FreddyYe updated this revision to Diff 486163.
FreddyYe marked 4 inline comments as done.
FreddyYe added a comment.
Address comments. Thanks for review!
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D140950/new/
https://reviews.llvm.org/D140950
Files:
clang/docs/ReleaseNotes.rst
clang/lib/Basic/Targets/X86.cpp
clang/test/CodeGen/attr-target-mv.c
clang/test/CodeGen/target-builtin-noerror.c
clang/test/Driver/x86-march.c
clang/test/Misc/target-invalid-cpu-note.c
clang/test/Preprocessor/predefined-arch-macros.c
compiler-rt/lib/builtins/cpu_model.c
llvm/docs/ReleaseNotes.rst
llvm/include/llvm/TargetParser/X86TargetParser.def
llvm/include/llvm/TargetParser/X86TargetParser.h
llvm/lib/Target/X86/X86.td
llvm/lib/TargetParser/Host.cpp
llvm/lib/TargetParser/X86TargetParser.cpp
llvm/test/CodeGen/X86/cpus-intel.ll
Index: llvm/test/CodeGen/X86/cpus-intel.ll
===================================================================
--- llvm/test/CodeGen/X86/cpus-intel.ll
+++ llvm/test/CodeGen/X86/cpus-intel.ll
@@ -22,6 +22,7 @@
; RUN: llc < %s -o /dev/null -mtriple=i686-unknown-unknown -mcpu=sierraforest 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
; 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=emeraldrapids 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
Index: llvm/lib/TargetParser/X86TargetParser.cpp
===================================================================
--- llvm/lib/TargetParser/X86TargetParser.cpp
+++ llvm/lib/TargetParser/X86TargetParser.cpp
@@ -391,8 +391,10 @@
{ {"sierraforest"}, CK_Sierraforest, FEATURE_AVX2, FeaturesSierraforest },
// Grandridge microarchitecture based processors.
{ {"grandridge"}, CK_Grandridge, FEATURE_AVX2, FeaturesGrandridge },
- // Graniterapids microarchitecture based processors.
+ // Granite Rapids microarchitecture based processors.
{ {"graniterapids"}, CK_Graniterapids, FEATURE_AVX512BF16, FeaturesGraniteRapids },
+ // Emerald Rapids microarchitecture based processors.
+ { {"emeraldrapids"}, CK_Emeraldrapids, FEATURE_AVX512BF16, FeaturesSapphireRapids },
// Knights Landing processor.
{ {"knl"}, CK_KNL, FEATURE_AVX512F, FeaturesKNL },
// Knights Mill processor.
Index: llvm/lib/TargetParser/Host.cpp
===================================================================
--- llvm/lib/TargetParser/Host.cpp
+++ llvm/lib/TargetParser/Host.cpp
@@ -848,6 +848,8 @@
*Subtype = X86::INTEL_COREI7_ICELAKE_SERVER;
break;
+ // Emerald Rapids:
+ case 0xcf:
// Sapphire Rapids:
case 0x8f:
CPU = "sapphirerapids";
Index: llvm/lib/Target/X86/X86.td
===================================================================
--- llvm/lib/Target/X86/X86.td
+++ llvm/lib/Target/X86/X86.td
@@ -1548,6 +1548,8 @@
ProcessorFeatures.ADLFeatures, ProcessorFeatures.ADLTuning>;
def : ProcModel<"graniterapids", SkylakeServerModel,
ProcessorFeatures.GNRFeatures, ProcessorFeatures.SPRTuning>;
+def : ProcModel<"emeraldrapids", SkylakeServerModel,
+ ProcessorFeatures.SPRFeatures, ProcessorFeatures.SPRTuning>;
// AMD CPUs.
Index: llvm/include/llvm/TargetParser/X86TargetParser.h
===================================================================
--- llvm/include/llvm/TargetParser/X86TargetParser.h
+++ llvm/include/llvm/TargetParser/X86TargetParser.h
@@ -109,6 +109,7 @@
CK_Sierraforest,
CK_Grandridge,
CK_Graniterapids,
+ CK_Emeraldrapids,
CK_KNL,
CK_KNM,
CK_Lakemont,
Index: llvm/include/llvm/TargetParser/X86TargetParser.def
===================================================================
--- llvm/include/llvm/TargetParser/X86TargetParser.def
+++ llvm/include/llvm/TargetParser/X86TargetParser.def
@@ -103,6 +103,7 @@
// 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")
#undef X86_CPU_SUBTYPE_ALIAS
#undef X86_CPU_SUBTYPE
Index: llvm/docs/ReleaseNotes.rst
===================================================================
--- llvm/docs/ReleaseNotes.rst
+++ llvm/docs/ReleaseNotes.rst
@@ -186,7 +186,7 @@
* Support ISA of ``AVX-IFMA``.
* Support ISA of ``AVX-VNNI-INT8``.
* Support ISA of ``AVX-NE-CONVERT``.
-* ``-mcpu=raptorlake`` and ``-mcpu=meteorlake`` are now supported.
+* ``-mcpu=raptorlake``, ``-mcpu=meteorlake`` and ``-mcpu=emeraldrapids`` are now supported.
* ``-mcpu=sierraforest``, ``-mcpu=graniterapids`` and ``-mcpu=grandridge`` are now supported.
Changes to the OCaml bindings
Index: compiler-rt/lib/builtins/cpu_model.c
===================================================================
--- compiler-rt/lib/builtins/cpu_model.c
+++ compiler-rt/lib/builtins/cpu_model.c
@@ -465,6 +465,8 @@
*Subtype = INTEL_COREI7_ICELAKE_SERVER;
break;
+ // Emerald Rapids:
+ case 0xcf:
// Sapphire Rapids:
case 0x8f:
CPU = "sapphirerapids";
@@ -472,7 +474,7 @@
*Subtype = INTEL_COREI7_SAPPHIRERAPIDS;
break;
- // Graniterapids:
+ // Granite Rapids:
case 0xae:
case 0xad:
CPU = "graniterapids";
Index: clang/test/Preprocessor/predefined-arch-macros.c
===================================================================
--- clang/test/Preprocessor/predefined-arch-macros.c
+++ clang/test/Preprocessor/predefined-arch-macros.c
@@ -1646,6 +1646,9 @@
// RUN: %clang -march=sapphirerapids -m32 -E -dM %s -o - 2>&1 \
// RUN: -target i386-unknown-linux \
// RUN: | FileCheck -match-full-lines %s -check-prefix=CHECK_SPR_M32
+// RUN: %clang -march=emeraldrapids -m32 -E -dM %s -o - 2>&1 \
+// RUN: -target i386-unknown-linux \
+// RUN: | FileCheck -match-full-lines %s -check-prefix=CHECK_SPR_M32
// CHECK_SPR_M32: #define __AES__ 1
// CHECK_SPR_M32: #define __AMXBF16__ 1
// CHECK_SPR_M32: #define __AMXINT8__ 1
@@ -1718,6 +1721,9 @@
// RUN: %clang -march=sapphirerapids -m64 -E -dM %s -o - 2>&1 \
// RUN: -target i386-unknown-linux \
// RUN: | FileCheck -match-full-lines %s -check-prefix=CHECK_SPR_M64
+// RUN: %clang -march=emeraldrapids -m64 -E -dM %s -o - 2>&1 \
+// RUN: -target i386-unknown-linux \
+// RUN: | FileCheck -match-full-lines %s -check-prefix=CHECK_SPR_M64
// CHECK_SPR_M64: #define __AES__ 1
// CHECK_SPR_M64: #define __AMXBF16__ 1
// CHECK_SPR_M64: #define __AMXINT8__ 1
Index: clang/test/Misc/target-invalid-cpu-note.c
===================================================================
--- clang/test/Misc/target-invalid-cpu-note.c
+++ clang/test/Misc/target-invalid-cpu-note.c
@@ -13,19 +13,19 @@
// 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, sierraforest, grandridge, graniterapids, 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{{$}}
+// X86-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, sierraforest, grandridge, graniterapids, emeraldrapids, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, x86-64-v2, x86-64-v3, x86-64-v4, geode{{$}}
// 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, sierraforest, grandridge, graniterapids, 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{{$}}
+// X86_64-NEXT: note: valid target CPU values are: nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, sierraforest, grandridge, graniterapids, emeraldrapids, knl, knm, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, x86-64-v2, x86-64-v3, x86-64-v4{{$}}
// 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, sierraforest, grandridge, graniterapids, 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{{$}}
+// TUNE_X86-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, sierraforest, grandridge, graniterapids, emeraldrapids, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, geode{{$}}
// 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, sierraforest, grandridge, graniterapids, 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{{$}}
+// TUNE_X86_64-NEXT: note: valid target CPU values are: i386, i486, winchip-c6, winchip2, c3, i586, pentium, pentium-mmx, pentiumpro, i686, pentium2, pentium3, pentium3m, pentium-m, c3-2, yonah, pentium4, pentium4m, prescott, nocona, core2, penryn, bonnell, atom, silvermont, slm, goldmont, goldmont-plus, tremont, nehalem, corei7, westmere, sandybridge, corei7-avx, ivybridge, core-avx-i, haswell, core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake, icelake-client, rocketlake, icelake-server, tigerlake, sapphirerapids, alderlake, raptorlake, meteorlake, sierraforest, grandridge, graniterapids, emeraldrapids, knl, knm, lakemont, k6, k6-2, k6-3, athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64, athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, znver3, znver4, x86-64, geode{{$}}
// 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'
Index: clang/test/Driver/x86-march.c
===================================================================
--- clang/test/Driver/x86-march.c
+++ clang/test/Driver/x86-march.c
@@ -131,6 +131,10 @@
// RUN: | FileCheck %s -check-prefix=graniterapids
// graniterapids: "-target-cpu" "graniterapids"
//
+// RUN: %clang -target x86_64-unknown-unknown -c -### %s -march=emeraldrapids 2>&1 \
+// RUN: | FileCheck %s -check-prefix=emeraldrapids
+// emeraldrapids: "-target-cpu" "emeraldrapids"
+//
// RUN: %clang -target x86_64-unknown-unknown -c -### %s -march=sapphirerapids 2>&1 \
// RUN: | FileCheck %s -check-prefix=sapphirerapids
// sapphirerapids: "-target-cpu" "sapphirerapids"
Index: clang/test/CodeGen/target-builtin-noerror.c
===================================================================
--- clang/test/CodeGen/target-builtin-noerror.c
+++ clang/test/CodeGen/target-builtin-noerror.c
@@ -109,6 +109,7 @@
(void)__builtin_cpu_is("goldmont-plus");
(void)__builtin_cpu_is("grandridge");
(void)__builtin_cpu_is("graniterapids");
+ (void)__builtin_cpu_is("emeraldrapids");
(void)__builtin_cpu_is("haswell");
(void)__builtin_cpu_is("icelake-client");
(void)__builtin_cpu_is("icelake-server");
Index: clang/test/CodeGen/attr-target-mv.c
===================================================================
--- clang/test/CodeGen/attr-target-mv.c
+++ clang/test/CodeGen/attr-target-mv.c
@@ -20,6 +20,7 @@
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("default"))) foo(void) { return 2; }
int bar(void) {
@@ -164,6 +165,8 @@
// LINUX: ret i32 17
// LINUX: define{{.*}} i32 @foo.arch_graniterapids()
// LINUX: ret i32 18
+// LINUX: define{{.*}} i32 @foo.arch_emeraldrapids()
+// LINUX: ret i32 19
// LINUX: define{{.*}} i32 @foo()
// LINUX: ret i32 2
// LINUX: define{{.*}} i32 @bar()
@@ -205,6 +208,8 @@
// WINDOWS: ret i32 17
// WINDOWS: define{{.*}} i32 @foo.arch_graniterapids()
// WINDOWS: ret i32 18
+// WINDOWS: define dso_local i32 @foo.arch_emeraldrapids()
+// WINDOWS: ret i32 19
// WINDOWS: define dso_local i32 @foo()
// WINDOWS: ret i32 2
// WINDOWS: define dso_local i32 @bar()
Index: clang/lib/Basic/Targets/X86.cpp
===================================================================
--- clang/lib/Basic/Targets/X86.cpp
+++ clang/lib/Basic/Targets/X86.cpp
@@ -529,6 +529,7 @@
case CK_Sierraforest:
case CK_Grandridge:
case CK_Graniterapids:
+ 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.
@@ -1422,6 +1423,7 @@
case CK_Sierraforest:
case CK_Grandridge:
case CK_Graniterapids:
+ case CK_Emeraldrapids:
case CK_KNL:
case CK_KNM:
// K7
Index: clang/docs/ReleaseNotes.rst
===================================================================
--- clang/docs/ReleaseNotes.rst
+++ clang/docs/ReleaseNotes.rst
@@ -802,7 +802,7 @@
* Support intrinsic of ``_mm(256)_cvtneobf16_ps``.
* Support intrinsic of ``_mm(256)_cvtneoph_ps``.
* Support intrinsic of ``_mm(256)_cvtneps_avx_pbh``.
-- ``-march=raptorlake`` and ``-march=meteorlake`` are now supported.
+- ``-march=raptorlake``, ``-march=meteorlake`` and ``-march=emeraldrapids`` are now supported.
- ``-march=sierraforest``, ``-march=graniterapids`` and ``-march=grandridge`` are now supported.
- Lift _BitInt() supported max width from 128 to 8388608.
- Support intrinsics of ``_mm(256)_reduce_(add|mul|or|and)_epi8/16``.
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
