X86: enable AVX2 under Haswell native compilation

Patch by Adam Strzelecki

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@195632 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Support/Host.cpp

@@ -95,6 +95,75 @@ static bool GetX86CpuIDAndInfo(unsigned value, unsigned *rEAX, unsigned *rEBX,
 #endif
 }
 
+/// GetX86CpuIDAndInfoEx - Execute the specified cpuid with subleaf and return the
+/// 4 values in the specified arguments.  If we can't run cpuid on the host,
+/// return true.
+bool GetX86CpuIDAndInfoEx(unsigned value, unsigned subleaf, unsigned *rEAX,
+                          unsigned *rEBX, unsigned *rECX, unsigned *rEDX) {
+#if defined(__x86_64__) || defined(_M_AMD64) || defined (_M_X64)
+  #if defined(__GNUC__)
+    // gcc doesn't know cpuid would clobber ebx/rbx. Preseve it manually.
+    asm ("movq\t%%rbx, %%rsi\n\t"
+         "cpuid\n\t"
+         "xchgq\t%%rbx, %%rsi\n\t"
+         : "=a" (*rEAX),
+           "=S" (*rEBX),
+           "=c" (*rECX),
+           "=d" (*rEDX)
+         :  "a" (value),
+            "c" (subleaf));
+    return false;
+  #elif defined(_MSC_VER)
+    // __cpuidex was added in MSVC++ 9.0 SP1
+    #if (_MSC_VER > 1500) || (_MSC_VER == 1500 && _MSC_FULL_VER >= 150030729)
+      int registers[4];
+      __cpuidex(registers, value, subleaf);
+      *rEAX = registers[0];
+      *rEBX = registers[1];
+      *rECX = registers[2];
+      *rEDX = registers[3];
+      return false;
+    #else
+      return true;
+    #endif
+  #else
+    return true;
+  #endif
+#elif defined(i386) || defined(__i386__) || defined(__x86__) || defined(_M_IX86)
+  #if defined(__GNUC__)
+    asm ("movl\t%%ebx, %%esi\n\t"
+         "cpuid\n\t"
+         "xchgl\t%%ebx, %%esi\n\t"
+         : "=a" (*rEAX),
+           "=S" (*rEBX),
+           "=c" (*rECX),
+           "=d" (*rEDX)
+         :  "a" (value),
+            "c" (subleaf));
+    return false;
+  #elif defined(_MSC_VER)
+    __asm {
+      mov   eax,value
+      mov   ecx,subleaf
+      cpuid
+      mov   esi,rEAX
+      mov   dword ptr [esi],eax
+      mov   esi,rEBX
+      mov   dword ptr [esi],ebx
+      mov   esi,rECX
+      mov   dword ptr [esi],ecx
+      mov   esi,rEDX
+      mov   dword ptr [esi],edx
+    }
+    return false;
+  #else
+    return true;
+  #endif
+#else
+  return true;
+#endif
+}
+
 static bool OSHasAVXSupport() {
 #if defined(__GNUC__)
   // Check xgetbv; this uses a .byte sequence instead of the instruction
@@ -131,6 +200,14 @@ std::string sys::getHostCPUName() {
   unsigned Model  = 0;
   DetectX86FamilyModel(EAX, Family, Model);
 
+  union {
+    unsigned u[3];
+    char     c[12];
+  } text;
+
+  GetX86CpuIDAndInfo(0, &EAX, text.u+0, text.u+2, text.u+1);
+
+  unsigned MaxLeaf = EAX;
   bool HasSSE3 = (ECX & 0x1);
   bool HasSSE41 = (ECX & 0x80000);
   // If CPUID indicates support for XSAVE, XRESTORE and AVX, and XGETBV 
@@ -138,15 +215,12 @@ std::string sys::getHostCPUName() {
   // switch, then we have full AVX support.
   const unsigned AVXBits = (1 << 27) | (1 << 28);
   bool HasAVX = ((ECX & AVXBits) == AVXBits) && OSHasAVXSupport();
+  bool HasAVX2 = HasAVX && MaxLeaf >= 0x7 &&
+                 !GetX86CpuIDAndInfoEx(0x7, 0x0, &EAX, &EBX, &ECX, &EDX) &&
+                 (EBX & 0x20);
   GetX86CpuIDAndInfo(0x80000001, &EAX, &EBX, &ECX, &EDX);
   bool Em64T = (EDX >> 29) & 0x1;
 
-  union {
-    unsigned u[3];
-    char     c[12];
-  } text;
-
-  GetX86CpuIDAndInfo(0, &EAX, text.u+0, text.u+2, text.u+1);
   if (memcmp(text.c, "GenuineIntel", 12) == 0) {
     switch (Family) {
     case 3:
@@ -254,10 +328,20 @@ std::string sys::getHostCPUName() {
 
       // Ivy Bridge:
       case 58:
+      case 62: // Ivy Bridge EP
         // Not all Ivy Bridge processors support AVX (such as the Pentium
         // versions instead of the i7 versions).
         return HasAVX ? "core-avx-i" : "corei7";
 
+      // Haswell:
+      case 60:
+      case 63:
+      case 69:
+      case 70:
+        // Not all Haswell processors support AVX too (such as the Pentium
+        // versions instead of the i7 versions).
+        return HasAVX2 ? "core-avx2" : "corei7";
+
       case 28: // Most 45 nm Intel Atom processors
       case 38: // 45 nm Atom Lincroft
       case 39: // 32 nm Atom Medfield

lib/Target/X86/X86Subtarget.cpp

@@ -285,7 +285,12 @@ void X86Subtarget::AutoDetectSubtargetFeatures() {
          (Family == 6 && Model == 0x2F) || // Westmere: Westmere-EX
          (Family == 6 && Model == 0x2A) || // SandyBridge
          (Family == 6 && Model == 0x2D) || // SandyBridge: SandyBridge-E*
-         (Family == 6 && Model == 0x3A))) {// IvyBridge
+         (Family == 6 && Model == 0x3A) || // IvyBridge
+         (Family == 6 && Model == 0x3E) || // IvyBridge EP
+         (Family == 6 && Model == 0x3C) || // Haswell
+         (Family == 6 && Model == 0x3F) || // ...
+         (Family == 6 && Model == 0x45) || // ...
+         (Family == 6 && Model == 0x46))) { // ...
       IsUAMemFast = true;
       ToggleFeature(X86::FeatureFastUAMem);
     }