diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index dba38f3e1a0bc..dd682e061e646 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -58574,6 +58574,7 @@ static SDValue combineEXTRACT_SUBVECTOR(SDNode *N, SelectionDAG &DAG,
 
 static SDValue combineSCALAR_TO_VECTOR(SDNode *N, SelectionDAG &DAG,
                                        const X86Subtarget &Subtarget) {
+  using namespace SDPatternMatch;
   EVT VT = N->getValueType(0);
   SDValue Src = N->getOperand(0);
   SDLoc DL(N);
@@ -58641,6 +58642,16 @@ static SDValue combineSCALAR_TO_VECTOR(SDNode *N, SelectionDAG &DAG,
       return DAG.getNode(X86ISD::MOVQ2DQ, DL, VT, SrcOp);
   }
 
+  if (VT == MVT::v4i32) {
+    SDValue HalfSrc;
+    // Combine (v4i32 (scalar_to_vector (i32 (anyext (bitcast (f16))))))
+    // to remove XMM->GPR->XMM moves.
+    if (sd_match(Src, m_AnyExt(m_BitCast(
+                          m_AllOf(m_SpecificVT(MVT::f16), m_Value(HalfSrc))))))
+      return DAG.getBitcast(
+          VT, DAG.getNode(ISD::SCALAR_TO_VECTOR, DL, MVT::v8f16, HalfSrc));
+  }
+
   // See if we're broadcasting the scalar value, in which case just reuse that.
   // Ensure the same SDValue from the SDNode use is being used.
   if (VT.getScalarType() == Src.getValueType())
diff --git a/llvm/test/CodeGen/X86/bfloat.ll b/llvm/test/CodeGen/X86/bfloat.ll
index a6b3e3fd1fd16..d67cd6b62c2b9 100644
--- a/llvm/test/CodeGen/X86/bfloat.ll
+++ b/llvm/test/CodeGen/X86/bfloat.ll
@@ -708,10 +708,8 @@ define <2 x bfloat> @pr62997(bfloat %a, bfloat %b) {
 ;
 ; BF16-LABEL: pr62997:
 ; BF16:       # %bb.0:
-; BF16-NEXT:    vpextrw $0, %xmm0, %eax
-; BF16-NEXT:    vpextrw $0, %xmm1, %ecx
-; BF16-NEXT:    vmovd %eax, %xmm0
-; BF16-NEXT:    vpinsrw $1, %ecx, %xmm0, %xmm0
+; BF16-NEXT:    vpextrw $0, %xmm1, %eax
+; BF16-NEXT:    vpinsrw $1, %eax, %xmm0, %xmm0
 ; BF16-NEXT:    retq
 ;
 ; FP16-LABEL: pr62997:
@@ -1652,66 +1650,63 @@ define <8 x bfloat> @fptrunc_v8f64(<8 x double> %a) nounwind {
 ; AVXNC-NEXT:    pushq %r12
 ; AVXNC-NEXT:    pushq %rbx
 ; AVXNC-NEXT:    subq $168, %rsp
-; AVXNC-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
+; AVXNC-NEXT:    vmovups %ymm1, (%rsp) # 32-byte Spill
 ; AVXNC-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
 ; AVXNC-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
 ; AVXNC-NEXT:    vzeroupper
 ; AVXNC-NEXT:    callq __truncdfbf2@PLT
 ; AVXNC-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
-; AVXNC-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
+; AVXNC-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; AVXNC-NEXT:    # xmm0 = mem[1,0]
+; AVXNC-NEXT:    callq __truncdfbf2@PLT
+; AVXNC-NEXT:    vmovapd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; AVXNC-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
 ; AVXNC-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVXNC-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; AVXNC-NEXT:    vmovapd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; AVXNC-NEXT:    vshufpd {{.*#+}} xmm0 = xmm0[1,0]
 ; AVXNC-NEXT:    vzeroupper
 ; AVXNC-NEXT:    callq __truncdfbf2@PLT
-; AVXNC-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
-; AVXNC-NEXT:    vpermilpd $1, (%rsp), %xmm0 # 16-byte Folded Reload
-; AVXNC-NEXT:    # xmm0 = mem[1,0]
-; AVXNC-NEXT:    callq __truncdfbf2@PLT
-; AVXNC-NEXT:    vmovapd %xmm0, (%rsp) # 16-byte Spill
-; AVXNC-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
+; AVXNC-NEXT:    vmovapd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; AVXNC-NEXT:    vmovups (%rsp), %ymm0 # 32-byte Reload
 ; AVXNC-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
 ; AVXNC-NEXT:    vzeroupper
 ; AVXNC-NEXT:    callq __truncdfbf2@PLT
 ; AVXNC-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
-; AVXNC-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
+; AVXNC-NEXT:    vpermilpd $1, (%rsp), %xmm0 # 16-byte Folded Reload
 ; AVXNC-NEXT:    # xmm0 = mem[1,0]
 ; AVXNC-NEXT:    callq __truncdfbf2@PLT
 ; AVXNC-NEXT:    vmovapd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
-; AVXNC-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
+; AVXNC-NEXT:    vmovups (%rsp), %ymm0 # 32-byte Reload
 ; AVXNC-NEXT:    vextractf128 $1, %ymm0, %xmm0
 ; AVXNC-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
 ; AVXNC-NEXT:    vzeroupper
 ; AVXNC-NEXT:    callq __truncdfbf2@PLT
-; AVXNC-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; AVXNC-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
 ; AVXNC-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
 ; AVXNC-NEXT:    # xmm0 = mem[1,0]
 ; AVXNC-NEXT:    callq __truncdfbf2@PLT
-; AVXNC-NEXT:    vpextrw $0, %xmm0, %eax
-; AVXNC-NEXT:    movl %eax, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
-; AVXNC-NEXT:    vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; AVXNC-NEXT:    vpextrw $0, %xmm0, %ebx
+; AVXNC-NEXT:    vmovdqa (%rsp), %xmm0 # 16-byte Reload
 ; AVXNC-NEXT:    vpextrw $0, %xmm0, %ebp
 ; AVXNC-NEXT:    vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
 ; AVXNC-NEXT:    vpextrw $0, %xmm0, %r14d
 ; AVXNC-NEXT:    vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
 ; AVXNC-NEXT:    vpextrw $0, %xmm0, %r15d
-; AVXNC-NEXT:    vmovdqa (%rsp), %xmm0 # 16-byte Reload
+; AVXNC-NEXT:    vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
 ; AVXNC-NEXT:    vpextrw $0, %xmm0, %r12d
 ; AVXNC-NEXT:    vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
 ; AVXNC-NEXT:    vpextrw $0, %xmm0, %r13d
 ; AVXNC-NEXT:    vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
-; AVXNC-NEXT:    vpextrw $0, %xmm0, %ebx
-; AVXNC-NEXT:    vpermilpd $1, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
-; AVXNC-NEXT:    # xmm0 = mem[1,0]
 ; AVXNC-NEXT:    callq __truncdfbf2@PLT
 ; AVXNC-NEXT:    vpextrw $0, %xmm0, %eax
-; AVXNC-NEXT:    vmovd %ebx, %xmm0
-; AVXNC-NEXT:    vpinsrw $1, %eax, %xmm0, %xmm0
-; AVXNC-NEXT:    vpinsrw $2, %r13d, %xmm0, %xmm0
+; AVXNC-NEXT:    vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; AVXNC-NEXT:    vpinsrw $1, %r13d, %xmm0, %xmm0
+; AVXNC-NEXT:    vpinsrw $2, %eax, %xmm0, %xmm0
 ; AVXNC-NEXT:    vpinsrw $3, %r12d, %xmm0, %xmm0
 ; AVXNC-NEXT:    vpinsrw $4, %r15d, %xmm0, %xmm0
 ; AVXNC-NEXT:    vpinsrw $5, %r14d, %xmm0, %xmm0
 ; AVXNC-NEXT:    vpinsrw $6, %ebp, %xmm0, %xmm0
-; AVXNC-NEXT:    vpinsrw $7, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 4-byte Folded Reload
+; AVXNC-NEXT:    vpinsrw $7, %ebx, %xmm0, %xmm0
 ; AVXNC-NEXT:    addq $168, %rsp
 ; AVXNC-NEXT:    popq %rbx
 ; AVXNC-NEXT:    popq %r12
diff --git a/llvm/test/CodeGen/X86/canonicalize-vars-f16-type.ll b/llvm/test/CodeGen/X86/canonicalize-vars-f16-type.ll
index fdf0bf3f692d6..e911a24d830f7 100644
--- a/llvm/test/CodeGen/X86/canonicalize-vars-f16-type.ll
+++ b/llvm/test/CodeGen/X86/canonicalize-vars-f16-type.ll
@@ -133,11 +133,7 @@ define half @complex_canonicalize_fmul_half(half %a, half %b) nounwind {
 ;
 ; AVX512-LABEL: complex_canonicalize_fmul_half:
 ; AVX512:       # %bb.0: # %entry
-; AVX512-NEXT:    vpextrw $0, %xmm1, %eax
-; AVX512-NEXT:    vpextrw $0, %xmm0, %ecx
-; AVX512-NEXT:    vmovd %ecx, %xmm0
 ; AVX512-NEXT:    vcvtph2ps %xmm0, %xmm0
-; AVX512-NEXT:    vmovd %eax, %xmm1
 ; AVX512-NEXT:    vcvtph2ps %xmm1, %xmm1
 ; AVX512-NEXT:    vsubss %xmm1, %xmm0, %xmm0
 ; AVX512-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
diff --git a/llvm/test/CodeGen/X86/cvt16.ll b/llvm/test/CodeGen/X86/cvt16.ll
index c7ef353f7f603..efc457e35e7f3 100644
--- a/llvm/test/CodeGen/X86/cvt16.ll
+++ b/llvm/test/CodeGen/X86/cvt16.ll
@@ -59,8 +59,7 @@ define float @test2(ptr nocapture %src) nounwind {
 ;
 ; F16C-LABEL: test2:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    movzwl (%rdi), %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
+; F16C-NEXT:    vpinsrw $0, (%rdi), %xmm0, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    retq
 ;
@@ -119,8 +118,7 @@ define double @test4(ptr nocapture %src) nounwind {
 ;
 ; F16C-LABEL: test4:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    movzwl (%rdi), %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
+; F16C-NEXT:    vpinsrw $0, (%rdi), %xmm0, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    vcvtss2sd %xmm0, %xmm0, %xmm0
 ; F16C-NEXT:    retq
diff --git a/llvm/test/CodeGen/X86/fp-roundeven.ll b/llvm/test/CodeGen/X86/fp-roundeven.ll
index 8037c783dd8e6..7d1c52cd65451 100644
--- a/llvm/test/CodeGen/X86/fp-roundeven.ll
+++ b/llvm/test/CodeGen/X86/fp-roundeven.ll
@@ -50,8 +50,6 @@ define half @roundeven_f16(half %h) {
 ;
 ; AVX512F-LABEL: roundeven_f16:
 ; AVX512F:       ## %bb.0: ## %entry
-; AVX512F-NEXT:    vpextrw $0, %xmm0, %eax
-; AVX512F-NEXT:    vmovd %eax, %xmm0
 ; AVX512F-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; AVX512F-NEXT:    vroundss $8, %xmm0, %xmm0, %xmm0
 ; AVX512F-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
diff --git a/llvm/test/CodeGen/X86/fp16-libcalls.ll b/llvm/test/CodeGen/X86/fp16-libcalls.ll
index 1515cd1366bc6..0d8290b120fa4 100644
--- a/llvm/test/CodeGen/X86/fp16-libcalls.ll
+++ b/llvm/test/CodeGen/X86/fp16-libcalls.ll
@@ -9,8 +9,6 @@
 define void @test_half_ceil(half %a0, ptr %p0) nounwind {
 ; F16C-LABEL: test_half_ceil:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    vroundss $10, %xmm0, %xmm0, %xmm0
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -107,8 +105,6 @@ define void @test_half_cos(half %a0, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rdi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    callq cosf@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -168,8 +164,6 @@ define void @test_half_exp(half %a0, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rdi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    callq expf@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -229,8 +223,6 @@ define void @test_half_exp2(half %a0, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rdi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    callq exp2f@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -290,8 +282,6 @@ define void @test_half_exp10(half %a0, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rdi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    callq exp10f@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -349,8 +339,6 @@ define void @test_half_exp10(half %a0, ptr %p0) nounwind {
 define void @test_half_fabs(half %a0, ptr %p0) nounwind {
 ; F16C-LABEL: test_half_fabs:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    vandps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -392,8 +380,6 @@ define void @test_half_fabs(half %a0, ptr %p0) nounwind {
 define void @test_half_floor(half %a0, ptr %p0) nounwind {
 ; F16C-LABEL: test_half_floor:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    vroundss $9, %xmm0, %xmm0, %xmm0
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -447,14 +433,8 @@ define void @test_half_fma(half %a0, half %a1, half %a2, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rdi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm2, %eax
-; F16C-NEXT:    vpextrw $0, %xmm1, %ecx
-; F16C-NEXT:    vpextrw $0, %xmm0, %edx
-; F16C-NEXT:    vmovd %edx, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
-; F16C-NEXT:    vmovd %ecx, %xmm1
 ; F16C-NEXT:    vcvtph2ps %xmm1, %xmm1
-; F16C-NEXT:    vmovd %eax, %xmm2
 ; F16C-NEXT:    vcvtph2ps %xmm2, %xmm2
 ; F16C-NEXT:    callq fmaf@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -542,8 +522,6 @@ define void @test_half_fma(half %a0, half %a1, half %a2, ptr %p0) nounwind {
 define void @test_half_fneg(half %a0, ptr %p0) nounwind {
 ; F16C-LABEL: test_half_fneg:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    vxorps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -587,8 +565,6 @@ define void @test_half_log(half %a0, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rdi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    callq logf@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -648,8 +624,6 @@ define void @test_half_log2(half %a0, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rdi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    callq log2f@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -709,8 +683,6 @@ define void @test_half_log10(half %a0, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rdi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    callq log10f@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -768,8 +740,6 @@ define void @test_half_log10(half %a0, ptr %p0) nounwind {
 define void @test_half_nearbyint(half %a0, ptr %p0) nounwind {
 ; F16C-LABEL: test_half_nearbyint:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    vroundss $12, %xmm0, %xmm0, %xmm0
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -823,11 +793,7 @@ define void @test_half_pow(half %a0, half %a1, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rdi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm1, %eax
-; F16C-NEXT:    vpextrw $0, %xmm0, %ecx
-; F16C-NEXT:    vmovd %ecx, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
-; F16C-NEXT:    vmovd %eax, %xmm1
 ; F16C-NEXT:    vcvtph2ps %xmm1, %xmm1
 ; F16C-NEXT:    callq powf@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -907,8 +873,6 @@ define void @test_half_powi(half %a0, i32 %a1, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rsi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    callq __powisf2@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -976,8 +940,6 @@ define void @test_half_powi(half %a0, i32 %a1, ptr %p0) nounwind {
 define void @test_half_rint(half %a0, ptr %p0) nounwind {
 ; F16C-LABEL: test_half_rint:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    vroundss $4, %xmm0, %xmm0, %xmm0
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -1031,8 +993,6 @@ define void @test_half_sin(half %a0, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rdi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    callq sinf@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -1090,8 +1050,6 @@ define void @test_half_sin(half %a0, ptr %p0) nounwind {
 define void @test_half_sqrt(half %a0, ptr %p0) nounwind {
 ; F16C-LABEL: test_half_sqrt:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    vsqrtss %xmm0, %xmm0, %xmm0
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -1146,8 +1104,6 @@ define void @test_half_tan(half %a0, ptr %p0) nounwind {
 ; F16C:       # %bb.0:
 ; F16C-NEXT:    pushq %rbx
 ; F16C-NEXT:    movq %rdi, %rbx
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    callq tanf@PLT
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -1205,8 +1161,6 @@ define void @test_half_tan(half %a0, ptr %p0) nounwind {
 define void @test_half_trunc(half %a0, ptr %p0) nounwind {
 ; F16C-LABEL: test_half_trunc:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    vroundss $11, %xmm0, %xmm0, %xmm0
 ; F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
diff --git a/llvm/test/CodeGen/X86/half-darwin.ll b/llvm/test/CodeGen/X86/half-darwin.ll
index 1d2f4eb39bbe6..ec099db4e7ca7 100644
--- a/llvm/test/CodeGen/X86/half-darwin.ll
+++ b/llvm/test/CodeGen/X86/half-darwin.ll
@@ -76,8 +76,7 @@ define float @extendhfsf(ptr %ptr) nounwind {
 ;
 ; CHECK-F16C-LABEL: extendhfsf:
 ; CHECK-F16C:       ## %bb.0:
-; CHECK-F16C-NEXT:    movzwl (%rdi), %eax
-; CHECK-F16C-NEXT:    vmovd %eax, %xmm0
+; CHECK-F16C-NEXT:    vpinsrw $0, (%rdi), %xmm0, %xmm0
 ; CHECK-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; CHECK-F16C-NEXT:    retq
 ;
diff --git a/llvm/test/CodeGen/X86/half-fp80-darwin.ll b/llvm/test/CodeGen/X86/half-fp80-darwin.ll
index 0ba734e66c7b2..65a26187c5857 100644
--- a/llvm/test/CodeGen/X86/half-fp80-darwin.ll
+++ b/llvm/test/CodeGen/X86/half-fp80-darwin.ll
@@ -19,8 +19,7 @@ define void @extendhfxf(ptr %outptr, ptr %inptr) nounwind {
 ;
 ; CHECK-F16C-LABEL: extendhfxf:
 ; CHECK-F16C:       ## %bb.0:
-; CHECK-F16C-NEXT:    movzwl (%rsi), %eax
-; CHECK-F16C-NEXT:    vmovd %eax, %xmm0
+; CHECK-F16C-NEXT:    vpinsrw $0, (%rsi), %xmm0, %xmm0
 ; CHECK-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; CHECK-F16C-NEXT:    vmovss %xmm0, -{{[0-9]+}}(%rsp)
 ; CHECK-F16C-NEXT:    flds -{{[0-9]+}}(%rsp)
diff --git a/llvm/test/CodeGen/X86/half.ll b/llvm/test/CodeGen/X86/half.ll
index 033cadae6a1e7..7bac075e48680 100644
--- a/llvm/test/CodeGen/X86/half.ll
+++ b/llvm/test/CodeGen/X86/half.ll
@@ -81,8 +81,7 @@ define float @test_extend32(ptr %addr) #0 {
 ;
 ; BWON-F16C-LABEL: test_extend32:
 ; BWON-F16C:       # %bb.0:
-; BWON-F16C-NEXT:    movzwl (%rdi), %eax
-; BWON-F16C-NEXT:    vmovd %eax, %xmm0
+; BWON-F16C-NEXT:    vpinsrw $0, (%rdi), %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; BWON-F16C-NEXT:    retq
 ;
@@ -113,8 +112,7 @@ define double @test_extend64(ptr %addr) #0 {
 ;
 ; BWON-F16C-LABEL: test_extend64:
 ; BWON-F16C:       # %bb.0:
-; BWON-F16C-NEXT:    movzwl (%rdi), %eax
-; BWON-F16C-NEXT:    vmovd %eax, %xmm0
+; BWON-F16C-NEXT:    vpinsrw $0, (%rdi), %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vcvtss2sd %xmm0, %xmm0, %xmm0
 ; BWON-F16C-NEXT:    retq
@@ -220,8 +218,7 @@ define i64 @test_fptosi_i64(ptr %p) #0 {
 ;
 ; BWON-F16C-LABEL: test_fptosi_i64:
 ; BWON-F16C:       # %bb.0:
-; BWON-F16C-NEXT:    movzwl (%rdi), %eax
-; BWON-F16C-NEXT:    vmovd %eax, %xmm0
+; BWON-F16C-NEXT:    vpinsrw $0, (%rdi), %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vcvttss2si %xmm0, %rax
 ; BWON-F16C-NEXT:    retq
@@ -312,8 +309,7 @@ define i64 @test_fptoui_i64(ptr %p) #0 {
 ;
 ; BWON-F16C-LABEL: test_fptoui_i64:
 ; BWON-F16C:       # %bb.0:
-; BWON-F16C-NEXT:    movzwl (%rdi), %eax
-; BWON-F16C-NEXT:    vmovd %eax, %xmm0
+; BWON-F16C-NEXT:    vpinsrw $0, (%rdi), %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vcvttss2si %xmm0, %rcx
 ; BWON-F16C-NEXT:    movq %rcx, %rdx
@@ -851,13 +847,12 @@ define float @test_sitofp_fadd_i32(i32 %a, ptr %b) #0 {
 ;
 ; BWON-F16C-LABEL: test_sitofp_fadd_i32:
 ; BWON-F16C:       # %bb.0:
-; BWON-F16C-NEXT:    vcvtsi2ss %edi, %xmm0, %xmm0
-; BWON-F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
-; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
-; BWON-F16C-NEXT:    movzwl (%rsi), %eax
-; BWON-F16C-NEXT:    vmovd %eax, %xmm1
+; BWON-F16C-NEXT:    vpinsrw $0, (%rsi), %xmm0, %xmm0
+; BWON-F16C-NEXT:    vcvtsi2ss %edi, %xmm1, %xmm1
+; BWON-F16C-NEXT:    vcvtps2ph $4, %xmm1, %xmm1
 ; BWON-F16C-NEXT:    vcvtph2ps %xmm1, %xmm1
-; BWON-F16C-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
+; BWON-F16C-NEXT:    vaddss %xmm1, %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; BWON-F16C-NEXT:    retq
@@ -916,8 +911,6 @@ define half @PR40273(half) #0 {
 ;
 ; BWON-F16C-LABEL: PR40273:
 ; BWON-F16C:       # %bb.0:
-; BWON-F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; BWON-F16C-NEXT:    vmovd %eax, %xmm0
 ; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; BWON-F16C-NEXT:    xorl %eax, %eax
 ; BWON-F16C-NEXT:    vxorps %xmm1, %xmm1, %xmm1
@@ -969,8 +962,6 @@ define void @brcond(half %0) #0 {
 ;
 ; BWON-F16C-LABEL: brcond:
 ; BWON-F16C:       # %bb.0: # %entry
-; BWON-F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; BWON-F16C-NEXT:    vmovd %eax, %xmm0
 ; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vxorps %xmm1, %xmm1, %xmm1
 ; BWON-F16C-NEXT:    vucomiss %xmm1, %xmm0
@@ -1024,8 +1015,6 @@ define half @test_sqrt(half %0) #0 {
 ;
 ; BWON-F16C-LABEL: test_sqrt:
 ; BWON-F16C:       # %bb.0: # %entry
-; BWON-F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; BWON-F16C-NEXT:    vmovd %eax, %xmm0
 ; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vsqrtss %xmm0, %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
@@ -1136,9 +1125,7 @@ define void @main.45() #0 {
 ; CHECK-LIBCALL-NEXT:    pushq %rbx
 ; CHECK-LIBCALL-NEXT:    pushq %rax
 ; CHECK-LIBCALL-NEXT:    pinsrw $0, (%rax), %xmm0
-; CHECK-LIBCALL-NEXT:    pextrw $0, %xmm0, %eax
-; CHECK-LIBCALL-NEXT:    movd %eax, %xmm1
-; CHECK-LIBCALL-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
+; CHECK-LIBCALL-NEXT:    pshuflw {{.*#+}} xmm1 = xmm0[0,0,0,0,4,5,6,7]
 ; CHECK-LIBCALL-NEXT:    movq %xmm1, %rbx
 ; CHECK-LIBCALL-NEXT:    movq %rbx, %r14
 ; CHECK-LIBCALL-NEXT:    shrq $48, %r14
@@ -1167,15 +1154,12 @@ define void @main.45() #0 {
 ; BWON-F16C-LABEL: main.45:
 ; BWON-F16C:       # %bb.0: # %entry
 ; BWON-F16C-NEXT:    vpinsrw $0, (%rax), %xmm0, %xmm0
-; BWON-F16C-NEXT:    vpextrw $0, %xmm0, %eax
 ; BWON-F16C-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
-; BWON-F16C-NEXT:    vmovd %eax, %xmm1
-; BWON-F16C-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
-; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
+; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm1
 ; BWON-F16C-NEXT:    vxorps %xmm2, %xmm2, %xmm2
-; BWON-F16C-NEXT:    vcmpunordps %xmm2, %xmm0, %xmm0
-; BWON-F16C-NEXT:    vpackssdw %xmm0, %xmm0, %xmm0
-; BWON-F16C-NEXT:    vpblendvb %xmm0, {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm0
+; BWON-F16C-NEXT:    vcmpunordps %xmm2, %xmm1, %xmm1
+; BWON-F16C-NEXT:    vpackssdw %xmm1, %xmm1, %xmm1
+; BWON-F16C-NEXT:    vpblendvb %xmm1, {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vmovq %xmm0, (%rax)
 ; BWON-F16C-NEXT:    retq
 ;
@@ -1185,12 +1169,11 @@ define void @main.45() #0 {
 ; CHECK-I686-NEXT:    pushl %esi
 ; CHECK-I686-NEXT:    subl $20, %esp
 ; CHECK-I686-NEXT:    pinsrw $0, (%eax), %xmm0
-; CHECK-I686-NEXT:    pextrw $0, %xmm0, %eax
-; CHECK-I686-NEXT:    movd %eax, %xmm0
-; CHECK-I686-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
-; CHECK-I686-NEXT:    movd %xmm0, %esi
+; CHECK-I686-NEXT:    pshuflw {{.*#+}} xmm1 = xmm0[0,0,0,0,4,5,6,7]
+; CHECK-I686-NEXT:    movd %xmm1, %esi
 ; CHECK-I686-NEXT:    movl %esi, %edi
 ; CHECK-I686-NEXT:    shrl $16, %edi
+; CHECK-I686-NEXT:    pextrw $0, %xmm0, %eax
 ; CHECK-I686-NEXT:    movw %ax, (%esp)
 ; CHECK-I686-NEXT:    calll __extendhfsf2
 ; CHECK-I686-NEXT:    fstps {{[0-9]+}}(%esp)
@@ -1336,13 +1319,9 @@ define half @pr61271(half %0, half %1) #0 {
 ;
 ; BWON-F16C-LABEL: pr61271:
 ; BWON-F16C:       # %bb.0:
-; BWON-F16C-NEXT:    vpextrw $0, %xmm0, %eax
-; BWON-F16C-NEXT:    vpextrw $0, %xmm1, %ecx
-; BWON-F16C-NEXT:    vmovd %ecx, %xmm0
-; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
-; BWON-F16C-NEXT:    vmovd %eax, %xmm1
 ; BWON-F16C-NEXT:    vcvtph2ps %xmm1, %xmm1
-; BWON-F16C-NEXT:    vminss %xmm0, %xmm1, %xmm0
+; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
+; BWON-F16C-NEXT:    vminss %xmm1, %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
 ; BWON-F16C-NEXT:    vmovd %xmm0, %eax
 ; BWON-F16C-NEXT:    vpinsrw $0, %eax, %xmm0, %xmm0
diff --git a/llvm/test/CodeGen/X86/pr114520.ll b/llvm/test/CodeGen/X86/pr114520.ll
index c557da6b3ab8c..9bd1f49ff67c9 100644
--- a/llvm/test/CodeGen/X86/pr114520.ll
+++ b/llvm/test/CodeGen/X86/pr114520.ll
@@ -5,7 +5,6 @@ define half @test1(half %x) {
 ; CHECK-LABEL: test1:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    vpextrw $0, %xmm0, %eax
-; CHECK-NEXT:    vmovd %eax, %xmm0
 ; CHECK-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; CHECK-NEXT:    vucomiss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
 ; CHECK-NEXT:    movl $64512, %ecx # imm = 0xFC00
diff --git a/llvm/test/CodeGen/X86/pr31088.ll b/llvm/test/CodeGen/X86/pr31088.ll
index ce37622c476db..1c9c8e40c009d 100644
--- a/llvm/test/CodeGen/X86/pr31088.ll
+++ b/llvm/test/CodeGen/X86/pr31088.ll
@@ -51,17 +51,7 @@ define <1 x half> @ir_fadd_v1f16(<1 x half> %arg0, <1 x half> %arg1) nounwind {
 ;
 ; F16C-O0-LABEL: ir_fadd_v1f16:
 ; F16C-O0:       # %bb.0:
-; F16C-O0-NEXT:    vpextrw $0, %xmm1, %eax
-; F16C-O0-NEXT:    movw %ax, %cx
-; F16C-O0-NEXT:    # implicit-def: $eax
-; F16C-O0-NEXT:    movw %cx, %ax
-; F16C-O0-NEXT:    vmovd %eax, %xmm1
 ; F16C-O0-NEXT:    vcvtph2ps %xmm1, %xmm1
-; F16C-O0-NEXT:    vpextrw $0, %xmm0, %eax
-; F16C-O0-NEXT:    movw %ax, %cx
-; F16C-O0-NEXT:    # implicit-def: $eax
-; F16C-O0-NEXT:    movw %cx, %ax
-; F16C-O0-NEXT:    vmovd %eax, %xmm0
 ; F16C-O0-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-O0-NEXT:    vaddss %xmm1, %xmm0, %xmm0
 ; F16C-O0-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
diff --git a/llvm/test/CodeGen/X86/pr86305.ll b/llvm/test/CodeGen/X86/pr86305.ll
index 79b42bb2532ca..0d2e1abe8e5fc 100644
--- a/llvm/test/CodeGen/X86/pr86305.ll
+++ b/llvm/test/CodeGen/X86/pr86305.ll
@@ -28,17 +28,16 @@ define <4 x bfloat> @fptrunc_v4f32(<4 x float> %a) nounwind {
 ; CHECK-LABEL: fptrunc_v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    pushq %rbp
-; CHECK-NEXT:    pushq %r15
 ; CHECK-NEXT:    pushq %r14
 ; CHECK-NEXT:    pushq %rbx
-; CHECK-NEXT:    subq $72, %rsp
+; CHECK-NEXT:    subq $64, %rsp
 ; CHECK-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
 ; CHECK-NEXT:    callq __truncsfbf2@PLT
 ; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
-; CHECK-NEXT:    vpermilpd $1, (%rsp), %xmm0 # 16-byte Folded Reload
-; CHECK-NEXT:    # xmm0 = mem[1,0]
+; CHECK-NEXT:    vmovshdup (%rsp), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,1,3,3]
 ; CHECK-NEXT:    callq __truncsfbf2@PLT
-; CHECK-NEXT:    vmovapd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
 ; CHECK-NEXT:    vpshufd $255, (%rsp), %xmm0 # 16-byte Folded Reload
 ; CHECK-NEXT:    # xmm0 = mem[3,3,3,3]
 ; CHECK-NEXT:    callq __truncsfbf2@PLT
@@ -49,24 +48,21 @@ define <4 x bfloat> @fptrunc_v4f32(<4 x float> %a) nounwind {
 ; CHECK-NEXT:    vpextrw $0, %xmm0, %ebp
 ; CHECK-NEXT:    vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
 ; CHECK-NEXT:    vpextrw $0, %xmm0, %r14d
-; CHECK-NEXT:    vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
-; CHECK-NEXT:    vpextrw $0, %xmm0, %r15d
-; CHECK-NEXT:    vmovshdup (%rsp), %xmm0 # 16-byte Folded Reload
-; CHECK-NEXT:    # xmm0 = mem[1,1,3,3]
+; CHECK-NEXT:    vpermilpd $1, (%rsp), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = mem[1,0]
 ; CHECK-NEXT:    callq __truncsfbf2@PLT
 ; CHECK-NEXT:    vpextrw $0, %xmm0, %eax
-; CHECK-NEXT:    vmovd %r15d, %xmm0
-; CHECK-NEXT:    vpinsrw $1, %eax, %xmm0, %xmm0
-; CHECK-NEXT:    vpinsrw $2, %r14d, %xmm0, %xmm0
+; CHECK-NEXT:    vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    vpinsrw $1, %r14d, %xmm0, %xmm0
+; CHECK-NEXT:    vpinsrw $2, %eax, %xmm0, %xmm0
 ; CHECK-NEXT:    vpinsrw $3, %ebp, %xmm0, %xmm0
 ; CHECK-NEXT:    vpinsrw $4, %ebx, %xmm0, %xmm0
 ; CHECK-NEXT:    vpinsrw $5, %ebx, %xmm0, %xmm0
 ; CHECK-NEXT:    vpinsrw $6, %ebx, %xmm0, %xmm0
 ; CHECK-NEXT:    vpinsrw $7, %ebx, %xmm0, %xmm0
-; CHECK-NEXT:    addq $72, %rsp
+; CHECK-NEXT:    addq $64, %rsp
 ; CHECK-NEXT:    popq %rbx
 ; CHECK-NEXT:    popq %r14
-; CHECK-NEXT:    popq %r15
 ; CHECK-NEXT:    popq %rbp
 ; CHECK-NEXT:    retq
   %b = fptrunc <4 x float> %a to <4 x bfloat>
diff --git a/llvm/test/CodeGen/X86/vector-half-conversions.ll b/llvm/test/CodeGen/X86/vector-half-conversions.ll
index 54acd012d1fe4..ec916060563a7 100644
--- a/llvm/test/CodeGen/X86/vector-half-conversions.ll
+++ b/llvm/test/CodeGen/X86/vector-half-conversions.ll
@@ -814,15 +814,13 @@ define float @load_cvt_i16_to_f32(ptr %a0) nounwind {
 ;
 ; F16C-LABEL: load_cvt_i16_to_f32:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    movzwl (%rdi), %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
+; F16C-NEXT:    vpinsrw $0, (%rdi), %xmm0, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    retq
 ;
 ; AVX512-LABEL: load_cvt_i16_to_f32:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    movzwl (%rdi), %eax
-; AVX512-NEXT:    vmovd %eax, %xmm0
+; AVX512-NEXT:    vpinsrw $0, (%rdi), %xmm0, %xmm0
 ; AVX512-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = load i16, ptr %a0
@@ -1830,16 +1828,14 @@ define double @load_cvt_i16_to_f64(ptr %a0) nounwind {
 ;
 ; F16C-LABEL: load_cvt_i16_to_f64:
 ; F16C:       # %bb.0:
-; F16C-NEXT:    movzwl (%rdi), %eax
-; F16C-NEXT:    vmovd %eax, %xmm0
+; F16C-NEXT:    vpinsrw $0, (%rdi), %xmm0, %xmm0
 ; F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; F16C-NEXT:    vcvtss2sd %xmm0, %xmm0, %xmm0
 ; F16C-NEXT:    retq
 ;
 ; AVX512-LABEL: load_cvt_i16_to_f64:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    movzwl (%rdi), %eax
-; AVX512-NEXT:    vmovd %eax, %xmm0
+; AVX512-NEXT:    vpinsrw $0, (%rdi), %xmm0, %xmm0
 ; AVX512-NEXT:    vcvtph2ps %xmm0, %xmm0
 ; AVX512-NEXT:    vcvtss2sd %xmm0, %xmm0, %xmm0
 ; AVX512-NEXT:    retq