b/gcc/common/config/i386/i386-common.c
@@ -78,6 +78,7 @@ along with GCC; see the file COPYING3. If not see
(OPTION_MASK_ISA_AVX512VBMI | OPTION_MASK_ISA_AVX512BW_SET)
#define OPTION_MASK_ISA_AVX5124FMAPS_SET OPTION_MASK_ISA_AVX5124FMAPS
#define OPTION_MASK_ISA_AVX5124VNNIW_SET OPTION_MASK_ISA_AVX5124VNNIW
+#define OPTION_MASK_ISA_AVX512VPOPCNTDQ_SET OPTION_MASK_ISA_AVX512VPOPCNTDQ
#define OPTION_MASK_ISA_RTM_SET OPTION_MASK_ISA_RTM
#define OPTION_MASK_ISA_PRFCHW_SET OPTION_MASK_ISA_PRFCHW
#define OPTION_MASK_ISA_RDSEED_SET OPTION_MASK_ISA_RDSEED
@@ -183,6 +184,7 @@ along with GCC; see the file COPYING3. If not see
#define OPTION_MASK_ISA_AVX512VBMI_UNSET OPTION_MASK_ISA_AVX512VBMI
#define OPTION_MASK_ISA_AVX5124FMAPS_UNSET OPTION_MASK_ISA_AVX5124FMAPS
#define OPTION_MASK_ISA_AVX5124VNNIW_UNSET OPTION_MASK_ISA_AVX5124VNNIW
+#define OPTION_MASK_ISA_AVX512VPOPCNTDQ_UNSET OPTION_MASK_ISA_AVX512VPOPCNTDQ
#define OPTION_MASK_ISA_RTM_UNSET OPTION_MASK_ISA_RTM
#define OPTION_MASK_ISA_PRFCHW_UNSET OPTION_MASK_ISA_PRFCHW
#define OPTION_MASK_ISA_RDSEED_UNSET OPTION_MASK_ISA_RDSEED
@@ -409,6 +411,8 @@ ix86_handle_option (struct gcc_options *opts,
opts->x_ix86_isa_flags2_explicit |= OPTION_MASK_ISA_AVX5124FMAPS_UNSET;
opts->x_ix86_isa_flags2 &= ~OPTION_MASK_ISA_AVX5124VNNIW_UNSET;
opts->x_ix86_isa_flags2_explicit |= OPTION_MASK_ISA_AVX5124VNNIW_UNSET;
+ opts->x_ix86_isa_flags2 &= ~OPTION_MASK_ISA_AVX512VPOPCNTDQ_UNSET;
+ opts->x_ix86_isa_flags2_explicit |= OPTION_MASK_ISA_AVX512VPOPCNTDQ_UNSET;
}
return true;
@@ -481,6 +485,21 @@ ix86_handle_option (struct gcc_options *opts,
}
return true;
+ case OPT_mavx512vpopcntdq:
+ if (value)
+ {
+ opts->x_ix86_isa_flags2 |= OPTION_MASK_ISA_AVX512VPOPCNTDQ_SET;
+ opts->x_ix86_isa_flags2_explicit |= OPTION_MASK_ISA_AVX512VPOPCNTDQ_SET;
+ opts->x_ix86_isa_flags |= OPTION_MASK_ISA_AVX512F_SET;
+ opts->x_ix86_isa_flags_explicit |= OPTION_MASK_ISA_AVX512F_SET;
+ }
+ else
+ {
+ opts->x_ix86_isa_flags2 &= ~OPTION_MASK_ISA_AVX512VPOPCNTDQ_UNSET;
+ opts->x_ix86_isa_flags2_explicit |= OPTION_MASK_ISA_AVX512VPOPCNTDQ_UNSET;
+ }
+ return true;
+
case OPT_mavx512dq:
if (value)
{
@@ -375,7 +375,8 @@ i[34567]86-*-*)
avx512vlintrin.h avx512vlbwintrin.h avx512vldqintrin.h
avx512ifmaintrin.h avx512ifmavlintrin.h avx512vbmiintrin.h
avx512vbmivlintrin.h avx5124fmapsintrin.h avx5124vnniwintrin.h
- clwbintrin.h mwaitxintrin.h clzerointrin.h pkuintrin.h"
+ avx512vpopcntdqintrin.h clwbintrin.h mwaitxintrin.h
+ clzerointrin.h pkuintrin.h"
;;
x86_64-*-*)
cpu_type=i386
@@ -397,7 +398,8 @@ x86_64-*-*)
avx512vlintrin.h avx512vlbwintrin.h avx512vldqintrin.h
avx512ifmaintrin.h avx512ifmavlintrin.h avx512vbmiintrin.h
avx512vbmivlintrin.h avx5124fmapsintrin.h avx5124vnniwintrin.h
- clwbintrin.h mwaitxintrin.h clzerointrin.h pkuintrin.h"
+ avx512vpopcntdqintrin.h clwbintrin.h mwaitxintrin.h
+ clzerointrin.h pkuintrin.h"
;;
ia64-*-*)
extra_headers=ia64intrin.h
b/gcc/config/i386/avx512vpopcntdqintrin.h
new file mode 100644
@@ -0,0 +1,90 @@
+/* Copyright (C) 2016 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/>. */
+
+#if !defined _IMMINTRIN_H_INCLUDED
+# error "Never use <avx512vpopcntdqintrin.h> directly; include
<x86intrin.h> instead."
+#endif
+
+#ifndef _AVX512VPOPCNTDQINTRIN_H_INCLUDED
+#define _AVX512VPOPCNTDQINTRIN_H_INCLUDED
+
+#ifndef __AVX512VPOPCNTDQ__
+#pragma GCC push_options
+#pragma GCC target("avx512vpopcntdq")
+#define __DISABLE_AVX512VPOPCNTDQ__
+#endif /* __AVX512VPOPCNTDQ__ */
+
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_popcnt_epi32 (__m512i __A)
+{
+ return (__m512i) __builtin_ia32_vpopcountd_v16si ((__v16si) __A);
+}
+
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_popcnt_epi32 (__m512i __A, __mmask16 __U, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_vpopcountd_v16si_mask ((__v16si) __A,
+ (__mmask16) __U,
+ (__v16si) __B);
+}
+
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_popcnt_epi32 (__mmask16 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_vpopcountd_v16si_maskz ((__mmask16) __U,
+ (__v16si) __A);
+}
+
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_popcnt_epi64 (__m512i __A)
+{
+ return (__m512i) __builtin_ia32_vpopcountq_v8di ((__v8di) __A);
+}
+
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_popcnt_epi64 (__m512i __A, __mmask8 __U, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_vpopcountq_v8di_mask ((__v8di) __A,
+ (__mmask8) __U,
+ (__v8di) __B);
+}
+
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_popcnt_epi64 (__mmask8 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_vpopcountq_v8di_maskz ((__mmask8) __U,
+ (__v8di) __A);
+}
+
+#ifdef __DISABLE_AVX512VPOPCNTDQ__
+#undef __DISABLE_AVX512VPOPCNTDQ__
+#pragma GCC pop_options
+#endif /* __DISABLE_AVX512VPOPCNTDQ__ */
+
+#endif /* _AVX512VPOPCNTDQINTRIN_H_INCLUDED */
@@ -54,6 +54,7 @@
#define bit_SSE4a (1 << 6)
#define bit_PRFCHW (1 << 8)
#define bit_XOP (1 << 11)
+#define bit_AVX512VPOPCNTDQ (1 << 14)
#define bit_LWP (1 << 15)
#define bit_FMA4 (1 << 16)
#define bit_TBM (1 << 21)
b/gcc/config/i386/i386-builtin-types.def
@@ -305,9 +305,15 @@ DEF_FUNCTION_TYPE (V8DF, V2DF)
DEF_FUNCTION_TYPE (V16SI, V4SI)
DEF_FUNCTION_TYPE (V16SI, V8SI)
DEF_FUNCTION_TYPE (V16SI, V16SF)
+DEF_FUNCTION_TYPE (V16SI, V16SI)
+DEF_FUNCTION_TYPE (V16SI, UHI, V16SI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, UHI, V16SI)
DEF_FUNCTION_TYPE (V16SI, V16SI, V16SI, UHI)
DEF_FUNCTION_TYPE (V8DI, V8DI, V8DI, UQI)
DEF_FUNCTION_TYPE (V8DI, PV8DI)
+DEF_FUNCTION_TYPE (V8DI, V8DI)
+DEF_FUNCTION_TYPE (V8DI, UQI, V8DI)
+DEF_FUNCTION_TYPE (V8DI, V8DI, UQI, V8DI)
DEF_FUNCTION_TYPE (DI, V2DI, INT)
DEF_FUNCTION_TYPE (DOUBLE, V2DF, INT)
@@ -486,6 +492,7 @@ DEF_FUNCTION_TYPE (V16SI, V16SI, INT)
DEF_FUNCTION_TYPE (V16SI, V16SI, V4SI, V16SI, UHI)
DEF_FUNCTION_TYPE (V16SI, V16SI, INT, V16SI, UHI)
DEF_FUNCTION_TYPE (V8SI, PCV8SI, V8SI)
+DEF_FUNCTION_TYPE (V4DI, V4DI)
DEF_FUNCTION_TYPE (V4DI, V4DI, V4DI)
DEF_FUNCTION_TYPE (V16SI, V8DF, V8DF)
DEF_FUNCTION_TYPE (V8DI, V8DI, V8DI, INT, V8DI, UQI)
@@ -2527,6 +2527,12 @@ BDESC (OPTION_MASK_ISA_AVX5124VNNIW,
CODE_FOR_avx5124vnniw_vp4dpwssd, "__builtin
BDESC (OPTION_MASK_ISA_AVX5124VNNIW,
CODE_FOR_avx5124vnniw_vp4dpwssd_mask, "__builtin_ia32_vp4dpwssd_mask",
IX86_BUILTIN_4DPWSSD_MASK, UNKNOWN, (int)
V16SI_FTYPE_V16SI_V16SI_V16SI_V16SI_V16SI_PCV4SI_V16SI_UHI)
BDESC (OPTION_MASK_ISA_AVX5124VNNIW,
CODE_FOR_avx5124vnniw_vp4dpwssds, "__builtin_ia32_vp4dpwssds",
IX86_BUILTIN_4DPWSSDS, UNKNOWN, (int)
V16SI_FTYPE_V16SI_V16SI_V16SI_V16SI_V16SI_PCV4SI)
BDESC (OPTION_MASK_ISA_AVX5124VNNIW,
CODE_FOR_avx5124vnniw_vp4dpwssds_mask,
"__builtin_ia32_vp4dpwssds_mask", IX86_BUILTIN_4DPWSSDS_MASK, UNKNOWN,
(int) V16SI_FTYPE_V16SI_V16SI_V16SI_V16SI_V16SI_PCV4SI_V16SI_UHI)
+BDESC (OPTION_MASK_ISA_AVX512VPOPCNTDQ, CODE_FOR_vpopcountv16si,
"__builtin_ia32_vpopcountd_v16si", IX86_BUILTIN_VPOPCOUNTDV16SI,
UNKNOWN, (int) V16SI_FTYPE_V16SI)
+BDESC (OPTION_MASK_ISA_AVX512VPOPCNTDQ, CODE_FOR_vpopcountv16si_mask,
"__builtin_ia32_vpopcountd_v16si_mask",
IX86_BUILTIN_VPOPCOUNTDV16SI_MASK, UNKNOWN, (int)
V16SI_FTYPE_V16SI_UHI_V16SI)
+BDESC (OPTION_MASK_ISA_AVX512VPOPCNTDQ,
CODE_FOR_vpopcountv16si_maskz,
"__builtin_ia32_vpopcountd_v16si_maskz",
IX86_BUILTIN_VPOPCOUNTDV16SI_MASKZ, UNKNOWN, (int)
V16SI_FTYPE_UHI_V16SI)
+BDESC (OPTION_MASK_ISA_AVX512VPOPCNTDQ, CODE_FOR_vpopcountv8di,
"__builtin_ia32_vpopcountq_v8di", IX86_BUILTIN_VPOPCOUNTQV8DI,
UNKNOWN, (int) V8DI_FTYPE_V8DI)
+BDESC (OPTION_MASK_ISA_AVX512VPOPCNTDQ, CODE_FOR_vpopcountv8di_mask,
"__builtin_ia32_vpopcountq_v8di_mask",
IX86_BUILTIN_VPOPCOUNTQV8DI_MASK, UNKNOWN, (int)
V8DI_FTYPE_V8DI_UQI_V8DI)
+BDESC (OPTION_MASK_ISA_AVX512VPOPCNTDQ, CODE_FOR_vpopcountv8di_maskz,
"__builtin_ia32_vpopcountq_v8di_maskz",
IX86_BUILTIN_VPOPCOUNTQV8DI_MASKZ, UNKNOWN, (int) V8DI_FTYPE_UQI_V8DI)
BDESC_END (ARGS2, MPX)
@@ -380,6 +380,8 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
def_or_undef (parse_in, "__AVX5124VNNIW__");
if (isa_flag2 & OPTION_MASK_ISA_AVX5124FMAPS)
def_or_undef (parse_in, "__AVX5124FMAPS__");
+ if (isa_flag2 & OPTION_MASK_ISA_AVX512VPOPCNTDQ)
+ def_or_undef (parse_in, "__AVX512VPOPCNTDQ__");
if (isa_flag & OPTION_MASK_ISA_FMA)
def_or_undef (parse_in, "__FMA__");
if (isa_flag & OPTION_MASK_ISA_RTM)
@@ -4320,6 +4320,7 @@ ix86_target_string (HOST_WIDE_INT isa,
HOST_WIDE_INT isa2, int flags,
{
{ "-mavx5124vnniw", OPTION_MASK_ISA_AVX5124VNNIW },
{ "-mavx5124fmaps", OPTION_MASK_ISA_AVX5124FMAPS },
+ { "-mavx512vpopcntdq", OPTION_MASK_ISA_AVX512VPOPCNTDQ },
};
/* Flag options. */
static struct ix86_target_opts flag_opts[] =
@@ -4919,6 +4920,7 @@ ix86_option_override_internal (bool main_args_p,
#define PTA_PKU (HOST_WIDE_INT_1 << 59)
#define PTA_AVX5124VNNIW (HOST_WIDE_INT_1 << 60)
#define PTA_AVX5124FMAPS (HOST_WIDE_INT_1 << 61)
+#define PTA_AVX512VPOPCNTDQ (HOST_WIDE_INT_1 << 62)
#define PTA_CORE2 \
(PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3 | PTA_SSSE3 \
@@ -5581,6 +5583,9 @@ ix86_option_override_internal (bool main_args_p,
if (processor_alias_table[i].flags & PTA_AVX5124FMAPS
&& !(opts->x_ix86_isa_flags2_explicit & OPTION_MASK_ISA_AVX5124FMAPS))
opts->x_ix86_isa_flags2 |= OPTION_MASK_ISA_AVX5124FMAPS;
+ if (processor_alias_table[i].flags & PTA_AVX512VPOPCNTDQ
+ && !(opts->x_ix86_isa_flags2_explicit & OPTION_MASK_ISA_AVX512VPOPCNTDQ))
+ opts->x_ix86_isa_flags2 |= OPTION_MASK_ISA_AVX512VPOPCNTDQ;
if (processor_alias_table[i].flags & (PTA_PREFETCH_SSE | PTA_SSE))
x86_prefetch_sse = true;
@@ -6625,6 +6630,7 @@ ix86_valid_target_attribute_inner_p (tree args,
char *p_strings[],
IX86_ATTR_ISA ("avx512vl", OPT_mavx512vl),
IX86_ATTR_ISA ("avx5124fmaps", OPT_mavx5124fmaps),
IX86_ATTR_ISA ("avx5124vnniw", OPT_mavx5124vnniw),
+ IX86_ATTR_ISA ("avx512vpopcntdq", OPT_mavx512vpopcntdq),
IX86_ATTR_ISA ("mmx", OPT_mmmx),
IX86_ATTR_ISA ("pclmul", OPT_mpclmul),
IX86_ATTR_ISA ("popcnt", OPT_mpopcnt),
@@ -33300,6 +33306,7 @@ fold_builtin_cpu (tree fndecl, tree *args)
F_AVX512IFMA,
F_AVX5124VNNIW,
F_AVX5124FMAPS,
+ F_AVX512VPOPCNTDQ,
F_MAX
};
@@ -33414,6 +33421,7 @@ fold_builtin_cpu (tree fndecl, tree *args)
{"avx512ifma",F_AVX512IFMA},
{"avx5124vnniw",F_AVX5124VNNIW},
{"avx5124fmaps",F_AVX5124FMAPS},
+ {"avx512vpopcntdq",F_AVX512VPOPCNTDQ},
};
tree __processor_model_type = build_processor_model_struct ();
@@ -34885,14 +34893,17 @@ ix86_expand_args_builtin (const struct
builtin_description *d,
case V16SI_FTYPE_UHI:
case V2DI_FTYPE_UQI:
case V4DI_FTYPE_UQI:
+ case V4DI_FTYPE_V4DI:
case V16SI_FTYPE_INT:
case V16SF_FTYPE_V8SF:
case V16SI_FTYPE_V8SI:
case V16SF_FTYPE_V4SF:
case V16SI_FTYPE_V4SI:
case V16SI_FTYPE_V16SF:
+ case V16SI_FTYPE_V16SI:
case V16SF_FTYPE_V16SF:
case V8DI_FTYPE_UQI:
+ case V8DI_FTYPE_V8DI:
case V8DF_FTYPE_V4DF:
case V8DF_FTYPE_V2DF:
case V8DF_FTYPE_V8DF:
@@ -34997,7 +35008,9 @@ ix86_expand_args_builtin (const struct
builtin_description *d,
case UHI_FTYPE_UHI_UHI:
case USI_FTYPE_USI_USI:
case UDI_FTYPE_UDI_UDI:
+ case V8DI_FTYPE_UQI_V8DI:
case V16SI_FTYPE_V8DF_V8DF:
+ case V16SI_FTYPE_UHI_V16SI:
nargs = 2;
break;
case V2DI_FTYPE_V2DI_INT_CONVERT:
@@ -35203,6 +35216,11 @@ ix86_expand_args_builtin (const struct
builtin_description *d,
nargs = 3;
nargs_constant = 1;
break;
+ case V8DI_FTYPE_V8DI_UQI_V8DI:
+ case V16SI_FTYPE_V16SI_UHI_V16SI:
+ nargs = 3;
+ mask_pos = 1;
+ break;
case V4DI_FTYPE_V4DI_V4DI_INT_CONVERT:
nargs = 3;
rmode = V4DImode;
@@ -85,6 +85,8 @@ see the files COPYING3 and COPYING.RUNTIME
respectively. If not, see
#define TARGET_AVX5124FMAPS_P(x) TARGET_ISA_AVX5124FMAPS_P(x)
#define TARGET_AVX5124VNNIW TARGET_ISA_AVX5124VNNIW
#define TARGET_AVX5124VNNIW_P(x) TARGET_ISA_AVX5124VNNIW_P(x)
+#define TARGET_AVX512VPOPCNTDQ TARGET_ISA_AVX512VPOPCNTDQ
+#define TARGET_AVX512VPOPCNTDQ_P(x) TARGET_ISA_AVX512VPOPCNTDQ_P(x)
#define TARGET_FMA TARGET_ISA_FMA
#define TARGET_FMA_P(x) TARGET_ISA_FMA_P(x)
#define TARGET_SSE4A TARGET_ISA_SSE4A
@@ -705,6 +705,10 @@ mavx5124vnniw
Target Report Mask(ISA_AVX5124VNNIW) Var(ix86_isa_flags2) Save
Support MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, AVX2,
AVX512F and AVX5124VNNIW built-in functions and code generation.
+mavx512vpopcntdq
+Target Report Mask(ISA_AVX512VPOPCNTDQ) Var(ix86_isa_flags2) Save
+Support MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, AVX2,
AVX512F and AVX512VPOPCNTDQ built-in functions and code generation.
+
mfma
Target Report Mask(ISA_FMA) Var(ix86_isa_flags) Save
Support MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX and FMA
built-in functions and code generation.
@@ -72,6 +72,8 @@
#include <avx5124vnniwintrin.h>
+#include <avx512vpopcntdqintrin.h>
+
#include <shaintrin.h>
#include <lzcntintrin.h>
@@ -155,6 +155,9 @@
UNSPEC_VP4FNMADD
UNSPEC_VP4DPWSSD
UNSPEC_VP4DPWSSDS
+
+ ;; For VPOPCOUNTDQ support
+ UNSPEC_VPOPCNTDQ
])
(define_c_enum "unspecv" [
@@ -265,6 +268,9 @@
(define_mode_iterator VF_512
[V16SF V8DF])
+(define_mode_iterator VI_AVX512F
+ [V16SI V8DI])
+
(define_mode_iterator VI48_AVX512VL
[V16SI (V8SI "TARGET_AVX512VL") (V4SI "TARGET_AVX512VL")
V8DI (V4DI "TARGET_AVX512VL") (V2DI "TARGET_AVX512VL")])
@@ -19881,3 +19887,44 @@
[(set_attr ("type") ("ssemuladd"))
(set_attr ("prefix") ("evex"))
(set_attr ("mode") ("TI"))])
+
+(define_insn "vpopcount<mode>"
+ [(set (match_operand:VI_AVX512F 0 "register_operand" "=v, v")
+ (popcount:VI_AVX512F
+ (match_operand:VI_AVX512F 1 "nonimmediate_operand" "v, m")))]
+ "TARGET_AVX512VPOPCNTDQ"
+ "vpopcnt<ssemodesuffix>\t{%1, %0|%0, %1}")
+
+(define_insn "vpopcountv16si_mask"
+ [(set (match_operand:V16SI 0 "register_operand" "=v, v")
+ (unspec:V16SI
+ [(match_operand:V16SI 1 "nonimmediate_operand" "v, m")
+ (match_operand:HI 2 "register_operand" "Yk, Yk")
+ (match_operand:V16SI 3 "nonimmediate_operand" "0, 0")] UNSPEC_VPOPCNTDQ))]
+ "TARGET_AVX512VPOPCNTDQ"
+ "vpopcntd\t{%1, %0%{%2%}|%{%2%}%0, %1}")
+
+(define_insn "vpopcountv16si_maskz"
+ [(set (match_operand:V16SI 0 "register_operand" "=v, v")
+ (unspec:V16SI
+ [(match_operand:HI 1 "register_operand" "Yk, Yk")
+ (match_operand:V16SI 2 "nonimmediate_operand" "v, m")] UNSPEC_VPOPCNTDQ))]
+ "TARGET_AVX512VPOPCNTDQ"
+ "vpopcntd\t{%2, %0%{%1%}%{z%}|%{%1%}%{z%}%0, %2}")
+
+(define_insn "vpopcountv8di_mask"
+ [(set (match_operand:V8DI 0 "register_operand" "=v, v")
+ (unspec:V8DI
+ [(match_operand:V8DI 1 "nonimmediate_operand" "v, m")
+ (match_operand:QI 2 "register_operand" "Yk, Yk")
+ (match_operand:V8DI 3 "nonimmediate_operand" "0, 0")] UNSPEC_VPOPCNTDQ))]
+ "TARGET_AVX512VPOPCNTDQ"
+ "vpopcntq\t{%1, %0%{%2%}|%{%2%}%0, %1}")
+
+(define_insn "vpopcountv8di_maskz"
+ [(set (match_operand:V8DI 0 "register_operand" "=v, v")
+ (unspec:V8DI
+ [(match_operand:QI 1 "register_operand" "Yk, Yk")
+ (match_operand:V8DI 2 "nonimmediate_operand" "v, m")] UNSPEC_VPOPCNTDQ))]
+ "TARGET_AVX512VPOPCNTDQ"
+ "vpopcntq\t{%2, %0%{%1%}%{z%}|%{%1%}%{z%}%0, %2}")
b/gcc/testsuite/g++.dg/other/i386-2.C
@@ -1,11 +1,11 @@
/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -pedantic-errors -march=k8 -msse4a -m3dnow -mavx
-mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2
-mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw
-madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf
-msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq
-mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx5124fmaps
-mavx5124vnniw -mclwb -mmwaitx -mclzero -mpku" } */
+/* { dg-options "-O -pedantic-errors -march=k8 -msse4a -m3dnow -mavx
-mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2
-mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw
-madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf
-msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq
-mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx5124fmaps
-mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku" } */
/* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h, fma4intrin.h,
xopintrin.h, abmintrin.h, bmiintrin.h, tbmintrin.h, lwpintrin.h,
popcntintrin.h, fmaintrin.h, pkuintrin.h, avx5124fmapsintrin.h,
- avx5124vnniwintrin.h and mm_malloc.h.h are usable with
- -O -pedantic-errors. */
+ avx5124vnniwintrin.h, avx512vpopcntdqintrin.h and mm_malloc.h.h are usable
+ with -O -pedantic-errors. */
#include <x86intrin.h>
b/gcc/testsuite/g++.dg/other/i386-3.C
@@ -1,10 +1,10 @@
/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -fkeep-inline-functions -march=k8 -msse4a -m3dnow
-mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi
-mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed
-mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd
-mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt
-mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi
-mavx5124fmaps -mavx5124vnniw -mclwb -mmwaitx -mclzero -mpku" } */
+/* { dg-options "-O -fkeep-inline-functions -march=k8 -msse4a -m3dnow
-mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi
-mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed
-mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd
-mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt
-mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi
-mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx
-mclzero -mpku" } */
/* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h, fma4intrin.h,
xopintrin.h, abmintrin.h, bmiintrin.h, tbmintrin.h, lwpintrin.h,
popcntintrin.h, fmaintrin.h, pkuintrin.h, avx5124fmapsintrin.h,
- avx5124vnniwintrin.h and mm_malloc.h are usable with
- -O -fkeep-inline-functions. */
+ avx5124vnniwintrin.h, avx512vpopcntdqintrin.h and mm_malloc.h are
+ usable with -O -fkeep-inline-functions. */
#include <x86intrin.h>
b/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntd.c
new file mode 100644
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512vpopcntdq" } */
+/* { dg-final { scan-assembler-times "vpopcntd\[
\\t\]+\[^\{\n\]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vpopcntd\[
\\t\]+\[^\{\n\]*%zmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vpopcntd\[
\\t\]+\[^\{\n\]*%zmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 }
} */
+
+#include <x86intrin.h>
+
+extern __m512i z, z1;
+
+int foo ()
+{
+ __mmask16 msk;
+ __m512i c = _mm512_popcnt_epi32 (z);
+ asm volatile ("" : "+v" (c));
+ c = _mm512_mask_popcnt_epi32 (z, msk, z1);
+ asm volatile ("" : "+v" (c));
+ c = _mm512_maskz_popcnt_epi32 (msk, z);
+ asm volatile ("" : "+v" (c));
+}
b/gcc/testsuite/gcc.target/i386/avx512vpopcntdq-vpopcntq.c
new file mode 100644
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512vpopcntdq" } */
+/* { dg-final { scan-assembler-times "vpopcntq\[
\\t\]+\[^\{\n\]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vpopcntq\[
\\t\]+\[^\{\n\]*%zmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vpopcntq\[
\\t\]+\[^\{\n\]*%zmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 }
} */
+
+#include <x86intrin.h>
+
+extern __m512i z, z1;
+
+int foo ()
+{
+ __mmask8 msk;
+ __m512i c = _mm512_popcnt_epi64 (z);
+ asm volatile ("" : "+v" (c));
+ c = _mm512_mask_popcnt_epi64 (z, msk, z1);
+ asm volatile ("" : "+v" (c));
+ c = _mm512_maskz_popcnt_epi64 (msk, z);
+ asm volatile ("" : "+v" (c));
+}
b/gcc/testsuite/gcc.target/i386/builtin_target.c
@@ -217,6 +217,8 @@ check_features (unsigned int ecx, unsigned int edx,
assert (__builtin_cpu_supports ("avx5124vnniw"));
if (edx & bit_AVX5124FMAPS)
assert (__builtin_cpu_supports ("avx5124fmaps"));
+ if (ecx & bit_AVX512VPOPCNTDQ)
+ assert (__builtin_cpu_supports ("avx512vpopcntdq"));
}
}
@@ -319,6 +321,8 @@ quick_check ()
assert (__builtin_cpu_supports ("avx5124fmaps") >= 0);
+ assert (__builtin_cpu_supports ("avx512vpopcntdq") >= 0);
+
/* Check CPU type. */
assert (__builtin_cpu_is ("amd") >= 0);
b/gcc/testsuite/gcc.target/i386/funcspec-56.inc
@@ -30,6 +30,7 @@ extern void test_avx512pf(void)
__attribute__((__target__("avx512pf")));
extern void test_avx512cd(void) __attribute__((__target__("avx512cd")));
extern void test_avx5124fmaps(void)
__attribute__((__target__("avx5124fmaps")));
extern void test_avx5124vnniw(void)
__attribute__((__target__("avx5124vnniw")));
+extern void test_avx512vpopcntdq(void)
__attribute__((__target__("avx512vpopcntdq")));
extern void test_bmi (void) __attribute__((__target__("bmi")));
extern void test_bmi2 (void) __attribute__((__target__("bmi2")));
@@ -63,6 +64,7 @@ extern void test_bo_avx512pf(void)
__attribute__((__target__("no-avx512pf")));
extern void test_no_avx512cd(void) __attribute__((__target__("no-avx512cd")));
extern void test_no_avx5124fmaps(void)
__attribute__((__target__("no-avx5124fmaps")));
extern void test_no_avx5124vnniw(void)
__attribute__((__target__("no-avx5124vnniw")));
+extern void test_no_avx512vpopcntdq(void)
__attribute__((__target__("no-avx512vpopcntdq")));
extern void test_no_bmi (void) __attribute__((__target__("no-bmi")));
extern void test_no_bmi2 (void) __attribute__((__target__("no-bmi2")));
b/gcc/testsuite/gcc.target/i386/sse-12.c
@@ -3,7 +3,7 @@
popcntintrin.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 -msse4a
-m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm
-mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm
-mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er
-mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves
-mclflushopt -mavx512bw -mavx512dq -mavx512vl -mavx512vbmi
-mavx512ifma -mavx5124fmaps -mavx5124vnniw -mclwb -mmwaitx -mclzero
-mpku" } */
+/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -msse4a
-m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm
-mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm
-mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er
-mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves
-mclflushopt -mavx512bw -mavx512dq -mavx512vl -mavx512vbmi
-mavx512ifma -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb
-mmwaitx -mclzero -mpku" } */
#include <x86intrin.h>
b/gcc/testsuite/gcc.target/i386/sse-13.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8
-msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt
-mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma
-mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er
-mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves
-mclflushopt -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi
-mavx512ifma -mavx5124fmaps -mavx5124vnniw -mclwb -mmwaitx -mclzero
-mpku" } */
+/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8
-msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt
-mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma
-mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er
-mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves
-mclflushopt -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi
-mavx512ifma -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb
-mmwaitx -mclzero -mpku" } */
/* { dg-add-options bind_pic_locally } */
#include <mm_malloc.h>
b/gcc/testsuite/gcc.target/i386/sse-22.c
@@ -9,8 +9,8 @@
are defined as inline functions in {,x,e,p,t,s,w,a,b,i}mmintrin.h,
mm3dnow.h, fma4intrin.h, xopintrin.h, abmintrin.h, bmiintrin.h,
tbmintrin.h, lwpintrin.h, popcntintrin.h, fmaintrin.h,
- avx5124fmapsintrin.h, avx5124vnniwintrin.h and mm_malloc.h
- that reference the proper builtin functions.
+ avx5124fmapsintrin.h, avx5124vnniwintrin.h, avx512vpopcntdqintrin.h and
+ mm_malloc.h that reference the proper builtin functions.
Defining away "extern" and "__inline" results in all of them being
compiled as proper functions. */
@@ -101,7 +101,7 @@
#ifndef DIFFERENT_PRAGMAS
-#pragma GCC target
("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,avx512f,avx512er,avx512cd,avx512pf,sha,prefetchwt1,avx512vl,avx512bw,avx512dq,avx512vbmi,avx512ifma,avx5124fmaps,avx5124vnniw")
+#pragma GCC target
("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,avx512f,avx512er,avx512cd,avx512pf,sha,prefetchwt1,avx512vl,avx512bw,avx512dq,avx512vbmi,avx512ifma,avx5124fmaps,avx5124vnniw,avx512vpopcntdq")
#endif
/* Following intrinsics require immediate arguments. They
@@ -218,7 +218,7 @@ test_4 (_mm_cmpestrz, int, __m128i, int, __m128i, int, 1)
/* immintrin.h (AVX/AVX2/RDRND/FSGSBASE/F16C/RTM/AVX512F/SHA) */
#ifdef DIFFERENT_PRAGMAS
-#pragma GCC target
("avx,avx2,rdrnd,fsgsbase,f16c,rtm,avx512f,avx512er,avx512cd,avx512pf,sha,avx512vl,avx512bw,avx512dq,avx512ifma,avx512vbmi,avx5124fmaps,avx5124vnniw")
+#pragma GCC target
("avx,avx2,rdrnd,fsgsbase,f16c,rtm,avx512f,avx512er,avx512cd,avx512pf,sha,avx512vl,avx512bw,avx512dq,avx512ifma,avx512vbmi,avx5124fmaps,avx5124vnniw,avx512vpopcntdq")
#endif
#include <immintrin.h>
test_1 (_cvtss_sh, unsigned short, float, 1)
b/gcc/testsuite/gcc.target/i386/sse-23.c
@@ -8,8 +8,8 @@
are defined as inline functions in {,x,e,p,t,s,w,a,b,i}mmintrin.h,
mm3dnow.h, fma4intrin.h, xopintrin.h, abmintrin.h, bmiintrin.h,
tbmintrin.h, lwpintrin.h, popcntintrin.h, fmaintrin.h,
- avx5124fmapsintrin.h, avx5124vnniwintrin.h and mm_malloc.h
- that reference the proper builtin functions.
+ avx5124fmapsintrin.h, avx5124vnniwintrin.h, avx512vpopcntdqintrin.h
+ and mm_malloc.h that reference the proper builtin functions.
Defining away "extern" and "__inline" results in all of them being
compiled as proper functions. */
@@ -595,6 +595,6 @@
#define __builtin_ia32_extracti64x2_256_mask(A, E, C, D)
__builtin_ia32_extracti64x2_256_mask(A, 1, C, D)
#define __builtin_ia32_extractf64x2_256_mask(A, E, C, D)
__builtin_ia32_extractf64x2_256_mask(A, 1, C, D)
-#pragma GCC target
("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,fma,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,avx512f,avx512er,avx512cd,avx512pf,sha,prefetchwt1,xsavec,xsaves,clflushopt,avx512bw,avx512dq,avx512vl,avx512vbmi,avx512ifma,avx5124fmaps,avx5124vnniw,clwb,mwaitx,clzero,pku")
+#pragma GCC target
("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,fma,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,avx512f,avx512er,avx512cd,avx512pf,sha,prefetchwt1,xsavec,xsaves,clflushopt,avx512bw,avx512dq,avx512vl,avx512vbmi,avx512ifma,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,clwb,mwaitx,clzero,pku")
#include <x86intrin.h>
@@ -277,6 +277,8 @@ get_available_features (unsigned int ecx, unsigned int edx,
features |= (1 << FEATURE_AVX5124VNNIW);
if (edx & bit_AVX5124FMAPS)
features |= (1 << FEATURE_AVX5124FMAPS);
+ if (ecx & bit_AVX512VPOPCNTDQ)
+ features |= (1 << FEATURE_AVX512VPOPCNTDQ);
}
unsigned int ext_level;
@@ -104,7 +104,8 @@ enum processor_features
FEATURE_AVX512VBMI,
FEATURE_AVX512IFMA,
FEATURE_AVX5124VNNIW,
- FEATURE_AVX5124FMAPS
+ FEATURE_AVX5124FMAPS,
+ FEATURE_AVX512VPOPCNTDQ
};
extern struct __processor_model
Hi, this patch enables AVX512 VPOPCNTD/VPOPCNTQ instructions recently added in Instruction Set Extensions (https://software.intel.com/sites/default/files/managed/c5/15/architecture-instruction-set-extensions-programming-reference.pdf). gcc/ * common/config/i386/i386-common.c (OPTION_MASK_ISA_AVX512VPOPCNTDQ_SET, OPTION_MASK_ISA_AVX512VPOPCNTDQ_UNSET): New. * config.gcc: Add avx512vpopcntdqintrin.h. * config/i386/avx512vpopcntdqintrin.h: New. * config/i386/cpuid.h (bit_AVX512VPOPCNTDQ): New. * config/i386/i386-builtin-types.def: Add new types. * config/i386/i386-builtin.def (__builtin_ia32_vpopcountd_v16si, __builtin_ia32_vpopcountd_v16si_mask, __builtin_ia32_vpopcountd_v16si_maskz, __builtin_ia32_vpopcountq_v8di, __builtin_ia32_vpopcountq_v8di_mask, __builtin_ia32_vpopcountq_v8di_maskz): New. * config/i386/i386-c.c (ix86_target_macros_internal): Define __AVX512VPOPCNTDQ__. * config/i386/i386.c (ix86_target_string): Add -mavx512vpopcntdq. (PTA_AVX512VPOPCNTDQ): Define. * config/i386/i386.h (TARGET_AVX512VPOPCNTDQ, TARGET_AVX512VPOPCNTDQ_P): Define. * config/i386/i386.opt: Add mavx512vpopcntdq. * config/i386/immintrin.h: Include avx512vpopcntdqintrin.h. * config/i386/sse.md (unspec): Add UNSPEC_VPOPCNTDQ. (define_insn "vpopcount<mode>"): New. (define_insn "vpopcountv16si_mask"): Ditto. (define_insn "vpopcountv16si_maskz"): Ditto. (define_insn "vpopcountv8di_mask"): Ditto. (define_insn "vpopcountv8di_maskz"): Ditto. (define_mode_iterator VI_AVX512F): Ditto. gcc/testsuite/ * g++.dg/other/i386-2.C: Add -mavx512vpopcntdq. * g++.dg/other/i386-3.C: Ditto. * gcc.target/i386/sse-12.c: Ditto. * gcc.target/i386/sse-13.c: Ditto. * gcc.target/i386/sse-22.c: Ditto. * gcc.target/i386/sse-23.c: Ditto. * gcc.target/i386/builtin_target.c: Handle new option. * gcc.target/i386/funcspec-56.inc: Test new attributes. * gcc.target/i386/avx512vpopcntdq-vpopcntd.c: New test. * gcc.target/i386/avx512vpopcntdq-vpopcntq.c: Ditto. libgcc/ * config/i386/cpuinfo.h (processor_features): Add FEATURE_AVX512VPOPCNTDQ. * config/i386/cpuinfo.c (get_available_features): Habdle new feature. Is this patch Ok? -- WBR, Andrew