Second pass at addressing PR15351 by explicitly checking for AVX support

when getting the host processor information.  It emits a .byte sequence on GNUC compilers to work around lack of xgetbv support with older assemblers, and resolves a comment typo found in the previous patch.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178636 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Support/Host.cpp b/lib/Support/Host.cpp
index b9bbcb9..f91fb37 100644 (file)
--- a/lib/Support/Host.cpp
+++ b/lib/Support/Host.cpp
@@ -112,6 +112,21 @@ static bool GetX86CpuIDAndInfo(unsigned value, unsigned *rEAX,
 #endif
 }
 
+static bool OSHasAVXSupport() {\r
+#if defined( __GNUC__ )\r
+  // Check xgetbv; this uses a .byte sequence instead of the instruction \r
+  // directly because older assemblers do not include support for xgetbv and \r
+  // there is no easy way to conditionally compile based on the assembler used.\r
+  int rEAX, rEDX;\r
+  __asm__ (".byte 0x0f, 0x01, 0xd0" : "=a" (rEAX), "=d" (rEDX) : "c" (0));\r
+#elif defined(_MSC_VER)\r
+  unsigned long long rEAX = _xgetbv(_XCR_XFEATURE_ENABLED_MASK);\r
+#else\r
+  int rEAX = 0; // Ensures we return false\r
+#endif\r
+  return (rEAX & 6) == 6;\r
+}
+
 static void DetectX86FamilyModel(unsigned EAX, unsigned &Family,
                                  unsigned &Model) {
   Family = (EAX >> 8) & 0xf; // Bits 8 - 11
@@ -134,6 +149,10 @@ std::string sys::getHostCPUName() {
   DetectX86FamilyModel(EAX, Family, Model);
 
   bool HasSSE3 = (ECX & 0x1);
+  // If CPUID indicates support for XSAVE, XRESTORE and AVX, and XGETBV 
+  // indicates that the AVX registers will be saved and restored on context
+  // switch, then we have full AVX support.
+  bool HasAVX = (ECX & ((1 << 28) | (1 << 27))) != 0 && OSHasAVXSupport();
   GetX86CpuIDAndInfo(0x80000001, &EAX, &EBX, &ECX, &EDX);
   bool Em64T = (EDX >> 29) & 0x1;
 
@@ -243,11 +262,15 @@ std::string sys::getHostCPUName() {
       case 42: // Intel Core i7 processor. All processors are manufactured
                // using the 32 nm process.
       case 45:
-        return "corei7-avx";
+        // Not all Sandy Bridge processors support AVX (such as the Pentium
+        // versions instead of the i7 versions).
+        return HasAVX ? "corei7-avx" : "corei7";
 
       // Ivy Bridge:
       case 58:
-        return "core-avx-i";
+        // Not all Ivy Bridge processors support AVX (such as the Pentium
+        // versions instead of the i7 versions).
+        return HasAVX ? "core-avx-i" : "corei7";
 
       case 28: // Most 45 nm Intel Atom processors
       case 38: // 45 nm Atom Lincroft