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
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 @@
/// 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 @@
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; }