On Thu, May 10, 2018 at 7:47 PM, Uros Bizjak <ubiz...@gmail.com> wrote:
> Please find attached the patch that fixes all the issues (plus some
> whitespace fixes). It is tested and generates acceptable code. Please
> update the ChangeLog (do not use past tense in the ChangeLog entry!)
> and, if it works for you, please commit the attached version.
Sure enough, I have attached the wrong version. Please find correct
patch attached to the message.
Uros.
Index: cpuid.h
===================================================================
--- cpuid.h (revision 260116)
+++ cpuid.h (working copy)
@@ -98,6 +98,7 @@
#define bit_AVX512VBMI (1 << 1)
#define bit_PKU (1 << 3)
#define bit_OSPKE (1 << 4)
+#define bit_WAITPKG (1 << 5)
#define bit_AVX512VBMI2 (1 << 6)
#define bit_SHSTK (1 << 7)
#define bit_GFNI (1 << 8)
Index: driver-i386.c
===================================================================
--- driver-i386.c (revision 260116)
+++ driver-i386.c (working copy)
@@ -424,6 +424,7 @@ const char *host_detect_local_cpu (int argc, const
unsigned int has_avx512vnni = 0, has_vaes = 0;
unsigned int has_vpclmulqdq = 0;
unsigned int has_movdiri = 0, has_movdir64b = 0;
+ unsigned int has_waitpkg = 0;
bool arch;
@@ -527,6 +528,7 @@ const char *host_detect_local_cpu (int argc, const
has_shstk = ecx & bit_SHSTK;
has_pconfig = edx & bit_PCONFIG;
+ has_waitpkg = ecx & bit_WAITPKG;
}
if (max_level >= 13)
@@ -1108,6 +1110,7 @@ const char *host_detect_local_cpu (int argc, const
const char *avx512bitalg = has_avx512bitalg ? " -mavx512bitalg" : "
-mno-avx512bitalg";
const char *movdiri = has_movdiri ? " -mmovdiri" : " -mno-movdiri";
const char *movdir64b = has_movdir64b ? " -mmovdir64b" : "
-mno-movdir64b";
+ const char *waitpkg = has_waitpkg ? " -mwaitpkg" : " -mno-waitpkg";
options = concat (options, mmx, mmx3dnow, sse, sse2, sse3, ssse3,
sse4a, cx16, sahf, movbe, aes, sha, pclmul,
popcnt, abm, lwp, fma, fma4, xop, bmi, sgx, bmi2,
@@ -1120,7 +1123,7 @@ const char *host_detect_local_cpu (int argc, const
avx512ifma, avx512vbmi, avx5124fmaps, avx5124vnniw,
clwb, mwaitx, clzero, pku, rdpid, gfni, shstk,
avx512vbmi2, avx512vnni, vaes, vpclmulqdq,
- avx512bitalg, movdiri, movdir64b, NULL);
+ avx512bitalg, movdiri, movdir64b, waitpkg, NULL);
}
done:
Index: i386-builtin-types.def
===================================================================
--- i386-builtin-types.def (revision 260116)
+++ i386-builtin-types.def (working copy)
@@ -290,6 +290,7 @@ DEF_FUNCTION_TYPE (VOID, UINT64)
DEF_FUNCTION_TYPE (VOID, UINT64, PVOID)
DEF_FUNCTION_TYPE (VOID, UNSIGNED)
DEF_FUNCTION_TYPE (VOID, UNSIGNED, PVOID)
+DEF_FUNCTION_TYPE (UINT8, UNSIGNED, UINT64)
DEF_FUNCTION_TYPE (INT, PUSHORT)
DEF_FUNCTION_TYPE (INT, PUNSIGNED)
DEF_FUNCTION_TYPE (INT, PULONGLONG)
Index: i386-c.c
===================================================================
--- i386-c.c (revision 260116)
+++ i386-c.c (working copy)
@@ -516,6 +516,8 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_fla
def_or_undef (parse_in, "__MOVDIRI__");
if (isa_flag2 & OPTION_MASK_ISA_MOVDIR64B)
def_or_undef (parse_in, "__MOVDIR64B__");
+ if (isa_flag2 & OPTION_MASK_ISA_WAITPKG)
+ def_or_undef (parse_in, "__WAITPKG__");
if (TARGET_IAMCU)
{
def_or_undef (parse_in, "__iamcu");
Index: i386.c
===================================================================
--- i386.c (revision 260116)
+++ i386.c (working copy)
@@ -2772,7 +2772,8 @@ ix86_target_string (HOST_WIDE_INT isa, HOST_WIDE_I
{ "-mmovbe", OPTION_MASK_ISA_MOVBE },
{ "-mclzero", OPTION_MASK_ISA_CLZERO },
{ "-mmwaitx", OPTION_MASK_ISA_MWAITX },
- { "-mmovdir64b", OPTION_MASK_ISA_MOVDIR64B }
+ { "-mmovdir64b", OPTION_MASK_ISA_MOVDIR64B },
+ { "-mwaitpkg", OPTION_MASK_ISA_WAITPKG }
};
static struct ix86_target_opts isa_opts[] =
{
@@ -3455,6 +3456,7 @@ ix86_option_override_internal (bool main_args_p,
const wide_int_bitmask PTA_RDPID (0, HOST_WIDE_INT_1U << 6);
const wide_int_bitmask PTA_PCONFIG (0, HOST_WIDE_INT_1U << 7);
const wide_int_bitmask PTA_WBNOINVD (0, HOST_WIDE_INT_1U << 8);
+ const wide_int_bitmask PTA_WAITPKG (0, HOST_WIDE_INT_1U << 9);
const wide_int_bitmask PTA_CORE2 = PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2
| PTA_SSE3 | PTA_SSSE3 | PTA_CX16 | PTA_FXSR;
@@ -5387,6 +5389,7 @@ ix86_valid_target_attribute_inner_p (tree args, ch
IX86_ATTR_ISA ("vpclmulqdq", OPT_mvpclmulqdq),
IX86_ATTR_ISA ("movdiri", OPT_mmovdiri),
IX86_ATTR_ISA ("movdir64b", OPT_mmovdir64b),
+ IX86_ATTR_ISA ("waitpkg", OPT_mwaitpkg),
/* enum options */
IX86_ATTR_ENUM ("fpmath=", OPT_mfpmath_),
@@ -30642,6 +30645,9 @@ enum ix86_builtins
IX86_BUILTIN_CLFLUSH,
IX86_BUILTIN_MONITOR,
IX86_BUILTIN_MWAIT,
+ IX86_BUILTIN_UMONITOR,
+ IX86_BUILTIN_UMWAIT,
+ IX86_BUILTIN_TPAUSE,
IX86_BUILTIN_CLZERO,
IX86_BUILTIN_VEC_INIT_V2SI,
IX86_BUILTIN_VEC_INIT_V4HI,
@@ -31973,6 +31979,14 @@ ix86_init_mmx_sse_builtins (void)
def_builtin2 (OPTION_MASK_ISA_CLZERO, "__builtin_ia32_clzero",
VOID_FTYPE_PCVOID, IX86_BUILTIN_CLZERO);
+ /* WAITPKG. */
+ def_builtin2 (OPTION_MASK_ISA_WAITPKG, "__builtin_ia32_umonitor",
+ VOID_FTYPE_PVOID, IX86_BUILTIN_UMONITOR);
+ def_builtin2 (OPTION_MASK_ISA_WAITPKG, "__builtin_ia32_umwait",
+ UINT8_FTYPE_UNSIGNED_UINT64, IX86_BUILTIN_UMWAIT);
+ def_builtin2 (OPTION_MASK_ISA_WAITPKG, "__builtin_ia32_tpause",
+ UINT8_FTYPE_UNSIGNED_UINT64, IX86_BUILTIN_TPAUSE);
+
/* Add FMA4 multi-arg argument instructions */
for (i = 0, d = bdesc_multi_arg; i < ARRAY_SIZE (bdesc_multi_arg); i++, d++)
{
@@ -37048,6 +37062,82 @@ ix86_expand_builtin (tree exp, rtx target, rtx sub
emit_insn (gen_mwaitx (op0, op1, op2));
return 0;
+ case IX86_BUILTIN_UMONITOR:
+ arg0 = CALL_EXPR_ARG (exp, 0);
+ op0 = expand_normal (arg0);
+
+ op0 = ix86_zero_extend_to_Pmode (op0);
+
+ insn = (TARGET_64BIT
+ ? gen_umonitor_di (op0)
+ : gen_umonitor_si (op0));
+
+ emit_insn (insn);
+ return 0;
+
+ case IX86_BUILTIN_UMWAIT:
+ case IX86_BUILTIN_TPAUSE:
+ arg0 = CALL_EXPR_ARG (exp, 0);
+ arg1 = CALL_EXPR_ARG (exp, 1);
+ op0 = expand_normal (arg0);
+ op1 = expand_normal (arg1);
+
+ if (!REG_P (op0))
+ op0 = copy_to_mode_reg (SImode, op0);
+
+ op1 = force_reg (DImode, op1);
+
+ if (TARGET_64BIT)
+ {
+ op2 = expand_simple_binop (DImode, LSHIFTRT, op1, GEN_INT (32),
+ NULL, 1, OPTAB_DIRECT);
+ switch (fcode)
+ {
+ case IX86_BUILTIN_UMWAIT:
+ icode = CODE_FOR_umwait_rex64;
+ break;
+ case IX86_BUILTIN_TPAUSE:
+ icode = CODE_FOR_tpause_rex64;
+ break;
+ default:
+ gcc_unreachable ();
+ }
+
+ op2 = gen_lowpart (SImode, op2);
+ op1 = gen_lowpart (SImode, op1);
+ pat = GEN_FCN (icode) (op0, op1, op2);
+ }
+ else
+ {
+ switch (fcode)
+ {
+ case IX86_BUILTIN_UMWAIT:
+ icode = CODE_FOR_umwait;
+ break;
+ case IX86_BUILTIN_TPAUSE:
+ icode = CODE_FOR_tpause;
+ break;
+ default:
+ gcc_unreachable ();
+ }
+ pat = GEN_FCN (icode) (op0, op1);
+ }
+
+ if (!pat)
+ return 0;
+
+ emit_insn (pat);
+
+ if (target == 0
+ || !register_operand (target, QImode))
+ target = gen_reg_rtx (QImode);
+
+ pat = gen_rtx_EQ (QImode, gen_rtx_REG (CCCmode, FLAGS_REG),
+ const0_rtx);
+ emit_insn (gen_rtx_SET (target, pat));
+
+ return target;
+
case IX86_BUILTIN_CLZERO:
arg0 = CALL_EXPR_ARG (exp, 0);
op0 = expand_normal (arg0);
Index: i386.h
===================================================================
--- i386.h (revision 260116)
+++ i386.h (working copy)
@@ -189,6 +189,8 @@ see the files COPYING3 and COPYING.RUNTIME respect
#define TARGET_MOVDIRI_P(x) TARGET_ISA_MOVDIRI_P(x)
#define TARGET_MOVDIR64B TARGET_ISA_MOVDIR64B
#define TARGET_MOVDIR64B_P(x) TARGET_ISA_MOVDIR64B_P(x)
+#define TARGET_WAITPKG TARGET_ISA_WAITPKG
+#define TARGET_WAITPKG_P(x) TARGET_ISA_WAITPKG_P(x)
#define TARGET_LP64 TARGET_ABI_64
#define TARGET_LP64_P(x) TARGET_ABI_64_P(x)
Index: i386.md
===================================================================
--- i386.md (revision 260116)
+++ i386.md (working copy)
@@ -289,8 +289,15 @@
UNSPECV_WRUSS
UNSPECV_SETSSBSY
UNSPECV_CLRSSBSY
+
+ ;; For MOVDIRI and MOVDIR64B support
UNSPECV_MOVDIRI
UNSPECV_MOVDIR64B
+
+ ;; For WAITPKG support
+ UNSPECV_UMWAIT
+ UNSPECV_UMONITOR
+ UNSPECV_TPAUSE
])
;; Constants to represent rounding modes in the ROUND instruction
@@ -20960,22 +20967,72 @@
"wbnoinvd"
[(set_attr "type" "other")])
+;; MOVDIRI and MOVDIR64B
+
(define_insn "movdiri<mode>"
- [(unspec_volatile:SWI48[(match_operand:SWI48 0 "memory_operand" "m")
- (match_operand:SWI48 1 "register_operand" "r")]
- UNSPECV_MOVDIRI)]
+ [(unspec_volatile:SWI48 [(match_operand:SWI48 0 "memory_operand" "m")
+ (match_operand:SWI48 1 "register_operand" "r")]
+ UNSPECV_MOVDIRI)]
"TARGET_MOVDIRI"
"movdiri\t{%1, %0|%0, %1}"
[(set_attr "type" "other")])
(define_insn "movdir64b_<mode>"
- [(unspec_volatile:XI[(match_operand:P 0 "register_operand" "r")
- (match_operand:XI 1 "memory_operand")]
- UNSPECV_MOVDIR64B)]
+ [(unspec_volatile:XI [(match_operand:P 0 "register_operand" "r")
+ (match_operand:XI 1 "memory_operand")]
+ UNSPECV_MOVDIR64B)]
"TARGET_MOVDIR64B"
"movdir64b\t{%1, %0|%0, %1}"
[(set_attr "type" "other")])
+;; WAITPKG
+
+(define_insn "umwait"
+ [(set (reg:CCC FLAGS_REG)
+ (unspec_volatile:CCC [(match_operand:SI 0 "register_operand" "r")
+ (match_operand:DI 1 "register_operand" "A")]
+ UNSPECV_UMWAIT))]
+ "!TARGET_64BIT && TARGET_WAITPKG"
+ "umwait\t%0"
+ [(set_attr "length" "3")])
+
+(define_insn "umwait_rex64"
+ [(set (reg:CCC FLAGS_REG)
+ (unspec_volatile:CCC [(match_operand:SI 0 "register_operand" "r")
+ (match_operand:SI 1 "register_operand" "a")
+ (match_operand:SI 2 "register_operand" "d")]
+ UNSPECV_UMWAIT))]
+ "TARGET_64BIT && TARGET_WAITPKG"
+ "umwait\t%0"
+ [(set_attr "length" "3")])
+
+(define_insn "umonitor_<mode>"
+ [(unspec_volatile [(match_operand:P 0 "register_operand" "r")]
+ UNSPECV_UMONITOR)]
+ "TARGET_WAITPKG"
+ "umonitor\t%0"
+ [(set (attr "length")
+ (symbol_ref ("(Pmode != word_mode) + 3")))])
+
+(define_insn "tpause"
+ [(set (reg:CCC FLAGS_REG)
+ (unspec_volatile:CCC [(match_operand:SI 0 "register_operand" "r")
+ (match_operand:DI 1 "register_operand" "A")]
+ UNSPECV_TPAUSE))]
+ "!TARGET_64BIT && TARGET_WAITPKG"
+ "tpause\t%0"
+ [(set_attr "length" "3")])
+
+(define_insn "tpause_rex64"
+ [(set (reg:CCC FLAGS_REG)
+ (unspec_volatile:CCC [(match_operand:SI 0 "register_operand" "r")
+ (match_operand:SI 1 "register_operand" "a")
+ (match_operand:SI 2 "register_operand" "d")]
+ UNSPECV_TPAUSE))]
+ "TARGET_64BIT && TARGET_WAITPKG"
+ "tpause\t%0"
+ [(set_attr "length" "3")])
+
(include "mmx.md")
(include "sse.md")
(include "sync.md")
Index: i386.opt
===================================================================
--- i386.opt (revision 260116)
+++ i386.opt (working copy)
@@ -1055,3 +1055,7 @@ Support MOVDIRI built-in functions and code genera
mmovdir64b
Target Report Mask(ISA_MOVDIR64B) Var(ix86_isa_flags2) Save
Support MOVDIR64B built-in functions and code generation.
+
+mwaitpkg
+Target Report Mask(ISA_WAITPKG) Var(ix86_isa_flags2) Save
+Support WAITPKG built-in functions and code generation.
Index: waitpkgintrin.h
===================================================================
--- waitpkgintrin.h (nonexistent)
+++ waitpkgintrin.h (working copy)
@@ -0,0 +1,63 @@
+/* Copyright (C) 2018 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 _X86INTRIN_H_INCLUDED
+# error "Never use <waitpkgintrin.h> directly; include <x86intrin.h> instead."
+#endif
+
+#ifndef _WAITPKG_H_INCLUDED
+#define _WAITPKG_H_INCLUDED
+
+#ifndef __WAITPKG__
+#pragma GCC push_options
+#pragma GCC target("waitpkg")
+#define __DISABLE_WAITPKG__
+#endif /* __WAITPKG__ */
+
+extern __inline void
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_umonitor (void *__A)
+{
+ __builtin_ia32_umonitor (__A);
+}
+
+extern __inline unsigned char
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_umwait (unsigned int __A, unsigned long long __B)
+{
+ return __builtin_ia32_umwait (__A, __B);
+}
+
+extern __inline unsigned char
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_tpause (unsigned int __A, unsigned long long __B)
+{
+ return __builtin_ia32_tpause (__A, __B);
+}
+
+#ifdef __DISABLE_WAITPKG__
+#undef __DISABLE_WAITPKG__
+#pragma GCC pop_options
+#endif /* __DISABLE_WAITPKG__ */
+
+#endif /* _WAITPKG_H_INCLUDED. */
Index: x86intrin.h
===================================================================
--- x86intrin.h (revision 260116)
+++ x86intrin.h (working copy)
@@ -101,6 +101,8 @@
#include <pkuintrin.h>
+#include <waitpkgintrin.h>
+
#endif /* __iamcu__ */
#endif /* _X86INTRIN_H_INCLUDED */
