cpu, arm: Distinguish Float* and SimdFloat*, create FloatMem* opClass

Modify the opClass assigned to AArch64 FP instructions from SimdFloat* to
Float*. Also create the FloatMemRead and FloatMemWrite opClasses, which
distinguishes writes to the INT and FP register banks.
Change the latency of (Simd)FloatMultAcc to 5, based on the Cortex-A72,
where the "latency" of FMADD is 3 if the next instruction is a FMADD and
has only the augend to destination dependency, otherwise it's 7 cycles.

Signed-off-by: Jason Lowe-Power <jason@lowepower.com>

src/cpu/FuncUnit.py

@@ -43,13 +43,15 @@ from m5.params import *
 
 class OpClass(Enum):
     vals = ['No_OpClass', 'IntAlu', 'IntMult', 'IntDiv', 'FloatAdd',
-            'FloatCmp', 'FloatCvt', 'FloatMult', 'FloatDiv', 'FloatSqrt',
+            'FloatCmp', 'FloatCvt', 'FloatMult', 'FloatMultAcc', 'FloatDiv',
+            'FloatMisc', 'FloatSqrt',
             'SimdAdd', 'SimdAddAcc', 'SimdAlu', 'SimdCmp', 'SimdCvt',
             'SimdMisc', 'SimdMult', 'SimdMultAcc', 'SimdShift', 'SimdShiftAcc',
             'SimdSqrt', 'SimdFloatAdd', 'SimdFloatAlu', 'SimdFloatCmp',
             'SimdFloatCvt', 'SimdFloatDiv', 'SimdFloatMisc', 'SimdFloatMult',
             'SimdFloatMultAcc', 'SimdFloatSqrt',
-            'MemRead', 'MemWrite', 'IprAccess', 'InstPrefetch']
+            'MemRead', 'MemWrite', 'FloatMemRead', 'FloatMemWrite',
+            'IprAccess', 'InstPrefetch']
 
 class OpDesc(SimObject):
     type = 'OpDesc'