[RISCV] Split long build_vector sequences to reduce critical path (#81312)

If we have a long chain of vslide1down instructions to build e.g. a <16
x i8> from scalar, we end up with a critical path going through the
entire chain. We can instead build two halves, and then combine them
with a vselect. This costs one additional temporary register, but
reduces the critical path by roughly half.

To avoid needing to change VL, we fill each half with undefs for the
elements which will come from the other half. The vselect will at worst
become a vmerge, but is often folded back into the final instruction of
the sequence building the lower half.

A couple notes on the heuristic here:
* This is restricted to LMUL1 to avoid quadratic costing reasoning.
* This only splits once. In future work, we can explore recursive
splitting here, but I'm a bit worried about register pressure and thus
decided to be conservative. It also happens to be "enough" at the
default zvl of 128.
* "8" is picked somewhat arbitrarily as being "long". In practice, our
build_vector codegen for 2 defined elements in a VL=4 vector appears to
need some work. 4 defined elements in a VL=8 vector seems to generally
produce reasonable results.
* Halves may not be an optimal split point. I went down the rabit hole
of trying to find the optimal one, and decided it wasn't worth the
effort to start with.

---------

Co-authored-by: Luke Lau <luke_lau@icloud.com>

5 files changed, 258 insertions, 275 deletions

diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 4caadef694d7..8235b536c4e0 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -3877,6 +3877,47 @@ static SDValue lowerBUILD_VECTOR(SDValue Op, SelectionDAG &DAG,
     return convertFromScalableVector(VT, Vec, DAG, Subtarget);
   }
 
+  // For m1 vectors, if we have non-undef values in both halves of our vector,
+  // split the vector into low and high halves, build them separately, then
+  // use a vselect to combine them.  For long vectors, this cuts the critical
+  // path of the vslide1down sequence in half, and gives us an opportunity
+  // to special case each half independently.  Note that we don't change the
+  // length of the sub-vectors here, so if both fallback to the generic
+  // vslide1down path, we should be able to fold the vselect into the final
+  // vslidedown (for the undef tail) for the first half w/ masking.
+  unsigned NumElts = VT.getVectorNumElements();
+  unsigned NumUndefElts =
+      count_if(Op->op_values(), [](const SDValue &V) { return V.isUndef(); });
+  unsigned NumDefElts = NumElts - NumUndefElts;
+  if (NumDefElts >= 8 && NumDefElts > NumElts / 2 &&
+      ContainerVT.bitsLE(getLMUL1VT(ContainerVT))) {
+    SmallVector<SDValue> SubVecAOps, SubVecBOps;
+    SmallVector<SDValue> MaskVals;
+    SDValue UndefElem = DAG.getUNDEF(Op->getOperand(0)->getValueType(0));
+    SubVecAOps.reserve(NumElts);
+    SubVecBOps.reserve(NumElts);
+    for (unsigned i = 0; i < NumElts; i++) {
+      SDValue Elem = Op->getOperand(i);
+      if (i < NumElts / 2) {
+        SubVecAOps.push_back(Elem);
+        SubVecBOps.push_back(UndefElem);
+      } else {
+        SubVecAOps.push_back(UndefElem);
+        SubVecBOps.push_back(Elem);
+      }
+      bool SelectMaskVal = (i < NumElts / 2);
+      MaskVals.push_back(DAG.getConstant(SelectMaskVal, DL, XLenVT));
+    }
+    assert(SubVecAOps.size() == NumElts && SubVecBOps.size() == NumElts &&
+           MaskVals.size() == NumElts);
+
+    SDValue SubVecA = DAG.getBuildVector(VT, DL, SubVecAOps);
+    SDValue SubVecB = DAG.getBuildVector(VT, DL, SubVecBOps);
+    MVT MaskVT = MVT::getVectorVT(MVT::i1, NumElts);
+    SDValue SelectMask = DAG.getBuildVector(MaskVT, DL, MaskVals);
+    return DAG.getNode(ISD::VSELECT, DL, VT, SelectMask, SubVecA, SubVecB);
+  }
+
   // Cap the cost at a value linear to the number of elements in the vector.
   // The default lowering is to use the stack.  The vector store + scalar loads
   // is linear in VL.  However, at high lmuls vslide1down and vslidedown end up
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec.ll
index a2bd862e2ce1..8e214e405478 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec.ll
@@ -1399,15 +1399,17 @@ define <2 x double> @vid_step2_v2f64() {
 define <8 x float> @buildvec_v8f32_zvl256(float %e0, float %e1, float %e2, float %e3, float %e4, float %e5, float %e6, float %e7) vscale_range(4, 128) {
 ; CHECK-LABEL: buildvec_v8f32_zvl256:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e32, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e32, m1, ta, mu
 ; CHECK-NEXT:    vfmv.v.f v8, fa0
 ; CHECK-NEXT:    vfslide1down.vf v8, v8, fa1
 ; CHECK-NEXT:    vfslide1down.vf v8, v8, fa2
-; CHECK-NEXT:    vfslide1down.vf v8, v8, fa3
-; CHECK-NEXT:    vfslide1down.vf v8, v8, fa4
+; CHECK-NEXT:    vfslide1down.vf v9, v8, fa3
+; CHECK-NEXT:    vfmv.v.f v8, fa4
 ; CHECK-NEXT:    vfslide1down.vf v8, v8, fa5
 ; CHECK-NEXT:    vfslide1down.vf v8, v8, fa6
+; CHECK-NEXT:    vmv.v.i v0, 15
 ; CHECK-NEXT:    vfslide1down.vf v8, v8, fa7
+; CHECK-NEXT:    vslidedown.vi v8, v9, 4, v0.t
 ; CHECK-NEXT:    ret
   %v0 = insertelement <8 x float> poison, float %e0, i64 0
   %v1 = insertelement <8 x float> %v0, float %e1, i64 1
@@ -1448,15 +1450,17 @@ define <8 x double> @buildvec_v8f64_zvl256(double %e0, double %e1, double %e2, d
 define <8 x double> @buildvec_v8f64_zvl512(double %e0, double %e1, double %e2, double %e3, double %e4, double %e5, double %e6, double %e7) vscale_range(8, 128) {
 ; CHECK-LABEL: buildvec_v8f64_zvl512:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e64, m1, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e64, m1, ta, mu
 ; CHECK-NEXT:    vfmv.v.f v8, fa0
 ; CHECK-NEXT:    vfslide1down.vf v8, v8, fa1
 ; CHECK-NEXT:    vfslide1down.vf v8, v8, fa2
-; CHECK-NEXT:    vfslide1down.vf v8, v8, fa3
-; CHECK-NEXT:    vfslide1down.vf v8, v8, fa4
+; CHECK-NEXT:    vfslide1down.vf v9, v8, fa3
+; CHECK-NEXT:    vfmv.v.f v8, fa4
 ; CHECK-NEXT:    vfslide1down.vf v8, v8, fa5
 ; CHECK-NEXT:    vfslide1down.vf v8, v8, fa6
+; CHECK-NEXT:    vmv.v.i v0, 15
 ; CHECK-NEXT:    vfslide1down.vf v8, v8, fa7
+; CHECK-NEXT:    vslidedown.vi v8, v9, 4, v0.t
 ; CHECK-NEXT:    ret
   %v0 = insertelement <8 x double> poison, double %e0, i64 0
   %v1 = insertelement <8 x double> %v0, double %e1, i64 1
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll
index ed0b15c6add5..85b849045e8c 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll
@@ -359,28 +359,28 @@ define void @fp2si_v8f64_v8i8(ptr %x, ptr %y) {
 ; RV32-NEXT:    feq.d a0, fa3, fa3
 ; RV32-NEXT:    fmax.d fa3, fa3, fa5
 ; RV32-NEXT:    fmin.d fa3, fa3, fa4
+; RV32-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; RV32-NEXT:    fld fa2, 40(sp)
 ; RV32-NEXT:    fcvt.w.d a2, fa3, rtz
-; RV32-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
-; RV32-NEXT:    fld fa3, 32(sp)
 ; RV32-NEXT:    neg a0, a0
 ; RV32-NEXT:    and a0, a0, a2
-; RV32-NEXT:    vslide1down.vx v8, v10, a0
-; RV32-NEXT:    feq.d a0, fa3, fa3
-; RV32-NEXT:    fmax.d fa3, fa3, fa5
+; RV32-NEXT:    feq.d a2, fa2, fa2
+; RV32-NEXT:    fmax.d fa3, fa2, fa5
 ; RV32-NEXT:    fmin.d fa3, fa3, fa4
-; RV32-NEXT:    fcvt.w.d a2, fa3, rtz
-; RV32-NEXT:    fld fa3, 40(sp)
-; RV32-NEXT:    neg a0, a0
-; RV32-NEXT:    and a0, a0, a2
-; RV32-NEXT:    vslide1down.vx v8, v8, a0
-; RV32-NEXT:    feq.d a0, fa3, fa3
+; RV32-NEXT:    fcvt.w.d a3, fa3, rtz
+; RV32-NEXT:    fld fa3, 32(sp)
+; RV32-NEXT:    vslide1down.vx v8, v10, a0
+; RV32-NEXT:    neg a0, a2
+; RV32-NEXT:    and a0, a0, a3
+; RV32-NEXT:    feq.d a2, fa3, fa3
+; RV32-NEXT:    neg a2, a2
 ; RV32-NEXT:    fmax.d fa3, fa3, fa5
 ; RV32-NEXT:    fmin.d fa3, fa3, fa4
-; RV32-NEXT:    fcvt.w.d a2, fa3, rtz
+; RV32-NEXT:    fcvt.w.d a3, fa3, rtz
 ; RV32-NEXT:    fld fa3, 48(sp)
-; RV32-NEXT:    neg a0, a0
-; RV32-NEXT:    and a0, a0, a2
-; RV32-NEXT:    vslide1down.vx v8, v8, a0
+; RV32-NEXT:    and a2, a2, a3
+; RV32-NEXT:    vmv.v.x v9, a2
+; RV32-NEXT:    vslide1down.vx v9, v9, a0
 ; RV32-NEXT:    feq.d a0, fa3, fa3
 ; RV32-NEXT:    fmax.d fa3, fa3, fa5
 ; RV32-NEXT:    fmin.d fa3, fa3, fa4
@@ -388,15 +388,17 @@ define void @fp2si_v8f64_v8i8(ptr %x, ptr %y) {
 ; RV32-NEXT:    fld fa3, 56(sp)
 ; RV32-NEXT:    neg a0, a0
 ; RV32-NEXT:    and a0, a0, a2
-; RV32-NEXT:    vslide1down.vx v8, v8, a0
+; RV32-NEXT:    vslide1down.vx v9, v9, a0
 ; RV32-NEXT:    feq.d a0, fa3, fa3
 ; RV32-NEXT:    neg a0, a0
 ; RV32-NEXT:    fmax.d fa5, fa3, fa5
 ; RV32-NEXT:    fmin.d fa5, fa5, fa4
 ; RV32-NEXT:    fcvt.w.d a2, fa5, rtz
 ; RV32-NEXT:    and a0, a0, a2
-; RV32-NEXT:    vslide1down.vx v8, v8, a0
-; RV32-NEXT:    vse8.v v8, (a1)
+; RV32-NEXT:    vmv.v.i v0, 15
+; RV32-NEXT:    vslide1down.vx v9, v9, a0
+; RV32-NEXT:    vslidedown.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vse8.v v9, (a1)
 ; RV32-NEXT:    addi sp, s0, -128
 ; RV32-NEXT:    lw ra, 124(sp) # 4-byte Folded Reload
 ; RV32-NEXT:    lw s0, 120(sp) # 4-byte Folded Reload
@@ -458,28 +460,28 @@ define void @fp2si_v8f64_v8i8(ptr %x, ptr %y) {
 ; RV64-NEXT:    feq.d a0, fa3, fa3
 ; RV64-NEXT:    fmax.d fa3, fa3, fa5
 ; RV64-NEXT:    fmin.d fa3, fa3, fa4
+; RV64-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; RV64-NEXT:    fld fa2, 40(sp)
 ; RV64-NEXT:    fcvt.l.d a2, fa3, rtz
-; RV64-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
-; RV64-NEXT:    fld fa3, 32(sp)
 ; RV64-NEXT:    neg a0, a0
 ; RV64-NEXT:    and a0, a0, a2
-; RV64-NEXT:    vslide1down.vx v8, v10, a0
-; RV64-NEXT:    feq.d a0, fa3, fa3
-; RV64-NEXT:    fmax.d fa3, fa3, fa5
+; RV64-NEXT:    feq.d a2, fa2, fa2
+; RV64-NEXT:    fmax.d fa3, fa2, fa5
 ; RV64-NEXT:    fmin.d fa3, fa3, fa4
-; RV64-NEXT:    fcvt.l.d a2, fa3, rtz
-; RV64-NEXT:    fld fa3, 40(sp)
-; RV64-NEXT:    neg a0, a0
-; RV64-NEXT:    and a0, a0, a2
-; RV64-NEXT:    vslide1down.vx v8, v8, a0
-; RV64-NEXT:    feq.d a0, fa3, fa3
+; RV64-NEXT:    fcvt.l.d a3, fa3, rtz
+; RV64-NEXT:    fld fa3, 32(sp)
+; RV64-NEXT:    vslide1down.vx v8, v10, a0
+; RV64-NEXT:    neg a0, a2
+; RV64-NEXT:    and a0, a0, a3
+; RV64-NEXT:    feq.d a2, fa3, fa3
+; RV64-NEXT:    negw a2, a2
 ; RV64-NEXT:    fmax.d fa3, fa3, fa5
 ; RV64-NEXT:    fmin.d fa3, fa3, fa4
-; RV64-NEXT:    fcvt.l.d a2, fa3, rtz
+; RV64-NEXT:    fcvt.l.d a3, fa3, rtz
 ; RV64-NEXT:    fld fa3, 48(sp)
-; RV64-NEXT:    neg a0, a0
-; RV64-NEXT:    and a0, a0, a2
-; RV64-NEXT:    vslide1down.vx v8, v8, a0
+; RV64-NEXT:    and a2, a2, a3
+; RV64-NEXT:    vmv.v.x v9, a2
+; RV64-NEXT:    vslide1down.vx v9, v9, a0
 ; RV64-NEXT:    feq.d a0, fa3, fa3
 ; RV64-NEXT:    fmax.d fa3, fa3, fa5
 ; RV64-NEXT:    fmin.d fa3, fa3, fa4
@@ -487,15 +489,17 @@ define void @fp2si_v8f64_v8i8(ptr %x, ptr %y) {
 ; RV64-NEXT:    fld fa3, 56(sp)
 ; RV64-NEXT:    neg a0, a0
 ; RV64-NEXT:    and a0, a0, a2
-; RV64-NEXT:    vslide1down.vx v8, v8, a0
+; RV64-NEXT:    vslide1down.vx v9, v9, a0
 ; RV64-NEXT:    feq.d a0, fa3, fa3
 ; RV64-NEXT:    neg a0, a0
 ; RV64-NEXT:    fmax.d fa5, fa3, fa5
 ; RV64-NEXT:    fmin.d fa5, fa5, fa4
 ; RV64-NEXT:    fcvt.l.d a2, fa5, rtz
 ; RV64-NEXT:    and a0, a0, a2
-; RV64-NEXT:    vslide1down.vx v8, v8, a0
-; RV64-NEXT:    vse8.v v8, (a1)
+; RV64-NEXT:    vmv.v.i v0, 15
+; RV64-NEXT:    vslide1down.vx v9, v9, a0
+; RV64-NEXT:    vslidedown.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vse8.v v9, (a1)
 ; RV64-NEXT:    addi sp, s0, -128
 ; RV64-NEXT:    ld ra, 120(sp) # 8-byte Folded Reload
 ; RV64-NEXT:    ld s0, 112(sp) # 8-byte Folded Reload
@@ -553,11 +557,11 @@ define void @fp2ui_v8f64_v8i8(ptr %x, ptr %y) {
 ; RV32-NEXT:    vslidedown.vi v8, v8, 3
 ; RV32-NEXT:    vfmv.f.s fa4, v8
 ; RV32-NEXT:    fmax.d fa4, fa4, fa3
-; RV32-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
-; RV32-NEXT:    fld fa2, 32(sp)
+; RV32-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; RV32-NEXT:    fld fa2, 40(sp)
 ; RV32-NEXT:    fmin.d fa4, fa4, fa5
 ; RV32-NEXT:    fcvt.wu.d a0, fa4, rtz
-; RV32-NEXT:    fld fa4, 40(sp)
+; RV32-NEXT:    fld fa4, 32(sp)
 ; RV32-NEXT:    fmax.d fa2, fa2, fa3
 ; RV32-NEXT:    fmin.d fa2, fa2, fa5
 ; RV32-NEXT:    fcvt.wu.d a2, fa2, rtz
@@ -570,14 +574,16 @@ define void @fp2ui_v8f64_v8i8(ptr %x, ptr %y) {
 ; RV32-NEXT:    fmin.d fa4, fa4, fa5
 ; RV32-NEXT:    fcvt.wu.d a0, fa4, rtz
 ; RV32-NEXT:    fld fa4, 56(sp)
-; RV32-NEXT:    vslide1down.vx v8, v8, a2
-; RV32-NEXT:    vslide1down.vx v8, v8, a3
-; RV32-NEXT:    vslide1down.vx v8, v8, a0
+; RV32-NEXT:    vmv.v.x v9, a3
+; RV32-NEXT:    vslide1down.vx v9, v9, a2
+; RV32-NEXT:    vslide1down.vx v9, v9, a0
 ; RV32-NEXT:    fmax.d fa4, fa4, fa3
 ; RV32-NEXT:    fmin.d fa5, fa4, fa5
 ; RV32-NEXT:    fcvt.wu.d a0, fa5, rtz
-; RV32-NEXT:    vslide1down.vx v8, v8, a0
-; RV32-NEXT:    vse8.v v8, (a1)
+; RV32-NEXT:    vmv.v.i v0, 15
+; RV32-NEXT:    vslide1down.vx v9, v9, a0
+; RV32-NEXT:    vslidedown.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vse8.v v9, (a1)
 ; RV32-NEXT:    addi sp, s0, -128
 ; RV32-NEXT:    lw ra, 124(sp) # 4-byte Folded Reload
 ; RV32-NEXT:    lw s0, 120(sp) # 4-byte Folded Reload
@@ -627,11 +633,11 @@ define void @fp2ui_v8f64_v8i8(ptr %x, ptr %y) {
 ; RV64-NEXT:    vslidedown.vi v8, v8, 3
 ; RV64-NEXT:    vfmv.f.s fa4, v8
 ; RV64-NEXT:    fmax.d fa4, fa4, fa3
-; RV64-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
-; RV64-NEXT:    fld fa2, 32(sp)
+; RV64-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; RV64-NEXT:    fld fa2, 40(sp)
 ; RV64-NEXT:    fmin.d fa4, fa4, fa5
 ; RV64-NEXT:    fcvt.lu.d a0, fa4, rtz
-; RV64-NEXT:    fld fa4, 40(sp)
+; RV64-NEXT:    fld fa4, 32(sp)
 ; RV64-NEXT:    fmax.d fa2, fa2, fa3
 ; RV64-NEXT:    fmin.d fa2, fa2, fa5
 ; RV64-NEXT:    fcvt.lu.d a2, fa2, rtz
@@ -644,14 +650,16 @@ define void @fp2ui_v8f64_v8i8(ptr %x, ptr %y) {
 ; RV64-NEXT:    fmin.d fa4, fa4, fa5
 ; RV64-NEXT:    fcvt.lu.d a0, fa4, rtz
 ; RV64-NEXT:    fld fa4, 56(sp)
-; RV64-NEXT:    vslide1down.vx v8, v8, a2
-; RV64-NEXT:    vslide1down.vx v8, v8, a3
-; RV64-NEXT:    vslide1down.vx v8, v8, a0
+; RV64-NEXT:    vmv.v.x v9, a3
+; RV64-NEXT:    vslide1down.vx v9, v9, a2
+; RV64-NEXT:    vslide1down.vx v9, v9, a0
 ; RV64-NEXT:    fmax.d fa4, fa4, fa3
 ; RV64-NEXT:    fmin.d fa5, fa4, fa5
 ; RV64-NEXT:    fcvt.lu.d a0, fa5, rtz
-; RV64-NEXT:    vslide1down.vx v8, v8, a0
-; RV64-NEXT:    vse8.v v8, (a1)
+; RV64-NEXT:    vmv.v.i v0, 15
+; RV64-NEXT:    vslide1down.vx v9, v9, a0
+; RV64-NEXT:    vslidedown.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vse8.v v9, (a1)
 ; RV64-NEXT:    addi sp, s0, -128
 ; RV64-NEXT:    ld ra, 120(sp) # 8-byte Folded Reload
 ; RV64-NEXT:    ld s0, 112(sp) # 8-byte Folded Reload
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
index e691e6358115..ed6c01aaf7fe 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
@@ -1181,89 +1181,46 @@ define <8 x i64> @v8xi64_exact_undef_prefix(i64 %a, i64 %b, i64 %c, i64 %d) vsca
 
 
 define <16 x i8> @buildvec_v16i8_loads_contigous(ptr %p) {
-; RV32-LABEL: buildvec_v16i8_loads_contigous:
-; RV32:       # %bb.0:
-; RV32-NEXT:    addi sp, sp, -16
-; RV32-NEXT:    .cfi_def_cfa_offset 16
-; RV32-NEXT:    sw s0, 12(sp) # 4-byte Folded Spill
-; RV32-NEXT:    .cfi_offset s0, -4
-; RV32-NEXT:    lbu a1, 1(a0)
-; RV32-NEXT:    lbu a2, 2(a0)
-; RV32-NEXT:    lbu a3, 3(a0)
-; RV32-NEXT:    lbu a4, 4(a0)
-; RV32-NEXT:    lbu a5, 5(a0)
-; RV32-NEXT:    lbu a6, 6(a0)
-; RV32-NEXT:    lbu a7, 7(a0)
-; RV32-NEXT:    lbu t0, 8(a0)
-; RV32-NEXT:    lbu t1, 9(a0)
-; RV32-NEXT:    lbu t2, 10(a0)
-; RV32-NEXT:    lbu t3, 11(a0)
-; RV32-NEXT:    lbu t4, 12(a0)
-; RV32-NEXT:    lbu t5, 13(a0)
-; RV32-NEXT:    lbu t6, 14(a0)
-; RV32-NEXT:    lbu s0, 15(a0)
-; RV32-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
-; RV32-NEXT:    vlse8.v v8, (a0), zero
-; RV32-NEXT:    vslide1down.vx v8, v8, a1
-; RV32-NEXT:    vslide1down.vx v8, v8, a2
-; RV32-NEXT:    vslide1down.vx v8, v8, a3
-; RV32-NEXT:    vslide1down.vx v8, v8, a4
-; RV32-NEXT:    vslide1down.vx v8, v8, a5
-; RV32-NEXT:    vslide1down.vx v8, v8, a6
-; RV32-NEXT:    vslide1down.vx v8, v8, a7
-; RV32-NEXT:    vslide1down.vx v8, v8, t0
-; RV32-NEXT:    vslide1down.vx v8, v8, t1
-; RV32-NEXT:    vslide1down.vx v8, v8, t2
-; RV32-NEXT:    vslide1down.vx v8, v8, t3
-; RV32-NEXT:    vslide1down.vx v8, v8, t4
-; RV32-NEXT:    vslide1down.vx v8, v8, t5
-; RV32-NEXT:    vslide1down.vx v8, v8, t6
-; RV32-NEXT:    vslide1down.vx v8, v8, s0
-; RV32-NEXT:    lw s0, 12(sp) # 4-byte Folded Reload
-; RV32-NEXT:    addi sp, sp, 16
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: buildvec_v16i8_loads_contigous:
-; RV64:       # %bb.0:
-; RV64-NEXT:    addi sp, sp, -16
-; RV64-NEXT:    .cfi_def_cfa_offset 16
-; RV64-NEXT:    sd s0, 8(sp) # 8-byte Folded Spill
-; RV64-NEXT:    .cfi_offset s0, -8
-; RV64-NEXT:    lbu a1, 1(a0)
-; RV64-NEXT:    lbu a2, 2(a0)
-; RV64-NEXT:    lbu a3, 3(a0)
-; RV64-NEXT:    lbu a4, 4(a0)
-; RV64-NEXT:    lbu a5, 5(a0)
-; RV64-NEXT:    lbu a6, 6(a0)
-; RV64-NEXT:    lbu a7, 7(a0)
-; RV64-NEXT:    lbu t0, 8(a0)
-; RV64-NEXT:    lbu t1, 9(a0)
-; RV64-NEXT:    lbu t2, 10(a0)
-; RV64-NEXT:    lbu t3, 11(a0)
-; RV64-NEXT:    lbu t4, 12(a0)
-; RV64-NEXT:    lbu t5, 13(a0)
-; RV64-NEXT:    lbu t6, 14(a0)
-; RV64-NEXT:    lbu s0, 15(a0)
-; RV64-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
-; RV64-NEXT:    vlse8.v v8, (a0), zero
-; RV64-NEXT:    vslide1down.vx v8, v8, a1
-; RV64-NEXT:    vslide1down.vx v8, v8, a2
-; RV64-NEXT:    vslide1down.vx v8, v8, a3
-; RV64-NEXT:    vslide1down.vx v8, v8, a4
-; RV64-NEXT:    vslide1down.vx v8, v8, a5
-; RV64-NEXT:    vslide1down.vx v8, v8, a6
-; RV64-NEXT:    vslide1down.vx v8, v8, a7
-; RV64-NEXT:    vslide1down.vx v8, v8, t0
-; RV64-NEXT:    vslide1down.vx v8, v8, t1
-; RV64-NEXT:    vslide1down.vx v8, v8, t2
-; RV64-NEXT:    vslide1down.vx v8, v8, t3
-; RV64-NEXT:    vslide1down.vx v8, v8, t4
-; RV64-NEXT:    vslide1down.vx v8, v8, t5
-; RV64-NEXT:    vslide1down.vx v8, v8, t6
-; RV64-NEXT:    vslide1down.vx v8, v8, s0
-; RV64-NEXT:    ld s0, 8(sp) # 8-byte Folded Reload
-; RV64-NEXT:    addi sp, sp, 16
-; RV64-NEXT:    ret
+; CHECK-LABEL: buildvec_v16i8_loads_contigous:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lbu a1, 1(a0)
+; CHECK-NEXT:    lbu a2, 2(a0)
+; CHECK-NEXT:    lbu a3, 3(a0)
+; CHECK-NEXT:    lbu a4, 4(a0)
+; CHECK-NEXT:    lbu a5, 5(a0)
+; CHECK-NEXT:    lbu a6, 6(a0)
+; CHECK-NEXT:    lbu a7, 7(a0)
+; CHECK-NEXT:    lbu t0, 9(a0)
+; CHECK-NEXT:    lbu t1, 10(a0)
+; CHECK-NEXT:    lbu t2, 11(a0)
+; CHECK-NEXT:    lbu t3, 12(a0)
+; CHECK-NEXT:    lbu t4, 13(a0)
+; CHECK-NEXT:    lbu t5, 14(a0)
+; CHECK-NEXT:    lbu t6, 15(a0)
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
+; CHECK-NEXT:    vlse8.v v8, (a0), zero
+; CHECK-NEXT:    addi a0, a0, 8
+; CHECK-NEXT:    vslide1down.vx v8, v8, a1
+; CHECK-NEXT:    vslide1down.vx v8, v8, a2
+; CHECK-NEXT:    vslide1down.vx v8, v8, a3
+; CHECK-NEXT:    vslide1down.vx v8, v8, a4
+; CHECK-NEXT:    vlse8.v v9, (a0), zero
+; CHECK-NEXT:    vslide1down.vx v8, v8, a5
+; CHECK-NEXT:    vslide1down.vx v8, v8, a6
+; CHECK-NEXT:    vslide1down.vx v10, v8, a7
+; CHECK-NEXT:    vslide1down.vx v8, v9, t0
+; CHECK-NEXT:    vslide1down.vx v8, v8, t1
+; CHECK-NEXT:    vslide1down.vx v8, v8, t2
+; CHECK-NEXT:    vslide1down.vx v8, v8, t3
+; CHECK-NEXT:    vslide1down.vx v8, v8, t4
+; CHECK-NEXT:    vslide1down.vx v8, v8, t5
+; CHECK-NEXT:    vslide1down.vx v8, v8, t6
+; CHECK-NEXT:    li a0, 255
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vmv.s.x v0, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, mu
+; CHECK-NEXT:    vslidedown.vi v8, v10, 8, v0.t
+; CHECK-NEXT:    ret
   %p2 = getelementptr i8, ptr %p, i32 1
   %p3 = getelementptr i8, ptr %p, i32 2
   %p4 = getelementptr i8, ptr %p, i32 3
@@ -1318,89 +1275,46 @@ define <16 x i8> @buildvec_v16i8_loads_contigous(ptr %p) {
 
 
 define <16 x i8> @buildvec_v16i8_loads_gather(ptr %p) {
-; RV32-LABEL: buildvec_v16i8_loads_gather:
-; RV32:       # %bb.0:
-; RV32-NEXT:    addi sp, sp, -16
-; RV32-NEXT:    .cfi_def_cfa_offset 16
-; RV32-NEXT:    sw s0, 12(sp) # 4-byte Folded Spill
-; RV32-NEXT:    .cfi_offset s0, -4
-; RV32-NEXT:    lbu a1, 1(a0)
-; RV32-NEXT:    lbu a2, 22(a0)
-; RV32-NEXT:    lbu a3, 31(a0)
-; RV32-NEXT:    lbu a4, 44(a0)
-; RV32-NEXT:    lbu a5, 55(a0)
-; RV32-NEXT:    lbu a6, 623(a0)
-; RV32-NEXT:    lbu a7, 75(a0)
-; RV32-NEXT:    lbu t0, 82(a0)
-; RV32-NEXT:    lbu t1, 93(a0)
-; RV32-NEXT:    lbu t2, 105(a0)
-; RV32-NEXT:    lbu t3, 161(a0)
-; RV32-NEXT:    lbu t4, 124(a0)
-; RV32-NEXT:    lbu t5, 163(a0)
-; RV32-NEXT:    lbu t6, 144(a0)
-; RV32-NEXT:    lbu s0, 154(a0)
-; RV32-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
-; RV32-NEXT:    vlse8.v v8, (a0), zero
-; RV32-NEXT:    vslide1down.vx v8, v8, a1
-; RV32-NEXT:    vslide1down.vx v8, v8, a2
-; RV32-NEXT:    vslide1down.vx v8, v8, a3
-; RV32-NEXT:    vslide1down.vx v8, v8, a4
-; RV32-NEXT:    vslide1down.vx v8, v8, a5
-; RV32-NEXT:    vslide1down.vx v8, v8, a6
-; RV32-NEXT:    vslide1down.vx v8, v8, a7
-; RV32-NEXT:    vslide1down.vx v8, v8, t0
-; RV32-NEXT:    vslide1down.vx v8, v8, t1
-; RV32-NEXT:    vslide1down.vx v8, v8, t2
-; RV32-NEXT:    vslide1down.vx v8, v8, t3
-; RV32-NEXT:    vslide1down.vx v8, v8, t4
-; RV32-NEXT:    vslide1down.vx v8, v8, t5
-; RV32-NEXT:    vslide1down.vx v8, v8, t6
-; RV32-NEXT:    vslide1down.vx v8, v8, s0
-; RV32-NEXT:    lw s0, 12(sp) # 4-byte Folded Reload
-; RV32-NEXT:    addi sp, sp, 16
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: buildvec_v16i8_loads_gather:
-; RV64:       # %bb.0:
-; RV64-NEXT:    addi sp, sp, -16
-; RV64-NEXT:    .cfi_def_cfa_offset 16
-; RV64-NEXT:    sd s0, 8(sp) # 8-byte Folded Spill
-; RV64-NEXT:    .cfi_offset s0, -8
-; RV64-NEXT:    lbu a1, 1(a0)
-; RV64-NEXT:    lbu a2, 22(a0)
-; RV64-NEXT:    lbu a3, 31(a0)
-; RV64-NEXT:    lbu a4, 44(a0)
-; RV64-NEXT:    lbu a5, 55(a0)
-; RV64-NEXT:    lbu a6, 623(a0)
-; RV64-NEXT:    lbu a7, 75(a0)
-; RV64-NEXT:    lbu t0, 82(a0)
-; RV64-NEXT:    lbu t1, 93(a0)
-; RV64-NEXT:    lbu t2, 105(a0)
-; RV64-NEXT:    lbu t3, 161(a0)
-; RV64-NEXT:    lbu t4, 124(a0)
-; RV64-NEXT:    lbu t5, 163(a0)
-; RV64-NEXT:    lbu t6, 144(a0)
-; RV64-NEXT:    lbu s0, 154(a0)
-; RV64-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
-; RV64-NEXT:    vlse8.v v8, (a0), zero
-; RV64-NEXT:    vslide1down.vx v8, v8, a1
-; RV64-NEXT:    vslide1down.vx v8, v8, a2
-; RV64-NEXT:    vslide1down.vx v8, v8, a3
-; RV64-NEXT:    vslide1down.vx v8, v8, a4
-; RV64-NEXT:    vslide1down.vx v8, v8, a5
-; RV64-NEXT:    vslide1down.vx v8, v8, a6
-; RV64-NEXT:    vslide1down.vx v8, v8, a7
-; RV64-NEXT:    vslide1down.vx v8, v8, t0
-; RV64-NEXT:    vslide1down.vx v8, v8, t1
-; RV64-NEXT:    vslide1down.vx v8, v8, t2
-; RV64-NEXT:    vslide1down.vx v8, v8, t3
-; RV64-NEXT:    vslide1down.vx v8, v8, t4
-; RV64-NEXT:    vslide1down.vx v8, v8, t5
-; RV64-NEXT:    vslide1down.vx v8, v8, t6
-; RV64-NEXT:    vslide1down.vx v8, v8, s0
-; RV64-NEXT:    ld s0, 8(sp) # 8-byte Folded Reload
-; RV64-NEXT:    addi sp, sp, 16
-; RV64-NEXT:    ret
+; CHECK-LABEL: buildvec_v16i8_loads_gather:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lbu a1, 1(a0)
+; CHECK-NEXT:    lbu a2, 22(a0)
+; CHECK-NEXT:    lbu a3, 31(a0)
+; CHECK-NEXT:    lbu a4, 44(a0)
+; CHECK-NEXT:    lbu a5, 55(a0)
+; CHECK-NEXT:    lbu a6, 623(a0)
+; CHECK-NEXT:    lbu a7, 75(a0)
+; CHECK-NEXT:    lbu t0, 93(a0)
+; CHECK-NEXT:    lbu t1, 105(a0)
+; CHECK-NEXT:    lbu t2, 161(a0)
+; CHECK-NEXT:    lbu t3, 124(a0)
+; CHECK-NEXT:    lbu t4, 163(a0)
+; CHECK-NEXT:    lbu t5, 144(a0)
+; CHECK-NEXT:    lbu t6, 154(a0)
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
+; CHECK-NEXT:    vlse8.v v8, (a0), zero
+; CHECK-NEXT:    addi a0, a0, 82
+; CHECK-NEXT:    vslide1down.vx v8, v8, a1
+; CHECK-NEXT:    vslide1down.vx v8, v8, a2
+; CHECK-NEXT:    vslide1down.vx v8, v8, a3
+; CHECK-NEXT:    vslide1down.vx v8, v8, a4
+; CHECK-NEXT:    vlse8.v v9, (a0), zero
+; CHECK-NEXT:    vslide1down.vx v8, v8, a5
+; CHECK-NEXT:    vslide1down.vx v8, v8, a6
+; CHECK-NEXT:    vslide1down.vx v10, v8, a7
+; CHECK-NEXT:    vslide1down.vx v8, v9, t0
+; CHECK-NEXT:    vslide1down.vx v8, v8, t1
+; CHECK-NEXT:    vslide1down.vx v8, v8, t2
+; CHECK-NEXT:    vslide1down.vx v8, v8, t3
+; CHECK-NEXT:    vslide1down.vx v8, v8, t4
+; CHECK-NEXT:    vslide1down.vx v8, v8, t5
+; CHECK-NEXT:    vslide1down.vx v8, v8, t6
+; CHECK-NEXT:    li a0, 255
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vmv.s.x v0, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, mu
+; CHECK-NEXT:    vslidedown.vi v8, v10, 8, v0.t
+; CHECK-NEXT:    ret
   %p2 = getelementptr i8, ptr %p, i32 1
   %p3 = getelementptr i8, ptr %p, i32 22
   %p4 = getelementptr i8, ptr %p, i32 31
@@ -1560,21 +1474,26 @@ define <16 x i8> @buildvec_v16i8_undef_edges(ptr %p) {
 ; CHECK-NEXT:    lbu a3, 55(a0)
 ; CHECK-NEXT:    lbu a4, 623(a0)
 ; CHECK-NEXT:    lbu a5, 75(a0)
-; CHECK-NEXT:    lbu a6, 82(a0)
-; CHECK-NEXT:    lbu a7, 93(a0)
-; CHECK-NEXT:    lbu t0, 105(a0)
-; CHECK-NEXT:    lbu a0, 161(a0)
+; CHECK-NEXT:    lbu a6, 93(a0)
+; CHECK-NEXT:    lbu a7, 105(a0)
+; CHECK-NEXT:    lbu t0, 161(a0)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vlse8.v v8, (a1), zero
+; CHECK-NEXT:    addi a0, a0, 82
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a2
+; CHECK-NEXT:    vlse8.v v9, (a0), zero
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a3
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a4
-; CHECK-NEXT:    vslide1down.vx v8, v8, a5
-; CHECK-NEXT:    vslide1down.vx v8, v8, a6
+; CHECK-NEXT:    vslide1down.vx v10, v8, a5
+; CHECK-NEXT:    vslide1down.vx v8, v9, a6
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a7
 ; CHECK-NEXT:    vslide1down.vx v8, v8, t0
-; CHECK-NEXT:    vslide1down.vx v8, v8, a0
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 4
+; CHECK-NEXT:    li a0, 255
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vmv.s.x v0, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, mu
+; CHECK-NEXT:    vslidedown.vi v8, v10, 8, v0.t
 ; CHECK-NEXT:    ret
   %p4 = getelementptr i8, ptr %p, i32 31
   %p5 = getelementptr i8, ptr %p, i32 44
@@ -1615,26 +1534,31 @@ define <16 x i8> @buildvec_v16i8_loads_undef_scattered(ptr %p) {
 ; CHECK-NEXT:    lbu a2, 44(a0)
 ; CHECK-NEXT:    lbu a3, 55(a0)
 ; CHECK-NEXT:    lbu a4, 75(a0)
-; CHECK-NEXT:    lbu a5, 82(a0)
-; CHECK-NEXT:    lbu a6, 93(a0)
-; CHECK-NEXT:    lbu a7, 124(a0)
-; CHECK-NEXT:    lbu t0, 144(a0)
-; CHECK-NEXT:    lbu t1, 154(a0)
+; CHECK-NEXT:    lbu a5, 93(a0)
+; CHECK-NEXT:    lbu a6, 124(a0)
+; CHECK-NEXT:    lbu a7, 144(a0)
+; CHECK-NEXT:    lbu t0, 154(a0)
 ; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
 ; CHECK-NEXT:    vlse8.v v8, (a0), zero
+; CHECK-NEXT:    addi a0, a0, 82
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a1
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a2
+; CHECK-NEXT:    vlse8.v v9, (a0), zero
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a3
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 1
-; CHECK-NEXT:    vslide1down.vx v8, v8, a4
-; CHECK-NEXT:    vslide1down.vx v8, v8, a5
-; CHECK-NEXT:    vslide1down.vx v8, v8, a6
+; CHECK-NEXT:    vslide1down.vx v10, v8, a4
+; CHECK-NEXT:    vslide1down.vx v8, v9, a5
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
-; CHECK-NEXT:    vslide1down.vx v8, v8, a7
+; CHECK-NEXT:    vslide1down.vx v8, v8, a6
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 1
+; CHECK-NEXT:    vslide1down.vx v8, v8, a7
 ; CHECK-NEXT:    vslide1down.vx v8, v8, t0
-; CHECK-NEXT:    vslide1down.vx v8, v8, t1
+; CHECK-NEXT:    li a0, 255
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vmv.s.x v0, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, mu
+; CHECK-NEXT:    vslidedown.vi v8, v10, 8, v0.t
 ; CHECK-NEXT:    ret
   %p2 = getelementptr i8, ptr %p, i32 1
   %p3 = getelementptr i8, ptr %p, i32 22
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll
index dd0fc5a11a0e..c295fed2c28c 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll
@@ -278,32 +278,34 @@ define <8 x i1> @buildvec_mask_nonconst_v8i1(i1 %x, i1 %y) {
 define <8 x i1> @buildvec_mask_nonconst_v8i1_2(i1 %x, i1 %y, i1 %z, i1 %w) {
 ; CHECK-LABEL: buildvec_mask_nonconst_v8i1_2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
 ; CHECK-NEXT:    vmv.v.x v8, a0
-; CHECK-NEXT:    vslide1down.vx v8, v8, a0
-; CHECK-NEXT:    li a4, 1
-; CHECK-NEXT:    vslide1down.vx v8, v8, a4
-; CHECK-NEXT:    vslide1down.vx v8, v8, a1
-; CHECK-NEXT:    vslide1down.vx v8, v8, a0
+; CHECK-NEXT:    vslide1down.vx v9, v8, a0
+; CHECK-NEXT:    li a0, 1
+; CHECK-NEXT:    vslide1down.vx v9, v9, a0
+; CHECK-NEXT:    vslide1down.vx v9, v9, a1
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a3
 ; CHECK-NEXT:    vslide1down.vx v8, v8, zero
+; CHECK-NEXT:    vmv.v.i v0, 15
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a2
+; CHECK-NEXT:    vslidedown.vi v8, v9, 4, v0.t
 ; CHECK-NEXT:    vand.vi v8, v8, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
 ;
 ; ZVE32F-LABEL: buildvec_mask_nonconst_v8i1_2:
 ; ZVE32F:       # %bb.0:
-; ZVE32F-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
+; ZVE32F-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
 ; ZVE32F-NEXT:    vmv.v.x v8, a0
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a0
-; ZVE32F-NEXT:    li a4, 1
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a4
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a1
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a0
+; ZVE32F-NEXT:    vslide1down.vx v9, v8, a0
+; ZVE32F-NEXT:    li a0, 1
+; ZVE32F-NEXT:    vslide1down.vx v9, v9, a0
+; ZVE32F-NEXT:    vslide1down.vx v9, v9, a1
 ; ZVE32F-NEXT:    vslide1down.vx v8, v8, a3
 ; ZVE32F-NEXT:    vslide1down.vx v8, v8, zero
+; ZVE32F-NEXT:    vmv.v.i v0, 15
 ; ZVE32F-NEXT:    vslide1down.vx v8, v8, a2
+; ZVE32F-NEXT:    vslidedown.vi v8, v9, 4, v0.t
 ; ZVE32F-NEXT:    vand.vi v8, v8, 1
 ; ZVE32F-NEXT:    vmsne.vi v0, v8, 0
 ; ZVE32F-NEXT:    ret
@@ -321,32 +323,34 @@ define <8 x i1> @buildvec_mask_nonconst_v8i1_2(i1 %x, i1 %y, i1 %z, i1 %w) {
 define <8 x i1> @buildvec_mask_optsize_nonconst_v8i1_2(i1 %x, i1 %y, i1 %z, i1 %w) optsize {
 ; CHECK-LABEL: buildvec_mask_optsize_nonconst_v8i1_2:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
 ; CHECK-NEXT:    vmv.v.x v8, a0
-; CHECK-NEXT:    vslide1down.vx v8, v8, a0
-; CHECK-NEXT:    li a4, 1
-; CHECK-NEXT:    vslide1down.vx v8, v8, a4
-; CHECK-NEXT:    vslide1down.vx v8, v8, a1
-; CHECK-NEXT:    vslide1down.vx v8, v8, a0
+; CHECK-NEXT:    vslide1down.vx v9, v8, a0
+; CHECK-NEXT:    li a0, 1
+; CHECK-NEXT:    vslide1down.vx v9, v9, a0
+; CHECK-NEXT:    vslide1down.vx v9, v9, a1
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a3
 ; CHECK-NEXT:    vslide1down.vx v8, v8, zero
+; CHECK-NEXT:    vmv.v.i v0, 15
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a2
+; CHECK-NEXT:    vslidedown.vi v8, v9, 4, v0.t
 ; CHECK-NEXT:    vand.vi v8, v8, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
 ;
 ; ZVE32F-LABEL: buildvec_mask_optsize_nonconst_v8i1_2:
 ; ZVE32F:       # %bb.0:
-; ZVE32F-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
+; ZVE32F-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
 ; ZVE32F-NEXT:    vmv.v.x v8, a0
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a0
-; ZVE32F-NEXT:    li a4, 1
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a4
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a1
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a0
+; ZVE32F-NEXT:    vslide1down.vx v9, v8, a0
+; ZVE32F-NEXT:    li a0, 1
+; ZVE32F-NEXT:    vslide1down.vx v9, v9, a0
+; ZVE32F-NEXT:    vslide1down.vx v9, v9, a1
 ; ZVE32F-NEXT:    vslide1down.vx v8, v8, a3
 ; ZVE32F-NEXT:    vslide1down.vx v8, v8, zero
+; ZVE32F-NEXT:    vmv.v.i v0, 15
 ; ZVE32F-NEXT:    vslide1down.vx v8, v8, a2
+; ZVE32F-NEXT:    vslidedown.vi v8, v9, 4, v0.t
 ; ZVE32F-NEXT:    vand.vi v8, v8, 1
 ; ZVE32F-NEXT:    vmsne.vi v0, v8, 0
 ; ZVE32F-NEXT:    ret
@@ -364,30 +368,32 @@ define <8 x i1> @buildvec_mask_optsize_nonconst_v8i1_2(i1 %x, i1 %y, i1 %z, i1 %
 define <8 x i1> @buildvec_mask_optsize_nonconst_v8i1(i1 %x, i1 %y) optsize {
 ; CHECK-LABEL: buildvec_mask_optsize_nonconst_v8i1:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
 ; CHECK-NEXT:    vmv.v.x v8, a0
-; CHECK-NEXT:    vslide1down.vx v8, v8, a0
-; CHECK-NEXT:    vslide1down.vx v8, v8, a1
-; CHECK-NEXT:    vslide1down.vx v8, v8, a1
-; CHECK-NEXT:    vslide1down.vx v8, v8, a0
+; CHECK-NEXT:    vslide1down.vx v9, v8, a0
+; CHECK-NEXT:    vslide1down.vx v9, v9, a1
+; CHECK-NEXT:    vslide1down.vx v9, v9, a1
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a1
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a1
+; CHECK-NEXT:    vmv.v.i v0, 15
 ; CHECK-NEXT:    vslide1down.vx v8, v8, a1
+; CHECK-NEXT:    vslidedown.vi v8, v9, 4, v0.t
 ; CHECK-NEXT:    vand.vi v8, v8, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
 ;
 ; ZVE32F-LABEL: buildvec_mask_optsize_nonconst_v8i1:
 ; ZVE32F:       # %bb.0:
-; ZVE32F-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
+; ZVE32F-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
 ; ZVE32F-NEXT:    vmv.v.x v8, a0
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a0
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a1
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a1
-; ZVE32F-NEXT:    vslide1down.vx v8, v8, a0
+; ZVE32F-NEXT:    vslide1down.vx v9, v8, a0
+; ZVE32F-NEXT:    vslide1down.vx v9, v9, a1
+; ZVE32F-NEXT:    vslide1down.vx v9, v9, a1
 ; ZVE32F-NEXT:    vslide1down.vx v8, v8, a1
 ; ZVE32F-NEXT:    vslide1down.vx v8, v8, a1
+; ZVE32F-NEXT:    vmv.v.i v0, 15
 ; ZVE32F-NEXT:    vslide1down.vx v8, v8, a1
+; ZVE32F-NEXT:    vslidedown.vi v8, v9, 4, v0.t
 ; ZVE32F-NEXT:    vand.vi v8, v8, 1
 ; ZVE32F-NEXT:    vmsne.vi v0, v8, 0
 ; ZVE32F-NEXT:    ret