+test_1 ( _mm_roti_epi64, __m128i, __m128i, 1)
+
#include <mm_malloc.h>
/* Test that the intrinsics compile without optimization. All of them are
- defined as inline functions in {,x,e,p,t,s,w,a}mmintrin.h and mm3dnow.h
+ defined as inline functions in {,x,e,p,t,s,w,a}mmintrin.h, xopintrin.h and mm3dnow.h
that reference the proper builtin functions. Defining away "extern" and
"__inline" results in all of them being compiled as proper functions. */
#ifndef DIFFERENT_PRAGMAS
-#pragma GCC target ("mmx,3dnow,sse,sse2,sse3,ssse3,sse4.1,sse4.2,sse4a,aes,pclmul")
+#pragma GCC target ("mmx,3dnow,sse,sse2,sse3,ssse3,sse4.1,sse4.2,sse4a,aes,pclmul,xop")
#endif
/* Following intrinsics require immediate arguments. They
test_1 (_mm_round_ps, __m128, __m128, 1)
test_2 (_mm_round_sd, __m128d, __m128d, __m128d, 1)
test_2 (_mm_round_ss, __m128, __m128, __m128, 1)
+
+/* xopintrin.h (XOP). */
+#ifdef DIFFERENT_PRAGMAS
+#pragma GCC target ("xop")
+#endif
+#include <x86intrin.h>
+test_1 ( _mm_roti_epi8, __m128i, __m128i, 1)
+test_1 ( _mm_roti_epi16, __m128i, __m128i, 1)
+test_1 ( _mm_roti_epi32, __m128i, __m128i, 1)
+test_1 ( _mm_roti_epi64, __m128i, __m128i, 1)
#include <mm_malloc.h>
/* Test that the intrinsics compile with optimization. All of them are
- defined as inline functions in {,x,e,p,t,s,w,a,b}mmintrin.h and mm3dnow.h
+ defined as inline functions in {,x,e,p,t,s,w,a}mmintrin.h, xopintrin.h and mm3dnow.h
that reference the proper builtin functions. Defining away "extern" and
"__inline" results in all of them being compiled as proper functions. */
#define __builtin_ia32_vec_ext_v4hi(A, N) __builtin_ia32_vec_ext_v4hi(A, 0)
#define __builtin_ia32_shufps(A, B, N) __builtin_ia32_shufps(A, B, 0)
-/* bmmintrin.h */
-#define __builtin_ia32_protbi(A, B) __builtin_ia32_protbi(A,1)
-#define __builtin_ia32_protwi(A, B) __builtin_ia32_protwi(A,1)
-#define __builtin_ia32_protdi(A, B) __builtin_ia32_protdi(A,1)
-#define __builtin_ia32_protqi(A, B) __builtin_ia32_protqi(A,1)
+/* xopintrin.h */
+#define __builtin_ia32_vprotbi(A, B) __builtin_ia32_vprotbi(A,1)
+#define __builtin_ia32_vprotwi(A, B) __builtin_ia32_vprotwi(A,1)
+#define __builtin_ia32_vprotdi(A, B) __builtin_ia32_vprotdi(A,1)
+#define __builtin_ia32_vprotqi(A, B) __builtin_ia32_vprotqi(A,1)
-
-#pragma GCC target ("3dnow,sse4,sse4a,aes,pclmul")
+#pragma GCC target ("3dnow,sse4,sse4a,aes,pclmul,xop")
#include <wmmintrin.h>
#include <smmintrin.h>
#include <mm3dnow.h>
--- /dev/null
+#include <stdlib.h>
+
+#include "cpuid.h"
+
+static void xop_test (void);
+
+int
+main ()
+{
+ unsigned int eax, ebx, ecx, edx;
+
+ if (!__get_cpuid (0x80000001, &eax, &ebx, &ecx, &edx))
+ return 0;
+
+ /* Run XOP test only if host has XOP support. */
+ if (ecx & bit_XOP)
+ xop_test ();
+
+ exit (0);
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target xop } */
+/* { dg-options "-O2 -mxop" } */
+
+#include "xop-check.h"
+
+#include <x86intrin.h>
+#include <string.h>
+
+#define NUM 10
+
+union
+{
+ __m128i x[NUM];
+ signed char ssi[NUM * 16];
+ short si[NUM * 8];
+ int li[NUM * 4];
+ long long lli[NUM * 2];
+} dst, res, src1;
+
+static void
+init_sbyte ()
+{
+ int i;
+ for (i=0; i < NUM * 16; i++)
+ src1.ssi[i] = i;
+}
+
+static void
+init_sword ()
+{
+ int i;
+ for (i=0; i < NUM * 8; i++)
+ src1.si[i] = i;
+}
+
+
+static void
+init_sdword ()
+{
+ int i;
+ for (i=0; i < NUM * 4; i++)
+ src1.li[i] = i;
+}
+
+static int
+check_sbyte2word ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < NUM * 16; i = i + 16)
+ {
+ for (j = 0; j < 8; j++)
+ {
+ t = i + (2 * j);
+ s = (i / 2) + j;
+ res.si[s] = src1.ssi[t] + src1.ssi[t + 1] ;
+ if (res.si[s] != dst.si[s])
+ check_fails++;
+ }
+ }
+}
+
+static int
+check_sbyte2dword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < NUM * 16; i = i + 16)
+ {
+ for (j = 0; j < 4; j++)
+ {
+ t = i + (4 * j);
+ s = (i / 4) + j;
+ res.li[s] = (src1.ssi[t] + src1.ssi[t + 1]) + (src1.ssi[t + 2]
+ + src1.ssi[t + 3]);
+ if (res.li[s] != dst.li[s])
+ check_fails++;
+ }
+ }
+ return check_fails++;
+}
+
+static int
+check_sbyte2qword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < NUM * 16; i = i + 16)
+ {
+ for (j = 0; j < 2; j++)
+ {
+ t = i + (8 * j);
+ s = (i / 8) + j;
+ res.lli[s] = ((src1.ssi[t] + src1.ssi[t + 1]) + (src1.ssi[t + 2]
+ + src1.ssi[t + 3])) + ((src1.ssi[t + 4] + src1.ssi[t +5])
+ + (src1.ssi[t + 6] + src1.ssi[t + 7]));
+ if (res.lli[s] != dst.lli[s])
+ check_fails++;
+ }
+ }
+ return check_fails++;
+}
+
+static int
+check_sword2dword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < (NUM * 8); i = i + 8)
+ {
+ for (j = 0; j < 4; j++)
+ {
+ t = i + (2 * j);
+ s = (i / 2) + j;
+ res.li[s] = src1.si[t] + src1.si[t + 1] ;
+ if (res.li[s] != dst.li[s])
+ check_fails++;
+ }
+ }
+}
+
+static int
+check_sword2qword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < NUM * 8; i = i + 8)
+ {
+ for (j = 0; j < 2; j++)
+ {
+ t = i + (4 * j);
+ s = (i / 4) + j;
+ res.lli[s] = (src1.si[t] + src1.si[t + 1]) + (src1.si[t + 2]
+ + src1.si[t + 3]);
+ if (res.lli[s] != dst.lli[s])
+ check_fails++;
+ }
+ }
+ return check_fails++;
+}
+
+static int
+check_dword2qword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < (NUM * 4); i = i + 4)
+ {
+ for (j = 0; j < 2; j++)
+ {
+ t = i + (2 * j);
+ s = (i / 2) + j;
+ res.lli[s] = src1.li[t] + src1.li[t + 1] ;
+ if (res.lli[s] != dst.lli[s])
+ check_fails++;
+ }
+ }
+}
+
+static void
+xop_test (void)
+{
+ int i;
+
+ init_sbyte ();
+
+ for (i = 0; i < NUM; i++)
+ dst.x[i] = _mm_haddw_epi8 (src1.x[i]);
+
+ if (check_sbyte2word())
+ abort ();
+
+
+ for (i = 0; i < (NUM ); i++)
+ dst.x[i] = _mm_haddd_epi8 (src1.x[i]);
+
+ if (check_sbyte2dword())
+ abort ();
+
+
+ for (i = 0; i < NUM; i++)
+ dst.x[i] = _mm_haddq_epi8 (src1.x[i]);
+
+ if (check_sbyte2qword())
+ abort ();
+
+
+ init_sword ();
+
+ for (i = 0; i < (NUM ); i++)
+ dst.x[i] = _mm_haddd_epi16 (src1.x[i]);
+
+ if (check_sword2dword())
+ abort ();
+
+ for (i = 0; i < NUM; i++)
+ dst.x[i] = _mm_haddq_epi16 (src1.x[i]);
+
+ if (check_sword2qword())
+ abort ();
+
+
+ init_sdword ();
+
+ for (i = 0; i < NUM; i++)
+ dst.x[i] = _mm_haddq_epi32 (src1.x[i]);
+
+ if (check_dword2qword())
+ abort ();
+
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target xop } */
+/* { dg-options "-O2 -mxop" } */
+
+#include "xop-check.h"
+
+#include <x86intrin.h>
+#include <string.h>
+
+#define NUM 10
+
+union
+{
+ __m128i x[NUM];
+ unsigned char ssi[NUM * 16];
+ unsigned short si[NUM * 8];
+ unsigned int li[NUM * 4];
+ unsigned long long lli[NUM * 2];
+} dst, res, src1;
+
+static void
+init_byte ()
+{
+ int i;
+ for (i=0; i < NUM * 16; i++)
+ src1.ssi[i] = i;
+}
+
+static void
+init_word ()
+{
+ int i;
+ for (i=0; i < NUM * 8; i++)
+ src1.si[i] = i;
+}
+
+
+static void
+init_dword ()
+{
+ int i;
+ for (i=0; i < NUM * 4; i++)
+ src1.li[i] = i;
+}
+
+static int
+check_byte2word ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < NUM * 16; i = i + 16)
+ {
+ for (j = 0; j < 8; j++)
+ {
+ t = i + (2 * j);
+ s = (i / 2) + j;
+ res.si[s] = src1.ssi[t] + src1.ssi[t + 1] ;
+ if (res.si[s] != dst.si[s])
+ check_fails++;
+ }
+ }
+}
+
+static int
+check_byte2dword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < NUM * 16; i = i + 16)
+ {
+ for (j = 0; j < 4; j++)
+ {
+ t = i + (4 * j);
+ s = (i / 4) + j;
+ res.li[s] = (src1.ssi[t] + src1.ssi[t + 1]) + (src1.ssi[t + 2]
+ + src1.ssi[t + 3]);
+ if (res.li[s] != dst.li[s])
+ check_fails++;
+ }
+ }
+ return check_fails++;
+}
+
+static int
+check_byte2qword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < NUM * 16; i = i + 16)
+ {
+ for (j = 0; j < 2; j++)
+ {
+ t = i + (8 * j);
+ s = (i / 8) + j;
+ res.lli[s] = ((src1.ssi[t] + src1.ssi[t + 1]) + (src1.ssi[t + 2]
+ + src1.ssi[t + 3])) + ((src1.ssi[t + 4] + src1.ssi[t +5])
+ + (src1.ssi[t + 6] + src1.ssi[t + 7]));
+ if (res.lli[s] != dst.lli[s])
+ check_fails++;
+ }
+ }
+ return check_fails++;
+}
+
+static int
+check_word2dword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < (NUM * 8); i = i + 8)
+ {
+ for (j = 0; j < 4; j++)
+ {
+ t = i + (2 * j);
+ s = (i / 2) + j;
+ res.li[s] = src1.si[t] + src1.si[t + 1] ;
+ if (res.li[s] != dst.li[s])
+ check_fails++;
+ }
+ }
+}
+
+static int
+check_word2qword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < NUM * 8; i = i + 8)
+ {
+ for (j = 0; j < 2; j++)
+ {
+ t = i + (4 * j);
+ s = (i / 4) + j;
+ res.lli[s] = (src1.si[t] + src1.si[t + 1]) + (src1.si[t + 2]
+ + src1.si[t + 3]);
+ if (res.lli[s] != dst.lli[s])
+ check_fails++;
+ }
+ }
+ return check_fails++;
+}
+
+static int
+check_dword2qword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < (NUM * 4); i = i + 4)
+ {
+ for (j = 0; j < 2; j++)
+ {
+ t = i + (2 * j);
+ s = (i / 2) + j;
+ res.lli[s] = src1.li[t] + src1.li[t + 1] ;
+ if (res.lli[s] != dst.lli[s])
+ check_fails++;
+ }
+ }
+}
+
+static void
+xop_test (void)
+{
+ int i;
+
+ /* Check haddubw */
+ init_byte ();
+
+ for (i = 0; i < NUM; i++)
+ dst.x[i] = _mm_haddw_epu8 (src1.x[i]);
+
+ if (check_byte2word())
+ abort ();
+
+ /* Check haddubd */
+ for (i = 0; i < (NUM ); i++)
+ dst.x[i] = _mm_haddd_epu8 (src1.x[i]);
+
+ if (check_byte2dword())
+ abort ();
+
+ /* Check haddubq */
+ for (i = 0; i < NUM; i++)
+ dst.x[i] = _mm_haddq_epu8 (src1.x[i]);
+
+ if (check_byte2qword())
+ abort ();
+
+ /* Check hadduwd */
+ init_word ();
+
+ for (i = 0; i < (NUM ); i++)
+ dst.x[i] = _mm_haddd_epu16 (src1.x[i]);
+
+ if (check_word2dword())
+ abort ();
+
+ /* Check haddbuwq */
+
+ for (i = 0; i < NUM; i++)
+ dst.x[i] = _mm_haddq_epu16 (src1.x[i]);
+
+ if (check_word2qword())
+ abort ();
+
+ /* Check hadudq */
+ init_dword ();
+ for (i = 0; i < NUM; i++)
+ dst.x[i] = _mm_haddq_epu32 (src1.x[i]);
+
+ if (check_dword2qword())
+ abort ();
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target xop } */
+/* { dg-options "-O2 -mxop" } */
+
+#include "xop-check.h"
+
+#include <x86intrin.h>
+#include <string.h>
+
+#define NUM 10
+
+union
+{
+ __m128i x[NUM];
+ signed char ssi[NUM * 16];
+ short si[NUM * 8];
+ int li[NUM * 4];
+ long long lli[NUM * 2];
+} dst, res, src1;
+
+static void
+init_sbyte ()
+{
+ int i;
+ for (i=0; i < NUM * 16; i++)
+ src1.ssi[i] = i;
+}
+
+static void
+init_sword ()
+{
+ int i;
+ for (i=0; i < NUM * 8; i++)
+ src1.si[i] = i;
+}
+
+
+static void
+init_sdword ()
+{
+ int i;
+ for (i=0; i < NUM * 4; i++)
+ src1.li[i] = i;
+}
+
+static int
+check_sbyte2word ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < NUM * 16; i = i + 16)
+ {
+ for (j = 0; j < 8; j++)
+ {
+ t = i + (2 * j);
+ s = (i / 2) + j;
+ res.si[s] = src1.ssi[t] - src1.ssi[t + 1] ;
+ if (res.si[s] != dst.si[s])
+ check_fails++;
+ }
+ }
+}
+
+static int
+check_sword2dword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < (NUM * 8); i = i + 8)
+ {
+ for (j = 0; j < 4; j++)
+ {
+ t = i + (2 * j);
+ s = (i / 2) + j;
+ res.li[s] = src1.si[t] - src1.si[t + 1] ;
+ if (res.li[s] != dst.li[s])
+ check_fails++;
+ }
+ }
+}
+
+static int
+check_dword2qword ()
+{
+ int i, j, s, t, check_fails = 0;
+ for (i = 0; i < (NUM * 4); i = i + 4)
+ {
+ for (j = 0; j < 2; j++)
+ {
+ t = i + (2 * j);
+ s = (i / 2) + j;
+ res.lli[s] = src1.li[t] - src1.li[t + 1] ;
+ if (res.lli[s] != dst.lli[s])
+ check_fails++;
+ }
+ }
+}
+
+static void
+xop_test (void)
+{
+ int i;
+
+ /* Check hsubbw */
+ init_sbyte ();
+
+ for (i = 0; i < NUM; i++)
+ dst.x[i] = _mm_hsubw_epi8 (src1.x[i]);
+
+ if (check_sbyte2word())
+ abort ();
+
+
+ /* Check hsubwd */
+ init_sword ();
+
+ for (i = 0; i < (NUM ); i++)
+ dst.x[i] = _mm_hsubd_epi16 (src1.x[i]);
+
+ if (check_sword2dword())
+ abort ();
+
+ /* Check hsubdq */
+ init_sdword ();
+ for (i = 0; i < NUM; i++)
+ dst.x[i] = _mm_hsubq_epi32 (src1.x[i]);
+
+ if (check_dword2qword())
+ abort ();
+}
--- /dev/null
+/* Test that the compiler properly optimizes floating point multiply and add
+ instructions vector into pmacsdd/etc. on XOP systems. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mxop -ftree-vectorize" } */
+
+extern void exit (int);
+
+typedef long __m128i __attribute__ ((__vector_size__ (16), __may_alias__));
+
+#define SIZE 10240
+
+union {
+ __m128i i_align;
+ int i32[SIZE];
+ long i64[SIZE];
+} a, b, c, d;
+
+void
+imul32_to_64 (void)
+{
+ int i;
+
+ for (i = 0; i < SIZE; i++)
+ a.i64[i] = ((long)b.i32[i]) * ((long)c.i32[i]);
+}
+
+int main ()
+{
+ imul32_to_64 ();
+ exit (0);
+}
+
+/* { dg-final { scan-assembler "vpmacsdql" } } */
+/* { dg-final { scan-assembler "vpmacsdqh" } } */
--- /dev/null
+/* Test that the compiler properly optimizes floating point multiply and add
+ instructions vector into pmacsdd/etc. on XOP systems. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mxop -ftree-vectorize" } */
+
+extern void exit (int);
+
+typedef long __m128i __attribute__ ((__vector_size__ (16), __may_alias__));
+
+#define SIZE 10240
+
+union {
+ __m128i i_align;
+ long i64[SIZE];
+} a, b, c, d;
+
+void
+imul64 (void)
+{
+ int i;
+
+ for (i = 0; i < SIZE; i++)
+ a.i64[i] = b.i64[i] * c.i64[i];
+}
+
+int main ()
+{
+ imul64 ();
+ exit (0);
+}
+
+/* { dg-final { scan-assembler "vpmacsdd" } } */
+/* { dg-final { scan-assembler "vphadddq" } } */
+/* { dg-final { scan-assembler "vpmacsdql" } } */
--- /dev/null
+/* Test that the compiler properly optimizes conditional floating point moves
+ into the pcmov instruction on XOP systems. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mxop" } */
+
+extern void exit (int);
+
+double dbl_test (double a, double b, double c, double d)
+{
+ return (a > b) ? c : d;
+}
+
+double dbl_a = 1, dbl_b = 2, dbl_c = 3, dbl_d = 4, dbl_e;
+
+int main()
+{
+ dbl_e = dbl_test (dbl_a, dbl_b, dbl_c, dbl_d);
+ exit (0);
+}
+
+/* { dg-final { scan-assembler "vpcmov" } } */
--- /dev/null
+/* Test that the compiler properly optimizes conditional floating point moves
+ into the pcmov instruction on XOP systems. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mxop" } */
+
+extern void exit (int);
+
+float flt_test (float a, float b, float c, float d)
+{
+ return (a > b) ? c : d;
+}
+
+float flt_a = 1, flt_b = 2, flt_c = 3, flt_d = 4, flt_e;
+
+int main()
+{
+ flt_e = flt_test (flt_a, flt_b, flt_c, flt_d);
+ exit (0);
+}
+
+/* { dg-final { scan-assembler "vpcmov" } } */
--- /dev/null
+/* Test that the compiler properly optimizes vector rotate instructions vector
+ into prot on XOP systems. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mxop -ftree-vectorize" } */
+
+extern void exit (int);
+
+typedef long __m128i __attribute__ ((__vector_size__ (16), __may_alias__));
+
+#define SIZE 10240
+
+union {
+ __m128i i_align;
+ unsigned u32[SIZE];
+} a, b, c;
+
+void
+left_rotate32 (void)
+{
+ int i;
+
+ for (i = 0; i < SIZE; i++)
+ a.u32[i] = (b.u32[i] << ((sizeof (int) * 8) - 4)) | (b.u32[i] >> 4);
+}
+
+int
+main ()
+{
+ left_rotate32 ();
+ exit (0);
+}
+
+/* { dg-final { scan-assembler "vprotd" } } */
--- /dev/null
+/* Test that the compiler properly optimizes vector rotate instructions vector
+ into prot on XOP systems. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mxop -ftree-vectorize" } */
+
+extern void exit (int);
+
+typedef long __m128i __attribute__ ((__vector_size__ (16), __may_alias__));
+
+#define SIZE 10240
+
+union {
+ __m128i i_align;
+ unsigned u32[SIZE];
+} a, b, c;
+
+void
+right_rotate32_b (void)
+{
+ int i;
+
+ for (i = 0; i < SIZE; i++)
+ a.u32[i] = (b.u32[i] >> ((sizeof (int) * 8) - 4)) | (b.u32[i] << 4);
+}
+
+int
+main ()
+{
+ right_rotate ();
+ exit (0);
+}
+
+/* { dg-final { scan-assembler "vprot" } } */
--- /dev/null
+/* Test that the compiler properly optimizes vector rotate instructions vector
+ into prot on XOP systems. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mxop -ftree-vectorize" } */
+
+extern void exit (int);
+
+typedef long __m128i __attribute__ ((__vector_size__ (16), __may_alias__));
+
+#define SIZE 10240
+
+union {
+ __m128i i_align;
+ unsigned u32[SIZE];
+} a, b, c;
+
+void
+vector_rotate32 (void)
+{
+ int i;
+
+ for (i = 0; i < SIZE; i++)
+ a.u32[i] = (b.u32[i] >> ((sizeof (int) * 8) - c.u32[i])) | (b.u32[i] << c.u32[i]);
+}
+
+int main ()
+{
+ vector_rotate32 ();
+ exit (0);
+}
+
+/* { dg-final { scan-assembler "vprotd" } } */
--- /dev/null
+/* Test that the compiler properly optimizes vector shift instructions into
+ psha/pshl on XOP systems. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mxop -ftree-vectorize" } */
+
+extern void exit (int);
+
+typedef long __m128i __attribute__ ((__vector_size__ (16), __may_alias__));
+
+#define SIZE 10240
+
+union {
+ __m128i i_align;
+ int i32[SIZE];
+ unsigned u32[SIZE];
+} a, b, c;
+
+void
+left_shift32 (void)
+{
+ int i;
+
+ for (i = 0; i < SIZE; i++)
+ a.i32[i] = b.i32[i] << c.i32[i];
+}
+
+int main ()
+{
+ left_shfit32 ();
+ exit (0);
+}
+
+/* { dg-final { scan-assembler "vpshad" } } */
--- /dev/null
+/* Test that the compiler properly optimizes vector shift instructions into
+ psha/pshl on XOP systems. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mxop -ftree-vectorize" } */
+
+extern void exit (int);
+
+typedef long __m128i __attribute__ ((__vector_size__ (16), __may_alias__));
+
+#define SIZE 10240
+
+union {
+ __m128i i_align;
+ int i32[SIZE];
+ unsigned u32[SIZE];
+} a, b, c;
+
+void
+right_sign_shift32 (void)
+{
+ int i;
+
+ for (i = 0; i < SIZE; i++)
+ a.i32[i] = b.i32[i] >> c.i32[i];
+}
+
+int main ()
+{
+ right_sign_shfit32 ();
+ exit (0);
+}
+
+/* { dg-final { scan-assembler "vpshad" } } */
--- /dev/null
+/* Test that the compiler properly optimizes vector shift instructions into
+ psha/pshl on XOP systems. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mxop -ftree-vectorize" } */
+
+extern void exit (int);
+
+typedef long __m128i __attribute__ ((__vector_size__ (16), __may_alias__));
+
+#define SIZE 10240
+
+union {
+ __m128i i_align;
+ int i32[SIZE];
+ unsigned u32[SIZE];
+} a, b, c;
+
+void
+right_uns_shift32 (void)
+{
+ int i;
+
+ for (i = 0; i < SIZE; i++)
+ a.u32[i] = b.u32[i] >> c.i32[i];
+}
+
+int main ()
+{
+ right_uns_shfit32 ();
+ exit (0);
+}
+
+/* { dg-final { scan-assembler "vpshld" } } */
git://gcc.gnu.org / gcc.git / commitdiff