diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 8c28985c8e8e7..91249f0bb009f 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -58485,10 +58485,26 @@ static SDValue combineEXTRACT_SUBVECTOR(SDNode *N, SelectionDAG &DAG,
                       DAG.isSplatValue(InVec, /*AllowUndefs*/ false)))
     return extractSubVector(InVec, 0, DAG, DL, SizeInBits);
 
-  // If we're extracting a broadcasted subvector, just use the lowest subvector.
-  if (IdxVal != 0 && InVec.getOpcode() == X86ISD::SUBV_BROADCAST_LOAD &&
-      cast<MemIntrinsicSDNode>(InVec)->getMemoryVT() == VT)
-    return extractSubVector(InVec, 0, DAG, DL, SizeInBits);
+  // Check if we're extracting a whole broadcasted subvector.
+  if (InVec.getOpcode() == X86ISD::SUBV_BROADCAST_LOAD) {
+    auto *MemIntr = cast<MemIntrinsicSDNode>(InVec);
+    EVT MemVT = MemIntr->getMemoryVT();
+    if (MemVT == VT) {
+      // Just use the lowest subvector.
+      if (IdxVal != 0)
+        return extractSubVector(InVec, 0, DAG, DL, SizeInBits);
+      // If this is the only use, we can replace with a regular load (this may
+      // have been missed by SimplifyDemandedVectorElts due to extra uses of the
+      // memory chain).
+      if (InVec.hasOneUse()) {
+        SDValue Ld =
+            DAG.getLoad(MemVT, DL, MemIntr->getChain(), MemIntr->getBasePtr(),
+                        MemIntr->getMemOperand());
+        DAG.makeEquivalentMemoryOrdering(SDValue(MemIntr, 1), Ld.getValue(1));
+        return Ld;
+      }
+    }
+  }
 
   // Attempt to extract from the source of a shuffle vector.
   if ((InSizeInBits % SizeInBits) == 0 && (IdxVal % NumSubElts) == 0) {
diff --git a/llvm/test/CodeGen/X86/any_extend_vector_inreg_of_broadcast_from_memory.ll b/llvm/test/CodeGen/X86/any_extend_vector_inreg_of_broadcast_from_memory.ll
index 3d72319f59ca9..e47a9ac3a0c0b 100644
--- a/llvm/test/CodeGen/X86/any_extend_vector_inreg_of_broadcast_from_memory.ll
+++ b/llvm/test/CodeGen/X86/any_extend_vector_inreg_of_broadcast_from_memory.ll
@@ -3634,19 +3634,18 @@ define void @vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3(ptr %i
 ;
 ; AVX-LABEL: vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3:
 ; AVX:       # %bb.0:
-; AVX-NEXT:    vbroadcastf128 {{.*#+}} ymm0 = mem[0,1,0,1]
-; AVX-NEXT:    vblendps {{.*#+}} xmm1 = xmm0[0],mem[1,2,3]
+; AVX-NEXT:    vmovdqa (%rdi), %xmm0
+; AVX-NEXT:    vpblendw {{.*#+}} xmm1 = xmm0[0,1],mem[2,3,4,5,6,7]
 ; AVX-NEXT:    vpaddb (%rsi), %xmm1, %xmm1
 ; AVX-NEXT:    vmovdqa (%rdi), %xmm2
 ; AVX-NEXT:    vmovdqa 16(%rdi), %xmm3
 ; AVX-NEXT:    vpaddb 48(%rsi), %xmm3, %xmm3
-; AVX-NEXT:    vpaddb 16(%rsi), %xmm0, %xmm0
 ; AVX-NEXT:    vpaddb 32(%rsi), %xmm2, %xmm2
-; AVX-NEXT:    vmovdqa %xmm2, 32(%rdx)
+; AVX-NEXT:    vpaddb 16(%rsi), %xmm0, %xmm0
 ; AVX-NEXT:    vmovdqa %xmm0, 16(%rdx)
+; AVX-NEXT:    vmovdqa %xmm2, 32(%rdx)
 ; AVX-NEXT:    vmovdqa %xmm3, 48(%rdx)
 ; AVX-NEXT:    vmovdqa %xmm1, (%rdx)
-; AVX-NEXT:    vzeroupper
 ; AVX-NEXT:    retq
 ;
 ; AVX2-LABEL: vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3:
@@ -3820,19 +3819,18 @@ define void @vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3(ptr %i
 ;
 ; AVX-LABEL: vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3:
 ; AVX:       # %bb.0:
-; AVX-NEXT:    vbroadcastf128 {{.*#+}} ymm0 = mem[0,1,0,1]
-; AVX-NEXT:    vblendps {{.*#+}} xmm1 = xmm0[0,1],mem[2,3]
+; AVX-NEXT:    vmovdqa (%rdi), %xmm0
+; AVX-NEXT:    vpblendw {{.*#+}} xmm1 = xmm0[0,1,2,3],mem[4,5,6,7]
 ; AVX-NEXT:    vpaddb (%rsi), %xmm1, %xmm1
 ; AVX-NEXT:    vmovdqa (%rdi), %xmm2
 ; AVX-NEXT:    vmovdqa 16(%rdi), %xmm3
 ; AVX-NEXT:    vpaddb 48(%rsi), %xmm3, %xmm3
-; AVX-NEXT:    vpaddb 16(%rsi), %xmm0, %xmm0
 ; AVX-NEXT:    vpaddb 32(%rsi), %xmm2, %xmm2
-; AVX-NEXT:    vmovdqa %xmm2, 32(%rdx)
+; AVX-NEXT:    vpaddb 16(%rsi), %xmm0, %xmm0
 ; AVX-NEXT:    vmovdqa %xmm0, 16(%rdx)
+; AVX-NEXT:    vmovdqa %xmm2, 32(%rdx)
 ; AVX-NEXT:    vmovdqa %xmm3, 48(%rdx)
 ; AVX-NEXT:    vmovdqa %xmm1, (%rdx)
-; AVX-NEXT:    vzeroupper
 ; AVX-NEXT:    retq
 ;
 ; AVX2-LABEL: vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3:
diff --git a/llvm/test/CodeGen/X86/zero_extend_vector_inreg_of_broadcast_from_memory.ll b/llvm/test/CodeGen/X86/zero_extend_vector_inreg_of_broadcast_from_memory.ll
index acedcf4263906..a3f134922ba3c 100644
--- a/llvm/test/CodeGen/X86/zero_extend_vector_inreg_of_broadcast_from_memory.ll
+++ b/llvm/test/CodeGen/X86/zero_extend_vector_inreg_of_broadcast_from_memory.ll
@@ -4044,18 +4044,17 @@ define void @vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3(ptr %i
 ;
 ; AVX-LABEL: vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3:
 ; AVX:       # %bb.0:
-; AVX-NEXT:    vbroadcastf128 {{.*#+}} ymm0 = mem[0,1,0,1]
-; AVX-NEXT:    vblendps {{.*#+}} xmm1 = xmm0[0],mem[1,2,3]
+; AVX-NEXT:    vmovdqa (%rdi), %xmm0
+; AVX-NEXT:    vpblendw {{.*#+}} xmm1 = xmm0[0,1],mem[2,3,4,5,6,7]
 ; AVX-NEXT:    vmovd {{.*#+}} xmm2 = mem[0],zero,zero,zero
-; AVX-NEXT:    vxorps %xmm3, %xmm3, %xmm3
-; AVX-NEXT:    vblendps {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3]
-; AVX-NEXT:    vpaddb 16(%rsi), %xmm0, %xmm0
 ; AVX-NEXT:    vpaddb (%rsi), %xmm1, %xmm1
+; AVX-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm3[2,3,4,5,6,7]
+; AVX-NEXT:    vpaddb 16(%rsi), %xmm0, %xmm0
 ; AVX-NEXT:    vpaddb 32(%rsi), %xmm2, %xmm2
 ; AVX-NEXT:    vmovdqa %xmm2, 32(%rdx)
-; AVX-NEXT:    vmovdqa %xmm1, (%rdx)
 ; AVX-NEXT:    vmovdqa %xmm0, 16(%rdx)
-; AVX-NEXT:    vzeroupper
+; AVX-NEXT:    vmovdqa %xmm1, (%rdx)
 ; AVX-NEXT:    retq
 ;
 ; AVX2-LABEL: vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3:
@@ -4263,17 +4262,16 @@ define void @vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3(ptr %i
 ;
 ; AVX-LABEL: vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3:
 ; AVX:       # %bb.0:
-; AVX-NEXT:    vbroadcastf128 {{.*#+}} ymm0 = mem[0,1,0,1]
-; AVX-NEXT:    vblendps {{.*#+}} xmm1 = xmm0[0,1],mem[2,3]
+; AVX-NEXT:    vmovdqa (%rdi), %xmm0
+; AVX-NEXT:    vpblendw {{.*#+}} xmm1 = xmm0[0,1,2,3],mem[4,5,6,7]
 ; AVX-NEXT:    vmovq {{.*#+}} xmm2 = mem[0],zero
+; AVX-NEXT:    vpaddb (%rsi), %xmm1, %xmm1
 ; AVX-NEXT:    vmovq {{.*#+}} xmm0 = xmm0[0],zero
 ; AVX-NEXT:    vpaddb 16(%rsi), %xmm0, %xmm0
-; AVX-NEXT:    vpaddb (%rsi), %xmm1, %xmm1
 ; AVX-NEXT:    vpaddb 32(%rsi), %xmm2, %xmm2
 ; AVX-NEXT:    vmovdqa %xmm2, 32(%rdx)
-; AVX-NEXT:    vmovdqa %xmm1, (%rdx)
 ; AVX-NEXT:    vmovdqa %xmm0, 16(%rdx)
-; AVX-NEXT:    vzeroupper
+; AVX-NEXT:    vmovdqa %xmm1, (%rdx)
 ; AVX-NEXT:    retq
 ;
 ; AVX2-LABEL: vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3: