diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -3157,6 +3157,7 @@
   // Don't perform this optimization when optimizing for size, since
   // materializing elements and inserting them tends to cause code bloat.
   if (!DAG.shouldOptForSize() && NumScalarLoads < NumElts &&
+      (NumElts != 2 || ISD::isBuildVectorOfConstantSDNodes(Op.getNode())) &&
       ((MostCommonCount > DominantValueCountThreshold) ||
        (ValueCounts.size() <= Log2_32(NumDefElts)))) {
     // Start by splatting the most common element.
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vector-shuffle-reverse.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vector-shuffle-reverse.ll
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vector-shuffle-reverse.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vector-shuffle-reverse.ll
@@ -18,12 +18,10 @@
 ; CHECK-NEXT:    vmerge.vim v8, v8, 1, v0
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 1
 ; CHECK-NEXT:    vmv.x.s a0, v8
-; CHECK-NEXT:    vfirst.m a1, v0
-; CHECK-NEXT:    seqz a1, a1
-; CHECK-NEXT:    vmv.v.x v8, a1
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
-; CHECK-NEXT:    vmv.s.x v8, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
+; CHECK-NEXT:    vslide1down.vx v8, v8, a0
+; CHECK-NEXT:    vfirst.m a0, v0
+; CHECK-NEXT:    seqz a0, a0
+; CHECK-NEXT:    vslide1down.vx v8, v8, a0
 ; CHECK-NEXT:    vand.vi v8, v8, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bitcast.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bitcast.ll
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bitcast.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-bitcast.ll
@@ -521,9 +521,8 @@
 ; RV32ELEN32-LABEL: bitcast_i64_v4i16:
 ; RV32ELEN32:       # %bb.0:
 ; RV32ELEN32-NEXT:    vsetivli zero, 2, e32, m1, ta, ma
-; RV32ELEN32-NEXT:    vmv.v.x v8, a1
-; RV32ELEN32-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
-; RV32ELEN32-NEXT:    vmv.s.x v8, a0
+; RV32ELEN32-NEXT:    vslide1down.vx v8, v8, a0
+; RV32ELEN32-NEXT:    vslide1down.vx v8, v8, a1
 ; RV32ELEN32-NEXT:    ret
 ;
 ; RV64ELEN32-LABEL: bitcast_i64_v4i16:
@@ -557,9 +556,8 @@
 ; RV32ELEN32-LABEL: bitcast_i64_v2i32:
 ; RV32ELEN32:       # %bb.0:
 ; RV32ELEN32-NEXT:    vsetivli zero, 2, e32, m1, ta, ma
-; RV32ELEN32-NEXT:    vmv.v.x v8, a1
-; RV32ELEN32-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
-; RV32ELEN32-NEXT:    vmv.s.x v8, a0
+; RV32ELEN32-NEXT:    vslide1down.vx v8, v8, a0
+; RV32ELEN32-NEXT:    vslide1down.vx v8, v8, a1
 ; RV32ELEN32-NEXT:    ret
 ;
 ; RV64ELEN32-LABEL: bitcast_i64_v2i32:
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll
@@ -191,7 +191,8 @@
 ; RV32:       # %bb.0:
 ; RV32-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
 ; RV32-NEXT:    vle64.v v8, (a0)
-; RV32-NEXT:    vfmv.f.s fa5, v8
+; RV32-NEXT:    vslidedown.vi v9, v8, 1
+; RV32-NEXT:    vfmv.f.s fa5, v9
 ; RV32-NEXT:    lui a0, %hi(.LCPI10_0)
 ; RV32-NEXT:    fld fa4, %lo(.LCPI10_0)(a0)
 ; RV32-NEXT:    lui a0, %hi(.LCPI10_1)
@@ -202,7 +203,6 @@
 ; RV32-NEXT:    fmin.d fa5, fa5, fa3
 ; RV32-NEXT:    fcvt.w.d a2, fa5, rtz
 ; RV32-NEXT:    and a0, a0, a2
-; RV32-NEXT:    vslidedown.vi v8, v8, 1
 ; RV32-NEXT:    vfmv.f.s fa5, v8
 ; RV32-NEXT:    feq.d a2, fa5, fa5
 ; RV32-NEXT:    neg a2, a2
@@ -211,9 +211,8 @@
 ; RV32-NEXT:    fcvt.w.d a3, fa5, rtz
 ; RV32-NEXT:    and a2, a2, a3
 ; RV32-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
-; RV32-NEXT:    vmv.v.x v8, a2
-; RV32-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
-; RV32-NEXT:    vmv.s.x v8, a0
+; RV32-NEXT:    vslide1down.vx v8, v8, a2
+; RV32-NEXT:    vslide1down.vx v8, v8, a0
 ; RV32-NEXT:    vse8.v v8, (a1)
 ; RV32-NEXT:    ret
 ;
@@ -221,7 +220,8 @@
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
 ; RV64-NEXT:    vle64.v v8, (a0)
-; RV64-NEXT:    vfmv.f.s fa5, v8
+; RV64-NEXT:    vslidedown.vi v9, v8, 1
+; RV64-NEXT:    vfmv.f.s fa5, v9
 ; RV64-NEXT:    lui a0, %hi(.LCPI10_0)
 ; RV64-NEXT:    fld fa4, %lo(.LCPI10_0)(a0)
 ; RV64-NEXT:    lui a0, %hi(.LCPI10_1)
@@ -232,7 +232,6 @@
 ; RV64-NEXT:    fmin.d fa5, fa5, fa3
 ; RV64-NEXT:    fcvt.l.d a2, fa5, rtz
 ; RV64-NEXT:    and a0, a0, a2
-; RV64-NEXT:    vslidedown.vi v8, v8, 1
 ; RV64-NEXT:    vfmv.f.s fa5, v8
 ; RV64-NEXT:    feq.d a2, fa5, fa5
 ; RV64-NEXT:    neg a2, a2
@@ -241,9 +240,8 @@
 ; RV64-NEXT:    fcvt.l.d a3, fa5, rtz
 ; RV64-NEXT:    and a2, a2, a3
 ; RV64-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
-; RV64-NEXT:    vmv.v.x v8, a2
-; RV64-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
-; RV64-NEXT:    vmv.s.x v8, a0
+; RV64-NEXT:    vslide1down.vx v8, v8, a2
+; RV64-NEXT:    vslide1down.vx v8, v8, a0
 ; RV64-NEXT:    vse8.v v8, (a1)
 ; RV64-NEXT:    ret
   %a = load <2 x double>, ptr %x
@@ -265,15 +263,16 @@
 ; RV32-NEXT:    fmax.d fa4, fa4, fa3
 ; RV32-NEXT:    fmin.d fa4, fa4, fa5
 ; RV32-NEXT:    fcvt.wu.d a0, fa4, rtz
+; RV32-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
+; RV32-NEXT:    vslide1down.vx v9, v8, a0
+; RV32-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; RV32-NEXT:    vslidedown.vi v8, v8, 1
 ; RV32-NEXT:    vfmv.f.s fa4, v8
 ; RV32-NEXT:    fmax.d fa4, fa4, fa3
 ; RV32-NEXT:    fmin.d fa5, fa4, fa5
-; RV32-NEXT:    fcvt.wu.d a2, fa5, rtz
-; RV32-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
-; RV32-NEXT:    vmv.v.x v8, a2
-; RV32-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
-; RV32-NEXT:    vmv.s.x v8, a0
+; RV32-NEXT:    fcvt.wu.d a0, fa5, rtz
+; RV32-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
+; RV32-NEXT:    vslide1down.vx v8, v9, a0
 ; RV32-NEXT:    vse8.v v8, (a1)
 ; RV32-NEXT:    ret
 ;
@@ -288,15 +287,16 @@
 ; RV64-NEXT:    fmax.d fa4, fa4, fa3
 ; RV64-NEXT:    fmin.d fa4, fa4, fa5
 ; RV64-NEXT:    fcvt.lu.d a0, fa4, rtz
+; RV64-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
+; RV64-NEXT:    vslide1down.vx v9, v8, a0
+; RV64-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; RV64-NEXT:    vslidedown.vi v8, v8, 1
 ; RV64-NEXT:    vfmv.f.s fa4, v8
 ; RV64-NEXT:    fmax.d fa4, fa4, fa3
 ; RV64-NEXT:    fmin.d fa5, fa4, fa5
-; RV64-NEXT:    fcvt.lu.d a2, fa5, rtz
-; RV64-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
-; RV64-NEXT:    vmv.v.x v8, a2
-; RV64-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
-; RV64-NEXT:    vmv.s.x v8, a0
+; RV64-NEXT:    fcvt.lu.d a0, fa5, rtz
+; RV64-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
+; RV64-NEXT:    vslide1down.vx v8, v9, a0
 ; RV64-NEXT:    vse8.v v8, (a1)
 ; RV64-NEXT:    ret
   %a = load <2 x double>, ptr %x
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-load.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-load.ll
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-load.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-load.ll
@@ -140,11 +140,10 @@
 ; RV64-LABEL: load_v6f16:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    ld a2, 0(a1)
-; RV64-NEXT:    addi a1, a1, 8
 ; RV64-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
-; RV64-NEXT:    vlse64.v v8, (a1), zero
-; RV64-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
-; RV64-NEXT:    vmv.s.x v8, a2
+; RV64-NEXT:    ld a1, 8(a1)
+; RV64-NEXT:    vslide1down.vx v8, v8, a2
+; RV64-NEXT:    vslide1down.vx v8, v8, a1
 ; RV64-NEXT:    sd a2, 0(a0)
 ; RV64-NEXT:    vslidedown.vi v8, v8, 2
 ; RV64-NEXT:    addi a0, a0, 8
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-mask-buildvec.ll
@@ -54,10 +54,8 @@
 ; CHECK-LABEL: buildvec_mask_nonconst_v2i1:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, ma
-; CHECK-NEXT:    vmv.v.x v8, a1
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, ma
-; CHECK-NEXT:    vmv.s.x v8, a0
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
+; CHECK-NEXT:    vslide1down.vx v8, v8, a0
+; CHECK-NEXT:    vslide1down.vx v8, v8, a1
 ; CHECK-NEXT:    vand.vi v8, v8, 1
 ; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
@@ -65,10 +63,8 @@
 ; ZVE32F-LABEL: buildvec_mask_nonconst_v2i1:
 ; ZVE32F:       # %bb.0:
 ; ZVE32F-NEXT:    vsetivli zero, 2, e8, mf4, ta, ma
-; ZVE32F-NEXT:    vmv.v.x v8, a1
-; ZVE32F-NEXT:    vsetvli zero, zero, e8, mf4, tu, ma
-; ZVE32F-NEXT:    vmv.s.x v8, a0
-; ZVE32F-NEXT:    vsetvli zero, zero, e8, mf4, ta, ma
+; ZVE32F-NEXT:    vslide1down.vx v8, v8, a0
+; ZVE32F-NEXT:    vslide1down.vx v8, v8, a1
 ; ZVE32F-NEXT:    vand.vi v8, v8, 1
 ; ZVE32F-NEXT:    vmsne.vi v0, v8, 0
 ; ZVE32F-NEXT:    ret
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll
@@ -1667,20 +1667,18 @@
 ; RV32ZVE32F-LABEL: mscatter_v2i64_truncstore_v2i32:
 ; RV32ZVE32F:       # %bb.0:
 ; RV32ZVE32F-NEXT:    lw a1, 0(a0)
-; RV32ZVE32F-NEXT:    addi a0, a0, 8
+; RV32ZVE32F-NEXT:    lw a0, 8(a0)
 ; RV32ZVE32F-NEXT:    vsetivli zero, 2, e32, m1, ta, ma
-; RV32ZVE32F-NEXT:    vlse32.v v9, (a0), zero
-; RV32ZVE32F-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
-; RV32ZVE32F-NEXT:    vmv.s.x v9, a1
+; RV32ZVE32F-NEXT:    vslide1down.vx v9, v8, a1
+; RV32ZVE32F-NEXT:    vslide1down.vx v9, v9, a0
 ; RV32ZVE32F-NEXT:    vsoxei32.v v9, (zero), v8, v0.t
 ; RV32ZVE32F-NEXT:    ret
 ;
 ; RV64ZVE32F-LABEL: mscatter_v2i64_truncstore_v2i32:
 ; RV64ZVE32F:       # %bb.0:
 ; RV64ZVE32F-NEXT:    vsetivli zero, 2, e32, m1, ta, ma
-; RV64ZVE32F-NEXT:    vmv.v.x v8, a1
-; RV64ZVE32F-NEXT:    vsetvli zero, zero, e32, m1, tu, ma
-; RV64ZVE32F-NEXT:    vmv.s.x v8, a0
+; RV64ZVE32F-NEXT:    vslide1down.vx v8, v8, a0
+; RV64ZVE32F-NEXT:    vslide1down.vx v8, v8, a1
 ; RV64ZVE32F-NEXT:    vsetvli zero, zero, e8, mf4, ta, ma
 ; RV64ZVE32F-NEXT:    vmv.x.s a0, v0
 ; RV64ZVE32F-NEXT:    andi a1, a0, 1
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-store.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-store.ll
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-store.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-store.ll
@@ -151,9 +151,8 @@
 ; RV64-NEXT:    slli a1, a1, 32
 ; RV64-NEXT:    srli a1, a1, 32
 ; RV64-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
-; RV64-NEXT:    vmv.v.x v8, a1
-; RV64-NEXT:    vsetvli zero, zero, e64, m1, tu, ma
-; RV64-NEXT:    vmv.s.x v8, a2
+; RV64-NEXT:    vslide1down.vx v8, v8, a2
+; RV64-NEXT:    vslide1down.vx v8, v8, a1
 ; RV64-NEXT:    vsetivli zero, 1, e64, m1, ta, ma
 ; RV64-NEXT:    vse64.v v8, (a0)
 ; RV64-NEXT:    vslidedown.vi v8, v8, 2
diff --git a/llvm/test/CodeGen/RISCV/rvv/fold-vector-cmp.ll b/llvm/test/CodeGen/RISCV/rvv/fold-vector-cmp.ll
--- a/llvm/test/CodeGen/RISCV/rvv/fold-vector-cmp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fold-vector-cmp.ll
@@ -12,14 +12,12 @@
 ;
 ; CHECK-V-LABEL: test:
 ; CHECK-V:       # %bb.0:
-; CHECK-V-NEXT:    lui a1, 524288
 ; CHECK-V-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
-; CHECK-V-NEXT:    vmv.v.x v8, a1
-; CHECK-V-NEXT:    vsetvli zero, zero, e32, mf2, tu, ma
-; CHECK-V-NEXT:    vmv.s.x v8, a0
-; CHECK-V-NEXT:    addiw a1, a1, 2
-; CHECK-V-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
-; CHECK-V-NEXT:    vmslt.vx v0, v8, a1
+; CHECK-V-NEXT:    vslide1down.vx v8, v8, a0
+; CHECK-V-NEXT:    lui a0, 524288
+; CHECK-V-NEXT:    vslide1down.vx v8, v8, a0
+; CHECK-V-NEXT:    addiw a0, a0, 2
+; CHECK-V-NEXT:    vmslt.vx v0, v8, a0
 ; CHECK-V-NEXT:    vmv.v.i v8, 0
 ; CHECK-V-NEXT:    vmerge.vim v8, v8, 1, v0
 ; CHECK-V-NEXT:    vslidedown.vi v8, v8, 1