[X86] Support -march=gracemont

[FreddyYe]

Summary

gracemont has some different tuning features from alderlake.

[RKSimon]

clang/lib/Basic/Targets/X86.cpp

553

Why not handle this above (below tremont) as the next in the *mont series?

[FreddyYe]

clang/lib/Basic/Targets/X86.cpp

553

Good catch. This isn't a short story... In short words, it was to save codes in predefined-arch-macros.c.
If set gracemont as a series of atom processors, macros like corei7(predefined-arch-macros.c:2061-2062) won't be generated by -march=gracemont, and for history reasons, atom series processors defined some extra macros of their names, like "tremont", "goldmont", ... but these macros are not used any longer IIRC. So I decided to define gracemont as a non-atom series one.

[RKSimon]

clang/lib/Basic/Targets/X86.cpp

553

Hmm - how about we move it after Tremont and then add a comment explaining that going forward atom/e-cores will share p-core defines?

case CK_Tremont:
    defineCPUMacros(Builder, "tremont");
    break;
case CK_Gracemont:
  // Gracemont and later atom-cores use p-core cpu macros.
  [[fallthrough]];
case CK_Nehalem:
 ...

[FreddyYe]

Address comment.

clang/lib/Basic/Targets/X86.cpp

553

Looks good! I refined a little bit and updated.

[RKSimon]

LGTM - cheers

clang/lib/Basic/Targets/X86.cpp

case CK_Goldmont:
     defineCPUMacros(Builder, "goldmont");
     break;
   case CK_GoldmontPlus:
     defineCPUMacros(Builder, "goldmont_plus");
     break;
   case CK_Tremont:
     defineCPUMacros(Builder, "tremont");
     break;
+  // Gracemont and later atom-cores use P-core cpu macros.
+  case CK_Gracemont:
   case CK_Nehalem:
   case CK_Westmere:
   case CK_SandyBridge:
   case CK_IvyBridge:
   case CK_Haswell:
   case CK_Broadwell:
   case CK_SkylakeClient:
   case CK_SkylakeServer:
   case CK_Cascadelake:
   case CK_Cooperlake:
   case CK_Cannonlake:
   case CK_IcelakeClient:
   case CK_Rocketlake:
   case CK_IcelakeServer:
   case CK_Tigerlake:
   case CK_SapphireRapids:
   case CK_Alderlake:
   case CK_Raptorlake:
   case CK_Meteorlake:
   case CK_Arrowlake:
   case CK_ArrowlakeS:
   case CK_Lunarlake:
   case CK_Sierraforest:
   case CK_Grandridge:
   case CK_Graniterapids:
   case CK_GraniterapidsD:
   case CK_Emeraldrapids:
     // FIXME: Historically, we defined this legacy name, it would be nice to
     // remove it at some point. We've never exposed fine-grained names for
     // recent primary x86 CPUs, and we should keep it that way.
     defineCPUMacros(Builder, "corei7");
switch (CPU) {
     case CK_Prescott:
     case CK_Nocona:
     // Atom
     case CK_Bonnell:
     case CK_Silvermont:
     case CK_Goldmont:
     case CK_GoldmontPlus:
     case CK_Tremont:
+    case CK_Gracemont:
 
     case CK_Westmere:
     case CK_SandyBridge:
     case CK_IvyBridge:
     case CK_Haswell:
     case CK_Broadwell:
     case CK_SkylakeClient:
     case CK_SkylakeServer:

clang/test/CodeGen/attr-cpuspecific-cpus.c

 ATTR(cpu_specific(sierraforest)) void CPU30(void){}
 ATTR(cpu_specific(grandridge)) void CPU31(void){}
 ATTR(cpu_specific(graniterapids)) void CPU32(void){}
 ATTR(cpu_specific(emeraldrapids)) void CPU33(void){}
 ATTR(cpu_specific(graniterapids_d)) void CPU34(void){}
 ATTR(cpu_specific(arrowlake)) void CPU35(void){}
 ATTR(cpu_specific(arrowlake_s)) void CPU36(void){}
 ATTR(cpu_specific(lunarlake)) void CPU37(void){}
+ATTR(cpu_specific(gracemont)) void CPU38(void){}

clang/test/CodeGen/attr-target-mv.c

 int __attribute__((target("arch=sierraforest"))) foo(void) {return 16;}
 int __attribute__((target("arch=grandridge"))) foo(void) {return 17;}
 int __attribute__((target("arch=graniterapids"))) foo(void) {return 18;}
 int __attribute__((target("arch=emeraldrapids"))) foo(void) {return 19;}
 int __attribute__((target("arch=graniterapids-d"))) foo(void) {return 20;}
 int __attribute__((target("arch=arrowlake"))) foo(void) {return 21;}
 int __attribute__((target("arch=arrowlake-s"))) foo(void) {return 22;}
 int __attribute__((target("arch=lunarlake"))) foo(void) {return 23;}
+int __attribute__((target("arch=gracemont"))) foo(void) {return 24;}
 int __attribute__((target("default"))) foo(void) { return 2; }
 
 int bar(void) {
   return foo();
 }
 
 inline int __attribute__((target("sse4.2"))) foo_inline(void) { return 0; }
 inline int __attribute__((target("arch=sandybridge"))) foo_inline(void);

 // LINUX: define{{.*}} i32 @foo.arch_graniterapids-d()
 // LINUX: ret i32 20
 // LINUX: define{{.*}} i32 @foo.arch_arrowlake()
 // LINUX: ret i32 21
 // LINUX: define{{.*}} i32 @foo.arch_arrowlake-s()
 // LINUX: ret i32 22
 // LINUX: define{{.*}} i32 @foo.arch_lunarlake()
 // LINUX: ret i32 23
+// LINUX: define{{.*}} i32 @foo.arch_gracemont()
+// LINUX: ret i32 24
 // LINUX: define{{.*}} i32 @foo()
 // LINUX: ret i32 2
 // LINUX: define{{.*}} i32 @bar()
 // LINUX: call i32 @foo.ifunc()
 
 // WINDOWS: define dso_local i32 @foo.sse4.2()
 // WINDOWS: ret i32 0
 // WINDOWS: define dso_local i32 @foo.arch_ivybridge()

 // WINDOWS: define dso_local i32 @foo.arch_graniterapids-d()
 // WINDOWS: ret i32 20
 // WINDOWS: define dso_local i32 @foo.arch_arrowlake()
 // WINDOWS: ret i32 21
 // WINDOWS: define dso_local i32 @foo.arch_arrowlake-s()
 // WINDOWS: ret i32 22
 // WINDOWS: define dso_local i32 @foo.arch_lunarlake()
 // WINDOWS: ret i32 23
+// WINDOWS: define dso_local i32 @foo.arch_gracemont()
+// WINDOWS: ret i32 24
 // WINDOWS: define dso_local i32 @foo()
 // WINDOWS: ret i32 2
 // WINDOWS: define dso_local i32 @bar()
 // WINDOWS: call i32 @foo.resolver()
 
 // LINUX: define weak_odr ptr @foo.resolver() comdat
 // LINUX: call void @__cpu_indicator_init()
 // LINUX: ret ptr @foo.arch_sandybridge

clang/test/CodeGen/target-builtin-noerror.c

void verifycpustrings(void) {
   (void)__builtin_cpu_is("sierraforest");
   (void)__builtin_cpu_is("silvermont");
   (void)__builtin_cpu_is("skylake");
   (void)__builtin_cpu_is("skylake-avx512");
   (void)__builtin_cpu_is("slm");
   (void)__builtin_cpu_is("tigerlake");
   (void)__builtin_cpu_is("sapphirerapids");
   (void)__builtin_cpu_is("tremont");
+  (void)__builtin_cpu_is("gracemont");
   (void)__builtin_cpu_is("westmere");
   (void)__builtin_cpu_is("znver1");
   (void)__builtin_cpu_is("znver2");
   (void)__builtin_cpu_is("znver3");
   (void)__builtin_cpu_is("znver4");
 }

clang/test/Driver/x86-march.c

 // RUN: %clang --target=x86_64 -c -### %s -march=arrowlake-s 2>&1 \
 // RUN:   | FileCheck %s -check-prefix=arrowlake-s
 // arrowlake-s: "-target-cpu" "arrowlake-s"
 //
 // RUN: %clang --target=x86_64 -c -### %s -march=lunarlake 2>&1 \
 // RUN:   | FileCheck %s -check-prefix=lunarlake
 // lunarlake: "-target-cpu" "lunarlake"
 //
+// RUN: %clang -target x86_64-unknown-unknown -c -### %s -march=gracemont 2>&1 \
+// RUN:   | FileCheck %s -check-prefix=gracemont
+// gracemont: "-target-cpu" "gracemont"
+//
 // RUN: %clang -target x86_64-unknown-unknown -c -### %s -march=lakemont 2>&1 \
 // RUN:   | FileCheck %s -check-prefix=lakemont
 // lakemont: "-target-cpu" "lakemont"
 //
 // RUN: %clang -target x86_64-unknown-unknown -c -### %s -march=bonnell 2>&1 \
 // RUN:   | FileCheck %s -check-prefix=bonnell
 // bonnell: "-target-cpu" "bonnell"
 //

clang/test/Misc/target-invalid-cpu-note.c

 // Use CHECK-NEXT instead of multiple CHECK-SAME to ensure we will fail if there is anything extra in the output.
 // RUN: not %clang_cc1 -triple armv5--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix ARM
 // ARM: error: unknown target CPU 'not-a-cpu'
 // ARM-NEXT: note: valid target CPU values are: arm8, arm810, strongarm, strongarm110, strongarm1100, strongarm1110, arm7tdmi, arm7tdmi-s, arm710t, arm720t, arm9, arm9tdmi, arm920, arm920t, arm922t, arm940t, ep9312, arm10tdmi, arm1020t, arm9e, arm946e-s, arm966e-s, arm968e-s, arm10e, arm1020e, arm1022e, arm926ej-s, arm1136j-s, arm1136jf-s, mpcore, mpcorenovfp, arm1176jz-s, arm1176jzf-s, arm1156t2-s, arm1156t2f-s, cortex-m0, cortex-m0plus, cortex-m1, sc000, cortex-a5, cortex-a7, cortex-a8, cortex-a9, cortex-a12, cortex-a15, cortex-a17, krait, cortex-r4, cortex-r4f, cortex-r5, cortex-r7, cortex-r8, cortex-r52, sc300, cortex-m3, cortex-m4, cortex-m7, cortex-m23, cortex-m33, cortex-m35p, cortex-m55, cortex-m85, cortex-a32, cortex-a35, cortex-a53, cortex-a55, cortex-a57, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-x1, cortex-x1c, neoverse-n1, neoverse-n2, neoverse-v1, cyclone, exynos-m3, exynos-m4, exynos-m5, kryo, iwmmxt, xscale, swift{{$}}
 
 // RUN: not %clang_cc1 -triple arm64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix AARCH64
 // AARCH64: error: unknown target CPU 'not-a-cpu'
 // AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-a715, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, neoverse-v2, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-m1, apple-m2, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, ampere1a, grace{{$}}
 
 // RUN: not %clang_cc1 -triple arm64--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_AARCH64
 // TUNE_AARCH64: error: unknown target CPU 'not-a-cpu'
 // TUNE_AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-a715, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, neoverse-v2, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16,  apple-m1, apple-m2, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, ampere1a, grace{{$}}
 
 // RUN: not %clang_cc1 -triple i386--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix X86
 // X86: error: unknown target CPU 'not-a-cpu'
-// X86-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, x86-64-v2, x86-64-v3, x86-64-v4, geode{{$}}
+// X86-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, x86-64-v2, x86-64-v3, x86-64-v4, geode{{$}}
 
 // RUN: not %clang_cc1 -triple x86_64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix X86_64
 // X86_64: error: unknown target CPU 'not-a-cpu'
-// X86_64-NEXT: note: valid target CPU values are: nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, knl, knm, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, x86-64-v2, x86-64-v3, x86-64-v4{{$}}
+// X86_64-NEXT: note: valid target CPU values are: nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, knl, knm, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, x86-64-v2, x86-64-v3, x86-64-v4{{$}}
 
 // RUN: not %clang_cc1 -triple i386--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_X86
 // TUNE_X86: error: unknown target CPU 'not-a-cpu'
-// TUNE_X86-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, geode{{$}}
+// TUNE_X86-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, geode{{$}}
 
 // RUN: not %clang_cc1 -triple x86_64--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_X86_64
 // TUNE_X86_64: error: unknown target CPU 'not-a-cpu'
-// TUNE_X86_64-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, geode{{$}}
+// TUNE_X86_64-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, arrowlake, arrowlake-s, lunarlake, gracemont, sierraforest, grandridge, graniterapids, graniterapids-d, emeraldrapids, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, geode{{$}}
 
 // RUN: not %clang_cc1 -triple nvptx--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix NVPTX
 // NVPTX: error: unknown target CPU 'not-a-cpu'
 // NVPTX-NEXT: note: valid target CPU values are: sm_20, sm_21, sm_30, sm_32, sm_35, sm_37, sm_50, sm_52, sm_53, sm_60, sm_61, sm_62, sm_70, sm_72, sm_75, sm_80, sm_86, sm_87, sm_89, sm_90, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151{{$}}
 
 // RUN: not %clang_cc1 -triple r600--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix R600
 // R600: error: unknown target CPU 'not-a-cpu'
 // R600-NEXT: note: valid target CPU values are: r600, rv630, rv635, r630, rs780, rs880, rv610, rv620, rv670, rv710, rv730, rv740, rv770, cedar, palm, cypress, hemlock, juniper, redwood, sumo, sumo2, barts, caicos, aruba, cayman, turks{{$}}

clang/test/Preprocessor/predefined-arch-macros.c

 // RUN:     -target i386-unknown-linux \
 // RUN:   | FileCheck -match-full-lines %s -check-prefix=CHECK_ADL_M32
 // RUN: %clang -march=raptorlake -m32 -E -dM %s -o - 2>&1 \
 // RUN:     -target i386-unknown-linux \
 // RUN:   | FileCheck -match-full-lines %s -check-prefix=CHECK_ADL_M32
 // RUN: %clang -march=meteorlake -m32 -E -dM %s -o - 2>&1 \
 // RUN:     -target i386-unknown-linux \
 // RUN:   | FileCheck -match-full-lines %s -check-prefix=CHECK_ADL_M32
+// RUN: %clang -march=gracemont -m32 -E -dM %s -o - 2>&1 \
+// RUN:     -target i386-unknown-linux \
+// RUN:   | FileCheck -match-full-lines %s -check-prefix=CHECK_ADL_M32
 // CHECK_ADL_M32: #define __ADX__ 1
 // CHECK_ADL_M32: #define __AES__ 1
 // CHECK_ADL_M32: #define __AVX2__ 1
 // CHECK_ADL_M32-NOT: AVX512
 // CHECK_ADL_M32: #define __AVXVNNI__ 1
 // CHECK_ADL_M32: #define __AVX__ 1
 // CHECK_ADL_M32: #define __BMI2__ 1
 // CHECK_ADL_M32: #define __BMI__ 1

 // RUN:     -target i386-unknown-linux \
 // RUN:   | FileCheck -match-full-lines %s -check-prefix=CHECK_ADL_M64
 // RUN: %clang -march=raptorlake -m64 -E -dM %s -o - 2>&1 \
 // RUN:     -target i386-unknown-linux \
 // RUN:   | FileCheck -match-full-lines %s -check-prefix=CHECK_ADL_M64
 // RUN: %clang -march=meteorlake -m64 -E -dM %s -o - 2>&1 \
 // RUN:     -target i386-unknown-linux \
 // RUN:   | FileCheck -match-full-lines %s -check-prefix=CHECK_ADL_M64
+// RUN: %clang -march=gracemont -m64 -E -dM %s -o - 2>&1 \
+// RUN:     -target i386-unknown-linux \
+// RUN:   | FileCheck -match-full-lines %s -check-prefix=CHECK_ADL_M64
 // CHECK_ADL_M64: #define __ADX__ 1
 // CHECK_ADL_M64: #define __AES__ 1
 // CHECK_ADL_M64: #define __AVX2__ 1
 // CHECK_ADL_M64-NOT: AVX512
 // CHECK_ADL_M64: #define __AVXVNNI__ 1
 // CHECK_ADL_M64: #define __AVX__ 1
 // CHECK_ADL_M64: #define __BMI2__ 1
 // CHECK_ADL_M64: #define __BMI__ 1

compiler-rt/lib/builtins/cpu_model.c

case 6:
     case 0x9a:
     // Raptorlake:
     case 0xb7:
     case 0xba:
     case 0xbf:
     // Meteorlake:
     case 0xaa:
     case 0xac:
+    // Gracemont:
+    case 0xbe:
       CPU = "alderlake";
       *Type = INTEL_COREI7;
       *Subtype = INTEL_COREI7_ALDERLAKE;
       break;
 
     // Arrowlake:
     case 0xc5:
       CPU = "arrowlake";

llvm/include/llvm/TargetParser/X86TargetParser.h

enum CPUKind {
   CK_Nocona,
   CK_Core2,
   CK_Penryn,
   CK_Bonnell,
   CK_Silvermont,
   CK_Goldmont,
   CK_GoldmontPlus,
   CK_Tremont,
+  CK_Gracemont,
   CK_Nehalem,
   CK_Westmere,
   CK_SandyBridge,
   CK_IvyBridge,
   CK_Haswell,
   CK_Broadwell,
   CK_SkylakeClient,
   CK_SkylakeServer,

llvm/include/llvm/TargetParser/X86TargetParser.def

 X86_CPU_SUBTYPE(INTEL_COREI7_ARROWLAKE,      "arrowlake")
 X86_CPU_SUBTYPE(INTEL_COREI7_ARROWLAKE_S,    "arrowlake-s")
 
 // Alternate names supported by __builtin_cpu_is and target multiversioning.
 X86_CPU_SUBTYPE_ALIAS(INTEL_COREI7_ALDERLAKE, "raptorlake")
 X86_CPU_SUBTYPE_ALIAS(INTEL_COREI7_ALDERLAKE, "meteorlake")
 X86_CPU_SUBTYPE_ALIAS(INTEL_COREI7_SAPPHIRERAPIDS, "emeraldrapids")
 X86_CPU_SUBTYPE_ALIAS(INTEL_COREI7_ARROWLAKE_S,"lunarlake")
+X86_CPU_SUBTYPE_ALIAS(INTEL_COREI7_ALDERLAKE, "gracemont")
 
 #undef X86_CPU_SUBTYPE_ALIAS
 #undef X86_CPU_SUBTYPE
 
 // This macro is used for cpu types present in compiler-rt/libgcc. The third
 // parameter PRIORITY is as required by the attribute 'target' checking. Note
 // that not all are supported/prioritized by GCC, so synchronization with GCC's
 // implementation may require changing some existing values.

llvm/lib/Target/X86/X86.td

list<SubtargetFeature> ADLAdditionalFeatures = [FeatureSERIALIZE,
                                                   FeatureWAITPKG];
   list<SubtargetFeature> ADLAdditionalTuning = [TuningPERMFalseDeps,
                                                 TuningPreferMovmskOverVTest,
                                                 TuningFastImmVectorShift];
   list<SubtargetFeature> ADLTuning = !listconcat(SKLTuning, ADLAdditionalTuning);
   list<SubtargetFeature> ADLFeatures =
     !listconcat(TRMFeatures, ADLAdditionalFeatures);
 
+  // Gracemont
+  list<SubtargetFeature> GRTTuning = [TuningMacroFusion,
+                                      TuningSlow3OpsLEA,
+                                      TuningSlowDivide32,
+                                      TuningSlowDivide64,
+                                      TuningFastScalarFSQRT,
+                                      TuningFastVectorFSQRT,
+                                      TuningFast15ByteNOP,
+                                      TuningFastVariablePerLaneShuffle,
+                                      TuningPOPCNTFalseDeps,
+                                      TuningInsertVZEROUPPER];
+
   // Sierraforest
   list<SubtargetFeature> SRFAdditionalFeatures = [FeatureCMPCCXADD,
                                                   FeatureAVXIFMA,
                                                   FeatureAVXNECONVERT,
                                                   FeatureENQCMD,
                                                   FeatureUINTR,
                                                   FeatureAVXVNNIINT8];
   list<SubtargetFeature> SRFFeatures =
def : ProcModel<P, IceLakeModel,
                 ProcessorFeatures.ICXFeatures, ProcessorFeatures.ICXTuning>;
 }
 def : ProcModel<"tigerlake", IceLakeModel,
                 ProcessorFeatures.TGLFeatures, ProcessorFeatures.TGLTuning>;
 def : ProcModel<"sapphirerapids", SapphireRapidsModel,
                 ProcessorFeatures.SPRFeatures, ProcessorFeatures.SPRTuning>;
 def : ProcModel<"alderlake", AlderlakePModel,
                 ProcessorFeatures.ADLFeatures, ProcessorFeatures.ADLTuning>;
+// FIXME: Use Gracemont Schedule Model when it is ready.
+def : ProcModel<"gracemont", AlderlakePModel,
+                ProcessorFeatures.ADLFeatures, ProcessorFeatures.GRTTuning>;
 def : ProcModel<"raptorlake", AlderlakePModel,
                 ProcessorFeatures.ADLFeatures, ProcessorFeatures.ADLTuning>;
 def : ProcModel<"meteorlake", AlderlakePModel,
                 ProcessorFeatures.ADLFeatures, ProcessorFeatures.ADLTuning>;
 def : ProcModel<"arrowlake", AlderlakePModel,
                 ProcessorFeatures.SRFFeatures, ProcessorFeatures.ADLTuning>;
 foreach P = ["arrowlake-s", "arrowlake_s", "lunarlake"] in {
 def : ProcModel<P, AlderlakePModel,

llvm/lib/TargetParser/Host.cpp

case 0x8d:
       CPU = "tigerlake";
       *Type = X86::INTEL_COREI7;
       *Subtype = X86::INTEL_COREI7_TIGERLAKE;
       break;
 
     // Alderlake:
     case 0x97:
     case 0x9a:
+    // Gracemont
+    case 0xbe:
     // Raptorlake:
     case 0xb7:
     case 0xba:
     case 0xbf:
     // Meteorlake:
     case 0xaa:
     case 0xac:
       CPU = "alderlake";

llvm/lib/TargetParser/X86TargetParser.cpp

// Empty processor. Include X87 and CMPXCHG8 for backwards compatibility.
   // Meteorlake microarchitecture based processors.
   { {"meteorlake"}, CK_Meteorlake, FEATURE_AVX2, FeaturesAlderlake, 'p', false },
   // Arrowlake microarchitecture based processors.
   { {"arrowlake"}, CK_Arrowlake, FEATURE_AVX2, FeaturesSierraforest, 'p', false },
   { {"arrowlake-s"}, CK_ArrowlakeS, FEATURE_AVX2, FeaturesArrowlakeS, '\0', false },
   { {"arrowlake_s"}, CK_ArrowlakeS, FEATURE_AVX2, FeaturesArrowlakeS, 'p', true },
   // Lunarlake microarchitecture based processors.
   { {"lunarlake"}, CK_Lunarlake, FEATURE_AVX2, FeaturesArrowlakeS, 'p', false },
+  // Gracemont microarchitecture based processors.
+  { {"gracemont"}, CK_Gracemont, FEATURE_AVX2, FeaturesAlderlake, 'p', false },
   // Sierraforest microarchitecture based processors.
   { {"sierraforest"}, CK_Sierraforest, FEATURE_AVX2, FeaturesSierraforest, 'p', false },
   // Grandridge microarchitecture based processors.
   { {"grandridge"}, CK_Grandridge, FEATURE_AVX2, FeaturesGrandridge, 'p', false },
   // Granite Rapids microarchitecture based processors.
   { {"graniterapids"}, CK_Graniterapids, FEATURE_AVX512BF16, FeaturesGraniteRapids, 'n', false },
   // Granite Rapids D microarchitecture based processors.
   { {"graniterapids-d"}, CK_GraniterapidsD, FEATURE_AVX512BF16, FeaturesGraniteRapids | FeatureAMX_COMPLEX, '\0', false },

llvm/test/CodeGen/X86/cpus-intel.ll

 ; RUN: llc < %s -o /dev/null -mtriple=i686-unknown-unknown -mcpu=grandridge 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=i686-unknown-unknown -mcpu=graniterapids 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=i686-unknown-unknown -mcpu=graniterapids-d 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=i686-unknown-unknown -mcpu=emeraldrapids 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=i686-unknown-unknown -mcpu=arrowlake 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=i686-unknown-unknown -mcpu=arrowlake-s 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=i686-unknown-unknown -mcpu=arrowlake_s 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=i686-unknown-unknown -mcpu=lunarlake 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
+; RUN: llc < %s -o /dev/null -mtriple=i686-unknown-unknown -mcpu=gracemont 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=nocona 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=core2 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=core_2_duo_ssse3 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=penryn 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=core_2_duo_sse4_1 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=nehalem 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=corei7 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty

 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=sierraforest 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=grandridge 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=graniterapids 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=graniterapids-d 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=arrowlake 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=arrowlake-s 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=arrowlake_s 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=lunarlake 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
+; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=gracemont 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 
 define void @foo() {
   ret void
 }