[RISCV] Move V0 to the end of register allocation order (#82967)

According to

https://riscv-optimization-guide-riseproject-c94355ae3e6872252baa952524.gitlab.io/riscv-optimization-guide.html:

> The v0 register defined by the RISC-V vector extension is special in
> that it can be used both as a general purpose vector register and also
> as a mask register. As a preference, use registers other than v0 for
> non-mask values. Otherwise data will have to be moved out of v0 when a
> mask is required in an operation. v0 may be used when all other
> registers are in use, and using v0 would avoid spilling register state
> to memory.

And using V0 register may stall masking pipeline and stop chaining
for some microarchitectures.

So we should try to not use V0 and register groups contained it as
much as possible. We achieve this via moving V0 to the end of RA
order.

Author: wangpc-pp

llvm/lib/Target/RISCV/RISCVRegisterInfo.td

@@ -508,19 +508,23 @@ defvar VM8VTs = [vint8m8_t, vint16m8_t, vint32m8_t, vint64m8_t,
                  vfloat16m8_t, vbfloat16m8_t,
                  vfloat32m8_t, vfloat64m8_t];
 
+// We reverse the order of last 8 registers so that we don't needlessly prevent
+// allocation of higher lmul register groups while still putting v0 last in the
+// allocation order.
+
 def VR : VReg<!listconcat(VM1VTs, VMaskVTs),
               (add (sequence "V%u", 8, 31),
-                   (sequence "V%u", 0, 7)), 1>;
+                   (sequence "V%u", 7, 0)), 1>;
 
 def VRNoV0 : VReg<!listconcat(VM1VTs, VMaskVTs), (sub VR, V0), 1>;
 
 def VRM2 : VReg<VM2VTs, (add (sequence "V%uM2", 8, 31, 2),
-                             (sequence "V%uM2", 0, 7, 2)), 2>;
+                             (sequence "V%uM2", 6, 0, 2)), 2>;
 
 def VRM2NoV0 : VReg<VM2VTs, (sub VRM2, V0M2), 2>;
 
 def VRM4 : VReg<VM4VTs, (add V8M4, V12M4, V16M4, V20M4,
-                             V24M4, V28M4, V0M4, V4M4), 4>;
+                             V24M4, V28M4, V4M4, V0M4), 4>;
 
 def VRM4NoV0 : VReg<VM4VTs, (sub VRM4, V0M4), 4>;