Update CPU capabilities for AMD machines

- added processors k8-sse3, opteron-sse3, athlon64-sse3, amdfam10, and
barcelona with appropriate sse3/4a levels
- added FeatureSSE4A for amdfam10 processors
in X86Subtarget:
- added hasSSE4A
- updated AutoDetectSubtargetFeatures to detect SSE4A
- updated GetCurrentX86CPU to detect family 15 with sse3 as k8-sse3 and
family 10h as amdfam10

New processor names match those used by gcc.

Patch by Paul Redmond!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72434 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 31 insertions, 3 deletions

diff --git a/lib/Target/X86/X86.td b/lib/Target/X86/X86.td
index 0e2c980..8df138d 100644
--- a/lib/Target/X86/X86.td
+++ b/lib/Target/X86/X86.td
@@ -52,6 +52,8 @@ def Feature64Bit   : SubtargetFeature<"64bit", "HasX86_64", "true",
                                       "Support 64-bit instructions">;
 def FeatureSlowBTMem : SubtargetFeature<"slow-bt-mem", "IsBTMemSlow", "true",
                                        "Bit testing of memory is slow">;
+def FeatureSSE4A   : SubtargetFeature<"sse4a", "HasSSE4A", "true",
+                                      "Support SSE 4a instructions">;
 
 //===----------------------------------------------------------------------===//
 // X86 processors supported.
@@ -97,6 +99,16 @@ def : Proc<"athlon64",        [FeatureSSE2,   Feature3DNowA, Feature64Bit,
                                FeatureSlowBTMem]>;
 def : Proc<"athlon-fx",       [FeatureSSE2,   Feature3DNowA, Feature64Bit,
                                FeatureSlowBTMem]>;
+def : Proc<"k8-sse3",         [FeatureSSE3,   Feature3DNowA, Feature64Bit,
+                               FeatureSlowBTMem]>;
+def : Proc<"opteron-sse3",    [FeatureSSE3,   Feature3DNowA, Feature64Bit,
+                               FeatureSlowBTMem]>;
+def : Proc<"athlon64-sse3",   [FeatureSSE3,   Feature3DNowA, Feature64Bit,
+                               FeatureSlowBTMem]>;
+def : Proc<"amdfam10",        [FeatureSSE3,   FeatureSSE4A,
+                               Feature3DNowA, Feature64Bit, FeatureSlowBTMem]>;
+def : Proc<"barcelona",       [FeatureSSE3,   FeatureSSE4A,
+                               Feature3DNowA, Feature64Bit, FeatureSlowBTMem]>;
 
 def : Proc<"winchip-c6",      [FeatureMMX]>;
 def : Proc<"winchip2",        [FeatureMMX, Feature3DNow]>;
diff --git a/lib/Target/X86/X86Subtarget.cpp b/lib/Target/X86/X86Subtarget.cpp
index d54ccb3..03ce1ae 100644
--- a/lib/Target/X86/X86Subtarget.cpp
+++ b/lib/Target/X86/X86Subtarget.cpp
@@ -216,6 +216,7 @@ void X86Subtarget::AutoDetectSubtargetFeatures() {
 
     X86::GetCpuIDAndInfo(0x80000001, &EAX, &EBX, &ECX, &EDX);
     HasX86_64 = (EDX >> 29) & 0x1;
+    HasSSE4A = IsAMD && ((ECX >> 6) & 0x1);
   }
 }
 
@@ -229,6 +230,7 @@ static const char *GetCurrentX86CPU() {
 
   X86::GetCpuIDAndInfo(0x80000001, &EAX, &EBX, &ECX, &EDX);
   bool Em64T = (EDX >> 29) & 0x1;
+  bool HasSSE3 = (ECX & 0x1);
 
   union {
     unsigned u[3];
@@ -311,10 +313,20 @@ static const char *GetCurrentX86CPU() {
         default: return "athlon";
         }
       case 15:
+        if (HasSSE3) {
+          switch (Model) {
+          default: return "k8-sse3";
+          }
+        } else {
+          switch (Model) {
+          case 1:  return "opteron";
+          case 5:  return "athlon-fx"; // also opteron
+          default: return "athlon64";
+          }
+        }
+      case 16:
         switch (Model) {
-        case 1:  return "opteron";
-        case 5:  return "athlon-fx"; // also opteron
-        default: return "athlon64";
+        default: return "amdfam10";
         }
     default:
       return "generic";
diff --git a/lib/Target/X86/X86Subtarget.h b/lib/Target/X86/X86Subtarget.h
index a5ca617..46476f2 100644
--- a/lib/Target/X86/X86Subtarget.h
+++ b/lib/Target/X86/X86Subtarget.h
@@ -67,6 +67,9 @@ protected:
   /// IsBTMemSlow - True if BT (bit test) of memory instructions are slow.
   bool IsBTMemSlow;
   
+  /// HasSSE4A - True if the processor supports SSE4A instructions.
+  bool HasSSE4A;
+
   /// DarwinVers - Nonzero if this is a darwin platform: the numeric
   /// version of the platform, e.g. 8 = 10.4 (Tiger), 9 = 10.5 (Leopard), etc.
   unsigned char DarwinVers; // Is any darwin-x86 platform.
@@ -127,6 +130,7 @@ public:
   bool hasSSSE3() const { return X86SSELevel >= SSSE3; }
   bool hasSSE41() const { return X86SSELevel >= SSE41; }
   bool hasSSE42() const { return X86SSELevel >= SSE42; }
+  bool hasSSE4A() const { return HasSSE4A; }
   bool has3DNow() const { return X863DNowLevel >= ThreeDNow; }
   bool has3DNowA() const { return X863DNowLevel >= ThreeDNowA; }