[riscv] Prefer to use previous VL for scalar move instructionsK

This patch is an alternative to a piece of D125270. Its direct motivation is to fix a wrong code bug (described below), but somewhat unexpectedly, it also results in a significant code quality improvement for idiomatic fixed length vector patterns.

The existing transform is simply wrong in its current location. We are correct about the fact that the scalar move itself can use the previous vsetvli, but we loose track of the fact that later instructions might depend on the state change represented. That is, the actual value of VL in the register is different than the abstract state thinks it is. Not simply due to precision of modeling, but e.g. the VL register could contain 3 when the abstract state says it is 1. This is annoying hard to demonstrate in practice due to differences in policy flags on the intrinsics, but this is at least a latent wrong code bug.

The code quality benefit comes from the fact we don't need to tie this to explicit vsetvli instructions at all. We can propagate the abstract state, and reduce a) the number of transitions, or b) the cost of those transitions. It turns out we have a bunch of cases - in tests at least - where fixed length AVLs are known non-zero, and we can leave VL unchanged while changing VTYPE.

Differential Revision: https://reviews.llvm.org/D125337

diff --git a/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp b/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
index 0a5d324..954ef7e 100644 (file)
--- a/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
+++ b/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
@@ -484,6 +484,7 @@ private:
   bool computeVLVTYPEChanges(const MachineBasicBlock &MBB);
   void computeIncomingVLVTYPE(const MachineBasicBlock &MBB);
   void emitVSETVLIs(MachineBasicBlock &MBB);
+  void doLocalPrepass(MachineBasicBlock &MBB);
 };
 
 } // end anonymous namespace
@@ -990,9 +991,8 @@ bool RISCVInsertVSETVLI::computeVLVTYPEChanges(const MachineBasicBlock &MBB) {
     // If this is something that 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)) {
+        MI.modifiesRegister(RISCV::VTYPE))
       BBInfo.Change = VSETVLIInfo::getUnknown();
-    }
   }
 
   // Initial exit state is whatever change we found in the block.
@@ -1170,13 +1170,6 @@ void RISCVInsertVSETVLI::emitVSETVLIs(MachineBasicBlock &MBB) {
               PrevVSETVLIMI->getOperand(2).setImm(NewInfo.encodeVTYPE());
               NeedInsertVSETVLI = false;
             }
-            if (isScalarMoveInstr(MI) &&
-                ((CurInfo.hasNonZeroAVL() && NewInfo.hasNonZeroAVL()) ||
-                 (CurInfo.hasZeroAVL() && NewInfo.hasZeroAVL())) &&
-                NewInfo.hasSameVLMAX(CurInfo)) {
-              PrevVSETVLIMI->getOperand(2).setImm(NewInfo.encodeVTYPE());
-              NeedInsertVSETVLI = false;
-            }
           }
           if (NeedInsertVSETVLI)
             insertVSETVLI(MBB, MI, NewInfo, CurInfo);
@@ -1186,7 +1179,7 @@ void RISCVInsertVSETVLI::emitVSETVLIs(MachineBasicBlock &MBB) {
       PrevVSETVLIMI = nullptr;
     }
 
-    // If this is something updates VL/VTYPE that we don't know about, set
+    // If this is something that 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)) {
@@ -1219,6 +1212,54 @@ void RISCVInsertVSETVLI::emitVSETVLIs(MachineBasicBlock &MBB) {
   }
 }
 
+void RISCVInsertVSETVLI::doLocalPrepass(MachineBasicBlock &MBB) {
+  VSETVLIInfo CurInfo = VSETVLIInfo::getUnknown();
+  for (MachineInstr &MI : MBB) {
+    // If this is an explicit VSETVLI or VSETIVLI, update our state.
+    if (isVectorConfigInstr(MI)) {
+      CurInfo = getInfoForVSETVLI(MI);
+      continue;
+    }
+
+    const uint64_t TSFlags = MI.getDesc().TSFlags;
+    if (isScalarMoveInstr(MI)) {
+      assert(RISCVII::hasSEWOp(TSFlags) && RISCVII::hasVLOp(TSFlags));
+      const VSETVLIInfo NewInfo = computeInfoForInstr(MI, TSFlags, MRI);
+
+      // For vmv.s.x and vfmv.s.f, there are only two behaviors, VL = 0 and
+      // VL > 0. We can discard the user requested AVL and just use the last
+      // one if we can prove it equally zero.  This removes a vsetvli entirely
+      // if the types match or allows use of cheaper avl preserving variant
+      // if VLMAX doesn't change.  If VLMAX might change, we couldn't use
+      // the 'vsetvli x0, x0, vtype" variant, so we avoid the transform to
+      // prevent extending live range of an avl register operand.
+      // TODO: We can probably relax this for immediates.
+      if (((CurInfo.hasNonZeroAVL() && NewInfo.hasNonZeroAVL()) ||
+           (CurInfo.hasZeroAVL() && NewInfo.hasZeroAVL())) &&
+          NewInfo.hasSameVLMAX(CurInfo)) {
+        MachineOperand &VLOp = MI.getOperand(getVLOpNum(MI));
+        if (CurInfo.hasAVLImm())
+          VLOp.ChangeToImmediate(CurInfo.getAVLImm());
+        else
+          VLOp.ChangeToRegister(CurInfo.getAVLReg(), /*IsDef*/ false);
+        CurInfo = computeInfoForInstr(MI, TSFlags, MRI);
+        continue;
+      }
+    }
+
+    if (RISCVII::hasSEWOp(TSFlags)) {
+      CurInfo = computeInfoForInstr(MI, TSFlags, MRI);
+      continue;
+    }
+
+    // If this is something that 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();
+  }
+}
+
 bool RISCVInsertVSETVLI::runOnMachineFunction(MachineFunction &MF) {
   // Skip if the vector extension is not enabled.
   const RISCVSubtarget &ST = MF.getSubtarget<RISCVSubtarget>();
@@ -1233,6 +1274,14 @@ bool RISCVInsertVSETVLI::runOnMachineFunction(MachineFunction &MF) {
   assert(BlockInfo.empty() && "Expect empty block infos");
   BlockInfo.resize(MF.getNumBlockIDs());
 
+  // Scan the block locally for cases where we can mutate the operands
+  // of the instructions to reduce state transitions.  Critically, this
+  // must be done before we start propagating data flow states as these
+  // transforms are allowed to change the contents of VTYPE and VL so
+  // long as the semantics of the program stays the same.
+  for (MachineBasicBlock &MBB : MF)
+    doLocalPrepass(MBB);
+
   bool HaveVectorOp = false;
 
   // Phase 1 - determine how VL/VTYPE are affected by the each block.

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bitreverse.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bitreverse.ll
index 9a1f30b..e5b3f18 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bitreverse.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bitreverse.ll
@@ -179,7 +179,7 @@ define void @bitreverse_v2i64(<2 x i64>* %x, <2 x i64>* %y) {
 ; RV32-NEXT:    lui a4, 4080
 ; RV32-NEXT:    vand.vx v10, v10, a4
 ; RV32-NEXT:    li a5, 5
-; RV32-NEXT:    vsetivli zero, 1, e8, mf8, ta, mu
+; RV32-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
 ; RV32-NEXT:    vmv.s.x v0, a5
 ; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; RV32-NEXT:    vmv.v.i v11, 0
@@ -871,7 +871,7 @@ define void @bitreverse_v4i64(<4 x i64>* %x, <4 x i64>* %y) {
 ; LMULMAX1-RV32-NEXT:    lui a5, 4080
 ; LMULMAX1-RV32-NEXT:    vand.vx v11, v9, a5
 ; LMULMAX1-RV32-NEXT:    li a6, 5
-; LMULMAX1-RV32-NEXT:    vsetivli zero, 1, e8, mf8, ta, mu
+; LMULMAX1-RV32-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
 ; LMULMAX1-RV32-NEXT:    vmv.s.x v0, a6
 ; LMULMAX1-RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; LMULMAX1-RV32-NEXT:    vmv.v.i v9, 0

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bswap.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bswap.ll
index 33ac1b4..7a156ea 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bswap.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bswap.ll
@@ -85,7 +85,7 @@ define void @bswap_v2i64(<2 x i64>* %x, <2 x i64>* %y) {
 ; RV32-NEXT:    lui a4, 4080
 ; RV32-NEXT:    vand.vx v10, v10, a4
 ; RV32-NEXT:    li a5, 5
-; RV32-NEXT:    vsetivli zero, 1, e8, mf8, ta, mu
+; RV32-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
 ; RV32-NEXT:    vmv.s.x v0, a5
 ; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; RV32-NEXT:    vmv.v.i v11, 0
@@ -447,7 +447,7 @@ define void @bswap_v4i64(<4 x i64>* %x, <4 x i64>* %y) {
 ; LMULMAX1-RV32-NEXT:    lui a5, 4080
 ; LMULMAX1-RV32-NEXT:    vand.vx v11, v11, a5
 ; LMULMAX1-RV32-NEXT:    li a6, 5
-; LMULMAX1-RV32-NEXT:    vsetivli zero, 1, e8, mf8, ta, mu
+; LMULMAX1-RV32-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
 ; LMULMAX1-RV32-NEXT:    vmv.s.x v0, a6
 ; LMULMAX1-RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; LMULMAX1-RV32-NEXT:    vmv.v.i v12, 0

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll
index c9313ec..f5fcc29 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll
@@ -77,9 +77,9 @@ define <4 x double> @interleave_v2f64(<2 x double> %x, <2 x double> %y) {
 ; RV32-V512-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV32-V512-NEXT:    vrgatherei16.vv v10, v8, v11
 ; RV32-V512-NEXT:    li a0, 10
-; RV32-V512-NEXT:    vsetivli zero, 1, e8, mf8, ta, mu
+; RV32-V512-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
 ; RV32-V512-NEXT:    vmv.s.x v0, a0
-; RV32-V512-NEXT:    vsetivli zero, 4, e64, m1, ta, mu
+; RV32-V512-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV32-V512-NEXT:    vrgatherei16.vv v10, v9, v11, v0.t
 ; RV32-V512-NEXT:    vmv.v.v v8, v10
 ; RV32-V512-NEXT:    ret
@@ -91,9 +91,9 @@ define <4 x double> @interleave_v2f64(<2 x double> %x, <2 x double> %y) {
 ; RV64-V512-NEXT:    vsrl.vi v11, v10, 1
 ; RV64-V512-NEXT:    vrgather.vv v10, v8, v11
 ; RV64-V512-NEXT:    li a0, 10
-; RV64-V512-NEXT:    vsetivli zero, 1, e8, mf8, ta, mu
+; RV64-V512-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
 ; RV64-V512-NEXT:    vmv.s.x v0, a0
-; RV64-V512-NEXT:    vsetivli zero, 4, e64, m1, ta, mu
+; RV64-V512-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV64-V512-NEXT:    vrgather.vv v10, v9, v11, v0.t
 ; RV64-V512-NEXT:    vmv.v.v v8, v10
 ; RV64-V512-NEXT:    ret

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll
index f42e327..217e2e4 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll
@@ -90,9 +90,9 @@ define <4 x i64> @interleave_v2i64(<2 x i64> %x, <2 x i64> %y) {
 ; RV32-V512-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV32-V512-NEXT:    vrgatherei16.vv v10, v8, v11
 ; RV32-V512-NEXT:    li a0, 10
-; RV32-V512-NEXT:    vsetivli zero, 1, e8, mf8, ta, mu
+; RV32-V512-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
 ; RV32-V512-NEXT:    vmv.s.x v0, a0
-; RV32-V512-NEXT:    vsetivli zero, 4, e64, m1, ta, mu
+; RV32-V512-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV32-V512-NEXT:    vrgatherei16.vv v10, v9, v11, v0.t
 ; RV32-V512-NEXT:    vmv.v.v v8, v10
 ; RV32-V512-NEXT:    ret
@@ -104,9 +104,9 @@ define <4 x i64> @interleave_v2i64(<2 x i64> %x, <2 x i64> %y) {
 ; RV64-V512-NEXT:    vsrl.vi v11, v10, 1
 ; RV64-V512-NEXT:    vrgather.vv v10, v8, v11
 ; RV64-V512-NEXT:    li a0, 10
-; RV64-V512-NEXT:    vsetivli zero, 1, e8, mf8, ta, mu
+; RV64-V512-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
 ; RV64-V512-NEXT:    vmv.s.x v0, a0
-; RV64-V512-NEXT:    vsetivli zero, 4, e64, m1, ta, mu
+; RV64-V512-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV64-V512-NEXT:    vrgather.vv v10, v9, v11, v0.t
 ; RV64-V512-NEXT:    vmv.v.v v8, v10
 ; RV64-V512-NEXT:    ret

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-splat.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-splat.ll
index a3396c0..a25117f 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-splat.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-splat.ll
@@ -748,7 +748,7 @@ define void @vadd_vx_v16i64(<16 x i64>* %a, i64 %b, <16 x i64>* %c) {
 ; LMULMAX1-RV32-NEXT:    addi a0, a0, 16
 ; LMULMAX1-RV32-NEXT:    vle64.v v15, (a0)
 ; LMULMAX1-RV32-NEXT:    li a0, 5
-; LMULMAX1-RV32-NEXT:    vsetivli zero, 1, e8, mf8, ta, mu
+; LMULMAX1-RV32-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
 ; LMULMAX1-RV32-NEXT:    vmv.s.x v0, a0
 ; LMULMAX1-RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
 ; LMULMAX1-RV32-NEXT:    vmv.v.x v16, a2

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-fp.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-fp.ll
index 3f8ce14..fae34a7 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-fp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-fp.ll
@@ -433,9 +433,9 @@ define float @vreduce_fwadd_v4f32(<4 x half>* %x, float %s) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
 ; CHECK-NEXT:    vle16.v v8, (a0)
-; CHECK-NEXT:    vsetivli zero, 1, e32, m1, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfmv.s.f v9, fa0
-; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfwredusum.vs v8, v8, v9
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
@@ -451,9 +451,9 @@ define float @vreduce_ord_fwadd_v4f32(<4 x half>* %x, float %s) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
 ; CHECK-NEXT:    vle16.v v8, (a0)
-; CHECK-NEXT:    vsetivli zero, 1, e32, m1, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfmv.s.f v9, fa0
-; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vfwredosum.vs v8, v8, v9
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
@@ -865,9 +865,9 @@ define double @vreduce_fwadd_v2f64(<2 x float>* %x, double %s) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
 ; CHECK-NEXT:    vle32.v v8, (a0)
-; CHECK-NEXT:    vsetivli zero, 1, e64, m1, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfmv.s.f v9, fa0
-; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfwredusum.vs v8, v8, v9
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
@@ -883,9 +883,9 @@ define double @vreduce_ord_fwadd_v2f64(<2 x float>* %x, double %s) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
 ; CHECK-NEXT:    vle32.v v8, (a0)
-; CHECK-NEXT:    vsetivli zero, 1, e64, m1, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfmv.s.f v9, fa0
-; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfwredosum.vs v8, v8, v9
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-int.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-int.ll
index 77d7233..1875213 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-int.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-int.ll
@@ -328,9 +328,9 @@ define i16 @vwreduce_add_v8i16(<8 x i8>* %x) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
 ; CHECK-NEXT:    vle8.v v8, (a0)
-; CHECK-NEXT:    vsetivli zero, 1, e16, m1, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmv.s.x v9, zero
-; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, ta, mu
 ; CHECK-NEXT:    vwredsum.vs v8, v8, v9
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
@@ -346,9 +346,9 @@ define i16 @vwreduce_uadd_v8i16(<8 x i8>* %x) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
 ; CHECK-NEXT:    vle8.v v8, (a0)
-; CHECK-NEXT:    vsetivli zero, 1, e16, m1, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmv.s.x v9, zero
-; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, ta, mu
 ; CHECK-NEXT:    vwredsumu.vs v8, v8, v9
 ; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
@@ -710,9 +710,9 @@ define i32 @vwreduce_add_v4i32(<4 x i16>* %x) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
 ; CHECK-NEXT:    vle16.v v8, (a0)
-; CHECK-NEXT:    vsetivli zero, 1, e32, m1, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmv.s.x v9, zero
-; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vwredsum.vs v8, v8, v9
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
@@ -728,9 +728,9 @@ define i32 @vwreduce_uadd_v4i32(<4 x i16>* %x) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
 ; CHECK-NEXT:    vle16.v v8, (a0)
-; CHECK-NEXT:    vsetivli zero, 1, e32, m1, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmv.s.x v9, zero
-; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vwredsumu.vs v8, v8, v9
 ; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
@@ -1082,9 +1082,9 @@ define i64 @vwreduce_add_v2i64(<2 x i32>* %x) {
 ; RV32:       # %bb.0:
 ; RV32-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
 ; RV32-NEXT:    vle32.v v8, (a0)
-; RV32-NEXT:    vsetivli zero, 1, e64, m1, ta, mu
+; RV32-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV32-NEXT:    vmv.s.x v9, zero
-; RV32-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; RV32-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; RV32-NEXT:    vwredsum.vs v8, v8, v9
 ; RV32-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV32-NEXT:    vmv.x.s a0, v8
@@ -1098,9 +1098,9 @@ define i64 @vwreduce_add_v2i64(<2 x i32>* %x) {
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
 ; RV64-NEXT:    vle32.v v8, (a0)
-; RV64-NEXT:    vsetivli zero, 1, e64, m1, ta, mu
+; RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV64-NEXT:    vmv.s.x v9, zero
-; RV64-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; RV64-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; RV64-NEXT:    vwredsum.vs v8, v8, v9
 ; RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV64-NEXT:    vmv.x.s a0, v8
@@ -1116,9 +1116,9 @@ define i64 @vwreduce_uadd_v2i64(<2 x i32>* %x) {
 ; RV32:       # %bb.0:
 ; RV32-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
 ; RV32-NEXT:    vle32.v v8, (a0)
-; RV32-NEXT:    vsetivli zero, 1, e64, m1, ta, mu
+; RV32-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV32-NEXT:    vmv.s.x v9, zero
-; RV32-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; RV32-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; RV32-NEXT:    vwredsumu.vs v8, v8, v9
 ; RV32-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV32-NEXT:    vmv.x.s a0, v8
@@ -1132,9 +1132,9 @@ define i64 @vwreduce_uadd_v2i64(<2 x i32>* %x) {
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
 ; RV64-NEXT:    vle32.v v8, (a0)
-; RV64-NEXT:    vsetivli zero, 1, e64, m1, ta, mu
+; RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV64-NEXT:    vmv.s.x v9, zero
-; RV64-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; RV64-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; RV64-NEXT:    vwredsumu.vs v8, v8, v9
 ; RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; RV64-NEXT:    vmv.x.s a0, v8