public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
* [PATCH 0/2] Intel Grand Ridge Support
@ 2022-11-07  1:41 Haochen Jiang
  2022-11-07  1:41 ` [PATCH 1/2] Initial Grand Ridge support Haochen Jiang
  2022-11-07  1:41 ` [PATCH 2/2] Add m_CORE_ATOM for atom cores Haochen Jiang
  0 siblings, 2 replies; 5+ messages in thread
From: Haochen Jiang @ 2022-11-07  1:41 UTC (permalink / raw)
  To: gcc-patches; +Cc: ubizjak, hongtao.liu

Hi all,

These patches aimed to add initial Granite Rapids support for GCC.
Also we added a new m_CORE_ATOM for future atom core tune. They need
to be checked in after RAO-INT patch.

The information for Granite Rapids comes following:
https://www.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html

Regtested on x86_64-pc-linux-gnu. Ok for trunk?

BRs,
Haochen



^ permalink raw reply	[flat|nested] 5+ messages in thread

* [PATCH 1/2] Initial Grand Ridge support
  2022-11-07  1:41 [PATCH 0/2] Intel Grand Ridge Support Haochen Jiang
@ 2022-11-07  1:41 ` Haochen Jiang
  2022-11-07  2:08   ` Hongtao Liu
  2022-11-07  1:41 ` [PATCH 2/2] Add m_CORE_ATOM for atom cores Haochen Jiang
  1 sibling, 1 reply; 5+ messages in thread
From: Haochen Jiang @ 2022-11-07  1:41 UTC (permalink / raw)
  To: gcc-patches; +Cc: ubizjak, hongtao.liu

gcc/ChangeLog:

	* common/config/i386/i386-common.cc
	(processor_names): Add grandridge.
	(processor_alias_table): Ditto.
	* common/config/i386/i386-cpuinfo.h:
	(enum processor_types): Add INTEL_GRANDRIDGE.
	* config.gcc: Add -march=grandridge.
	* config/i386/driver-i386.cc (host_detect_local_cpu):
	Handle grandridge.
	* config/i386/i386-c.cc (ix86_target_macros_internal):
	Ditto.
	* config/i386/i386-options.cc (m_GRANDRIDGE): New define.
	(processor_cost_table): Add grandridge.
	* config/i386/i386.h (enum processor_type):
	Add PROCESSOR_GRANDRIDGE.
	(PTA_GRANDRIDGE): Ditto.
	* doc/extend.texi: Add grandridge.
	* doc/invoke.texi: Ditto.

gcc/testsuite/ChangeLog:

	* gcc/testsuite/g++.target/i386/mv16.C: Add grandridge.
	* gcc.target/i386/funcspec-56.inc: Handle new march.
---
 gcc/common/config/i386/cpuinfo.h              | 6 ++++++
 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               | 2 ++
 gcc/config/i386/i386.h                        | 2 ++
 gcc/doc/extend.texi                           | 3 +++
 gcc/doc/invoke.texi                           | 9 +++++++++
 gcc/testsuite/g++.target/i386/mv16.C          | 6 ++++++
 gcc/testsuite/gcc.target/i386/funcspec-56.inc | 1 +
 12 files changed, 45 insertions(+), 2 deletions(-)

diff --git a/gcc/common/config/i386/cpuinfo.h b/gcc/common/config/i386/cpuinfo.h
index df3500adc83..4d1bcffb978 100644
--- a/gcc/common/config/i386/cpuinfo.h
+++ b/gcc/common/config/i386/cpuinfo.h
@@ -573,6 +573,12 @@ get_intel_cpu (struct __processor_model *cpu_model,
       cpu_model->__cpu_type = INTEL_COREI7;
       cpu_model->__cpu_subtype = INTEL_COREI7_GRANITERAPIDS;
       break;
+    case 0xb6:
+      /* Grand Ridge.  */
+      cpu = "grandridge";
+      CHECK___builtin_cpu_is ("grandridge");
+      cpu_model->__cpu_type = INTEL_GRANDRIDGE;
+      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 60a193a651c..431fd0d3ad1 100644
--- a/gcc/common/config/i386/i386-common.cc
+++ b/gcc/common/config/i386/i386-common.cc
@@ -1920,6 +1920,7 @@ const char *const processor_names[] =
   "goldmont-plus",
   "tremont",
   "sierraforest",
+  "grandridge",
   "knl",
   "knm",
   "skylake",
@@ -2071,6 +2072,8 @@ const pta processor_alias_table[] =
     M_CPU_TYPE (INTEL_TREMONT), P_PROC_SSE4_2},
   {"sierraforest", PROCESSOR_SIERRAFOREST, CPU_HASWELL, PTA_SIERRAFOREST,
     M_CPU_SUBTYPE (INTEL_SIERRAFOREST), P_PROC_AVX2},
+  {"grandridge", PROCESSOR_GRANDRIDGE, CPU_HASWELL, PTA_GRANDRIDGE,
+    M_CPU_TYPE (INTEL_GRANDRIDGE), P_PROC_AVX2},
   {"knl", PROCESSOR_KNL, CPU_SLM, PTA_KNL,
     M_CPU_TYPE (INTEL_KNL), P_PROC_AVX512F},
   {"knm", PROCESSOR_KNM, CPU_SLM, PTA_KNM,
diff --git a/gcc/common/config/i386/i386-cpuinfo.h b/gcc/common/config/i386/i386-cpuinfo.h
index 345fda648ff..fe2e9e21fd2 100644
--- a/gcc/common/config/i386/i386-cpuinfo.h
+++ b/gcc/common/config/i386/i386-cpuinfo.h
@@ -61,6 +61,7 @@ enum processor_types
   AMDFAM19H,
   ZHAOXIN_FAM7H,
   INTEL_SIERRAFOREST,
+  INTEL_GRANDRIDGE,
   CPU_TYPE_MAX,
   BUILTIN_CPU_TYPE_MAX = CPU_TYPE_MAX
 };
diff --git a/gcc/config.gcc b/gcc/config.gcc
index 84c040746dc..b5eda046033 100644
--- a/gcc/config.gcc
+++ b/gcc/config.gcc
@@ -669,7 +669,7 @@ 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 native"
+sierraforest graniterapids 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 3117d83de00..95c16c23c7f 100644
--- a/gcc/config/i386/driver-i386.cc
+++ b/gcc/config/i386/driver-i386.cc
@@ -591,8 +591,11 @@ const char *host_detect_local_cpu (int argc, const char **argv)
 	      /* This is unknown family 0x6 CPU.  */
 	      if (has_feature (FEATURE_AVX))
 		{
+		  /* Assume Grand Ridge.  */
+		  if (has_feature (FEATURE_RAOINT))
+		    cpu = "grandridge";
 		  /* Assume Granite Rapids.  */
-		  if (has_feature (FEATURE_AMX_FP16))
+		  else if (has_feature (FEATURE_AMX_FP16))
 		    cpu = "graniterapids";
 		  /* Assume Sierra Forest.  */
 		  else if (has_feature (FEATURE_AVXVNNIINT8))
diff --git a/gcc/config/i386/i386-c.cc b/gcc/config/i386/i386-c.cc
index a877d24148d..44fab6e80ae 100644
--- a/gcc/config/i386/i386-c.cc
+++ b/gcc/config/i386/i386-c.cc
@@ -206,6 +206,10 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
       def_or_undef (parse_in, "__sierraforest");
       def_or_undef (parse_in, "__sierraforest__");
       break;
+    case PROCESSOR_GRANDRIDGE:
+      def_or_undef (parse_in, "__grandridge");
+      def_or_undef (parse_in, "__grandridge__");
+      break;
     case PROCESSOR_KNL:
       def_or_undef (parse_in, "__knl");
       def_or_undef (parse_in, "__knl__");
@@ -395,6 +399,9 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
     case PROCESSOR_SIERRAFOREST:
       def_or_undef (parse_in, "__tune_sierraforest__");
       break;
+    case PROCESSOR_GRANDRIDGE:
+      def_or_undef (parse_in, "__tune_grandridge__");
+      break;
     case PROCESSOR_KNL:
       def_or_undef (parse_in, "__tune_knl__");
       break;
diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
index 3c7570c5edd..23ab1f867d0 100644
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -138,6 +138,7 @@ along with GCC; see the file COPYING3.  If not see
 #define m_GOLDMONT_PLUS (HOST_WIDE_INT_1U<<PROCESSOR_GOLDMONT_PLUS)
 #define m_TREMONT (HOST_WIDE_INT_1U<<PROCESSOR_TREMONT)
 #define m_SIERRAFOREST (HOST_WIDE_INT_1U<<PROCESSOR_SIERRAFOREST)
+#define m_GRANDRIDGE (HOST_WIDE_INT_1U<<PROCESSOR_GRANDRIDGE)
 #define m_INTEL (HOST_WIDE_INT_1U<<PROCESSOR_INTEL)
 
 #define m_LUJIAZUI (HOST_WIDE_INT_1U<<PROCESSOR_LUJIAZUI)
@@ -750,6 +751,7 @@ static const struct processor_costs *processor_cost_table[] =
   &slm_cost,
   &tremont_cost,
   &alderlake_cost,
+  &alderlake_cost,
   &slm_cost,
   &slm_cost,
   &skylake_cost,
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index e3e675d36c5..b32db8da109 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -2226,6 +2226,7 @@ enum processor_type
   PROCESSOR_GOLDMONT_PLUS,
   PROCESSOR_TREMONT,
   PROCESSOR_SIERRAFOREST,
+  PROCESSOR_GRANDRIDGE,
   PROCESSOR_KNL,
   PROCESSOR_KNM,
   PROCESSOR_SKYLAKE,
@@ -2351,6 +2352,7 @@ 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;
+constexpr wide_int_bitmask PTA_GRANDRIDGE = PTA_SIERRAFOREST | PTA_RAOINT;
 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 33a49338bd3..8da0db9770d 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -21986,6 +21986,9 @@ Intel Atom Tremont CPU.
 @item sierraforest
 Intel Atom Sierra Forest CPU.
 
+@item grandridge
+Intel Atom Grand Ridge CPU.
+
 @item knl
 Intel Knights Landing CPU.
 
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 7417f528bb1..f9cd41fac28 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -32080,6 +32080,15 @@ MOVDIR64B, CLDEMOTE, WAITPKG, ADCX, AVX, AVX2, BMI, BMI2, F16C, FMA, LZCNT,
 PCONFIG, PKU, VAES, VPCLMULQDQ, SERIALIZE, HRESET, KL, WIDEKL, AVX-VNNI,
 AVXIFMA, AVXVNNIINT8, AVXNECONVERT and CMPCCXADD instruction set support.
 
+@item grandridge
+Intel Grand Ridge CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3,
+SSSE3, SSE4.1, SSE4.2, POPCNT, AES, PREFETCHW, PCLMUL, RDRND, XSAVE, XSAVEC,
+XSAVES, XSAVEOPT, FSGSBASE, PTWRITE, RDPID, SGX, GFNI-SSE, CLWB, MOVDIRI,
+MOVDIR64B, CLDEMOTE, WAITPKG, ADCX, AVX, AVX2, BMI, BMI2, F16C, FMA, LZCNT,
+PCONFIG, PKU, VAES, VPCLMULQDQ, SERIALIZE, HRESET, KL, WIDEKL, AVX-VNNI,
+AVXIFMA, AVXVNNIINT8, AVXNECONVERT, CMPCCXADD and RAOINT instruction set
+support.
+
 @item knl
 Intel Knight's Landing CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3,
 SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE,
diff --git a/gcc/testsuite/g++.target/i386/mv16.C b/gcc/testsuite/g++.target/i386/mv16.C
index e0e0f153d1c..772791b96e8 100644
--- a/gcc/testsuite/g++.target/i386/mv16.C
+++ b/gcc/testsuite/g++.target/i386/mv16.C
@@ -100,6 +100,10 @@ int __attribute__ ((target("arch=graniterapids"))) foo () {
   return 26;
 }
 
+int __attribute__ ((target("arch=grandridge"))) foo () {
+  return 27;
+}
+
 int main ()
 {
   int val = foo ();
@@ -142,6 +146,8 @@ int main ()
     assert (val == 25);
   else if (__builtin_cpu_is ("graniterapids"))
     assert (val == 26);
+  else if (__builtin_cpu_is ("grandridge"))
+    assert (val == 27);
   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 7eb18c6952d..37802307bcf 100644
--- a/gcc/testsuite/gcc.target/i386/funcspec-56.inc
+++ b/gcc/testsuite/gcc.target/i386/funcspec-56.inc
@@ -186,6 +186,7 @@ extern void test_arch_goldmont (void)		__attribute__((__target__("arch=goldmont"
 extern void test_arch_goldmont_plus (void)	__attribute__((__target__("arch=goldmont-plus")));
 extern void test_arch_tremont (void)		__attribute__((__target__("arch=tremont")));
 extern void test_arch_sierraforest (void)       __attribute__((__target__("arch=sierraforest")));
+extern void test_arch_grandridge (void)		__attribute__((__target__("arch=grandridge")));
 extern void test_arch_knl (void)		__attribute__((__target__("arch=knl")));
 extern void test_arch_knm (void)		__attribute__((__target__("arch=knm")));
 extern void test_arch_skylake (void)		__attribute__((__target__("arch=skylake")));
-- 
2.18.1


^ permalink raw reply	[flat|nested] 5+ messages in thread

* [PATCH 2/2] Add m_CORE_ATOM for atom cores
  2022-11-07  1:41 [PATCH 0/2] Intel Grand Ridge Support Haochen Jiang
  2022-11-07  1:41 ` [PATCH 1/2] Initial Grand Ridge support Haochen Jiang
@ 2022-11-07  1:41 ` Haochen Jiang
  2022-11-07  9:13   ` Uros Bizjak
  1 sibling, 1 reply; 5+ messages in thread
From: Haochen Jiang @ 2022-11-07  1:41 UTC (permalink / raw)
  To: gcc-patches; +Cc: ubizjak, hongtao.liu

gcc/ChangeLog:

	* config/i386/i386-options.cc (m_CORE_ATOM): New.
	* config/i386/x86-tune.def
	(X86_TUNE_SCHEDULE): Initial tune for CORE_ATOM.
	(X86_TUNE_PARTIAL_REG_DEPENDENCY): Ditto.
	(X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY): Ditto.
	(X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY): Ditto.
	(X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY): Ditto.
	(X86_TUNE_DEST_FALSE_DEP_FOR_GLC): Ditto.
	(X86_TUNE_MEMORY_MISMATCH_STALL): Ditto.
	(X86_TUNE_USE_LEAVE): Ditto.
	(X86_TUNE_PUSH_MEMORY): Ditto.
	(X86_TUNE_USE_INCDEC): Ditto.
	(X86_TUNE_INTEGER_DFMODE_MOVES): Ditto.
	(X86_TUNE_PREFER_KNOWN_REP_MOVSB_STOSB): Ditto.
	(X86_TUNE_MISALIGNED_MOVE_STRING_PRO_EPILOGUES): Ditto.
	(X86_TUNE_USE_SAHF): Ditto.
	(X86_TUNE_USE_BT): Ditto.
	(X86_TUNE_AVOID_FALSE_DEP_FOR_BMI): Ditto.
	(X86_TUNE_ONE_IF_CONV_INSN): Ditto.
	(X86_TUNE_AVOID_MFENCE): Ditto.
	(X86_TUNE_USE_SIMODE_FIOP): Ditto.
	(X86_TUNE_EXT_80387_CONSTANTS): Ditto.
	(X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL): Ditto.
	(X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL): Ditto.
	(X86_TUNE_SSE_TYPELESS_STORES): Ditto.
	(X86_TUNE_SSE_LOAD0_BY_PXOR): Ditto.
	(X86_TUNE_AVOID_4BYTE_PREFIXES): Ditto.
	(X86_TUNE_USE_GATHER_2PARTS): Ditto.
	(X86_TUNE_USE_GATHER_4PARTS): Ditto.
	(X86_TUNE_USE_GATHER): Ditto.
---
 gcc/config/i386/i386-options.cc |  1 +
 gcc/config/i386/x86-tune.def    | 71 +++++++++++++++++++--------------
 2 files changed, 41 insertions(+), 31 deletions(-)

diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
index 23ab1f867d0..e5c77f3a84d 100644
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -139,6 +139,7 @@ along with GCC; see the file COPYING3.  If not see
 #define m_TREMONT (HOST_WIDE_INT_1U<<PROCESSOR_TREMONT)
 #define m_SIERRAFOREST (HOST_WIDE_INT_1U<<PROCESSOR_SIERRAFOREST)
 #define m_GRANDRIDGE (HOST_WIDE_INT_1U<<PROCESSOR_GRANDRIDGE)
+#define m_CORE_ATOM (m_SIERRAFOREST | m_GRANDRIDGE)
 #define m_INTEL (HOST_WIDE_INT_1U<<PROCESSOR_INTEL)
 
 #define m_LUJIAZUI (HOST_WIDE_INT_1U<<PROCESSOR_LUJIAZUI)
diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index 540e45d02f9..58e29e7806a 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -42,7 +42,8 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 DEF_TUNE (X86_TUNE_SCHEDULE, "schedule",
           m_PENT | m_LAKEMONT | m_PPRO | m_CORE_ALL | m_BONNELL | m_SILVERMONT
 	  | m_INTEL | m_KNL | m_KNM | m_K6_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI
-     | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_GENERIC)
+	  | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM
+	  | m_GENERIC)
 
 /* X86_TUNE_PARTIAL_REG_DEPENDENCY: Enable more register renaming
    on modern chips.  Prefer stores affecting whole integer register
@@ -52,7 +53,7 @@ DEF_TUNE (X86_TUNE_PARTIAL_REG_DEPENDENCY, "partial_reg_dependency",
           m_P4_NOCONA | m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE | m_CORE_AVX2
 	  | m_BONNELL | m_SILVERMONT | m_GOLDMONT | m_GOLDMONT_PLUS | m_INTEL
 	  | m_KNL | m_KNM | m_AMD_MULTIPLE | m_LUJIAZUI | m_TREMONT
-	  | m_ALDERLAKE | m_GENERIC)
+	  | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY: This knob promotes all store
    destinations to be 128bit to allow register renaming on 128bit SSE units,
@@ -63,7 +64,7 @@ DEF_TUNE (X86_TUNE_PARTIAL_REG_DEPENDENCY, "partial_reg_dependency",
 DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY, "sse_partial_reg_dependency",
           m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_AMDFAM10
 	  | m_BDVER | m_ZNVER | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE
-	  | m_GENERIC)
+	  | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY: This knob avoids
    partial write to the destination in scalar SSE conversion from FP
@@ -71,20 +72,23 @@ DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY, "sse_partial_reg_dependency",
 DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY,
 	  "sse_partial_reg_fp_converts_dependency",
 	  m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_AMDFAM10
-	  | m_BDVER | m_ZNVER | m_LUJIAZUI | m_ALDERLAKE | m_GENERIC)
+	  | m_BDVER | m_ZNVER | m_LUJIAZUI | m_ALDERLAKE | m_CORE_ATOM
+	  | m_GENERIC)
 
 /* X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY: This knob avoids partial
    write to the destination in scalar SSE conversion from integer to FP.  */
 DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY,
 	  "sse_partial_reg_converts_dependency",
 	  m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_AMDFAM10
-	  | m_BDVER | m_ZNVER | m_LUJIAZUI | m_ALDERLAKE | m_GENERIC)
+	  | m_BDVER | m_ZNVER | m_LUJIAZUI | m_ALDERLAKE | m_CORE_ATOM
+	  | m_GENERIC)
 
 /* X86_TUNE_DEST_FALSE_DEP_FOR_GLC: This knob inserts zero-idiom before
    several insns to break false dependency on the dest register for GLC
    micro-architecture.  */
 DEF_TUNE (X86_TUNE_DEST_FALSE_DEP_FOR_GLC,
-	  "dest_false_dep_for_glc", m_SAPPHIRERAPIDS | m_ALDERLAKE)
+	  "dest_false_dep_for_glc", m_SAPPHIRERAPIDS | m_ALDERLAKE
+	  | m_CORE_ATOM)
 
 /* X86_TUNE_SSE_SPLIT_REGS: Set for machines where the type and dependencies
    are resolved on SSE register parts instead of whole registers, so we may
@@ -110,14 +114,14 @@ DEF_TUNE (X86_TUNE_MOVX, "movx",
           m_PPRO | m_P4_NOCONA | m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE
 	  | m_BONNELL | m_SILVERMONT | m_GOLDMONT | m_KNL | m_KNM | m_INTEL
 	  | m_GOLDMONT_PLUS | m_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI
-	  | m_CORE_AVX2 | m_TREMONT | m_ALDERLAKE | m_GENERIC)
+	  | m_CORE_AVX2 | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_MEMORY_MISMATCH_STALL: Avoid partial stores that are followed by
    full sized loads.  */
 DEF_TUNE (X86_TUNE_MEMORY_MISMATCH_STALL, "memory_mismatch_stall",
           m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_INTEL
 	  | m_KNL | m_KNM | m_GOLDMONT | m_GOLDMONT_PLUS | m_AMD_MULTIPLE
-	  | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_GENERIC)
+	  | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_FUSE_CMP_AND_BRANCH_32: Fuse compare with a subsequent
    conditional jump instruction for 32 bit TARGET.  */
@@ -173,14 +177,14 @@ DEF_TUNE (X86_TUNE_EPILOGUE_USING_MOVE, "epilogue_using_move",
 /* X86_TUNE_USE_LEAVE: Use "leave" instruction in epilogues where it fits.  */
 DEF_TUNE (X86_TUNE_USE_LEAVE, "use_leave",
 	  m_386 | m_CORE_ALL | m_K6_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI
-	  | m_TREMONT | m_ALDERLAKE | m_GENERIC)
+	  | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_PUSH_MEMORY: Enable generation of "push mem" instructions.
    Some chips, like 486 and Pentium works faster with separate load
    and push instructions.  */
 DEF_TUNE (X86_TUNE_PUSH_MEMORY, "push_memory",
           m_386 | m_P4_NOCONA | m_CORE_ALL | m_K6_GEODE | m_AMD_MULTIPLE
-	  | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_GENERIC)
+	  | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_SINGLE_PUSH: Enable if single push insn is preferred
    over esp subtraction.  */
@@ -250,15 +254,16 @@ DEF_TUNE (X86_TUNE_READ_MODIFY, "read_modify", ~(m_PENT | m_LAKEMONT | m_PPRO))
 DEF_TUNE (X86_TUNE_USE_INCDEC, "use_incdec",
           ~(m_P4_NOCONA | m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE
 	    | m_BONNELL | m_SILVERMONT | m_INTEL |  m_KNL | m_KNM | m_GOLDMONT
-	    | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_LUJIAZUI
-	    | m_GENERIC))
+	    | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM
+	    | m_LUJIAZUI | m_GENERIC))
 
 /* X86_TUNE_INTEGER_DFMODE_MOVES: Enable if integer moves are preferred
    for DFmode copies */
 DEF_TUNE (X86_TUNE_INTEGER_DFMODE_MOVES, "integer_dfmode_moves",
           ~(m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT
 	    | m_KNL | m_KNM | m_INTEL | m_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI
-	    | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_GENERIC))
+	    | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE
+	    | m_CORE_ATOM | m_GENERIC))
 
 /* X86_TUNE_OPT_AGU: Optimize for Address Generation Unit. This flag
    will impact LEA instruction selection. */
@@ -296,7 +301,8 @@ DEF_TUNE (X86_TUNE_SINGLE_STRINGOP, "single_stringop", m_386 | m_P4_NOCONA)
    move/set sequences of bytes with known size.  */
 DEF_TUNE (X86_TUNE_PREFER_KNOWN_REP_MOVSB_STOSB,
 	  "prefer_known_rep_movsb_stosb",
-	  m_SKYLAKE | m_ALDERLAKE | m_TREMONT | m_CORE_AVX512 | m_LUJIAZUI)
+	  m_SKYLAKE | m_ALDERLAKE | m_CORE_ATOM | m_TREMONT | m_CORE_AVX512
+	  | m_LUJIAZUI)
 
 /* X86_TUNE_MISALIGNED_MOVE_STRING_PRO_EPILOGUES: Enable generation of
    compact prologues and epilogues by issuing a misaligned moves.  This
@@ -306,14 +312,14 @@ DEF_TUNE (X86_TUNE_PREFER_KNOWN_REP_MOVSB_STOSB,
 DEF_TUNE (X86_TUNE_MISALIGNED_MOVE_STRING_PRO_EPILOGUES,
 	  "misaligned_move_string_pro_epilogues",
 	  m_386 | m_486 | m_CORE_ALL | m_AMD_MULTIPLE | m_LUJIAZUI | m_TREMONT
-	  | m_ALDERLAKE | m_GENERIC)
+	  | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_USE_SAHF: Controls use of SAHF.  */
 DEF_TUNE (X86_TUNE_USE_SAHF, "use_sahf",
           m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT
 	  | m_KNL | m_KNM | m_INTEL | m_K6_GEODE | m_K8 | m_AMDFAM10 | m_BDVER
 	  | m_BTVER | m_ZNVER | m_LUJIAZUI | m_GOLDMONT | m_GOLDMONT_PLUS
-	  | m_TREMONT | m_ALDERLAKE | m_GENERIC)
+	  | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_USE_CLTD: Controls use of CLTD and CTQO instructions.  */
 DEF_TUNE (X86_TUNE_USE_CLTD, "use_cltd",
@@ -324,13 +330,13 @@ DEF_TUNE (X86_TUNE_USE_CLTD, "use_cltd",
 DEF_TUNE (X86_TUNE_USE_BT, "use_bt",
           m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_KNL | m_KNM | m_INTEL
 	  | m_LAKEMONT | m_AMD_MULTIPLE | m_LUJIAZUI | m_GOLDMONT
-	  | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_GENERIC)
+	  | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_AVOID_FALSE_DEP_FOR_BMI: Avoid false dependency
    for bit-manipulation instructions.  */
 DEF_TUNE (X86_TUNE_AVOID_FALSE_DEP_FOR_BMI, "avoid_false_dep_for_bmi",
-	  m_SANDYBRIDGE | m_CORE_AVX2 | m_TREMONT | m_ALDERLAKE | m_LUJIAZUI
-     | m_GENERIC)
+	  m_SANDYBRIDGE | m_CORE_AVX2 | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM
+	  | m_LUJIAZUI | m_GENERIC)
 
 /* X86_TUNE_ADJUST_UNROLL: This enables adjusting the unroll factor based
    on hardware capabilities. Bdver3 hardware has a loop buffer which makes
@@ -342,12 +348,13 @@ DEF_TUNE (X86_TUNE_ADJUST_UNROLL, "adjust_unroll_factor", m_BDVER3 | m_BDVER4)
    if-converted sequence to one.  */
 DEF_TUNE (X86_TUNE_ONE_IF_CONV_INSN, "one_if_conv_insn",
 	  m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_CORE_ALL | m_GOLDMONT
-	  | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_LUJIAZUI | m_GENERIC)
+	  | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_LUJIAZUI
+	  | m_GENERIC)
 
 /* X86_TUNE_AVOID_MFENCE: Use lock prefixed instructions instead of mfence.  */
 DEF_TUNE (X86_TUNE_AVOID_MFENCE, "avoid_mfence",
 	 m_CORE_ALL | m_BDVER | m_ZNVER | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE
-    | m_GENERIC)
+	 | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_EXPAND_ABS: This enables a new abs pattern by
    generating instructions for abs (x) = (((signed) x >> (W-1) ^ x) -
@@ -372,7 +379,7 @@ DEF_TUNE (X86_TUNE_USE_SIMODE_FIOP, "use_simode_fiop",
           ~(m_PENT | m_LAKEMONT | m_PPRO | m_CORE_ALL | m_BONNELL
 	    | m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_AMD_MULTIPLE
 	    | m_LUJIAZUI | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT
-	    | m_ALDERLAKE | m_GENERIC))
+	    | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC))
 
 /* X86_TUNE_USE_FFREEP: Use freep instruction instead of fstp.  */
 DEF_TUNE (X86_TUNE_USE_FFREEP, "use_ffreep", m_AMD_MULTIPLE | m_LUJIAZUI)
@@ -381,7 +388,8 @@ DEF_TUNE (X86_TUNE_USE_FFREEP, "use_ffreep", m_AMD_MULTIPLE | m_LUJIAZUI)
 DEF_TUNE (X86_TUNE_EXT_80387_CONSTANTS, "ext_80387_constants",
           m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT
 	  | m_KNL | m_KNM | m_INTEL | m_K6_GEODE | m_ATHLON_K8 | m_LUJIAZUI
-	  | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_GENERIC)
+	  | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM
+	  | m_GENERIC)
 
 /*****************************************************************************/
 /* SSE instruction selection tuning                                          */
@@ -397,14 +405,15 @@ DEF_TUNE (X86_TUNE_GENERAL_REGS_SSE_SPILL, "general_regs_sse_spill",
 DEF_TUNE (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL, "sse_unaligned_load_optimal",
 	  m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_SILVERMONT | m_KNL | m_KNM
 	  | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE
-	  | m_AMDFAM10 | m_BDVER | m_BTVER | m_ZNVER | m_LUJIAZUI | m_GENERIC)
+	  | m_CORE_ATOM | m_AMDFAM10 | m_BDVER | m_BTVER | m_ZNVER | m_LUJIAZUI
+	  | m_GENERIC)
 
 /* X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL: Use movups for misaligned stores
    instead of a sequence loading registers by parts.  */
 DEF_TUNE (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL, "sse_unaligned_store_optimal",
 	  m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_SILVERMONT | m_KNL | m_KNM
 	  | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE
-	  | m_BDVER | m_ZNVER | m_LUJIAZUI | m_GENERIC)
+	  | m_CORE_ATOM | m_BDVER | m_ZNVER | m_LUJIAZUI | m_GENERIC)
 
 /* X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL: Use packed single
    precision 128bit instructions instead of double where possible.   */
@@ -414,13 +423,13 @@ DEF_TUNE (X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL, "sse_packed_single_insn_optim
 /* X86_TUNE_SSE_TYPELESS_STORES: Always movaps/movups for 128bit stores.   */
 DEF_TUNE (X86_TUNE_SSE_TYPELESS_STORES, "sse_typeless_stores",
 	  m_AMD_MULTIPLE | m_LUJIAZUI | m_CORE_ALL | m_TREMONT | m_ALDERLAKE
-	  | m_GENERIC)
+	  | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_SSE_LOAD0_BY_PXOR: Always use pxor to load0 as opposed to
    xorps/xorpd and other variants.  */
 DEF_TUNE (X86_TUNE_SSE_LOAD0_BY_PXOR, "sse_load0_by_pxor",
 	  m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BDVER | m_BTVER | m_ZNVER
-	  | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_GENERIC)
+	  | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
 
 /* X86_TUNE_INTER_UNIT_MOVES_TO_VEC: Enable moves in from integer
    to SSE registers.  If disabled, the moves will be done by storing
@@ -467,22 +476,22 @@ DEF_TUNE (X86_TUNE_SLOW_PSHUFB, "slow_pshufb",
 /* X86_TUNE_AVOID_4BYTE_PREFIXES: Avoid instructions requiring 4+ bytes of prefixes.  */
 DEF_TUNE (X86_TUNE_AVOID_4BYTE_PREFIXES, "avoid_4byte_prefixes",
 	  m_SILVERMONT | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE
-	  | m_INTEL)
+	  | m_CORE_ATOM | m_INTEL)
 
 /* X86_TUNE_USE_GATHER_2PARTS: Use gather instructions for vectors with 2
    elements.  */
 DEF_TUNE (X86_TUNE_USE_GATHER_2PARTS, "use_gather_2parts",
-	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ALDERLAKE | m_GENERIC))
+	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC))
 
 /* X86_TUNE_USE_GATHER_4PARTS: Use gather instructions for vectors with 4
    elements.  */
 DEF_TUNE (X86_TUNE_USE_GATHER_4PARTS, "use_gather_4parts",
-	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ALDERLAKE | m_GENERIC))
+	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC))
 
 /* X86_TUNE_USE_GATHER: Use gather instructions for vectors with 8 or more
    elements.  */
 DEF_TUNE (X86_TUNE_USE_GATHER, "use_gather",
-	  ~(m_ZNVER1 | m_ZNVER2 | m_ALDERLAKE | m_GENERIC))
+	  ~(m_ZNVER1 | m_ZNVER2 | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC))
 
 /* X86_TUNE_AVOID_128FMA_CHAINS: Avoid creating loops with tight 128bit or
    smaller FMA chain.  */
-- 
2.18.1


^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: [PATCH 1/2] Initial Grand Ridge support
  2022-11-07  1:41 ` [PATCH 1/2] Initial Grand Ridge support Haochen Jiang
@ 2022-11-07  2:08   ` Hongtao Liu
  0 siblings, 0 replies; 5+ messages in thread
From: Hongtao Liu @ 2022-11-07  2:08 UTC (permalink / raw)
  To: Haochen Jiang; +Cc: gcc-patches, ubizjak, hongtao.liu

On Mon, Nov 7, 2022 at 9:41 AM Haochen Jiang via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
>
> gcc/ChangeLog:
>
>         * common/config/i386/i386-common.cc
>         (processor_names): Add grandridge.
>         (processor_alias_table): Ditto.
>         * common/config/i386/i386-cpuinfo.h:
>         (enum processor_types): Add INTEL_GRANDRIDGE.
>         * config.gcc: Add -march=grandridge.
>         * config/i386/driver-i386.cc (host_detect_local_cpu):
>         Handle grandridge.
>         * config/i386/i386-c.cc (ix86_target_macros_internal):
>         Ditto.
>         * config/i386/i386-options.cc (m_GRANDRIDGE): New define.
>         (processor_cost_table): Add grandridge.
>         * config/i386/i386.h (enum processor_type):
>         Add PROCESSOR_GRANDRIDGE.
>         (PTA_GRANDRIDGE): Ditto.
>         * doc/extend.texi: Add grandridge.
>         * doc/invoke.texi: Ditto.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc/testsuite/g++.target/i386/mv16.C: Add grandridge.
>         * gcc.target/i386/funcspec-56.inc: Handle new march.
> ---
LGTM.
>  gcc/common/config/i386/cpuinfo.h              | 6 ++++++
>  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               | 2 ++
>  gcc/config/i386/i386.h                        | 2 ++
>  gcc/doc/extend.texi                           | 3 +++
>  gcc/doc/invoke.texi                           | 9 +++++++++
>  gcc/testsuite/g++.target/i386/mv16.C          | 6 ++++++
>  gcc/testsuite/gcc.target/i386/funcspec-56.inc | 1 +
>  12 files changed, 45 insertions(+), 2 deletions(-)
>
> diff --git a/gcc/common/config/i386/cpuinfo.h b/gcc/common/config/i386/cpuinfo.h
> index df3500adc83..4d1bcffb978 100644
> --- a/gcc/common/config/i386/cpuinfo.h
> +++ b/gcc/common/config/i386/cpuinfo.h
> @@ -573,6 +573,12 @@ get_intel_cpu (struct __processor_model *cpu_model,
>        cpu_model->__cpu_type = INTEL_COREI7;
>        cpu_model->__cpu_subtype = INTEL_COREI7_GRANITERAPIDS;
>        break;
> +    case 0xb6:
> +      /* Grand Ridge.  */
> +      cpu = "grandridge";
> +      CHECK___builtin_cpu_is ("grandridge");
> +      cpu_model->__cpu_type = INTEL_GRANDRIDGE;
> +      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 60a193a651c..431fd0d3ad1 100644
> --- a/gcc/common/config/i386/i386-common.cc
> +++ b/gcc/common/config/i386/i386-common.cc
> @@ -1920,6 +1920,7 @@ const char *const processor_names[] =
>    "goldmont-plus",
>    "tremont",
>    "sierraforest",
> +  "grandridge",
>    "knl",
>    "knm",
>    "skylake",
> @@ -2071,6 +2072,8 @@ const pta processor_alias_table[] =
>      M_CPU_TYPE (INTEL_TREMONT), P_PROC_SSE4_2},
>    {"sierraforest", PROCESSOR_SIERRAFOREST, CPU_HASWELL, PTA_SIERRAFOREST,
>      M_CPU_SUBTYPE (INTEL_SIERRAFOREST), P_PROC_AVX2},
> +  {"grandridge", PROCESSOR_GRANDRIDGE, CPU_HASWELL, PTA_GRANDRIDGE,
> +    M_CPU_TYPE (INTEL_GRANDRIDGE), P_PROC_AVX2},
>    {"knl", PROCESSOR_KNL, CPU_SLM, PTA_KNL,
>      M_CPU_TYPE (INTEL_KNL), P_PROC_AVX512F},
>    {"knm", PROCESSOR_KNM, CPU_SLM, PTA_KNM,
> diff --git a/gcc/common/config/i386/i386-cpuinfo.h b/gcc/common/config/i386/i386-cpuinfo.h
> index 345fda648ff..fe2e9e21fd2 100644
> --- a/gcc/common/config/i386/i386-cpuinfo.h
> +++ b/gcc/common/config/i386/i386-cpuinfo.h
> @@ -61,6 +61,7 @@ enum processor_types
>    AMDFAM19H,
>    ZHAOXIN_FAM7H,
>    INTEL_SIERRAFOREST,
> +  INTEL_GRANDRIDGE,
>    CPU_TYPE_MAX,
>    BUILTIN_CPU_TYPE_MAX = CPU_TYPE_MAX
>  };
> diff --git a/gcc/config.gcc b/gcc/config.gcc
> index 84c040746dc..b5eda046033 100644
> --- a/gcc/config.gcc
> +++ b/gcc/config.gcc
> @@ -669,7 +669,7 @@ 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 native"
> +sierraforest graniterapids 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 3117d83de00..95c16c23c7f 100644
> --- a/gcc/config/i386/driver-i386.cc
> +++ b/gcc/config/i386/driver-i386.cc
> @@ -591,8 +591,11 @@ const char *host_detect_local_cpu (int argc, const char **argv)
>               /* This is unknown family 0x6 CPU.  */
>               if (has_feature (FEATURE_AVX))
>                 {
> +                 /* Assume Grand Ridge.  */
> +                 if (has_feature (FEATURE_RAOINT))
> +                   cpu = "grandridge";
>                   /* Assume Granite Rapids.  */
> -                 if (has_feature (FEATURE_AMX_FP16))
> +                 else if (has_feature (FEATURE_AMX_FP16))
>                     cpu = "graniterapids";
>                   /* Assume Sierra Forest.  */
>                   else if (has_feature (FEATURE_AVXVNNIINT8))
> diff --git a/gcc/config/i386/i386-c.cc b/gcc/config/i386/i386-c.cc
> index a877d24148d..44fab6e80ae 100644
> --- a/gcc/config/i386/i386-c.cc
> +++ b/gcc/config/i386/i386-c.cc
> @@ -206,6 +206,10 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
>        def_or_undef (parse_in, "__sierraforest");
>        def_or_undef (parse_in, "__sierraforest__");
>        break;
> +    case PROCESSOR_GRANDRIDGE:
> +      def_or_undef (parse_in, "__grandridge");
> +      def_or_undef (parse_in, "__grandridge__");
> +      break;
>      case PROCESSOR_KNL:
>        def_or_undef (parse_in, "__knl");
>        def_or_undef (parse_in, "__knl__");
> @@ -395,6 +399,9 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
>      case PROCESSOR_SIERRAFOREST:
>        def_or_undef (parse_in, "__tune_sierraforest__");
>        break;
> +    case PROCESSOR_GRANDRIDGE:
> +      def_or_undef (parse_in, "__tune_grandridge__");
> +      break;
>      case PROCESSOR_KNL:
>        def_or_undef (parse_in, "__tune_knl__");
>        break;
> diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
> index 3c7570c5edd..23ab1f867d0 100644
> --- a/gcc/config/i386/i386-options.cc
> +++ b/gcc/config/i386/i386-options.cc
> @@ -138,6 +138,7 @@ along with GCC; see the file COPYING3.  If not see
>  #define m_GOLDMONT_PLUS (HOST_WIDE_INT_1U<<PROCESSOR_GOLDMONT_PLUS)
>  #define m_TREMONT (HOST_WIDE_INT_1U<<PROCESSOR_TREMONT)
>  #define m_SIERRAFOREST (HOST_WIDE_INT_1U<<PROCESSOR_SIERRAFOREST)
> +#define m_GRANDRIDGE (HOST_WIDE_INT_1U<<PROCESSOR_GRANDRIDGE)
>  #define m_INTEL (HOST_WIDE_INT_1U<<PROCESSOR_INTEL)
>
>  #define m_LUJIAZUI (HOST_WIDE_INT_1U<<PROCESSOR_LUJIAZUI)
> @@ -750,6 +751,7 @@ static const struct processor_costs *processor_cost_table[] =
>    &slm_cost,
>    &tremont_cost,
>    &alderlake_cost,
> +  &alderlake_cost,
>    &slm_cost,
>    &slm_cost,
>    &skylake_cost,
> diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
> index e3e675d36c5..b32db8da109 100644
> --- a/gcc/config/i386/i386.h
> +++ b/gcc/config/i386/i386.h
> @@ -2226,6 +2226,7 @@ enum processor_type
>    PROCESSOR_GOLDMONT_PLUS,
>    PROCESSOR_TREMONT,
>    PROCESSOR_SIERRAFOREST,
> +  PROCESSOR_GRANDRIDGE,
>    PROCESSOR_KNL,
>    PROCESSOR_KNM,
>    PROCESSOR_SKYLAKE,
> @@ -2351,6 +2352,7 @@ 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;
> +constexpr wide_int_bitmask PTA_GRANDRIDGE = PTA_SIERRAFOREST | PTA_RAOINT;
>  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 33a49338bd3..8da0db9770d 100644
> --- a/gcc/doc/extend.texi
> +++ b/gcc/doc/extend.texi
> @@ -21986,6 +21986,9 @@ Intel Atom Tremont CPU.
>  @item sierraforest
>  Intel Atom Sierra Forest CPU.
>
> +@item grandridge
> +Intel Atom Grand Ridge CPU.
> +
>  @item knl
>  Intel Knights Landing CPU.
>
> diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
> index 7417f528bb1..f9cd41fac28 100644
> --- a/gcc/doc/invoke.texi
> +++ b/gcc/doc/invoke.texi
> @@ -32080,6 +32080,15 @@ MOVDIR64B, CLDEMOTE, WAITPKG, ADCX, AVX, AVX2, BMI, BMI2, F16C, FMA, LZCNT,
>  PCONFIG, PKU, VAES, VPCLMULQDQ, SERIALIZE, HRESET, KL, WIDEKL, AVX-VNNI,
>  AVXIFMA, AVXVNNIINT8, AVXNECONVERT and CMPCCXADD instruction set support.
>
> +@item grandridge
> +Intel Grand Ridge CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3,
> +SSSE3, SSE4.1, SSE4.2, POPCNT, AES, PREFETCHW, PCLMUL, RDRND, XSAVE, XSAVEC,
> +XSAVES, XSAVEOPT, FSGSBASE, PTWRITE, RDPID, SGX, GFNI-SSE, CLWB, MOVDIRI,
> +MOVDIR64B, CLDEMOTE, WAITPKG, ADCX, AVX, AVX2, BMI, BMI2, F16C, FMA, LZCNT,
> +PCONFIG, PKU, VAES, VPCLMULQDQ, SERIALIZE, HRESET, KL, WIDEKL, AVX-VNNI,
> +AVXIFMA, AVXVNNIINT8, AVXNECONVERT, CMPCCXADD and RAOINT instruction set
> +support.
> +
>  @item knl
>  Intel Knight's Landing CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3,
>  SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE,
> diff --git a/gcc/testsuite/g++.target/i386/mv16.C b/gcc/testsuite/g++.target/i386/mv16.C
> index e0e0f153d1c..772791b96e8 100644
> --- a/gcc/testsuite/g++.target/i386/mv16.C
> +++ b/gcc/testsuite/g++.target/i386/mv16.C
> @@ -100,6 +100,10 @@ int __attribute__ ((target("arch=graniterapids"))) foo () {
>    return 26;
>  }
>
> +int __attribute__ ((target("arch=grandridge"))) foo () {
> +  return 27;
> +}
> +
>  int main ()
>  {
>    int val = foo ();
> @@ -142,6 +146,8 @@ int main ()
>      assert (val == 25);
>    else if (__builtin_cpu_is ("graniterapids"))
>      assert (val == 26);
> +  else if (__builtin_cpu_is ("grandridge"))
> +    assert (val == 27);
>    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 7eb18c6952d..37802307bcf 100644
> --- a/gcc/testsuite/gcc.target/i386/funcspec-56.inc
> +++ b/gcc/testsuite/gcc.target/i386/funcspec-56.inc
> @@ -186,6 +186,7 @@ extern void test_arch_goldmont (void)               __attribute__((__target__("arch=goldmont"
>  extern void test_arch_goldmont_plus (void)     __attribute__((__target__("arch=goldmont-plus")));
>  extern void test_arch_tremont (void)           __attribute__((__target__("arch=tremont")));
>  extern void test_arch_sierraforest (void)       __attribute__((__target__("arch=sierraforest")));
> +extern void test_arch_grandridge (void)                __attribute__((__target__("arch=grandridge")));
>  extern void test_arch_knl (void)               __attribute__((__target__("arch=knl")));
>  extern void test_arch_knm (void)               __attribute__((__target__("arch=knm")));
>  extern void test_arch_skylake (void)           __attribute__((__target__("arch=skylake")));
> --
> 2.18.1
>


-- 
BR,
Hongtao

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: [PATCH 2/2] Add m_CORE_ATOM for atom cores
  2022-11-07  1:41 ` [PATCH 2/2] Add m_CORE_ATOM for atom cores Haochen Jiang
@ 2022-11-07  9:13   ` Uros Bizjak
  0 siblings, 0 replies; 5+ messages in thread
From: Uros Bizjak @ 2022-11-07  9:13 UTC (permalink / raw)
  To: Haochen Jiang; +Cc: gcc-patches, hongtao.liu

On Mon, Nov 7, 2022 at 2:41 AM Haochen Jiang <haochen.jiang@intel.com> wrote:
>
> gcc/ChangeLog:
>
>         * config/i386/i386-options.cc (m_CORE_ATOM): New.
>         * config/i386/x86-tune.def
>         (X86_TUNE_SCHEDULE): Initial tune for CORE_ATOM.
>         (X86_TUNE_PARTIAL_REG_DEPENDENCY): Ditto.
>         (X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY): Ditto.
>         (X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY): Ditto.
>         (X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY): Ditto.
>         (X86_TUNE_DEST_FALSE_DEP_FOR_GLC): Ditto.
>         (X86_TUNE_MEMORY_MISMATCH_STALL): Ditto.
>         (X86_TUNE_USE_LEAVE): Ditto.
>         (X86_TUNE_PUSH_MEMORY): Ditto.
>         (X86_TUNE_USE_INCDEC): Ditto.
>         (X86_TUNE_INTEGER_DFMODE_MOVES): Ditto.
>         (X86_TUNE_PREFER_KNOWN_REP_MOVSB_STOSB): Ditto.
>         (X86_TUNE_MISALIGNED_MOVE_STRING_PRO_EPILOGUES): Ditto.
>         (X86_TUNE_USE_SAHF): Ditto.
>         (X86_TUNE_USE_BT): Ditto.
>         (X86_TUNE_AVOID_FALSE_DEP_FOR_BMI): Ditto.
>         (X86_TUNE_ONE_IF_CONV_INSN): Ditto.
>         (X86_TUNE_AVOID_MFENCE): Ditto.
>         (X86_TUNE_USE_SIMODE_FIOP): Ditto.
>         (X86_TUNE_EXT_80387_CONSTANTS): Ditto.
>         (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL): Ditto.
>         (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL): Ditto.
>         (X86_TUNE_SSE_TYPELESS_STORES): Ditto.
>         (X86_TUNE_SSE_LOAD0_BY_PXOR): Ditto.
>         (X86_TUNE_AVOID_4BYTE_PREFIXES): Ditto.
>         (X86_TUNE_USE_GATHER_2PARTS): Ditto.
>         (X86_TUNE_USE_GATHER_4PARTS): Ditto.
>         (X86_TUNE_USE_GATHER): Ditto.

OK.

Thanks,
Uros.

> ---
>  gcc/config/i386/i386-options.cc |  1 +
>  gcc/config/i386/x86-tune.def    | 71 +++++++++++++++++++--------------
>  2 files changed, 41 insertions(+), 31 deletions(-)
>
> diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
> index 23ab1f867d0..e5c77f3a84d 100644
> --- a/gcc/config/i386/i386-options.cc
> +++ b/gcc/config/i386/i386-options.cc
> @@ -139,6 +139,7 @@ along with GCC; see the file COPYING3.  If not see
>  #define m_TREMONT (HOST_WIDE_INT_1U<<PROCESSOR_TREMONT)
>  #define m_SIERRAFOREST (HOST_WIDE_INT_1U<<PROCESSOR_SIERRAFOREST)
>  #define m_GRANDRIDGE (HOST_WIDE_INT_1U<<PROCESSOR_GRANDRIDGE)
> +#define m_CORE_ATOM (m_SIERRAFOREST | m_GRANDRIDGE)
>  #define m_INTEL (HOST_WIDE_INT_1U<<PROCESSOR_INTEL)
>
>  #define m_LUJIAZUI (HOST_WIDE_INT_1U<<PROCESSOR_LUJIAZUI)
> diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
> index 540e45d02f9..58e29e7806a 100644
> --- a/gcc/config/i386/x86-tune.def
> +++ b/gcc/config/i386/x86-tune.def
> @@ -42,7 +42,8 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
>  DEF_TUNE (X86_TUNE_SCHEDULE, "schedule",
>            m_PENT | m_LAKEMONT | m_PPRO | m_CORE_ALL | m_BONNELL | m_SILVERMONT
>           | m_INTEL | m_KNL | m_KNM | m_K6_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI
> -     | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_GENERIC)
> +         | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM
> +         | m_GENERIC)
>
>  /* X86_TUNE_PARTIAL_REG_DEPENDENCY: Enable more register renaming
>     on modern chips.  Prefer stores affecting whole integer register
> @@ -52,7 +53,7 @@ DEF_TUNE (X86_TUNE_PARTIAL_REG_DEPENDENCY, "partial_reg_dependency",
>            m_P4_NOCONA | m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE | m_CORE_AVX2
>           | m_BONNELL | m_SILVERMONT | m_GOLDMONT | m_GOLDMONT_PLUS | m_INTEL
>           | m_KNL | m_KNM | m_AMD_MULTIPLE | m_LUJIAZUI | m_TREMONT
> -         | m_ALDERLAKE | m_GENERIC)
> +         | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY: This knob promotes all store
>     destinations to be 128bit to allow register renaming on 128bit SSE units,
> @@ -63,7 +64,7 @@ DEF_TUNE (X86_TUNE_PARTIAL_REG_DEPENDENCY, "partial_reg_dependency",
>  DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY, "sse_partial_reg_dependency",
>            m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_AMDFAM10
>           | m_BDVER | m_ZNVER | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE
> -         | m_GENERIC)
> +         | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY: This knob avoids
>     partial write to the destination in scalar SSE conversion from FP
> @@ -71,20 +72,23 @@ DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY, "sse_partial_reg_dependency",
>  DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY,
>           "sse_partial_reg_fp_converts_dependency",
>           m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_AMDFAM10
> -         | m_BDVER | m_ZNVER | m_LUJIAZUI | m_ALDERLAKE | m_GENERIC)
> +         | m_BDVER | m_ZNVER | m_LUJIAZUI | m_ALDERLAKE | m_CORE_ATOM
> +         | m_GENERIC)
>
>  /* X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY: This knob avoids partial
>     write to the destination in scalar SSE conversion from integer to FP.  */
>  DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY,
>           "sse_partial_reg_converts_dependency",
>           m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_AMDFAM10
> -         | m_BDVER | m_ZNVER | m_LUJIAZUI | m_ALDERLAKE | m_GENERIC)
> +         | m_BDVER | m_ZNVER | m_LUJIAZUI | m_ALDERLAKE | m_CORE_ATOM
> +         | m_GENERIC)
>
>  /* X86_TUNE_DEST_FALSE_DEP_FOR_GLC: This knob inserts zero-idiom before
>     several insns to break false dependency on the dest register for GLC
>     micro-architecture.  */
>  DEF_TUNE (X86_TUNE_DEST_FALSE_DEP_FOR_GLC,
> -         "dest_false_dep_for_glc", m_SAPPHIRERAPIDS | m_ALDERLAKE)
> +         "dest_false_dep_for_glc", m_SAPPHIRERAPIDS | m_ALDERLAKE
> +         | m_CORE_ATOM)
>
>  /* X86_TUNE_SSE_SPLIT_REGS: Set for machines where the type and dependencies
>     are resolved on SSE register parts instead of whole registers, so we may
> @@ -110,14 +114,14 @@ DEF_TUNE (X86_TUNE_MOVX, "movx",
>            m_PPRO | m_P4_NOCONA | m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE
>           | m_BONNELL | m_SILVERMONT | m_GOLDMONT | m_KNL | m_KNM | m_INTEL
>           | m_GOLDMONT_PLUS | m_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI
> -         | m_CORE_AVX2 | m_TREMONT | m_ALDERLAKE | m_GENERIC)
> +         | m_CORE_AVX2 | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_MEMORY_MISMATCH_STALL: Avoid partial stores that are followed by
>     full sized loads.  */
>  DEF_TUNE (X86_TUNE_MEMORY_MISMATCH_STALL, "memory_mismatch_stall",
>            m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_INTEL
>           | m_KNL | m_KNM | m_GOLDMONT | m_GOLDMONT_PLUS | m_AMD_MULTIPLE
> -         | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_GENERIC)
> +         | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_FUSE_CMP_AND_BRANCH_32: Fuse compare with a subsequent
>     conditional jump instruction for 32 bit TARGET.  */
> @@ -173,14 +177,14 @@ DEF_TUNE (X86_TUNE_EPILOGUE_USING_MOVE, "epilogue_using_move",
>  /* X86_TUNE_USE_LEAVE: Use "leave" instruction in epilogues where it fits.  */
>  DEF_TUNE (X86_TUNE_USE_LEAVE, "use_leave",
>           m_386 | m_CORE_ALL | m_K6_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI
> -         | m_TREMONT | m_ALDERLAKE | m_GENERIC)
> +         | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_PUSH_MEMORY: Enable generation of "push mem" instructions.
>     Some chips, like 486 and Pentium works faster with separate load
>     and push instructions.  */
>  DEF_TUNE (X86_TUNE_PUSH_MEMORY, "push_memory",
>            m_386 | m_P4_NOCONA | m_CORE_ALL | m_K6_GEODE | m_AMD_MULTIPLE
> -         | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_GENERIC)
> +         | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_SINGLE_PUSH: Enable if single push insn is preferred
>     over esp subtraction.  */
> @@ -250,15 +254,16 @@ DEF_TUNE (X86_TUNE_READ_MODIFY, "read_modify", ~(m_PENT | m_LAKEMONT | m_PPRO))
>  DEF_TUNE (X86_TUNE_USE_INCDEC, "use_incdec",
>            ~(m_P4_NOCONA | m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE
>             | m_BONNELL | m_SILVERMONT | m_INTEL |  m_KNL | m_KNM | m_GOLDMONT
> -           | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_LUJIAZUI
> -           | m_GENERIC))
> +           | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM
> +           | m_LUJIAZUI | m_GENERIC))
>
>  /* X86_TUNE_INTEGER_DFMODE_MOVES: Enable if integer moves are preferred
>     for DFmode copies */
>  DEF_TUNE (X86_TUNE_INTEGER_DFMODE_MOVES, "integer_dfmode_moves",
>            ~(m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT
>             | m_KNL | m_KNM | m_INTEL | m_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI
> -           | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_GENERIC))
> +           | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE
> +           | m_CORE_ATOM | m_GENERIC))
>
>  /* X86_TUNE_OPT_AGU: Optimize for Address Generation Unit. This flag
>     will impact LEA instruction selection. */
> @@ -296,7 +301,8 @@ DEF_TUNE (X86_TUNE_SINGLE_STRINGOP, "single_stringop", m_386 | m_P4_NOCONA)
>     move/set sequences of bytes with known size.  */
>  DEF_TUNE (X86_TUNE_PREFER_KNOWN_REP_MOVSB_STOSB,
>           "prefer_known_rep_movsb_stosb",
> -         m_SKYLAKE | m_ALDERLAKE | m_TREMONT | m_CORE_AVX512 | m_LUJIAZUI)
> +         m_SKYLAKE | m_ALDERLAKE | m_CORE_ATOM | m_TREMONT | m_CORE_AVX512
> +         | m_LUJIAZUI)
>
>  /* X86_TUNE_MISALIGNED_MOVE_STRING_PRO_EPILOGUES: Enable generation of
>     compact prologues and epilogues by issuing a misaligned moves.  This
> @@ -306,14 +312,14 @@ DEF_TUNE (X86_TUNE_PREFER_KNOWN_REP_MOVSB_STOSB,
>  DEF_TUNE (X86_TUNE_MISALIGNED_MOVE_STRING_PRO_EPILOGUES,
>           "misaligned_move_string_pro_epilogues",
>           m_386 | m_486 | m_CORE_ALL | m_AMD_MULTIPLE | m_LUJIAZUI | m_TREMONT
> -         | m_ALDERLAKE | m_GENERIC)
> +         | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_USE_SAHF: Controls use of SAHF.  */
>  DEF_TUNE (X86_TUNE_USE_SAHF, "use_sahf",
>            m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT
>           | m_KNL | m_KNM | m_INTEL | m_K6_GEODE | m_K8 | m_AMDFAM10 | m_BDVER
>           | m_BTVER | m_ZNVER | m_LUJIAZUI | m_GOLDMONT | m_GOLDMONT_PLUS
> -         | m_TREMONT | m_ALDERLAKE | m_GENERIC)
> +         | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_USE_CLTD: Controls use of CLTD and CTQO instructions.  */
>  DEF_TUNE (X86_TUNE_USE_CLTD, "use_cltd",
> @@ -324,13 +330,13 @@ DEF_TUNE (X86_TUNE_USE_CLTD, "use_cltd",
>  DEF_TUNE (X86_TUNE_USE_BT, "use_bt",
>            m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_KNL | m_KNM | m_INTEL
>           | m_LAKEMONT | m_AMD_MULTIPLE | m_LUJIAZUI | m_GOLDMONT
> -         | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_GENERIC)
> +         | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_AVOID_FALSE_DEP_FOR_BMI: Avoid false dependency
>     for bit-manipulation instructions.  */
>  DEF_TUNE (X86_TUNE_AVOID_FALSE_DEP_FOR_BMI, "avoid_false_dep_for_bmi",
> -         m_SANDYBRIDGE | m_CORE_AVX2 | m_TREMONT | m_ALDERLAKE | m_LUJIAZUI
> -     | m_GENERIC)
> +         m_SANDYBRIDGE | m_CORE_AVX2 | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM
> +         | m_LUJIAZUI | m_GENERIC)
>
>  /* X86_TUNE_ADJUST_UNROLL: This enables adjusting the unroll factor based
>     on hardware capabilities. Bdver3 hardware has a loop buffer which makes
> @@ -342,12 +348,13 @@ DEF_TUNE (X86_TUNE_ADJUST_UNROLL, "adjust_unroll_factor", m_BDVER3 | m_BDVER4)
>     if-converted sequence to one.  */
>  DEF_TUNE (X86_TUNE_ONE_IF_CONV_INSN, "one_if_conv_insn",
>           m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_CORE_ALL | m_GOLDMONT
> -         | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_LUJIAZUI | m_GENERIC)
> +         | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_LUJIAZUI
> +         | m_GENERIC)
>
>  /* X86_TUNE_AVOID_MFENCE: Use lock prefixed instructions instead of mfence.  */
>  DEF_TUNE (X86_TUNE_AVOID_MFENCE, "avoid_mfence",
>          m_CORE_ALL | m_BDVER | m_ZNVER | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE
> -    | m_GENERIC)
> +        | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_EXPAND_ABS: This enables a new abs pattern by
>     generating instructions for abs (x) = (((signed) x >> (W-1) ^ x) -
> @@ -372,7 +379,7 @@ DEF_TUNE (X86_TUNE_USE_SIMODE_FIOP, "use_simode_fiop",
>            ~(m_PENT | m_LAKEMONT | m_PPRO | m_CORE_ALL | m_BONNELL
>             | m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_AMD_MULTIPLE
>             | m_LUJIAZUI | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT
> -           | m_ALDERLAKE | m_GENERIC))
> +           | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC))
>
>  /* X86_TUNE_USE_FFREEP: Use freep instruction instead of fstp.  */
>  DEF_TUNE (X86_TUNE_USE_FFREEP, "use_ffreep", m_AMD_MULTIPLE | m_LUJIAZUI)
> @@ -381,7 +388,8 @@ DEF_TUNE (X86_TUNE_USE_FFREEP, "use_ffreep", m_AMD_MULTIPLE | m_LUJIAZUI)
>  DEF_TUNE (X86_TUNE_EXT_80387_CONSTANTS, "ext_80387_constants",
>            m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT
>           | m_KNL | m_KNM | m_INTEL | m_K6_GEODE | m_ATHLON_K8 | m_LUJIAZUI
> -         | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_GENERIC)
> +         | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM
> +         | m_GENERIC)
>
>  /*****************************************************************************/
>  /* SSE instruction selection tuning                                          */
> @@ -397,14 +405,15 @@ DEF_TUNE (X86_TUNE_GENERAL_REGS_SSE_SPILL, "general_regs_sse_spill",
>  DEF_TUNE (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL, "sse_unaligned_load_optimal",
>           m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_SILVERMONT | m_KNL | m_KNM
>           | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE
> -         | m_AMDFAM10 | m_BDVER | m_BTVER | m_ZNVER | m_LUJIAZUI | m_GENERIC)
> +         | m_CORE_ATOM | m_AMDFAM10 | m_BDVER | m_BTVER | m_ZNVER | m_LUJIAZUI
> +         | m_GENERIC)
>
>  /* X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL: Use movups for misaligned stores
>     instead of a sequence loading registers by parts.  */
>  DEF_TUNE (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL, "sse_unaligned_store_optimal",
>           m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_SILVERMONT | m_KNL | m_KNM
>           | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE
> -         | m_BDVER | m_ZNVER | m_LUJIAZUI | m_GENERIC)
> +         | m_CORE_ATOM | m_BDVER | m_ZNVER | m_LUJIAZUI | m_GENERIC)
>
>  /* X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL: Use packed single
>     precision 128bit instructions instead of double where possible.   */
> @@ -414,13 +423,13 @@ DEF_TUNE (X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL, "sse_packed_single_insn_optim
>  /* X86_TUNE_SSE_TYPELESS_STORES: Always movaps/movups for 128bit stores.   */
>  DEF_TUNE (X86_TUNE_SSE_TYPELESS_STORES, "sse_typeless_stores",
>           m_AMD_MULTIPLE | m_LUJIAZUI | m_CORE_ALL | m_TREMONT | m_ALDERLAKE
> -         | m_GENERIC)
> +         | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_SSE_LOAD0_BY_PXOR: Always use pxor to load0 as opposed to
>     xorps/xorpd and other variants.  */
>  DEF_TUNE (X86_TUNE_SSE_LOAD0_BY_PXOR, "sse_load0_by_pxor",
>           m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BDVER | m_BTVER | m_ZNVER
> -         | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_GENERIC)
> +         | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC)
>
>  /* X86_TUNE_INTER_UNIT_MOVES_TO_VEC: Enable moves in from integer
>     to SSE registers.  If disabled, the moves will be done by storing
> @@ -467,22 +476,22 @@ DEF_TUNE (X86_TUNE_SLOW_PSHUFB, "slow_pshufb",
>  /* X86_TUNE_AVOID_4BYTE_PREFIXES: Avoid instructions requiring 4+ bytes of prefixes.  */
>  DEF_TUNE (X86_TUNE_AVOID_4BYTE_PREFIXES, "avoid_4byte_prefixes",
>           m_SILVERMONT | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE
> -         | m_INTEL)
> +         | m_CORE_ATOM | m_INTEL)
>
>  /* X86_TUNE_USE_GATHER_2PARTS: Use gather instructions for vectors with 2
>     elements.  */
>  DEF_TUNE (X86_TUNE_USE_GATHER_2PARTS, "use_gather_2parts",
> -         ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ALDERLAKE | m_GENERIC))
> +         ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC))
>
>  /* X86_TUNE_USE_GATHER_4PARTS: Use gather instructions for vectors with 4
>     elements.  */
>  DEF_TUNE (X86_TUNE_USE_GATHER_4PARTS, "use_gather_4parts",
> -         ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ALDERLAKE | m_GENERIC))
> +         ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC))
>
>  /* X86_TUNE_USE_GATHER: Use gather instructions for vectors with 8 or more
>     elements.  */
>  DEF_TUNE (X86_TUNE_USE_GATHER, "use_gather",
> -         ~(m_ZNVER1 | m_ZNVER2 | m_ALDERLAKE | m_GENERIC))
> +         ~(m_ZNVER1 | m_ZNVER2 | m_ALDERLAKE | m_CORE_ATOM | m_GENERIC))
>
>  /* X86_TUNE_AVOID_128FMA_CHAINS: Avoid creating loops with tight 128bit or
>     smaller FMA chain.  */
> --
> 2.18.1
>

^ permalink raw reply	[flat|nested] 5+ messages in thread

end of thread, other threads:[~2022-11-07  9:13 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-11-07  1:41 [PATCH 0/2] Intel Grand Ridge Support Haochen Jiang
2022-11-07  1:41 ` [PATCH 1/2] Initial Grand Ridge support Haochen Jiang
2022-11-07  2:08   ` Hongtao Liu
2022-11-07  1:41 ` [PATCH 2/2] Add m_CORE_ATOM for atom cores Haochen Jiang
2022-11-07  9:13   ` Uros Bizjak

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).