[X86] AMD znver2 enablement

This patch enables the following

1) AMD family 17h "znver2" tune flag (-march, -mcpu).
2) ISAs that are enabled for "znver2" architecture.
3) For the time being, it uses the znver1 scheduler model.
4) Tests are updated.
5) This patch is the clang counterpart to D58343

Reviewers: craig.topper
Tags: #clang

Differential Revision: https://reviews.llvm.org/D58344

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@354899 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Basic/X86Target.def b/include/clang/Basic/X86Target.def
index c6719ff2aff0f5950c9b3d8e80b36c8ba8bcc177..5776f6484c9558851ed19b1063739787ac770702 100644 (file)
--- a/include/clang/Basic/X86Target.def
+++ b/include/clang/Basic/X86Target.def
@@ -236,6 +236,7 @@ PROC_WITH_FEAT(BDVER4, "bdver4", PROC_64_BIT, FEATURE_AVX2)
 /// Zen architecture processors.
 //@{
 PROC_WITH_FEAT(ZNVER1, "znver1", PROC_64_BIT, FEATURE_AVX2)
+PROC_WITH_FEAT(ZNVER2, "znver2", PROC_64_BIT, FEATURE_AVX2)
 //@}
 
 /// This specification is deprecated and will be removed in the future.

diff --git a/lib/Basic/Targets/X86.cpp b/lib/Basic/Targets/X86.cpp
index c3385033e90761f80d8f83a1b7d4c426aedbf85d..69a766cd4a687e6138e4077a0cf2869ae7718b4c 100644 (file)
--- a/lib/Basic/Targets/X86.cpp
+++ b/lib/Basic/Targets/X86.cpp
@@ -347,6 +347,11 @@ bool X86TargetInfo::initFeatureMap(
     setFeatureEnabledImpl(Features, "sahf", true);
     break;
 
+  case CK_ZNVER2:
+    setFeatureEnabledImpl(Features, "clwb", true);
+    setFeatureEnabledImpl(Features, "rdpid", true);
+    setFeatureEnabledImpl(Features, "wbnoinvd", true);
+    LLVM_FALLTHROUGH;
   case CK_ZNVER1:
     setFeatureEnabledImpl(Features, "adx", true);
     setFeatureEnabledImpl(Features, "aes", true);
@@ -1030,6 +1035,9 @@ void X86TargetInfo::getTargetDefines(const LangOptions &Opts,
   case CK_ZNVER1:
     defineCPUMacros(Builder, "znver1");
     break;
+  case CK_ZNVER2:
+    defineCPUMacros(Builder, "znver2");
+    break;
   case CK_Geode:
     defineCPUMacros(Builder, "geode");
     break;

diff --git a/test/CodeGen/target-builtin-noerror.c b/test/CodeGen/target-builtin-noerror.c
index 400c5e696ad8eff7955e653ff126529b71d5bb29..f8d73ef9923a4a84ab3047aec85ab9b7d503e72a 100644 (file)
--- a/test/CodeGen/target-builtin-noerror.c
+++ b/test/CodeGen/target-builtin-noerror.c
@@ -120,4 +120,5 @@ void verifycpustrings() {
   (void)__builtin_cpu_is("tremont");
   (void)__builtin_cpu_is("westmere");
   (void)__builtin_cpu_is("znver1");
+  (void)__builtin_cpu_is("znver2");
 }

diff --git a/test/Driver/x86-march.c b/test/Driver/x86-march.c
index bc1194ff73b4c60be22b60239cdaa22825f1bdd7..5edc890224b43f1fa26ff6a75e0166707f40bf1c 100644 (file)
--- a/test/Driver/x86-march.c
+++ b/test/Driver/x86-march.c
@@ -159,3 +159,7 @@
 // RUN: %clang -target x86_64-unknown-unknown -c -### %s -march=znver1 2>&1 \
 // RUN:   | FileCheck %s -check-prefix=znver1
 // znver1: "-target-cpu" "znver1"
+//
+// RUN: %clang -target x86_64-unknown-unknown -c -### %s -march=znver2 2>&1 \
+// RUN:   | FileCheck %s -check-prefix=znver2
+// znver2: "-target-cpu" "znver2"

diff --git a/test/Frontend/x86-target-cpu.c b/test/Frontend/x86-target-cpu.c
index 0ec301f4426ec9fe299f9f65cae16c7186644a66..05b28f0f68fec476c61cd316f0871ae7afee574a 100644 (file)
--- a/test/Frontend/x86-target-cpu.c
+++ b/test/Frontend/x86-target-cpu.c
@@ -35,5 +35,6 @@
 // RUN: %clang_cc1 -triple x86_64-unknown-unknown -target-cpu btver1 -verify %s
 // RUN: %clang_cc1 -triple x86_64-unknown-unknown -target-cpu btver2 -verify %s
 // RUN: %clang_cc1 -triple x86_64-unknown-unknown -target-cpu znver1 -verify %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -target-cpu znver2 -verify %s
 //
 // expected-no-diagnostics

diff --git a/test/Misc/target-invalid-cpu-note.c b/test/Misc/target-invalid-cpu-note.c
index 7a37edaa7bba87930dbffb4d77f92a4399550ab6..5af321bc8b2d72f56def23ae7cd31f7af40fe5fe 100644 (file)
--- a/test/Misc/target-invalid-cpu-note.c
+++ b/test/Misc/target-invalid-cpu-note.c
@@ -19,7 +19,7 @@
 // X86-SAME: skx, cascadelake, cannonlake, icelake-client, icelake-server, knl, knm, lakemont, k6, k6-2, k6-3,
 // 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,
+// X86-SAME: barcelona, btver1, btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2,
 // X86-SAME: x86-64, geode
 
 // RUN: not %clang_cc1 -triple x86_64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix X86_64
@@ -30,7 +30,7 @@
 // X86_64-SAME: core-avx2, broadwell, skylake, skylake-avx512, skx, cascadelake, cannonlake,
 // X86_64-SAME: icelake-client, icelake-server, 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, x86-64
+// X86_64-SAME: btver2, bdver1, bdver2, bdver3, bdver4, znver1, znver2, x86-64
 
 // 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/test/Preprocessor/predefined-arch-macros.c b/test/Preprocessor/predefined-arch-macros.c
index 65d3a3ec319c4ff83455eceebbff557cb9b78eca..f98f0ee54e0bbd6f35d138338822dd7b73074d17 100644 (file)
--- a/test/Preprocessor/predefined-arch-macros.c
+++ b/test/Preprocessor/predefined-arch-macros.c
@@ -2676,6 +2676,100 @@
 // CHECK_ZNVER1_M64: #define __znver1 1
 // CHECK_ZNVER1_M64: #define __znver1__ 1
 
+// RUN: %clang -march=znver2 -m32 -E -dM %s -o - 2>&1 \
+// RUN:     -target i386-unknown-linux \
+// RUN:   | FileCheck -match-full-lines %s -check-prefix=CHECK_ZNVER2_M32
+// CHECK_ZNVER2_M32-NOT: #define __3dNOW_A__ 1
+// CHECK_ZNVER2_M32-NOT: #define __3dNOW__ 1
+// CHECK_ZNVER2_M32: #define __ADX__ 1
+// CHECK_ZNVER2_M32: #define __AES__ 1
+// CHECK_ZNVER2_M32: #define __AVX2__ 1
+// CHECK_ZNVER2_M32: #define __AVX__ 1
+// CHECK_ZNVER2_M32: #define __BMI2__ 1
+// CHECK_ZNVER2_M32: #define __BMI__ 1
+// CHECK_ZNVER2_M32: #define __CLFLUSHOPT__ 1
+// CHECK_ZNVER2_M32: #define __CLWB__ 1
+// CHECK_ZNVER2_M32: #define __CLZERO__ 1
+// CHECK_ZNVER2_M32: #define __F16C__ 1
+// CHECK_ZNVER2_M32: #define __FMA__ 1
+// CHECK_ZNVER2_M32: #define __FSGSBASE__ 1
+// CHECK_ZNVER2_M32: #define __LZCNT__ 1
+// CHECK_ZNVER2_M32: #define __MMX__ 1
+// CHECK_ZNVER2_M32: #define __PCLMUL__ 1
+// CHECK_ZNVER2_M32: #define __POPCNT__ 1
+// CHECK_ZNVER2_M32: #define __PRFCHW__ 1
+// CHECK_ZNVER2_M32: #define __RDPID__ 1
+// CHECK_ZNVER2_M32: #define __RDRND__ 1
+// CHECK_ZNVER2_M32: #define __RDSEED__ 1
+// CHECK_ZNVER2_M32: #define __SHA__ 1
+// CHECK_ZNVER2_M32: #define __SSE2_MATH__ 1
+// CHECK_ZNVER2_M32: #define __SSE2__ 1
+// CHECK_ZNVER2_M32: #define __SSE3__ 1
+// CHECK_ZNVER2_M32: #define __SSE4A__ 1
+// CHECK_ZNVER2_M32: #define __SSE4_1__ 1
+// CHECK_ZNVER2_M32: #define __SSE4_2__ 1
+// CHECK_ZNVER2_M32: #define __SSE_MATH__ 1
+// CHECK_ZNVER2_M32: #define __SSE__ 1
+// CHECK_ZNVER2_M32: #define __SSSE3__ 1
+// CHECK_ZNVER2_M32: #define __WBNOINVD__ 1
+// CHECK_ZNVER2_M32: #define __XSAVEC__ 1
+// CHECK_ZNVER2_M32: #define __XSAVEOPT__ 1
+// CHECK_ZNVER2_M32: #define __XSAVES__ 1
+// CHECK_ZNVER2_M32: #define __XSAVE__ 1
+// CHECK_ZNVER2_M32: #define __i386 1
+// CHECK_ZNVER2_M32: #define __i386__ 1
+// CHECK_ZNVER2_M32: #define __tune_znver2__ 1
+// CHECK_ZNVER2_M32: #define __znver2 1
+// CHECK_ZNVER2_M32: #define __znver2__ 1
+
+// RUN: %clang -march=znver2 -m64 -E -dM %s -o - 2>&1 \
+// RUN:     -target i386-unknown-linux \
+// RUN:   | FileCheck -match-full-lines %s -check-prefix=CHECK_ZNVER2_M64
+// CHECK_ZNVER2_M64-NOT: #define __3dNOW_A__ 1
+// CHECK_ZNVER2_M64-NOT: #define __3dNOW__ 1
+// CHECK_ZNVER2_M64: #define __ADX__ 1
+// CHECK_ZNVER2_M64: #define __AES__ 1
+// CHECK_ZNVER2_M64: #define __AVX2__ 1
+// CHECK_ZNVER2_M64: #define __AVX__ 1
+// CHECK_ZNVER2_M64: #define __BMI2__ 1
+// CHECK_ZNVER2_M64: #define __BMI__ 1
+// CHECK_ZNVER2_M64: #define __CLFLUSHOPT__ 1
+// CHECK_ZNVER2_M64: #define __CLWB__ 1
+// CHECK_ZNVER2_M64: #define __CLZERO__ 1
+// CHECK_ZNVER2_M64: #define __F16C__ 1
+// CHECK_ZNVER2_M64: #define __FMA__ 1
+// CHECK_ZNVER2_M64: #define __FSGSBASE__ 1
+// CHECK_ZNVER2_M64: #define __LZCNT__ 1
+// CHECK_ZNVER2_M64: #define __MMX__ 1
+// CHECK_ZNVER2_M64: #define __PCLMUL__ 1
+// CHECK_ZNVER2_M64: #define __POPCNT__ 1
+// CHECK_ZNVER2_M64: #define __PRFCHW__ 1
+// CHECK_ZNVER2_M64: #define __RDPID__ 1
+// CHECK_ZNVER2_M64: #define __RDRND__ 1
+// CHECK_ZNVER2_M64: #define __RDSEED__ 1
+// CHECK_ZNVER2_M64: #define __SHA__ 1
+// CHECK_ZNVER2_M64: #define __SSE2_MATH__ 1
+// CHECK_ZNVER2_M64: #define __SSE2__ 1
+// CHECK_ZNVER2_M64: #define __SSE3__ 1
+// CHECK_ZNVER2_M64: #define __SSE4A__ 1
+// CHECK_ZNVER2_M64: #define __SSE4_1__ 1
+// CHECK_ZNVER2_M64: #define __SSE4_2__ 1
+// CHECK_ZNVER2_M64: #define __SSE_MATH__ 1
+// CHECK_ZNVER2_M64: #define __SSE__ 1
+// CHECK_ZNVER2_M64: #define __SSSE3__ 1
+// CHECK_ZNVER2_M64: #define __WBNOINVD__ 1
+// CHECK_ZNVER2_M64: #define __XSAVEC__ 1
+// CHECK_ZNVER2_M64: #define __XSAVEOPT__ 1
+// CHECK_ZNVER2_M64: #define __XSAVES__ 1
+// CHECK_ZNVER2_M64: #define __XSAVE__ 1
+// CHECK_ZNVER2_M64: #define __amd64 1
+// CHECK_ZNVER2_M64: #define __amd64__ 1
+// CHECK_ZNVER2_M64: #define __tune_znver2__ 1
+// CHECK_ZNVER2_M64: #define __x86_64 1
+// CHECK_ZNVER2_M64: #define __x86_64__ 1
+// CHECK_ZNVER2_M64: #define __znver2 1
+// CHECK_ZNVER2_M64: #define __znver2__ 1
+
 // End X86/GCC/Linux tests ------------------
 
 // Begin PPC/GCC/Linux tests ----------------