[RISCV] Correct resource cycles for vzext/vsext in SiFive7 scheduler.

[craig.topper]

Summary

The instructions produce DLEN bits per cycle. The vsetvli LMUL for these
instructions is the output EMUL. The input EMUL is scaled down by
the vector factor suffix on the instruction name.

So for LMUL=1 there are 2*DLEN bits of result produced over 2 cycles.
This makes SiFive7GetCyclesDefault the correct resource cycles.

[monkchiang]

LGTM

llvm/lib/Target/RISCV/RISCVSchedSiFive7.td

int c = !cond(
     !eq(mx, "M2") : 8,
     !eq(mx, "M4") : 16,
     !eq(mx, "MF2") : 2,
     !eq(mx, "MF4") : 1,
     !eq(mx, "MF8") : 1
   );
 }
 
-class SiFive7GetCyclesOutputLMUL<string mx> {
-  int c = !cond(
-    !eq(mx, "M1") : 1,
-    !eq(mx, "M2") : 2,
-    !eq(mx, "M4") : 4,
-    !eq(mx, "M8") : 8,
-    !eq(mx, "MF2") : 1,
-    !eq(mx, "MF4") : 1,
-    !eq(mx, "MF8") : 1
-  );
-}
-
 class SiFive7GetCyclesVMask<string mx> {
   int c = !cond(
     !eq(mx, "M1") : 1,
     !eq(mx, "M2") : 1,
     !eq(mx, "M4") : 1,
     !eq(mx, "M8") : 2,
     !eq(mx, "MF2") : 1,
     !eq(mx, "MF4") : 1,
foreach mx = SchedMxList in {
   // Mask results can't chain.
   let Latency = !add(Cycles, 3), ResourceCycles = [Cycles] in {
     defm "" : LMULWriteResMX<"WriteVICmpV",     [SiFive7VA], mx, IsWorstCase>;
     defm "" : LMULWriteResMX<"WriteVICmpX",     [SiFive7VA], mx, IsWorstCase>;
     defm "" : LMULWriteResMX<"WriteVICmpI",     [SiFive7VA], mx, IsWorstCase>;
   }
 }
 foreach mx = SchedMxList in {
-  defvar Cycles = SiFive7GetCyclesOutputLMUL<mx>.c;
+  defvar Cycles = SiFive7GetCyclesDefault<mx>.c;
   defvar IsWorstCase = SiFive7IsWorstCaseMX<mx, SchedMxList>.c;
   let Latency = 4, ResourceCycles = [Cycles] in {
     defm "" : LMULWriteResMX<"WriteVExtV",      [SiFive7VA], mx, IsWorstCase>;
   }
 }
 foreach mx = SchedMxList in {
   foreach sew = SchedSEWSet<mx>.val in {
     defvar Cycles = !mul(SiFive7GetDivOrSqrtFactor<sew>.c,