i386: Zhaoxin yongfeng enablement

Enable -march/-mtune=yongfeng. Costs and tunings are set according
to the characteristics of the processor. Add a new .md file to describe
yongfeng processor.

gcc/ChangeLog:

	* common/config/i386/cpuinfo.h (get_zhaoxin_cpu): Recognize yongfeng.
	* common/config/i386/i386-common.cc: Add yongfeng.
	* common/config/i386/i386-cpuinfo.h (enum processor_subtypes):
	Add ZHAOXIN_FAM7H_YONGFENG.
	* config.gcc: Add yongfeng.
	* config/i386/driver-i386.cc (host_detect_local_cpu):
	Let -march=native recognize yongfeng processors.
	* config/i386/i386-c.cc (ix86_target_macros_internal): Add yongfeng.
	* config/i386/i386-options.cc (m_YONGFENG): New definition.
	(m_ZHAOXIN): Ditto.
	* config/i386/i386.h (enum processor_type): Add PROCESSOR_YONGFENG.
	* config/i386/i386.md: Add yongfeng.
	* config/i386/lujiazui.md: Fix typo.
	* config/i386/x86-tune-costs.h (struct processor_costs):
	Add yongfeng costs.
	* config/i386/x86-tune-sched.cc (ix86_issue_rate): Add yongfeng.
	(ix86_adjust_cost): Ditto.
	* config/i386/x86-tune.def (X86_TUNE_SCHEDULE): Replace
	m_LUJIAZUI with m_ZHAOXIN.
	(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_MOVX): Ditto.
	(X86_TUNE_MEMORY_MISMATCH_STALL): Ditto.
	(X86_TUNE_FUSE_CMP_AND_BRANCH_32): Ditto.
	(X86_TUNE_FUSE_CMP_AND_BRANCH_64): Ditto.
	(X86_TUNE_FUSE_CMP_AND_BRANCH_SOFLAGS): Ditto.
	(X86_TUNE_FUSE_ALU_AND_BRANCH): Ditto.
	(X86_TUNE_ACCUMULATE_OUTGOING_ARGS): Ditto.
	(X86_TUNE_USE_LEAVE): Ditto.
	(X86_TUNE_PUSH_MEMORY): Ditto.
	(X86_TUNE_LCP_STALL): Ditto.
	(X86_TUNE_INTEGER_DFMODE_MOVES): Ditto.
	(X86_TUNE_OPT_AGU): 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_EXPAND_ABS): Ditto.
	(X86_TUNE_USE_SIMODE_FIOP): Ditto.
	(X86_TUNE_USE_FFREEP): 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_USE_GATHER_2PARTS): Add m_YONGFENG.
	(X86_TUNE_USE_GATHER_4PARTS): Ditto.
	(X86_TUNE_USE_GATHER_8PARTS): Ditto.
	(X86_TUNE_AVOID_128FMA_CHAINS): Ditto.
	* doc/extend.texi: Add details about yongfeng.
	* doc/invoke.texi: Ditto.
	* config/i386/yongfeng.md: New file to describe yongfeng processor.

gcc/testsuite/ChangeLog:

	* g++.target/i386/mv32.C: Handle new -march.
	* gcc.target/i386/funcspec-56.inc: Ditto.

gcc/common/config/i386/cpuinfo.h

@@ -663,6 +663,12 @@ get_zhaoxin_cpu (struct __processor_model *cpu_model,
 	  reset_cpu_feature (cpu_model, cpu_features2, FEATURE_F16C);
 	  cpu_model->__cpu_subtype = ZHAOXIN_FAM7H_LUJIAZUI;
 	}
+     else if (model >= 0x5b)
+	{
+	  cpu = "yongfeng";
+	  CHECK___builtin_cpu_is ("yongfeng");
+	  cpu_model->__cpu_subtype = ZHAOXIN_FAM7H_YONGFENG;
+	}
       break;
     default:
       break;

gcc/common/config/i386/i386-common.cc

@@ -2098,6 +2098,7 @@ const char *const processor_names[] =
   "pantherlake",
   "intel",
   "lujiazui",
+  "yongfeng",
   "geode",
   "k6",
   "athlon",
@@ -2305,12 +2306,11 @@ const pta processor_alias_table[] =
     PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3
       | PTA_SSSE3 | PTA_SSE4_1 | PTA_FXSR, 0, P_NONE},
   {"lujiazui", PROCESSOR_LUJIAZUI, CPU_LUJIAZUI,
-    PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3
-	| PTA_CX16 | PTA_ABM | PTA_SSSE3 | PTA_SSE4_1
-	| PTA_SSE4_2 | PTA_AES | PTA_PCLMUL | PTA_BMI | PTA_BMI2
-	| PTA_PRFCHW | PTA_FXSR | PTA_XSAVE | PTA_XSAVEOPT | PTA_FSGSBASE
-	| PTA_RDRND | PTA_MOVBE | PTA_ADX | PTA_RDSEED | PTA_POPCNT,
+	PTA_LUJIAZUI,
 	M_CPU_SUBTYPE (ZHAOXIN_FAM7H_LUJIAZUI), P_NONE},
+  {"yongfeng", PROCESSOR_YONGFENG, CPU_YONGFENG,
+	PTA_YONGFENG,
+	M_CPU_SUBTYPE (ZHAOXIN_FAM7H_YONGFENG), P_NONE},
   {"k8", PROCESSOR_K8, CPU_K8,
     PTA_64BIT | PTA_MMX | PTA_3DNOW | PTA_3DNOW_A | PTA_SSE
       | PTA_SSE2 | PTA_NO_SAHF | PTA_FXSR, 0, P_NONE},

gcc/common/config/i386/i386-cpuinfo.h

@@ -103,6 +103,7 @@ enum processor_subtypes
   INTEL_COREI7_ARROWLAKE,
   INTEL_COREI7_ARROWLAKE_S,
   INTEL_COREI7_PANTHERLAKE,
+  ZHAOXIN_FAM7H_YONGFENG,
   CPU_SUBTYPE_MAX
 };
 

gcc/config.gcc

@@ -706,7 +706,7 @@ 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 lujiazui x86-64 x86-64-v2 x86-64-v3 x86-64-v4 \
+nano-x2 eden-x4 nano-x4 lujiazui yongfeng x86-64 x86-64-v2 x86-64-v3 x86-64-v4 \
 sierraforest graniterapids graniterapids-d grandridge arrowlake arrowlake-s \
 clearwaterforest pantherlake native"
 
@@ -3811,6 +3811,10 @@ case ${target} in
 	arch=lujiazui
 	cpu=lujiazui
 	;;
+      yongfeng-*)
+	arch=yongfeng
+	cpu=yongfeng
+	;;
       pentium2-*)
 	arch=pentium2
 	cpu=pentium2
@@ -3924,10 +3928,14 @@ case ${target} in
 	arch=k8
 	cpu=k8
 	;;
-    lujiazui-*)
+      lujiazui-*)
 	arch=lujiazui
 	cpu=lujiazui
 	;;
+      yongfeng-*)
+	arch=yongfeng
+	cpu=yongfeng
+	;;
       nocona-*)
 	arch=nocona
 	cpu=nocona

gcc/config/i386/driver-i386.cc

@@ -530,6 +530,8 @@ const char *host_detect_local_cpu (int argc, const char **argv)
 	case 7:
 	  if (model == 0x3b)
 	    processor = PROCESSOR_LUJIAZUI;
+	  else if (model >= 0x5b)
+	    processor = PROCESSOR_YONGFENG;
 	  break;
 	default:
 	  break;
@@ -817,6 +819,9 @@ const char *host_detect_local_cpu (int argc, const char **argv)
     case PROCESSOR_LUJIAZUI:
       cpu = "lujiazui";
       break;
+    case PROCESSOR_YONGFENG:
+      cpu = "yongfeng";
+      break;
 
     default:
       /* Use something reasonable.  */

gcc/config/i386/i386-c.cc

@@ -148,6 +148,10 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
       def_or_undef (parse_in, "__lujiazui");
       def_or_undef (parse_in, "__lujiazui__");
       break;
+    case PROCESSOR_YONGFENG:
+      def_or_undef (parse_in, "__yongfeng");
+      def_or_undef (parse_in, "__yongfeng__");
+      break;
     case PROCESSOR_PENTIUM4:
       def_or_undef (parse_in, "__pentium4");
       def_or_undef (parse_in, "__pentium4__");
@@ -379,6 +383,9 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
     case PROCESSOR_LUJIAZUI:
       def_or_undef (parse_in, "__tune_lujiazui__");
        break;
+    case PROCESSOR_YONGFENG:
+      def_or_undef (parse_in, "__tune_yongfeng__");
+       break;
     case PROCESSOR_PENTIUM4:
       def_or_undef (parse_in, "__tune_pentium4__");
       break;

gcc/config/i386/i386-options.cc

@@ -154,6 +154,8 @@ along with GCC; see the file COPYING3.  If not see
 	       | m_TIGERLAKE | m_COOPERLAKE | m_ROCKETLAKE)
 
 #define m_LUJIAZUI (HOST_WIDE_INT_1U<<PROCESSOR_LUJIAZUI)
+#define m_YONGFENG (HOST_WIDE_INT_1U<<PROCESSOR_YONGFENG)
+#define m_ZHAOXIN  (m_LUJIAZUI | m_YONGFENG)
 
 #define m_GEODE (HOST_WIDE_INT_1U<<PROCESSOR_GEODE)
 #define m_K6 (HOST_WIDE_INT_1U<<PROCESSOR_K6)
@@ -792,6 +794,7 @@ static const struct processor_costs *processor_cost_table[] =
   &alderlake_cost,
   &intel_cost,
   &lujiazui_cost,
+  &yongfeng_cost,
   &geode_cost,
   &k6_cost,
   &athlon_cost,

gcc/config/i386/i386.h

@@ -2297,6 +2297,7 @@ enum processor_type
   PROCESSOR_PANTHERLAKE,
   PROCESSOR_INTEL,
   PROCESSOR_LUJIAZUI,
+  PROCESSOR_YONGFENG,
   PROCESSOR_GEODE,
   PROCESSOR_K6,
   PROCESSOR_ATHLON,
@@ -2435,6 +2436,14 @@ constexpr wide_int_bitmask PTA_ZNVER4 = PTA_ZNVER3 | PTA_AVX512F | PTA_AVX512DQ
   | PTA_AVX512BF16 | PTA_AVX512VBMI | PTA_AVX512VBMI2 | PTA_GFNI
   | PTA_AVX512VNNI | PTA_AVX512BITALG | PTA_AVX512VPOPCNTDQ;
 
+constexpr wide_int_bitmask PTA_LUJIAZUI = PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2
+  | PTA_SSE3 | PTA_CX16 | PTA_ABM | PTA_SSSE3 | PTA_SSE4_1 | PTA_SSE4_2 | PTA_AES
+  | PTA_PCLMUL | PTA_BMI | PTA_BMI2 | PTA_PRFCHW | PTA_FXSR | PTA_XSAVE | PTA_XSAVEOPT
+  | PTA_FSGSBASE | PTA_RDRND | PTA_MOVBE | PTA_ADX | PTA_RDSEED | PTA_POPCNT;
+
+constexpr wide_int_bitmask PTA_YONGFENG = PTA_LUJIAZUI | PTA_AVX | PTA_AVX2 | PTA_F16C
+  | PTA_FMA | PTA_SHA | PTA_LZCNT;
+
 #ifndef GENERATOR_FILE
 
 #include "insn-attr-common.h"

gcc/config/i386/i386.md

@@ -508,7 +508,7 @@
 
 ;; Processor type.
 (define_attr "cpu" "none,pentium,pentiumpro,geode,k6,athlon,k8,core2,nehalem,
-		    atom,slm,glm,haswell,generic,lujiazui,amdfam10,bdver1,
+		    atom,slm,glm,haswell,generic,lujiazui,yongfeng,amdfam10,bdver1,
 		    bdver2,bdver3,bdver4,btver2,znver1,znver2,znver3,znver4"
   (const (symbol_ref "ix86_schedule")))
 
@@ -1382,6 +1382,7 @@
 (include "core2.md")
 (include "haswell.md")
 (include "lujiazui.md")
+(include "yongfeng.md")
 
 
 ;; Operand and operator predicates and constraints

gcc/config/i386/lujiazui.md

@@ -137,7 +137,7 @@
 (define_insn_reservation "lua_lea" 1
 			 (and (eq_attr "cpu" "lujiazui")
 				  (eq_attr "type" "lea"))
-			 "hsw_decodern,lua_p45")
+			 "lua_decodern,lua_p45")
 
 (define_insn_reservation "lua_shift_rotate" 1
 			 (and (eq_attr "cpu" "lujiazui")

gcc/config/i386/x86-tune-costs.h

@@ -3393,6 +3393,122 @@ struct processor_costs lujiazui_cost = {
   2,					/* Small unroll factor.  */
 };
 
+/* yongfeng_cost should produce code tuned for ZHAOXIN yongfeng CPU.  */
+static stringop_algs yongfeng_memcpy[2] = {
+  {libcall, {{6, unrolled_loop, true}, {256, unrolled_loop, false},
+			 {-1, libcall, false}}},
+  {libcall, {{8, loop, false}, {512, unrolled_loop, false},
+			 {-1, libcall, false}}}};
+static stringop_algs yongfeng_memset[2] = {
+  {libcall, {{6, loop_1_byte, false}, {128, loop, false},
+			 {-1, libcall, false}}},
+  {libcall, {{2, rep_prefix_4_byte, false}, {64, loop, false},
+			 {1024, vector_loop, false},
+			 {-1, libcall, false}}}};
+static const
+struct processor_costs yongfeng_cost = {
+  {
+  /* Start of register allocator costs.  integer->integer move cost is 2.  */
+  8,				/* cost for loading QImode using movzbl.  */
+  {8, 8, 8},			/* cost of loading integer registers
+					   in QImode, HImode and SImode.
+					   Relative to reg-reg move (2).  */
+  {8, 8, 8},			/* cost of storing integer registers.  */
+  2,					/* cost of reg,reg fld/fst.  */
+  {8, 8, 8},			/* cost of loading fp registers
+				in SFmode, DFmode and XFmode.  */
+  {8, 8, 8},			/* cost of storing fp registers
+				in SFmode, DFmode and XFmode.  */
+  2,				/* cost of moving MMX register.  */
+  {8, 8},			/* cost of loading MMX registers
+				in SImode and DImode.  */
+  {8, 8},			/* cost of storing MMX registers
+				in SImode and DImode.  */
+  2, 3, 4,			/* cost of moving XMM,YMM,ZMM register.  */
+  {8, 8, 8, 10, 15},	/* cost of loading SSE registers
+				in 32,64,128,256 and 512-bit.  */
+  {8, 8, 8, 10, 15},	/* cost of storing SSE registers
+				in 32,64,128,256 and 512-bit.  */
+  8, 8,				/* SSE->integer and integer->SSE moves.  */
+  8, 8,				/* mask->integer and integer->mask moves.  */
+  {8, 8, 8},		/* cost of loading mask register
+				in QImode, HImode, SImode.  */
+  {8, 8, 8},		/* cost if storing mask register
+				in QImode, HImode, SImode.  */
+  2,				/* cost of moving mask register.  */
+  /* End of register allocator costs.  */
+  },
+
+  COSTS_N_INSNS (1),			/* cost of an add instruction.  */
+  COSTS_N_INSNS (1),		        /* cost of a lea instruction.  */
+  COSTS_N_INSNS (1),			/* variable shift costs.  */
+  COSTS_N_INSNS (1),			/* constant shift costs.  */
+  {COSTS_N_INSNS (2),			/* cost of starting multiply for QI.  */
+   COSTS_N_INSNS (3),			/*				 HI.  */
+   COSTS_N_INSNS (2),			/*				 SI.  */
+   COSTS_N_INSNS (2),			/*				 DI.  */
+   COSTS_N_INSNS (3)},		/*				 other.  */
+  0,				/* cost of multiply per each bit set.  */
+  {COSTS_N_INSNS (8),			/* cost of a divide/mod for QI.  */
+   COSTS_N_INSNS (9),			/*			    HI.  */
+   COSTS_N_INSNS (8),			/*			    SI.  */
+   COSTS_N_INSNS (41),			/*			    DI.  */
+   COSTS_N_INSNS (41)},		/*			    other.  */
+  COSTS_N_INSNS (1),			/* cost of movsx.  */
+  COSTS_N_INSNS (1),			/* cost of movzx.  */
+  8,					/* "large" insn.  */
+  17,					/* MOVE_RATIO.  */
+  6,					/* CLEAR_RATIO.  */
+  {8, 8, 8},				/* cost of loading integer registers
+					   in QImode, HImode and SImode.
+					   Relative to reg-reg move (2).  */
+  {8, 8, 8},			/* cost of storing integer registers.  */
+  {8, 8, 8, 12, 15},			/* cost of loading SSE register
+				in 32bit, 64bit, 128bit, 256bit and 512bit.  */
+  {8, 8, 8, 12, 15},			/* cost of storing SSE register
+				in 32bit, 64bit, 128bit, 256bit and 512bit.  */
+  {8, 8, 8, 12, 15},			/* cost of unaligned loads.  */
+  {8, 8, 8, 12, 15},			/* cost of unaligned storess.  */
+  2, 3, 4,			/* cost of moving XMM,YMM,ZMM register.  */
+  8,				/* cost of moving SSE register to integer.  */
+  18, 6,				/* Gather load static, per_elt.  */
+  18, 6,				/* Gather store static, per_elt.  */
+  32,				  	/* size of l1 cache.  */
+  256,					/* size of l2 cache.  */
+  64,					/* size of prefetch block.  */
+  12,					/* number of parallel prefetches.  */
+  3,					/* Branch cost.  */
+  COSTS_N_INSNS (3),			/* cost of FADD and FSUB insns.  */
+  COSTS_N_INSNS (3),			/* cost of FMUL instruction.  */
+  COSTS_N_INSNS (14),			/* cost of FDIV instruction.  */
+  COSTS_N_INSNS (1),			/* cost of FABS instruction.  */
+  COSTS_N_INSNS (1),			/* cost of FCHS instruction.  */
+  COSTS_N_INSNS (40),			/* cost of FSQRT instruction.  */
+
+  COSTS_N_INSNS (1),			/* cost of cheap SSE instruction.  */
+  COSTS_N_INSNS (3),			/* cost of ADDSS/SD SUBSS/SD insns.  */
+  COSTS_N_INSNS (3),			/* cost of MULSS instruction.  */
+  COSTS_N_INSNS (3),			/* cost of MULSD instruction.  */
+  COSTS_N_INSNS (5),			/* cost of FMA SS instruction.  */
+  COSTS_N_INSNS (5),			/* cost of FMA SD instruction.  */
+  COSTS_N_INSNS (10),			/* cost of DIVSS instruction.  */
+  COSTS_N_INSNS (14),			/* cost of DIVSD instruction.  */
+  COSTS_N_INSNS (20),			/* cost of SQRTSS instruction.  */
+  COSTS_N_INSNS (35),			/* cost of SQRTSD instruction.  */
+  4, 4, 4, 4,				/* reassoc int, fp, vec_int, vec_fp.  */
+  yongfeng_memcpy,
+  yongfeng_memset,
+  COSTS_N_INSNS (3),			/* cond_taken_branch_cost.  */
+  COSTS_N_INSNS (1),			/* cond_not_taken_branch_cost.  */
+  "16:11:8",				/* Loop alignment.  */
+  "16:11:8",				/* Jump alignment.  */
+  "0:0:8",				/* Label alignment.  */
+  "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+};
+
+
 /* Generic should produce code tuned for Core-i7 (and newer chips)
    and btver1 (and newer chips).  */
 

gcc/config/i386/x86-tune-sched.cc

@@ -79,6 +79,7 @@ ix86_issue_rate (void)
     case PROCESSOR_CASCADELAKE:
     case PROCESSOR_CANNONLAKE:
     case PROCESSOR_ALDERLAKE:
+    case PROCESSOR_YONGFENG:
     case PROCESSOR_GENERIC:
       return 4;
 
@@ -384,7 +385,6 @@ ix86_adjust_cost (rtx_insn *insn, int dep_type, rtx_insn *dep_insn, int cost,
 
     case PROCESSOR_ATHLON:
     case PROCESSOR_K8:
-    case PROCESSOR_LUJIAZUI:
       memory = get_attr_memory (insn);
 
       /* Show ability of reorder buffer to hide latency of load by executing
@@ -445,6 +445,31 @@ ix86_adjust_cost (rtx_insn *insn, int dep_type, rtx_insn *dep_insn, int cost,
 	}
       break;
 
+    case PROCESSOR_YONGFENG:
+      /* Stack engine allows to execute push&pop instructions in parallel.  */
+      if ((insn_type == TYPE_PUSH || insn_type == TYPE_POP)
+	  && (dep_insn_type == TYPE_PUSH || dep_insn_type == TYPE_POP))
+	return 0;
+      /* FALLTHRU */
+
+    case PROCESSOR_LUJIAZUI:
+      memory = get_attr_memory (insn);
+
+      /* Show ability of reorder buffer to hide latency of load by executing
+	  in parallel with previous instruction in case
+	  previous instruction is not needed to compute the address.  */
+      if ((memory == MEMORY_LOAD || memory == MEMORY_BOTH)
+	  && !ix86_agi_dependent (dep_insn, insn))
+	  {
+	    int loadcost = 4;
+
+	    if (cost >= loadcost)
+	      cost -= loadcost;
+	    else
+	      cost = 0;
+	  }
+       break;
+
     case PROCESSOR_CORE2:
     case PROCESSOR_NEHALEM:
     case PROCESSOR_SANDYBRIDGE: