[RISCV] Reduce VL of vmerge.vvm's true operand

This extends the peephole added in #104689 to also reduce the VL of a PseudoVMERGE_VVM's true operand.

We could extend this later to reduce the false operand as well, but this starts with just the true operand since it allows vmerges that are converted to vmv.v.vs (convertVMergeToVMv) to be potentially further folded into their source (foldVMV_V_V).

Author: lukel97

llvm/lib/Target/RISCV/RISCVVectorPeephole.cpp

@@ -131,6 +131,9 @@ bool RISCVVectorPeephole::tryToReduceVL(MachineInstr &MI) const {
   case RISCV::VMV_V_V:
     SrcIdx = 2;
     break;
+  case RISCV::VMERGE_VVM:
+    SrcIdx = 3; // TODO: We can also handle the false operand.
+    break;
   }
 
   MachineOperand &VL = MI.getOperand(RISCVII::getVLOpNum(MI.getDesc()));

llvm/test/CodeGen/RISCV/rvv/rvv-peephole-vmerge-masked-vops.ll

@@ -159,9 +159,8 @@ define <vscale x 2 x i32> @vmerge_larger_vl_same_passthru(<vscale x 2 x i32> %pa
 define <vscale x 2 x i32> @vmerge_smaller_vl_different_passthru(<vscale x 2 x i32> %pt1, <vscale x 2 x i32> %pt2, <vscale x 2 x i32> %x, <vscale x 2 x i32> %y, <vscale x 2 x i1> %m) {
 ; CHECK-LABEL: vmerge_smaller_vl_different_passthru:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 3, e32, m1, tu, mu
+; CHECK-NEXT:    vsetivli zero, 2, e32, m1, tu, mu
 ; CHECK-NEXT:    vadd.vv v8, v10, v11, v0.t
-; CHECK-NEXT:    vsetivli zero, 2, e32, m1, tu, ma
 ; CHECK-NEXT:    vmv.v.v v9, v8
 ; CHECK-NEXT:    vmv1r.v v8, v9
 ; CHECK-NEXT:    ret

llvm/test/CodeGen/RISCV/rvv/rvv-peephole-vmerge-vops.ll

@@ -1072,9 +1072,8 @@ define <vscale x 2 x i32> @vmerge_larger_vl_same_passthru(<vscale x 2 x i32> %pa
 define <vscale x 2 x i32> @vmerge_smaller_vl_different_passthru(<vscale x 2 x i32> %pt1, <vscale x 2 x i32> %pt2, <vscale x 2 x i32> %x, <vscale x 2 x i32> %y, <vscale x 2 x i1> %m) {
 ; CHECK-LABEL: vmerge_smaller_vl_different_passthru:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 3, e32, m1, tu, ma
-; CHECK-NEXT:    vadd.vv v8, v10, v11
 ; CHECK-NEXT:    vsetivli zero, 2, e32, m1, tu, ma
+; CHECK-NEXT:    vadd.vv v8, v10, v11
 ; CHECK-NEXT:    vmerge.vvm v9, v9, v8, v0
 ; CHECK-NEXT:    vmv1r.v v8, v9
 ; CHECK-NEXT:    ret