[X86] Support -march=x86-64-v[234]
PR47686. These micro-architecture levels are defined in the x86-64 psABI:
https://gitlab.com/x86-psABIs/x86-64-ABI/-/commit/77566eb03bc6a326811cb7e9
GCC 11 will support these levels.
Note, -mtune=x86-64-v[234] are invalid and __builtin_cpu_is cannot be
used on them.
Reviewed By: craig.topper, RKSimon
Differential Revision: https://reviews.llvm.org/D89197
diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst
index 66427f2..d0ef03a 100644
--- a/clang/docs/ReleaseNotes.rst
+++ b/clang/docs/ReleaseNotes.rst
@@ -188,7 +188,10 @@
- The x86 intrinsics ``__rorb``, ``__rorw``, ``__rord``, ``__rorq`, ``_rotr``,
``_rotwr`` and ``_lrotr`` may now be used within constant expressions.
-- Support for -march=sapphirerapids was added.
+- Support for ``-march=sapphirerapids`` was added.
+
+- Support for ``-march=x86-64-v[234]`` has been added.
+ See :doc:`UsersManual` for details about these micro-architecture levels.
- The -mtune command line option is no longer ignored for X86. This can be used
to request microarchitectural optimizations independent on -march. -march=<cpu>
diff --git a/clang/docs/UsersManual.rst b/clang/docs/UsersManual.rst
index ed6c9e3..f313ce7 100644
--- a/clang/docs/UsersManual.rst
+++ b/clang/docs/UsersManual.rst
@@ -3201,6 +3201,15 @@
appropriate for a CPU running in 16-bit mode, with address-size and
operand-size prefixes to enable 32-bit addressing and operations.
+Several micro-architecture levels as specified by the x86-64 psABI are defined.
+They are cumulative in the sense that features from previous levels are
+implicitly included in later levels.
+
+- ``-march=x86-64``: CMOV, CMPXCHG8B, FPU, FXSR, MMX, FXSR, SCE, SSE, SSE2
+- ``-march=x86-64-v2``: (close to Nehalem) CMPXCHG16B, LAHF-SAHF, POPCNT, SSE3, SSE4.1, SSE4.2, SSSE3
+- ``-march=x86-64-v3``: (close to Haswell) AVX, AVX2, BMI1, BMI2, F16C, FMA, LZCNT, MOVBE, XSAVE
+- ``-march=x86-64-v4``: AVX512F, AVX512BW, AVX512CD, AVX512DQ, AVX512VL
+
ARM
^^^
diff --git a/clang/lib/Basic/Targets/X86.cpp b/clang/lib/Basic/Targets/X86.cpp
index ef83703d6..98ac13b 100644
--- a/clang/lib/Basic/Targets/X86.cpp
+++ b/clang/lib/Basic/Targets/X86.cpp
@@ -506,6 +506,9 @@
case CK_K8:
case CK_K8SSE3:
case CK_x86_64:
+ case CK_x86_64_v2:
+ case CK_x86_64_v3:
+ case CK_x86_64_v4:
defineCPUMacros(Builder, "k8");
break;
case CK_AMDFAM10:
@@ -1312,6 +1315,9 @@
case CK_ZNVER2:
// Deprecated
case CK_x86_64:
+ case CK_x86_64_v2:
+ case CK_x86_64_v3:
+ case CK_x86_64_v4:
case CK_Yonah:
case CK_Penryn:
case CK_Core2:
@@ -1456,7 +1462,7 @@
}
void X86TargetInfo::fillValidTuneCPUList(SmallVectorImpl<StringRef> &Values) const {
- llvm::X86::fillValidCPUArchList(Values);
+ llvm::X86::fillValidTuneCPUList(Values);
}
ArrayRef<const char *> X86TargetInfo::getGCCRegNames() const {
diff --git a/clang/lib/Basic/Targets/X86.h b/clang/lib/Basic/Targets/X86.h
index 7b2b7dc..4fc495a 100644
--- a/clang/lib/Basic/Targets/X86.h
+++ b/clang/lib/Basic/Targets/X86.h
@@ -314,7 +314,7 @@
// Allow 32-bit only CPUs regardless of 64-bit mode unlike isValidCPUName.
// NOTE: gcc rejects 32-bit mtune CPUs in 64-bit mode. But being lenient
// since mtune was ignored by clang for so long.
- return llvm::X86::parseArchX86(Name) != llvm::X86::CK_None;
+ return llvm::X86::parseTuneCPU(Name) != llvm::X86::CK_None;
}
void fillValidCPUList(SmallVectorImpl<StringRef> &Values) const override;
diff --git a/clang/test/CodeGen/attr-target-x86.c b/clang/test/CodeGen/attr-target-x86.c
index 738b65b..99cca0b 100644
--- a/clang/test/CodeGen/attr-target-x86.c
+++ b/clang/test/CodeGen/attr-target-x86.c
@@ -32,6 +32,10 @@
int __attribute__((target("tune=sandybridge"))) walrus(int a) { return 4; }
+void __attribute__((target("arch=x86-64-v2"))) x86_64_v2() {}
+void __attribute__((target("arch=x86-64-v3"))) x86_64_v3() {}
+void __attribute__((target("arch=x86-64-v4"))) x86_64_v4() {}
+
// Check that we emit the additional subtarget and cpu features for foo and not for baz or bar.
// CHECK: baz{{.*}} #0
// CHECK: foo{{.*}} #1
@@ -59,3 +63,10 @@
// CHECK: #7 = {{.*}}"target-cpu"="lakemont" "target-features"="+cx8,+mmx"
// CHECK-NOT: tune-cpu
// CHECK: #8 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87" "tune-cpu"="sandybridge"
+
+// CHECK: "target-cpu"="x86-64-v2"
+// CHECK-SAME: "target-features"="+cx16,+cx8,+fxsr,+mmx,+popcnt,+sahf,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87"
+// CHECK: "target-cpu"="x86-64-v3"
+// CHECK-SAME: "target-features"="+avx,+avx2,+bmi,+bmi2,+cx16,+cx8,+f16c,+fma,+fxsr,+lzcnt,+mmx,+movbe,+popcnt,+sahf,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave"
+// CHECK: "target-cpu"="x86-64-v4"
+// CHECK-SAME: "target-features"="+avx,+avx2,+avx512bw,+avx512cd,+avx512dq,+avx512f,+avx512vl,+bmi,+bmi2,+cx16,+cx8,+f16c,+fma,+fxsr,+lzcnt,+mmx,+movbe,+popcnt,+sahf,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave"
diff --git a/clang/test/Driver/x86-march.c b/clang/test/Driver/x86-march.c
index 57882a5..26ffc16 100644
--- a/clang/test/Driver/x86-march.c
+++ b/clang/test/Driver/x86-march.c
@@ -175,3 +175,12 @@
// RUN: %clang -target x86_64-unknown-unknown -c -### %s -march=znver2 2>&1 \
// RUN: | FileCheck %s -check-prefix=znver2
// znver2: "-target-cpu" "znver2"
+
+// RUN: %clang -target x86_64 -c -### %s -march=x86-64 2>&1 | FileCheck %s --check-prefix=x86-64
+// x86-64: "-target-cpu" "x86-64"
+// RUN: %clang -target x86_64 -c -### %s -march=x86-64-v2 2>&1 | FileCheck %s --check-prefix=x86-64-v2
+// x86-64-v2: "-target-cpu" "x86-64-v2"
+// RUN: %clang -target x86_64 -c -### %s -march=x86-64-v3 2>&1 | FileCheck %s --check-prefix=x86-64-v3
+// x86-64-v3: "-target-cpu" "x86-64-v3"
+// RUN: %clang -target x86_64 -c -### %s -march=x86-64-v4 2>&1 | FileCheck %s --check-prefix=x86-64-v4
+// x86-64-v4: "-target-cpu" "x86-64-v4"
diff --git a/clang/test/Driver/x86-mtune.c b/clang/test/Driver/x86-mtune.c
index a313412..9ab4bf1 100644
--- a/clang/test/Driver/x86-mtune.c
+++ b/clang/test/Driver/x86-mtune.c
@@ -40,3 +40,8 @@
// RUN: | FileCheck %s -check-prefix=marchmtune
// marchmtune: "-target-cpu" "core2"
// mmarchmtune: "-tune-cpu" "nehalem"
+
+// RUN: not %clang %s -target x86_64 -E -mtune=x86-64-v2 2>&1 | FileCheck %s --check-prefix=INVALID
+// RUN: not %clang %s -target x86_64 -E -mtune=x86-64-v3 2>&1 | FileCheck %s --check-prefix=INVALID
+// RUN: not %clang %s -target x86_64 -E -mtune=x86-64-v4 2>&1 | FileCheck %s --check-prefix=INVALID
+// INVALID: error: unknown target CPU '{{.*}}'
diff --git a/clang/test/Misc/target-invalid-cpu-note.c b/clang/test/Misc/target-invalid-cpu-note.c
index 4f5dbac..c35e6c2 100644
--- a/clang/test/Misc/target-invalid-cpu-note.c
+++ b/clang/test/Misc/target-invalid-cpu-note.c
@@ -25,7 +25,7 @@
// X86-SAME: athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64,
// X86-SAME: athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10,
// X86-SAME: barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2,
-// X86-SAME: x86-64, geode
+// X86-SAME: x86-64, x86-64-v2, x86-64-v3, x86-64-v4, geode{{$}}
// RUN: not %clang_cc1 -triple x86_64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix X86_64
// X86_64: error: unknown target CPU 'not-a-cpu'
@@ -35,7 +35,8 @@
// X86_64-SAME: core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cooperlake, cannonlake,
// X86_64-SAME: icelake-client, icelake-server, tigerlake, sapphirerapids, knl, knm, k8, athlon64, athlon-fx, opteron, k8-sse3,
// X86_64-SAME: athlon64-sse3, opteron-sse3, amdfam10, barcelona, btver1,
-// X86_64-SAME: btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, x86-64
+// X86_64-SAME: btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2,
+// X86_64-SAME: x86-64, x86-64-v2, x86-64-v3, x86-64-v4{{$}}
// 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'
@@ -49,7 +50,7 @@
// TUNE_X86-SAME: athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64,
// TUNE_X86-SAME: athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10,
// TUNE_X86-SAME: barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2,
-// TUNE_X86-SAME: x86-64, geode
+// TUNE_X86-SAME: x86-64, geode{{$}}
// RUN: not %clang_cc1 -triple x86_64--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_X86_64
// TUNE_X86_64: error: unknown target CPU 'not-a-cpu'
@@ -63,7 +64,7 @@
// TUNE_X86_64-SAME: athlon, athlon-tbird, athlon-xp, athlon-mp, athlon-4, k8, athlon64,
// TUNE_X86_64-SAME: athlon-fx, opteron, k8-sse3, athlon64-sse3, opteron-sse3, amdfam10,
// TUNE_X86_64-SAME: barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2,
-// TUNE_X86_64-SAME: x86-64, geode
+// TUNE_X86_64-SAME: x86-64, geode{{$}}
// 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'
diff --git a/clang/test/Preprocessor/predefined-arch-macros-x86.c b/clang/test/Preprocessor/predefined-arch-macros-x86.c
new file mode 100644
index 0000000..37b7c61
--- /dev/null
+++ b/clang/test/Preprocessor/predefined-arch-macros-x86.c
@@ -0,0 +1,54 @@
+// RUN: %clang -target x86_64 -march=x86-64 -E -dM %s > %tv1
+// RUN: FileCheck %s --check-prefix=X86_64_V1 < %tv1
+
+// X86_64_V1: #define __MMX__ 1
+// X86_64_V1: #define __SSE2_MATH__ 1
+// X86_64_V1: #define __SSE2__ 1
+// X86_64_V1: #define __SSE_MATH__ 1
+// X86_64_V1: #define __SSE__ 1
+// X86_64_V1: #define __amd64 1
+// X86_64_V1: #define __amd64__ 1
+// X86_64_V1: #define __k8 1
+// X86_64_V1: #define __k8__ 1
+// X86_64_V1: #define __x86_64 1
+// X86_64_V1: #define __x86_64__ 1
+
+// RUN: %clang -target x86_64 -march=x86-64-v2 -E -dM %s > %tv2
+// RUN: diff %tv1 %tv2 > %t.txt || true
+// RUN: FileCheck %s --check-prefix=X86_64_V2 < %t.txt
+
+/// v2 is close to Nehalem.
+// X86_64_V2: #define __GCC_HAVE_SYNC_COMPARE_AND_SWAP_16 1
+// X86_64_V2: #define __LAHF_SAHF__ 1
+// X86_64_V2: #define __POPCNT__ 1
+// X86_64_V2: #define __SSE3__ 1
+// X86_64_V2-NEXT: #define __SSE4_1__ 1
+// X86_64_V2-NEXT: #define __SSE4_2__ 1
+// X86_64_V2: #define __SSSE3__ 1
+
+/// v3 is close to Haswell.
+// RUN: %clang -target x86_64 -march=x86-64-v3 -E -dM %s > %tv3
+// RUN: diff %tv2 %tv3 > %t.txt || true
+// RUN: FileCheck %s --check-prefix=X86_64_V3 < %t.txt
+
+// X86_64_V3: #define __AVX2__ 1
+// X86_64_V3-NEXT: #define __AVX__ 1
+// X86_64_V3: #define __BMI2__ 1
+// X86_64_V3-NEXT: #define __BMI__ 1
+// X86_64_V3: #define __F16C__ 1
+// X86_64_V3: #define __FMA__ 1
+// X86_64_V3: #define __LZCNT__ 1
+// X86_64_V3: #define __MOVBE__ 1
+// X86_64_V3: #define __XSAVE__ 1
+
+/// v4 is close to the AVX-512 level implemented by Xeon Scalable Processors.
+// RUN: %clang -target x86_64 -march=x86-64-v4 -E -dM %s > %tv4
+// RUN: diff %tv3 %tv4 > %t.txt || true
+// RUN: FileCheck %s --check-prefix=X86_64_V4 < %t.txt
+
+// X86_64_V4: #define __AVX512BW__ 1
+// X86_64_V4-NEXT: #define __AVX512CD__ 1
+// X86_64_V4-NEXT: #define __AVX512DQ__ 1
+// X86_64_V4-NEXT: #define __AVX512F__ 1
+// X86_64_V4-NEXT: #define __AVX512VL__ 1
+// X86_64_V4-NOT: #define __AVX512{{.*}}
diff --git a/clang/test/Preprocessor/predefined-arch-macros.c b/clang/test/Preprocessor/predefined-arch-macros.c
index 7993c58..820a242 100644
--- a/clang/test/Preprocessor/predefined-arch-macros.c
+++ b/clang/test/Preprocessor/predefined-arch-macros.c
@@ -2263,21 +2263,6 @@
// CHECK_X86_64_M32: #define __k8__ 1
// CHECK_X86_64_M32: #define i386 1
-// RUN: %clang -march=x86-64 -m64 -E -dM %s -o - 2>&1 \
-// RUN: -target i386-unknown-linux \
-// RUN: | FileCheck -match-full-lines %s -check-prefix=CHECK_X86_64_M64
-// CHECK_X86_64_M64: #define __MMX__ 1
-// CHECK_X86_64_M64: #define __SSE2_MATH__ 1
-// CHECK_X86_64_M64: #define __SSE2__ 1
-// CHECK_X86_64_M64: #define __SSE_MATH__ 1
-// CHECK_X86_64_M64: #define __SSE__ 1
-// CHECK_X86_64_M64: #define __amd64 1
-// CHECK_X86_64_M64: #define __amd64__ 1
-// CHECK_X86_64_M64: #define __k8 1
-// CHECK_X86_64_M64: #define __k8__ 1
-// CHECK_X86_64_M64: #define __x86_64 1
-// CHECK_X86_64_M64: #define __x86_64__ 1
-
// RUN: %clang -march=k8 -m32 -E -dM %s -o - 2>&1 \
// RUN: -target i386-unknown-linux \
// RUN: | FileCheck -match-full-lines %s -check-prefix=CHECK_K8_M32
diff --git a/clang/test/Sema/builtin-cpu-supports.c b/clang/test/Sema/builtin-cpu-supports.c
index 026b5b7..05b5831 100644
--- a/clang/test/Sema/builtin-cpu-supports.c
+++ b/clang/test/Sema/builtin-cpu-supports.c
@@ -15,6 +15,11 @@
if (__builtin_cpu_is("int")) // expected-error {{invalid cpu name for builtin}}
a("intel");
+
+ (void)__builtin_cpu_is("x86-64"); // expected-error {{invalid cpu name for builtin}}
+ (void)__builtin_cpu_is("x86-64-v2"); // expected-error {{invalid cpu name for builtin}}
+ (void)__builtin_cpu_is("x86-64-v3"); // expected-error {{invalid cpu name for builtin}}
+ (void)__builtin_cpu_is("x86-64-v4"); // expected-error {{invalid cpu name for builtin}}
#else
if (__builtin_cpu_supports("vsx")) // expected-error {{use of unknown builtin}}
a("vsx");