gcc/0077-Initial-Granite-Rapids-Support.patch

From 7f0f8b585cf60b4c09bca42b5339995c2cc74633 Mon Sep 17 00:00:00 2001
From: Haochen Jiang <haochen.jiang@intel.com>
Date: Mon, 7 Nov 2022 11:04:57 +0800
Subject: [PATCH 22/32] Initial Granite Rapids Support

gcc/ChangeLog:

	* common/config/i386/cpuinfo.h
	(get_intel_cpu): Handle Granite Rapids.
	* common/config/i386/i386-common.cc:
	(processor_names): Add graniterapids.
	(processor_alias_table): Ditto.
	* common/config/i386/i386-cpuinfo.h
	(enum processor_subtypes): Add INTEL_GRANTIERAPIDS.
	* config.gcc: Add -march=graniterapids.
	* config/i386/driver-i386.cc (host_detect_local_cpu):
	Handle graniterapids.
	* config/i386/i386-c.cc (ix86_target_macros_internal):
	Ditto.
	* config/i386/i386-options.cc (m_GRANITERAPIDS): New.
	(processor_cost_table): Add graniterapids.
	* config/i386/i386.h (enum processor_type):
	Add PROCESSOR_GRANITERAPIDS.
	(PTA_GRANITERAPIDS): Ditto.
	* doc/extend.texi: Add graniterapids.
	* doc/invoke.texi: Ditto.

gcc/testsuite/ChangeLog:

	* g++.target/i386/mv16.C: Add graniterapids.
	* gcc.target/i386/funcspec-56.inc: Handle new march.

(cherry picked from commit 339ffc5a792dd66647392a235f2f7f6344c5359e)
---
 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                |  5 ++++-
 gcc/config/i386/i386-c.cc                     |  7 +++++++
 gcc/config/i386/i386-options.cc               |  4 +++-
 gcc/config/i386/i386.h                        |  3 +++
 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, 52 insertions(+), 3 deletions(-)

diff --git a/gcc/common/config/i386/cpuinfo.h b/gcc/common/config/i386/cpuinfo.h
index f17e88144..1f75ff1ca 100644
--- a/gcc/common/config/i386/cpuinfo.h
+++ b/gcc/common/config/i386/cpuinfo.h
@@ -528,6 +528,15 @@ get_intel_cpu (struct __processor_model *cpu_model,
       cpu_model->__cpu_type = INTEL_COREI7;
       cpu_model->__cpu_subtype = INTEL_COREI7_SAPPHIRERAPIDS;
       break;
+    case 0xad:
+    case 0xae:
+      /* Granite Rapids.  */
+      cpu = "graniterapids";
+      CHECK___builtin_cpu_is ("corei7");
+      CHECK___builtin_cpu_is ("graniterapids");
+      cpu_model->__cpu_type = INTEL_COREI7;
+      cpu_model->__cpu_subtype = INTEL_COREI7_GRANITERAPIDS;
+      break;
     case 0x17:
     case 0x1d:
       /* Penryn.  */
diff --git a/gcc/common/config/i386/i386-common.cc b/gcc/common/config/i386/i386-common.cc
index c8cf532cf..1aa163463 100644
--- a/gcc/common/config/i386/i386-common.cc
+++ b/gcc/common/config/i386/i386-common.cc
@@ -1855,6 +1855,7 @@ const char *const processor_names[] =
   "sapphirerapids",
   "alderlake",
   "rocketlake",
+  "graniterapids",
   "intel",
   "geode",
   "k6",
@@ -1973,6 +1974,8 @@ const pta processor_alias_table[] =
     M_CPU_SUBTYPE (INTEL_COREI7_ALDERLAKE), P_PROC_AVX2},
   {"meteorlake", PROCESSOR_ALDERLAKE, CPU_HASWELL, PTA_ALDERLAKE,
     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},
   {"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 95b078acf..7b2d4d242 100644
--- a/gcc/common/config/i386/i386-cpuinfo.h
+++ b/gcc/common/config/i386/i386-cpuinfo.h
@@ -92,6 +92,7 @@ enum processor_subtypes
   AMDFAM19H_ZNVER3,
   INTEL_COREI7_ROCKETLAKE,
   AMDFAM19H_ZNVER4,
+  INTEL_COREI7_GRANITERAPIDS,
   CPU_SUBTYPE_MAX
 };
 
diff --git a/gcc/config.gcc b/gcc/config.gcc
index 81012c651..9bad238e3 100644
--- a/gcc/config.gcc
+++ b/gcc/config.gcc
@@ -670,7 +670,7 @@ slm nehalem westmere sandybridge ivybridge haswell broadwell bonnell \
 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 x86-64 x86-64-v2 x86-64-v3 x86-64-v4 native"
+nano-x2 eden-x4 nano-x4 x86-64 x86-64-v2 x86-64-v3 x86-64-v4 graniterapids 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 3b5161aed..ea8c3d8d1 100644
--- a/gcc/config/i386/driver-i386.cc
+++ b/gcc/config/i386/driver-i386.cc
@@ -576,8 +576,11 @@ const char *host_detect_local_cpu (int argc, const char **argv)
 	      /* This is unknown family 0x6 CPU.  */
 	      if (has_feature (FEATURE_AVX))
 		{
+		  /* Assume Granite Rapids.  */
+		  if (has_feature (FEATURE_AMX_FP16))
+		    cpu = "graniterapids";
 		  /* Assume Tiger Lake */
-		  if (has_feature (FEATURE_AVX512VP2INTERSECT))
+		  else if (has_feature (FEATURE_AVX512VP2INTERSECT))
 		    cpu = "tigerlake";
 		  /* Assume Sapphire Rapids.  */
 		  else if (has_feature (FEATURE_TSXLDTRK))
diff --git a/gcc/config/i386/i386-c.cc b/gcc/config/i386/i386-c.cc
index 00880bd17..04f1dd682 100644
--- a/gcc/config/i386/i386-c.cc
+++ b/gcc/config/i386/i386-c.cc
@@ -242,6 +242,10 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
       def_or_undef (parse_in, "__sapphirerapids");
       def_or_undef (parse_in, "__sapphirerapids__");
       break;
+    case PROCESSOR_GRANITERAPIDS:
+      def_or_undef (parse_in, "__graniterapids");
+      def_or_undef (parse_in, "__graniterapids__");
+      break;
     case PROCESSOR_ALDERLAKE:
       def_or_undef (parse_in, "__alderlake");
       def_or_undef (parse_in, "__alderlake__");
@@ -419,6 +423,9 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
     case PROCESSOR_ROCKETLAKE:
       def_or_undef (parse_in, "__tune_rocketlake__");
       break;
+    case PROCESSOR_GRANITERAPIDS:
+      def_or_undef (parse_in, "__tune_graniterapids__");
+      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 724375f02..6645e3259 100644
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -127,10 +127,11 @@ along with GCC; see the file COPYING3.  If not see
 #define m_SAPPHIRERAPIDS (HOST_WIDE_INT_1U<<PROCESSOR_SAPPHIRERAPIDS)
 #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_CORE_AVX512 (m_SKYLAKE_AVX512 | m_CANNONLAKE \
 		       | m_ICELAKE_CLIENT | m_ICELAKE_SERVER | m_CASCADELAKE \
 		       | m_TIGERLAKE | m_COOPERLAKE | m_SAPPHIRERAPIDS \
-		       | m_ROCKETLAKE)
+		       | m_ROCKETLAKE | m_GRANITERAPIDS)
 #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)
@@ -761,6 +762,7 @@ static const struct processor_costs *processor_cost_table[] =
   &icelake_cost,
   &alderlake_cost,
   &icelake_cost,
+  &icelake_cost,
   &intel_cost,
   &geode_cost,
   &k6_cost,
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index aaa136ba0..75953defc 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -2250,6 +2250,7 @@ enum processor_type
   PROCESSOR_SAPPHIRERAPIDS,
   PROCESSOR_ALDERLAKE,
   PROCESSOR_ROCKETLAKE,
+  PROCESSOR_GRANITERAPIDS,
   PROCESSOR_INTEL,
   PROCESSOR_GEODE,
   PROCESSOR_K6,
@@ -2356,6 +2357,8 @@ constexpr wide_int_bitmask PTA_ALDERLAKE = PTA_TREMONT | PTA_ADX | PTA_AVX
   | PTA_AVX2 | PTA_BMI | PTA_BMI2 | PTA_F16C | PTA_FMA | PTA_LZCNT
   | PTA_PCONFIG | PTA_PKU | PTA_VAES | PTA_VPCLMULQDQ | PTA_SERIALIZE
   | PTA_HRESET | PTA_KL | PTA_WIDEKL | PTA_AVXVNNI;
+constexpr wide_int_bitmask PTA_GRANITERAPIDS = PTA_SAPPHIRERAPIDS | PTA_AMX_FP16
+  | PTA_PREFETCHI;
 constexpr wide_int_bitmask PTA_KNM = PTA_KNL | PTA_AVX5124VNNIW
   | PTA_AVX5124FMAPS | PTA_AVX512VPOPCNTDQ;
 constexpr wide_int_bitmask PTA_ZNVER1 = PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index cb987f469..ba9faf4b2 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -21829,6 +21829,9 @@ Intel Core i7 Alderlake CPU.
 @item rocketlake
 Intel Core i7 Rocketlake CPU.
 
+@item graniterapids
+Intel Core i7 graniterapids CPU.
+
 @item bonnell
 Intel Atom Bonnell CPU.
 
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 211b970c0..8ca831dc1 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -31615,6 +31615,17 @@ CLFLUSHOPT, XSAVEC, XSAVES, AVX512F, AVX512VL, AVX512BW, AVX512DQ, AVX512CD
 PKU, AVX512VBMI, AVX512IFMA, SHA, AVX512VNNI, GFNI, VAES, AVX512VBMI2,
 VPCLMULQDQ, AVX512BITALG, RDPID and AVX512VPOPCNTDQ instruction set support.
 
+@item graniterapids
+Intel graniterapids 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 and PREFETCHI 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 683928729..65cc24f32 100644
--- a/gcc/testsuite/g++.target/i386/mv16.C
+++ b/gcc/testsuite/g++.target/i386/mv16.C
@@ -92,6 +92,10 @@ int __attribute__ ((target("arch=rocketlake"))) foo () {
   return 24;
 }
 
+int __attribute__ ((target("arch=graniterapids"))) foo () {
+  return 26;
+}
+
 int main ()
 {
   int val = foo ();
@@ -130,6 +134,8 @@ int main ()
     assert (val == 23);
   else if (__builtin_cpu_is ("rocketlake"))
     assert (val == 24);
+  else if (__builtin_cpu_is ("graniterapids"))
+    assert (val == 25);
   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 9f073f78c..bdcfdbc88 100644
--- a/gcc/testsuite/gcc.target/i386/funcspec-56.inc
+++ b/gcc/testsuite/gcc.target/i386/funcspec-56.inc
@@ -188,6 +188,7 @@ extern void test_arch_cooperlake (void)         __attribute__((__target__("arch=
 extern void test_arch_sapphirerapids (void)	__attribute__((__target__("arch=sapphirerapids")));
 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_k8 (void)			__attribute__((__target__("arch=k8")));
 extern void test_arch_k8_sse3 (void)		__attribute__((__target__("arch=k8-sse3")));
 extern void test_arch_opteron (void)		__attribute__((__target__("arch=opteron")));
-- 
2.28.0.windows.1