x64CPUDetect: Add flag for slow PDEP/PEXT on AMD Zen

For some unknown reason PDEP and PEXT are ridiculously slow on AMD Zen
architecture.

Source/Core/Common/CPUDetect.h

@@ -42,6 +42,9 @@ struct CPUInfo
   bool bAVX2 = false;
   bool bBMI1 = false;
   bool bBMI2 = false;
+  // PDEP and PEXT are ridiculously slow on AMD Zen, so we have this flag to avoid using them there
+  // Zen 2 is also affected by this issue
+  bool bFastBMI2 = false;
   bool bFMA = false;
   bool bFMA4 = false;
   bool bAES = false;

Source/Core/Common/x64CPUDetect.cpp

@@ -175,6 +175,7 @@ void CPUInfo::Detect()
   }
 
   bFlushToZero = bSSE;
+  bFastBMI2 = bBMI2 && !bZen;
 
   if (max_ex_fn >= 0x80000004)
   {