[RISCV] Teach VSETVLI insertion to merge the unused VSETVLI with the …

…one need to be insert after it.

If a vsetvli instruction is not compatible with the next vector instruction,
and there is no other things that may update or use VL/VTYPE, we could merge
it with the next vsetvli instruction that should be insert for the vector
instruction.

This commit only merge VTYPE with the former vsetvli instruction which has
the same VL.

Reviewed By: craig.topper

Differential Revision: https://reviews.llvm.org/D106857

llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp

@@ -633,6 +633,8 @@ bool RISCVInsertVSETVLI::needVSETVLIPHI(const VSETVLIInfo &Require,
 
 void RISCVInsertVSETVLI::emitVSETVLIs(MachineBasicBlock &MBB) {
   VSETVLIInfo CurInfo;
+  // Only be set if current VSETVLIInfo is from an explicit VSET(I)VLI.
+  MachineInstr *PrevVSETVLIMI = nullptr;
 
   for (MachineInstr &MI : MBB) {
     // If this is an explicit VSETVLI or VSETIVLI, update our state.
@@ -645,6 +647,7 @@ void RISCVInsertVSETVLI::emitVSETVLIs(MachineBasicBlock &MBB) {
       MI.getOperand(3).setIsDead(false);
       MI.getOperand(4).setIsDead(false);
       CurInfo = getInfoForVSETVLI(MI);
+      PrevVSETVLIMI = &MI;
       continue;
     }
 
@@ -678,17 +681,36 @@ void RISCVInsertVSETVLI::emitVSETVLIs(MachineBasicBlock &MBB) {
         // If this instruction isn't compatible with the previous VL/VTYPE
         // we need to insert a VSETVLI.
         if (needVSETVLI(NewInfo, CurInfo)) {
-          insertVSETVLI(MBB, MI, NewInfo, CurInfo);
+          // If the previous VL/VTYPE is set by VSETVLI and do not use, Merge it
+          // with current VL/VTYPE.
+          bool NeedInsertVSETVLI = true;
+          if (PrevVSETVLIMI) {
+            bool HasSameAVL =
+                CurInfo.hasSameAVL(NewInfo) ||
+                (NewInfo.hasAVLReg() && NewInfo.getAVLReg().isVirtual() &&
+                 NewInfo.getAVLReg() == PrevVSETVLIMI->getOperand(0).getReg());
+            // If these two VSETVLI have the same AVL and the same VLMAX,
+            // we could merge these two VSETVLI.
+            if (HasSameAVL &&
+                CurInfo.getSEWLMULRatio() == NewInfo.getSEWLMULRatio()) {
+              PrevVSETVLIMI->getOperand(2).setImm(NewInfo.encodeVTYPE());
+              NeedInsertVSETVLI = false;
+            }
+          }
+          if (NeedInsertVSETVLI)
+            insertVSETVLI(MBB, MI, NewInfo, CurInfo);
           CurInfo = NewInfo;
         }
       }
+      PrevVSETVLIMI = nullptr;
     }
 
     // If this is something updates VL/VTYPE that we don't know about, set
     // the state to unknown.
     if (MI.isCall() || MI.isInlineAsm() || MI.modifiesRegister(RISCV::VL) ||
         MI.modifiesRegister(RISCV::VTYPE)) {
       CurInfo = VSETVLIInfo::getUnknown();
+      PrevVSETVLIMI = nullptr;
     }
   }
 }

llvm/test/CodeGen/RISCV/rvv/vsetvli-insert.ll

@@ -16,8 +16,7 @@ declare <vscale x 1 x i64> @llvm.riscv.vle.mask.nxv1i64(
 define <vscale x 1 x double> @test1(i64 %avl, <vscale x 1 x double> %a, <vscale x 1 x double> %b) nounwind {
 ; CHECK-LABEL: test1:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    vsetvli a0, a0, e32, mf2, ta, mu
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vsetvli a0, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfadd.vv v8, v8, v9
 ; CHECK-NEXT:    ret
 entry:
@@ -32,8 +31,7 @@ entry:
 define <vscale x 1 x double> @test2(i64 %avl, <vscale x 1 x double> %a, <vscale x 1 x double> %b) nounwind {
 ; CHECK-LABEL: test2:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    vsetvli a0, a0, e32, mf2, ta, mu
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
+; CHECK-NEXT:    vsetvli a0, a0, e64, m1, ta, mu
 ; CHECK-NEXT:    vfadd.vv v8, v8, v9
 ; CHECK-NEXT:    ret
 entry:
@@ -48,8 +46,7 @@ entry:
 define <vscale x 1 x i64> @test3(i64 %avl, <vscale x 1 x i64> %a, <vscale x 1 x i64>* %b, <vscale x 1 x i1> %c) nounwind {
 ; CHECK-LABEL: test3:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    vsetvli a0, a0, e64, m1, ta, mu
-; CHECK-NEXT:    vsetvli zero, a0, e64, m1, tu, mu
+; CHECK-NEXT:    vsetvli a0, a0, e64, m1, tu, mu
 ; CHECK-NEXT:    vle64.v v8, (a1), v0.t
 ; CHECK-NEXT:    ret
 entry:
@@ -66,8 +63,7 @@ entry:
 define <vscale x 1 x i64> @test4(i64 %avl, <vscale x 1 x i64> %a, <vscale x 1 x i64>* %b, <vscale x 1 x i1> %c) nounwind {
 ; CHECK-LABEL: test4:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    vsetvli a0, a0, e64, m1, ta, mu
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, tu, mu
+; CHECK-NEXT:    vsetvli a0, a0, e64, m1, tu, mu
 ; CHECK-NEXT:    vle64.v v8, (a1), v0.t
 ; CHECK-NEXT:    ret
 entry: