[2/2] Initial Diamond Rapids Support

Message ID 20241101032345.3501979-3-haochen.jiang@intel.com
State Committed
Commit 74ae651bd61a7128c77ca08328956564fd49a23b
Headers
Series Add arch support for Intel CPUs |

Checks

Context Check Description
linaro-tcwg-bot/tcwg_gcc_build--master-arm success Build passed
linaro-tcwg-bot/tcwg_gcc_build--master-aarch64 success Build passed
linaro-tcwg-bot/tcwg_gcc_check--master-aarch64 success Test passed
linaro-tcwg-bot/tcwg_gcc_check--master-arm success Test passed

Commit Message

Jiang, Haochen Nov. 1, 2024, 3:23 a.m. UTC
  gcc/ChangeLog:

	* common/config/i386/cpuinfo.h
	(get_intel_cpu): Handle Diamond Rapids.
	* common/config/i386/i386-common.cc (processor_name):
	Add Diamond Rapids.
	(processor_alias_table): Ditto.
	* common/config/i386/i386-cpuinfo.h (enum processor_types):
	Add INTEL_COREI7_DIAMONDRAPIDS.
	* config.gcc: Add -march=diamondrapids.
	* config/i386/driver-i386.cc (host_detect_local_cpu): Handle
	diamondrapids.
	* config/i386/i386-c.cc (ix86_target_macros_internal): Ditto.
	* config/i386/i386-options.cc (processor_cost_table): Ditto.
	(m_DIAMONDRAPIDS): New.
	(m_CORE_AVX512): Add diamondrapids.
	* config/i386/i386.h (enum processor_type): Ditto.
	* doc/extend.texi: Ditto.
	* doc/invoke.texi: Ditto.

gcc/testsuite/ChangeLog:

	* g++.target/i386/mv16.C: Ditto.
	* gcc.target/i386/funcspec-56.inc: Handle new march.
---
 gcc/common/config/i386/cpuinfo.h              | 16 ++++++++++++++++
 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                |  8 ++++++--
 gcc/config/i386/i386-c.cc                     |  7 +++++++
 gcc/config/i386/i386-options.cc               |  5 ++++-
 gcc/config/i386/i386.h                        | 11 +++++++++++
 gcc/doc/extend.texi                           |  3 +++
 gcc/doc/invoke.texi                           | 14 ++++++++++++++
 gcc/testsuite/g++.target/i386/mv16.C          |  6 ++++++
 gcc/testsuite/gcc.target/i386/funcspec-56.inc |  1 +
 12 files changed, 73 insertions(+), 4 deletions(-)
  

Patch

diff --git a/gcc/common/config/i386/cpuinfo.h b/gcc/common/config/i386/cpuinfo.h
index f415fc92ec4..310eba3ef8c 100644
--- a/gcc/common/config/i386/cpuinfo.h
+++ b/gcc/common/config/i386/cpuinfo.h
@@ -636,6 +636,22 @@  get_intel_cpu (struct __processor_model *cpu_model,
       default:
 	break;
       }
+  /* Parse family and model for family 0x13.  */
+  else if (cpu_model2->__cpu_family == 0x13)
+    switch (cpu_model2->__cpu_model)
+      {
+      case 0x00:
+      case 0x01:
+	/* Diamond Rapids.  */
+	cpu = "diamondrapids";
+	CHECK___builtin_cpu_is ("corei7");
+	CHECK___builtin_cpu_is ("diamondrapids");
+	cpu_model->__cpu_type = INTEL_COREI7;
+	cpu_model->__cpu_subtype = INTEL_COREI7_DIAMONDRAPIDS;
+	break;
+      default:
+	break;
+      }
 
   return cpu;
 }
diff --git a/gcc/common/config/i386/i386-common.cc b/gcc/common/config/i386/i386-common.cc
index b2c2f0bdc11..b044cba758b 100644
--- a/gcc/common/config/i386/i386-common.cc
+++ b/gcc/common/config/i386/i386-common.cc
@@ -2206,6 +2206,7 @@  const char *const processor_names[] =
   "arrowlake",
   "arrowlake-s",
   "pantherlake",
+  "diamondrapids",
   "intel",
   "lujiazui",
   "yongfeng",
@@ -2343,6 +2344,8 @@  const pta processor_alias_table[] =
     M_CPU_SUBTYPE (INTEL_COREI7_ARROWLAKE_S), P_PROC_AVX2},
   {"pantherlake", PROCESSOR_PANTHERLAKE, CPU_HASWELL, PTA_PANTHERLAKE,
     M_CPU_SUBTYPE (INTEL_COREI7_PANTHERLAKE), P_PROC_AVX2},
+  {"diamondrapids", PROCESSOR_DIAMONDRAPIDS, CPU_HASWELL, PTA_DIAMONDRAPIDS,
+    M_CPU_SUBTYPE (INTEL_COREI7_DIAMONDRAPIDS), 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 23c995037ed..4c99b358552 100644
--- a/gcc/common/config/i386/i386-cpuinfo.h
+++ b/gcc/common/config/i386/i386-cpuinfo.h
@@ -105,6 +105,7 @@  enum processor_subtypes
   ZHAOXIN_FAM7H_YONGFENG,
   AMDFAM1AH_ZNVER5,
   ZHAOXIN_FAM7H_SHIJIDADAO,
+  INTEL_COREI7_DIAMONDRAPIDS,
   CPU_SUBTYPE_MAX
 };
 
diff --git a/gcc/config.gcc b/gcc/config.gcc
index 3bdee5bf96f..71d74571672 100644
--- a/gcc/config.gcc
+++ b/gcc/config.gcc
@@ -721,7 +721,7 @@  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 yongfeng shijidadao x86-64 x86-64-v2 \
 x86-64-v3 x86-64-v4 sierraforest graniterapids graniterapids-d grandridge \
-arrowlake arrowlake-s clearwaterforest pantherlake native"
+arrowlake arrowlake-s clearwaterforest pantherlake diamondrapids 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 f0ce017bfdc..a8b02765245 100644
--- a/gcc/config/i386/driver-i386.cc
+++ b/gcc/config/i386/driver-i386.cc
@@ -581,6 +581,7 @@  const char *host_detect_local_cpu (int argc, const char **argv)
 	  processor = PROCESSOR_PENTIUM;
 	  break;
 	case 6:
+	case 19:
 	  processor = PROCESSOR_PENTIUMPRO;
 	  break;
 	case 15:
@@ -623,11 +624,14 @@  const char *host_detect_local_cpu (int argc, const char **argv)
 	{
 	  if (arch)
 	    {
-	      /* This is unknown family 0x6 CPU.  */
+	      /* This is unknown CPU.  */
 	      if (has_feature (FEATURE_AVX512F))
 		{
+		  /* Assume Diamond Rapids.  */
+		  if (has_feature (FEATURE_AVX10_2_512))
+		    cpu = "diamondrapids";
 		  /* Assume Granite Rapids D.  */
-		  if (has_feature (FEATURE_AMX_COMPLEX))
+		  else if (has_feature (FEATURE_AMX_COMPLEX))
 		    cpu = "graniterapids-d";
 		  /* Assume Granite Rapids.  */
 		  else if (has_feature (FEATURE_AMX_FP16))
diff --git a/gcc/config/i386/i386-c.cc b/gcc/config/i386/i386-c.cc
index da60da40205..64b0723d23a 100644
--- a/gcc/config/i386/i386-c.cc
+++ b/gcc/config/i386/i386-c.cc
@@ -291,6 +291,10 @@  ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
       def_or_undef (parse_in, "__pantherlake");
       def_or_undef (parse_in, "__pantherlake__");
       break;
+    case PROCESSOR_DIAMONDRAPIDS:
+      def_or_undef (parse_in, "__diamondrapids");
+      def_or_undef (parse_in, "__diamondrapids__");
+      break;
 
     /* use PROCESSOR_max to not set/unset the arch macro.  */
     case PROCESSOR_max:
@@ -491,6 +495,9 @@  ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
     case PROCESSOR_PANTHERLAKE:
       def_or_undef (parse_in, "__tune_pantherlake__");
       break;
+    case PROCESSOR_DIAMONDRAPIDS:
+      def_or_undef (parse_in, "__tune_diamondrapids__");
+      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 239269ecbdd..603166d249c 100644
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -132,10 +132,12 @@  along with GCC; see the file COPYING3.  If not see
 #define m_ARROWLAKE (HOST_WIDE_INT_1U<<PROCESSOR_ARROWLAKE)
 #define m_ARROWLAKE_S (HOST_WIDE_INT_1U<<PROCESSOR_ARROWLAKE_S)
 #define m_PANTHERLAKE (HOST_WIDE_INT_1U<<PROCESSOR_PANTHERLAKE)
+#define m_DIAMONDRAPIDS (HOST_WIDE_INT_1U<<PROCESSOR_DIAMONDRAPIDS)
 #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_GRANITERAPIDS_D)
+		       | m_ROCKETLAKE | m_GRANITERAPIDS | m_GRANITERAPIDS_D \
+		       | m_DIAMONDRAPIDS)
 #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_CORE_HYBRID (m_ALDERLAKE | m_ARROWLAKE | m_ARROWLAKE_S \
@@ -800,6 +802,7 @@  static const struct processor_costs *processor_cost_table[] =
   &alderlake_cost,
   &alderlake_cost,
   &alderlake_cost,
+  &icelake_cost,
   &intel_cost,
   &lujiazui_cost,
   &yongfeng_cost,
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 3c9e8d86dd5..6282cfcdd2a 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -2311,6 +2311,7 @@  enum processor_type
   PROCESSOR_ARROWLAKE,
   PROCESSOR_ARROWLAKE_S,
   PROCESSOR_PANTHERLAKE,
+  PROCESSOR_DIAMONDRAPIDS,
   PROCESSOR_INTEL,
   PROCESSOR_LUJIAZUI,
   PROCESSOR_YONGFENG,
@@ -2434,6 +2435,16 @@  constexpr wide_int_bitmask PTA_CLEARWATERFOREST = PTA_SIERRAFOREST
   | PTA_AVXVNNIINT16 | PTA_SHA512 | PTA_SM3 | PTA_SM4 | PTA_USER_MSR
   | PTA_PREFETCHI;
 constexpr wide_int_bitmask PTA_PANTHERLAKE = PTA_ARROWLAKE_S | PTA_PREFETCHI;
+constexpr wide_int_bitmask PTA_DIAMONDRAPIDS = PTA_SKYLAKE | PTA_PKU | PTA_SHA
+  | PTA_GFNI | PTA_VAES | PTA_VPCLMULQDQ | PTA_RDPID | PTA_PCONFIG
+  | PTA_WBNOINVD | PTA_CLWB | PTA_MOVDIRI | PTA_MOVDIR64B | PTA_ENQCMD
+  | PTA_CLDEMOTE | PTA_PTWRITE | PTA_WAITPKG | PTA_SERIALIZE | PTA_TSXLDTRK
+  | PTA_AMX_TILE | PTA_AMX_INT8 | PTA_AMX_BF16 | PTA_UINTR | PTA_AVXVNNI
+  | PTA_AMX_FP16 | PTA_PREFETCHI | PTA_AMX_COMPLEX | PTA_AVX10_1_512
+  | PTA_AVXIFMA | PTA_AVXNECONVERT | PTA_AVXVNNIINT16 | PTA_AVXVNNIINT8
+  | PTA_CMPCCXADD | PTA_SHA512 | PTA_SM3 | PTA_SM4 | PTA_AVX10_2_512
+  | PTA_APX_F | PTA_AMX_AVX512 | PTA_AMX_FP8 | PTA_AMX_TF32 | PTA_AMX_TRANSPOSE
+  | PTA_MOVRS | PTA_AMX_MOVRS | PTA_USER_MSR;
 
 constexpr wide_int_bitmask PTA_BDVER1 = PTA_64BIT | PTA_MMX | PTA_SSE
   | PTA_SSE2 | PTA_SSE3 | PTA_SSE4A | PTA_CX16 | PTA_ABM | PTA_SSSE3
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index df71675a1c7..ed0d0af3ffe 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -26607,6 +26607,9 @@  Intel Core i7 Arrow Lake S CPU.
 @item pantherlake
 Intel Core i7 Panther Lake CPU.
 
+@item diamondrapids
+Intel Core i7 Diamond Rapids CPU.
+
 @item bonnell
 Intel Atom Bonnell CPU.
 
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 709b0814d4d..33465637774 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -34620,6 +34620,20 @@  MOVDIRI, MOVDIR64B, 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 diamondrapids
+Intel Diamond Rapids 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, ENQCMD, CLDEMOTE, PTWRITE, WAITPKG, SERIALIZE, TSXLDTRK,
+UINTR, AMX-BF16, AMX-TILE, AMX-INT8, AVX-VNNI, AVX512FP16, AVX512BF16, AMX-FP16,
+PREFETCHI, AMX-COMPLEX, AVX10.1-512, AVX-IFMA, AVX-NE-CONVERT, AVX-VNNI-INT16,
+AVX-VNNI-INT8, CMPccXADD, SHA512, SM3, SM4, AVX10.2-512, APX_F, AMX-AVX512,
+AMX-FP8, AMX-TF32, AMX-TRANSPOSE, MOVRS, AMX-MOVRS and USER_MSR instruction set
+support.
+
 @item bonnell
 @itemx atom
 Intel Bonnell CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3 and SSSE3
diff --git a/gcc/testsuite/g++.target/i386/mv16.C b/gcc/testsuite/g++.target/i386/mv16.C
index ef47831f93c..75198f54ab9 100644
--- a/gcc/testsuite/g++.target/i386/mv16.C
+++ b/gcc/testsuite/g++.target/i386/mv16.C
@@ -124,6 +124,10 @@  int __attribute__ ((target("arch=pantherlake"))) foo () {
   return 32;
 }
 
+int __attribute__ ((target("arch=diamondrapids"))) foo () {
+  return 33;
+}
+
 int main ()
 {
   int val = foo ();
@@ -178,6 +182,8 @@  int main ()
     assert (val == 31);
   else if (__builtin_cpu_is ("pantherlake"))
     assert (val == 32);
+  else if (__builtin_cpu_is ("diamondrapids"))
+    assert (val == 33);
   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 09276ad45d9..ac663a70e2e 100644
--- a/gcc/testsuite/gcc.target/i386/funcspec-56.inc
+++ b/gcc/testsuite/gcc.target/i386/funcspec-56.inc
@@ -220,6 +220,7 @@  extern void test_arch_graniterapids_d (void)	__attribute__((__target__("arch=gra
 extern void test_arch_arrowlake (void)		__attribute__((__target__("arch=arrowlake")));
 extern void test_arch_arrowlake_s (void)	__attribute__((__target__("arch=arrowlake-s")));
 extern void test_arch_pantherlake (void)	__attribute__((__target__("arch=pantherlake")));
+extern void test_arch_diamondrapids (void)	__attribute__((__target__("arch=diamondrapids")));
 extern void test_arch_lujiazui (void)		__attribute__((__target__("arch=lujiazui")));
 extern void test_arch_yongfeng (void)		__attribute__((__target__("arch=yongfeng")));
 extern void test_arch_shijidadao (void)		__attribute__((__target__("arch=shijidadao")));