[X86] Don't disable xsave when avx is disabled. Implicitly enable xsave with avx...

CPUs with avx always have xsave, but some CPUs without avx also
have xsave. So we shouldn't disable xsave just because avx is
disabled. This would prevent xsave from being enabled with
-march=native on CPUs with xsave and not avx.

But we also don't want -mavx -mno-avx to leave xsave eanabled.
So only enable xsave if avx is enabled after processing all features.

I thought about just not turning xsave on with avx at all, but
there might be someone out there depending on it.

diff --git a/clang/lib/Basic/Targets/X86.cpp b/clang/lib/Basic/Targets/X86.cpp
index 22ed922..fdc59f0 100644 (file)
--- a/clang/lib/Basic/Targets/X86.cpp
+++ b/clang/lib/Basic/Targets/X86.cpp
@@ -360,6 +360,7 @@ SkylakeCommon:
     setFeatureEnabledImpl(Features, "bmi", true);
     setFeatureEnabledImpl(Features, "f16c", true);
     setFeatureEnabledImpl(Features, "xsaveopt", true);
+    setFeatureEnabledImpl(Features, "xsave", true);
     setFeatureEnabledImpl(Features, "movbe", true);
     LLVM_FALLTHROUGH;
   case CK_BTVER1:
@@ -459,6 +460,12 @@ SkylakeCommon:
       llvm::find(FeaturesVec, "-mmx") == FeaturesVec.end())
     Features["mmx"] = true;
 
+  // Enable xsave if avx is enabled and xsave is not explicitly disabled.
+  I = Features.find("avx");
+  if (I != Features.end() && I->getValue() &&
+      llvm::find(FeaturesVec, "-xsave") == FeaturesVec.end())
+    Features["xsave"] = true;
+
   return true;
 }
 
@@ -476,7 +483,6 @@ void X86TargetInfo::setSSELevel(llvm::StringMap<bool> &Features,
       LLVM_FALLTHROUGH;
     case AVX:
       Features["avx"] = true;
-      Features["xsave"] = true;
       LLVM_FALLTHROUGH;
     case SSE42:
       Features["sse4.2"] = true;
@@ -526,8 +532,7 @@ void X86TargetInfo::setSSELevel(llvm::StringMap<bool> &Features,
     LLVM_FALLTHROUGH;
   case AVX:
     Features["fma"] = Features["avx"] = Features["f16c"] = false;
-    Features["xsave"] = Features["xsaveopt"] = Features["vaes"] = false;
-    Features["vpclmulqdq"] = false;
+    Features["vaes"] = Features["vpclmulqdq"] = false;
     setXOPLevel(Features, FMA4, false);
     LLVM_FALLTHROUGH;
   case AVX2:

diff --git a/clang/test/CodeGen/attr-target-x86.c b/clang/test/CodeGen/attr-target-x86.c
index 73486e5..feed175 100644 (file)
--- a/clang/test/CodeGen/attr-target-x86.c
+++ b/clang/test/CodeGen/attr-target-x86.c
@@ -50,9 +50,9 @@ int __attribute__((target("arch=lakemont,mmx"))) use_before_def(void) {
 // CHECK: use_before_def{{.*}} #7
 // CHECK: #0 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87"
 // CHECK: #1 = {{.*}}"target-cpu"="ivybridge" "target-features"="+avx,+cx16,+cx8,+f16c,+fsgsbase,+fxsr,+mmx,+pclmul,+popcnt,+rdrnd,+sahf,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsaveopt"
-// CHECK: #2 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87,-aes,-avx,-avx2,-avx512bf16,-avx512bitalg,-avx512bw,-avx512cd,-avx512dq,-avx512er,-avx512f,-avx512ifma,-avx512pf,-avx512vbmi,-avx512vbmi2,-avx512vl,-avx512vnni,-avx512vp2intersect,-avx512vpopcntdq,-f16c,-fma,-fma4,-gfni,-pclmul,-sha,-sse2,-sse3,-sse4.1,-sse4.2,-sse4a,-ssse3,-vaes,-vpclmulqdq,-xop,-xsave,-xsaveopt"
+// CHECK: #2 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87,-aes,-avx,-avx2,-avx512bf16,-avx512bitalg,-avx512bw,-avx512cd,-avx512dq,-avx512er,-avx512f,-avx512ifma,-avx512pf,-avx512vbmi,-avx512vbmi2,-avx512vl,-avx512vnni,-avx512vp2intersect,-avx512vpopcntdq,-f16c,-fma,-fma4,-gfni,-pclmul,-sha,-sse2,-sse3,-sse4.1,-sse4.2,-sse4a,-ssse3,-vaes,-vpclmulqdq,-xop"
 // CHECK: #3 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+mmx,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87"
-// CHECK: #4 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87,-avx,-avx2,-avx512bf16,-avx512bitalg,-avx512bw,-avx512cd,-avx512dq,-avx512er,-avx512f,-avx512ifma,-avx512pf,-avx512vbmi,-avx512vbmi2,-avx512vl,-avx512vnni,-avx512vp2intersect,-avx512vpopcntdq,-f16c,-fma,-fma4,-sse4.1,-sse4.2,-vaes,-vpclmulqdq,-xop,-xsave,-xsaveopt"
+// CHECK: #4 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87,-avx,-avx2,-avx512bf16,-avx512bitalg,-avx512bw,-avx512cd,-avx512dq,-avx512er,-avx512f,-avx512ifma,-avx512pf,-avx512vbmi,-avx512vbmi2,-avx512vl,-avx512vnni,-avx512vp2intersect,-avx512vpopcntdq,-f16c,-fma,-fma4,-sse4.1,-sse4.2,-vaes,-vpclmulqdq,-xop"
 // CHECK: #5 = {{.*}}"target-cpu"="ivybridge" "target-features"="+avx,+cx16,+cx8,+f16c,+fsgsbase,+fxsr,+mmx,+pclmul,+popcnt,+rdrnd,+sahf,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsaveopt,-aes,-vaes"
 // CHECK: #6 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87,-3dnow,-3dnowa,-mmx"
 // CHECK: #7 = {{.*}}"target-cpu"="lakemont" "target-features"="+cx8,+mmx"