RE: [PATCH] Initial Granite Rapids D Support

[Liu, Hongtao via Gcc-patches]

> -----Original Message-----
> From: Mo, Zewei <zewei...@intel.com>
> Sent: Thursday, July 6, 2023 2:37 PM
> To: gcc-patches@gcc.gnu.org
> Cc: Liu, Hongtao <hongtao....@intel.com>; ubiz...@gmail.com
> Subject: [PATCH] Initial Granite Rapids D Support
> 
> Hi all,
> 
> This patch is to add initial support for Granite Rapids D for GCC.
> The link of related information is listed below:
> https://www.intel.com/content/www/us/en/develop/download/intel-
> architecture-instruction-set-extensions-programming-reference.html
> 
> Also, the patch of removing AMX-COMPLEX from Granite Rapids will be
> backported to GCC13.
Ok.
> 
> This has been tested on x86_64-pc-linux-gnu. Is this ok for trunk? Thank you.
> 
> Sincerely,
> Zewei Mo
> 
> gcc/ChangeLog:
> 
>       * common/config/i386/cpuinfo.h
>       (get_intel_cpu): Handle Granite Rapids D.
>       * common/config/i386/i386-common.cc:
>       (processor_names): Add graniterapids-d.
>       (processor_alias_table): Ditto.
>       * common/config/i386/i386-cpuinfo.h
>       (enum processor_subtypes): Add INTEL_GRANITERAPIDS_D.
>       * config.gcc: Add -march=graniterapids-d.
>       * config/i386/driver-i386.cc (host_detect_local_cpu):
>       Handle graniterapids-d.
>       * config/i386/i386-c.cc (ix86_target_macros_internal):
>       Ditto.
>       * config/i386/i386-options.cc (m_GRANITERAPIDSD): New.
>       (processor_cost_table): Add graniterapids-d.
>       * config/i386/i386.h (enum processor_type):
>       Add PROCESSOR_GRANITERAPIDS_D.
>       * doc/extend.texi: Add graniterapids-d.
>       * doc/invoke.texi: Ditto.
> 
> gcc/testsuite/ChangeLog:
> 
>       * g++.target/i386/mv16.C: Add graniterapids-d.
>       * gcc.target/i386/funcspec-56.inc: Handle new march.
> ---
>  gcc/common/config/i386/cpuinfo.h              |  9 ++++++++-
>  gcc/common/config/i386/i386-common.cc         |  3 +++
>  gcc/common/config/i386/i386-cpuinfo.h         |  1 +
>  gcc/config.gcc                                |  2 +-
>  gcc/config/i386/driver-i386.cc                |  3 +++
>  gcc/config/i386/i386-c.cc                     |  7 +++++++
>  gcc/config/i386/i386-options.cc               |  4 +++-
>  gcc/config/i386/i386.h                        |  5 ++++-
>  gcc/doc/extend.texi                           |  3 +++
>  gcc/doc/invoke.texi                           | 11 +++++++++++
>  gcc/testsuite/g++.target/i386/mv16.C          |  6 ++++++
>  gcc/testsuite/gcc.target/i386/funcspec-56.inc |  1 +
>  12 files changed, 51 insertions(+), 4 deletions(-)
> 
> diff --git a/gcc/common/config/i386/cpuinfo.h
> b/gcc/common/config/i386/cpuinfo.h
> index ae48bc17771..7c2565c1d93 100644
> --- a/gcc/common/config/i386/cpuinfo.h
> +++ b/gcc/common/config/i386/cpuinfo.h
> @@ -565,7 +565,6 @@ get_intel_cpu (struct __processor_model
> *cpu_model,
>        cpu_model->__cpu_type = INTEL_SIERRAFOREST;
>        break;
>      case 0xad:
> -    case 0xae:
>        /* Granite Rapids.  */
>        cpu = "graniterapids";
>        CHECK___builtin_cpu_is ("corei7"); @@ -573,6 +572,14 @@
> get_intel_cpu (struct __processor_model *cpu_model,
>        cpu_model->__cpu_type = INTEL_COREI7;
>        cpu_model->__cpu_subtype = INTEL_COREI7_GRANITERAPIDS;
>        break;
> +    case 0xae:
> +      /* Granite Rapids D.  */
> +      cpu = "graniterapids-d";
> +      CHECK___builtin_cpu_is ("corei7");
> +      CHECK___builtin_cpu_is ("graniterapids-d");
> +      cpu_model->__cpu_type = INTEL_COREI7;
> +      cpu_model->__cpu_subtype = INTEL_COREI7_GRANITERAPIDS_D;
> +      break;
>      case 0xb6:
>        /* Grand Ridge.  */
>        cpu = "grandridge";
> diff --git a/gcc/common/config/i386/i386-common.cc
> b/gcc/common/config/i386/i386-common.cc
> index bf126f14073..5a337c5b8be 100644
> --- a/gcc/common/config/i386/i386-common.cc
> +++ b/gcc/common/config/i386/i386-common.cc
> @@ -1971,6 +1971,7 @@ const char *const processor_names[] =
>    "alderlake",
>    "rocketlake",
>    "graniterapids",
> +  "graniterapids-d",
>    "intel",
>    "lujiazui",
>    "geode",
> @@ -2094,6 +2095,8 @@ const pta processor_alias_table[] =
>      M_CPU_SUBTYPE (INTEL_COREI7_ALDERLAKE), P_PROC_AVX2},
>    {"graniterapids", PROCESSOR_GRANITERAPIDS, CPU_HASWELL,
> PTA_GRANITERAPIDS,
>      M_CPU_SUBTYPE (INTEL_COREI7_GRANITERAPIDS), P_PROC_AVX512F},
> +  {"graniterapids-d", PROCESSOR_GRANITERAPIDS_D, CPU_HASWELL,
> PTA_GRANITERAPIDS_D,
> +    M_CPU_SUBTYPE (INTEL_COREI7_GRANITERAPIDS_D),
> P_PROC_AVX512F},
>    {"bonnell", PROCESSOR_BONNELL, CPU_ATOM, PTA_BONNELL,
>      M_CPU_TYPE (INTEL_BONNELL), P_PROC_SSSE3},
>    {"atom", PROCESSOR_BONNELL, CPU_ATOM, PTA_BONNELL, diff --git
> a/gcc/common/config/i386/i386-cpuinfo.h b/gcc/common/config/i386/i386-
> cpuinfo.h
> index 2dafbb25a49..254dfec70e5 100644
> --- a/gcc/common/config/i386/i386-cpuinfo.h
> +++ b/gcc/common/config/i386/i386-cpuinfo.h
> @@ -98,6 +98,7 @@ enum processor_subtypes
>    ZHAOXIN_FAM7H_LUJIAZUI,
>    AMDFAM19H_ZNVER4,
>    INTEL_COREI7_GRANITERAPIDS,
> +  INTEL_COREI7_GRANITERAPIDS_D,
>    CPU_SUBTYPE_MAX
>  };
> 
> diff --git a/gcc/config.gcc b/gcc/config.gcc index d88071773c9..1446eb2b3ca
> 100644
> --- a/gcc/config.gcc
> +++ b/gcc/config.gcc
> @@ -682,7 +682,7 @@ silvermont knl knm skylake-avx512 cannonlake
> icelake-client icelake-server \  skylake goldmont goldmont-plus tremont
> cascadelake tigerlake cooperlake \  sapphirerapids alderlake rocketlake
> eden-x2 nano nano-1000 nano-2000 nano-3000 \
>  nano-x2 eden-x4 nano-x4 lujiazui x86-64 x86-64-v2 x86-64-v3 x86-64-v4 \ -
> sierraforest graniterapids grandridge native"
> +sierraforest graniterapids graniterapids-d grandridge native"
> 
>  # Additional x86 processors supported by --with-cpu=.  Each processor  #
> MUST be separated by exactly one space.
> diff --git a/gcc/config/i386/driver-i386.cc b/gcc/config/i386/driver-i386.cc
> index 54c019a7fa3..4c362ffcfa3 100644
> --- a/gcc/config/i386/driver-i386.cc
> +++ b/gcc/config/i386/driver-i386.cc
> @@ -594,6 +594,9 @@ const char *host_detect_local_cpu (int argc, const
> char **argv)
>                 /* Assume Grand Ridge.  */
>                 if (has_feature (FEATURE_RAOINT))
>                   cpu = "grandridge";
> +               /* Assume Granite Rapids D.  */
> +               else if (has_feature (FEATURE_AMX_COMPLEX))
> +                 cpu = "graniterapids-d";
>                 /* Assume Granite Rapids.  */
>                 else if (has_feature (FEATURE_AMX_FP16))
>                   cpu = "graniterapids";
> diff --git a/gcc/config/i386/i386-c.cc b/gcc/config/i386/i386-c.cc index
> e7bd7cc706c..5b886e8a760 100644
> --- a/gcc/config/i386/i386-c.cc
> +++ b/gcc/config/i386/i386-c.cc
> @@ -258,6 +258,10 @@ ix86_target_macros_internal (HOST_WIDE_INT
> isa_flag,
>        def_or_undef (parse_in, "__graniterapids");
>        def_or_undef (parse_in, "__graniterapids__");
>        break;
> +    case PROCESSOR_GRANITERAPIDS_D:
> +      def_or_undef (parse_in, "__graniterapids_d");
> +      def_or_undef (parse_in, "__graniterapids_d__");
> +      break;
>      case PROCESSOR_ALDERLAKE:
>        def_or_undef (parse_in, "__alderlake");
>        def_or_undef (parse_in, "__alderlake__"); @@ -447,6 +451,9 @@
> ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
>      case PROCESSOR_GRANITERAPIDS:
>        def_or_undef (parse_in, "__tune_graniterapids__");
>        break;
> +    case PROCESSOR_GRANITERAPIDS_D:
> +      def_or_undef (parse_in, "__tune_graniterapids_d__");
> +      break;
>      case PROCESSOR_INTEL:
>      case PROCESSOR_GENERIC:
>        break;
> diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
> index 37cb5a0dcc4..553fb5576f3 100644
> --- a/gcc/config/i386/i386-options.cc
> +++ b/gcc/config/i386/i386-options.cc
> @@ -128,10 +128,11 @@ along with GCC; see the file COPYING3.  If not see
> #define m_ALDERLAKE (HOST_WIDE_INT_1U<<PROCESSOR_ALDERLAKE)
>  #define m_ROCKETLAKE (HOST_WIDE_INT_1U<<PROCESSOR_ROCKETLAKE)
>  #define m_GRANITERAPIDS
> (HOST_WIDE_INT_1U<<PROCESSOR_GRANITERAPIDS)
> +#define m_GRANITERAPIDS_D
> (HOST_WIDE_INT_1U<<PROCESSOR_GRANITERAPIDS_D)
>  #define m_CORE_AVX512 (m_SKYLAKE_AVX512 | m_CANNONLAKE \
>                      | m_ICELAKE_CLIENT | m_ICELAKE_SERVER |
> m_CASCADELAKE \
>                      | m_TIGERLAKE | m_COOPERLAKE | m_SAPPHIRERAPIDS
> \
> -                    | m_ROCKETLAKE | m_GRANITERAPIDS)
> +                    | m_ROCKETLAKE | m_GRANITERAPIDS |
> m_GRANITERAPIDS_D)
>  #define m_CORE_AVX2 (m_HASWELL | m_SKYLAKE | m_CORE_AVX512)
> #define m_CORE_ALL (m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE |
> m_CORE_AVX2)  #define m_GOLDMONT
> (HOST_WIDE_INT_1U<<PROCESSOR_GOLDMONT)
> @@ -767,6 +768,7 @@ static const struct processor_costs
> *processor_cost_table[] =
>    &alderlake_cost,
>    &icelake_cost,
>    &icelake_cost,
> +  &icelake_cost,
>    &intel_cost,
>    &lujiazui_cost,
>    &geode_cost,
> diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h index
> 5ac9c78d3ba..3b5fb84b733 100644
> --- a/gcc/config/i386/i386.h
> +++ b/gcc/config/i386/i386.h
> @@ -2233,6 +2233,7 @@ enum processor_type
>    PROCESSOR_ALDERLAKE,
>    PROCESSOR_ROCKETLAKE,
>    PROCESSOR_GRANITERAPIDS,
> +  PROCESSOR_GRANITERAPIDS_D,
>    PROCESSOR_INTEL,
>    PROCESSOR_LUJIAZUI,
>    PROCESSOR_GEODE,
> @@ -2343,7 +2344,9 @@ constexpr wide_int_bitmask PTA_ALDERLAKE =
> PTA_TREMONT | PTA_ADX | PTA_AVX  constexpr wide_int_bitmask
> PTA_SIERRAFOREST = PTA_ALDERLAKE | PTA_AVXIFMA
>    | PTA_AVXVNNIINT8 | PTA_AVXNECONVERT | PTA_CMPCCXADD;
> constexpr wide_int_bitmask PTA_GRANITERAPIDS = PTA_SAPPHIRERAPIDS |
> PTA_AMX_FP16
> -  | PTA_PREFETCHI | PTA_AMX_COMPLEX;
> +  | PTA_PREFETCHI;
> +constexpr wide_int_bitmask PTA_GRANITERAPIDS_D =
> PTA_GRANITERAPIDS
> +  | PTA_AMX_COMPLEX;
>  constexpr wide_int_bitmask PTA_GRANDRIDGE = PTA_SIERRAFOREST |
> PTA_RAOINT;  constexpr wide_int_bitmask PTA_KNM = PTA_KNL |
> PTA_AVX5124VNNIW
>    | PTA_AVX5124FMAPS | PTA_AVX512VPOPCNTDQ; diff --git
> a/gcc/doc/extend.texi b/gcc/doc/extend.texi index
> d1b018ee6d6..17436e4579b 100644
> --- a/gcc/doc/extend.texi
> +++ b/gcc/doc/extend.texi
> @@ -22144,6 +22144,9 @@ Intel Core i7 Rocketlake CPU.
>  @item graniterapids
>  Intel Core i7 graniterapids CPU.
> 
> +@item graniterapids-d
> +Intel Core i7 graniterapids D CPU.
> +
>  @item bonnell
>  Intel Atom Bonnell CPU.
> 
> diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi index
> efcf3bfb3d6..059500f58b4 100644
> --- a/gcc/doc/invoke.texi
> +++ b/gcc/doc/invoke.texi
> @@ -32663,6 +32663,17 @@ MOVDIRI, MOVDIR64B, AVX512VP2INTERSECT,
> ENQCMD, CLDEMOTE, PTWRITE, WAITPKG,  SERIALIZE, TSXLDTRK, UINTR,
> AMX-BF16, AMX-TILE, AMX-INT8, AVX-VNNI, AVX512-FP16,  AVX512BF16,
> AMX-FP16 and PREFETCHI instruction set support.
> 
> +@item graniterapids-d
> +Intel graniterapids D CPU with 64-bit extensions, MOVBE, MMX, SSE,
> +SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX,
> +XSAVE, PCLMUL, FSGSBASE, RDRND, F16C, AVX2, BMI, BMI2, LZCNT, FMA,
> +MOVBE, HLE, RDSEED, ADCX, PREFETCHW, AES, CLFLUSHOPT, XSAVEC,
> XSAVES,
> +SGX, AVX512F, AVX512VL, AVX512BW, AVX512DQ, AVX512CD, PKU,
> AVX512VBMI,
> +AVX512IFMA, SHA, AVX512VNNI, GFNI, VAES, AVX512VBMI2,
> VPCLMULQDQ,
> +AVX512BITALG, RDPID, AVX512VPOPCNTDQ, PCONFIG, WBNOINVD, CLWB,
> MOVDIRI,
> +MOVDIR64B, AVX512VP2INTERSECT, ENQCMD, CLDEMOTE, PTWRITE,
> WAITPKG,
> +SERIALIZE, TSXLDTRK, UINTR, AMX-BF16, AMX-TILE, AMX-INT8, AVX-VNNI,
> AVX512FP16, AVX512BF16, AMX-FP16, PREFETCHI and AMX-COMPLEX
> instruction set support.
> +
>  @item k6
>  AMD K6 CPU with MMX instruction set support.
> 
> diff --git a/gcc/testsuite/g++.target/i386/mv16.C
> b/gcc/testsuite/g++.target/i386/mv16.C
> index 772791b96e8..2158d58a94e 100644
> --- a/gcc/testsuite/g++.target/i386/mv16.C
> +++ b/gcc/testsuite/g++.target/i386/mv16.C
> @@ -104,6 +104,10 @@ int __attribute__ ((target("arch=grandridge"))) foo ()
> {
>    return 27;
>  }
> 
> +int __attribute__ ((target("arch=graniterapids-d"))) foo () {
> +  return 28;
> +}
> +
>  int main ()
>  {
>    int val = foo ();
> @@ -148,6 +152,8 @@ int main ()
>      assert (val == 26);
>    else if (__builtin_cpu_is ("grandridge"))
>      assert (val == 27);
> +  else if (__builtin_cpu_is ("graniterapids-d"))
> +    assert (val == 28);
>    else
>      assert (val == 0);
> 
> diff --git a/gcc/testsuite/gcc.target/i386/funcspec-56.inc
> b/gcc/testsuite/gcc.target/i386/funcspec-56.inc
> index cf2899f9c32..f466962c36c 100644
> --- a/gcc/testsuite/gcc.target/i386/funcspec-56.inc
> +++ b/gcc/testsuite/gcc.target/i386/funcspec-56.inc
> @@ -203,6 +203,7 @@ extern void test_arch_sapphirerapids (void)
>       __attribute__((__target__("arch=sapp
>  extern void test_arch_alderlake (void)
> __attribute__((__target__("arch=alderlake")));
>  extern void test_arch_rocketlake (void)
> __attribute__((__target__("arch=rocketlake")));
>  extern void test_arch_graniterapids (void)
>       __attribute__((__target__("arch=graniterapids")));
> +extern void test_arch_graniterapids_d (void)
>       __attribute__((__target__("arch=graniterapids-d")));
>  extern void test_arch_lujiazui (void)
>       __attribute__((__target__("arch=lujiazui")));
>  extern void test_arch_k8 (void)
>       __attribute__((__target__("arch=k8")));
>  extern void test_arch_k8_sse3 (void)
>       __attribute__((__target__("arch=k8-sse3")));
> --
> 2.31.1