diff --git a/llvm/lib/Target/X86/X86PreTileConfig.cpp b/llvm/lib/Target/X86/X86PreTileConfig.cpp
--- a/llvm/lib/Target/X86/X86PreTileConfig.cpp
+++ b/llvm/lib/Target/X86/X86PreTileConfig.cpp
@@ -378,36 +378,31 @@
   // Zero stack slot.
   MachineBasicBlock &MBB = MF.front();
   MachineInstr *MI = &*MBB.begin();
+  auto ZeroSS = [&](unsigned Opc) {
+    Register Xmm = MRI->createVirtualRegister(&X86::VR128RegClass);
+    BuildMI(MBB, MI, DL, TII->get(X86::V_SET0), Xmm);
+    addFrameReference(BuildMI(MBB, MI, DL, TII->get(Opc)), SS).addReg(Xmm);
+    addFrameReference(BuildMI(MBB, MI, DL, TII->get(Opc)), SS, 16).addReg(Xmm);
+    addFrameReference(BuildMI(MBB, MI, DL, TII->get(Opc)), SS, 32).addReg(Xmm);
+    addFrameReference(BuildMI(MBB, MI, DL, TII->get(Opc)), SS, 48).addReg(Xmm);
+  };
   if (ST.hasAVX512()) {
     Register Zmm = MRI->createVirtualRegister(&X86::VR512RegClass);
-    BuildMI(MBB, MI, DL, TII->get(X86::VPXORDZrr), Zmm)
-        .addReg(Zmm, RegState::Undef)
-        .addReg(Zmm, RegState::Undef);
+    BuildMI(MBB, MI, DL, TII->get(X86::AVX512_512_SET0), Zmm);
     addFrameReference(BuildMI(MBB, MI, DL, TII->get(X86::VMOVUPSZmr)), SS)
         .addReg(Zmm);
   } else if (ST.hasAVX2()) {
     Register Ymm = MRI->createVirtualRegister(&X86::VR256RegClass);
-    BuildMI(MBB, MI, DL, TII->get(X86::VPXORYrr), Ymm)
-        .addReg(Ymm, RegState::Undef)
-        .addReg(Ymm, RegState::Undef);
+    BuildMI(MBB, MI, DL, TII->get(X86::AVX_SET0), Ymm);
     addFrameReference(BuildMI(MBB, MI, DL, TII->get(X86::VMOVUPSYmr)), SS)
         .addReg(Ymm);
     addFrameReference(BuildMI(MBB, MI, DL, TII->get(X86::VMOVUPSYmr)), SS, 32)
         .addReg(Ymm);
+  } else if (ST.hasAVX()) {
+    ZeroSS(X86::VMOVUPSmr);
   } else {
     assert(ST.hasSSE2() && "AMX should assume SSE2 enabled");
-    Register Xmm = MRI->createVirtualRegister(&X86::VR128RegClass);
-    BuildMI(MBB, MI, DL, TII->get(X86::PXORrr), Xmm)
-        .addReg(Xmm, RegState::Undef)
-        .addReg(Xmm, RegState::Undef);
-    addFrameReference(BuildMI(MBB, MI, DL, TII->get(X86::MOVUPSmr)), SS)
-        .addReg(Xmm);
-    addFrameReference(BuildMI(MBB, MI, DL, TII->get(X86::MOVUPSmr)), SS, 16)
-        .addReg(Xmm);
-    addFrameReference(BuildMI(MBB, MI, DL, TII->get(X86::MOVUPSmr)), SS, 32)
-        .addReg(Xmm);
-    addFrameReference(BuildMI(MBB, MI, DL, TII->get(X86::MOVUPSmr)), SS, 48)
-        .addReg(Xmm);
+    ZeroSS(X86::MOVUPSmr);
   }
   // Fill in the palette first.
   addFrameReference(BuildMI(MBB, MI, DL, TII->get(X86::MOV8mi)), SS).addImm(1);
diff --git a/llvm/test/CodeGen/X86/AMX/amx-across-func.ll b/llvm/test/CodeGen/X86/AMX/amx-across-func.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-across-func.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-across-func.ll
@@ -26,8 +26,8 @@
 ; CHECK-NEXT:    subq $2120, %rsp # imm = 0x848
 ; CHECK-NEXT:    movl %esi, %ebx
 ; CHECK-NEXT:    movl %edi, %ebp
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, (%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, (%rsp)
 ; CHECK-NEXT:    movb $1, (%rsp)
 ; CHECK-NEXT:    movw $8, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $8, {{[0-9]+}}(%rsp)
@@ -68,8 +68,8 @@
 ; IPRA-LABEL: test_api:
 ; IPRA:       # %bb.0:
 ; IPRA-NEXT:    subq $72, %rsp
-; IPRA-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; IPRA-NEXT:    vmovdqu64 %zmm0, {{[0-9]+}}(%rsp)
+; IPRA-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; IPRA-NEXT:    vmovups %zmm0, {{[0-9]+}}(%rsp)
 ; IPRA-NEXT:    movb $1, {{[0-9]+}}(%rsp)
 ; IPRA-NEXT:    movw $8, {{[0-9]+}}(%rsp)
 ; IPRA-NEXT:    movb $8, {{[0-9]+}}(%rsp)
@@ -113,8 +113,8 @@
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    subq $1096, %rsp # imm = 0x448
 ; CHECK-NEXT:    movl %edi, %r14d
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, (%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, (%rsp)
 ; CHECK-NEXT:    movb $1, (%rsp)
 ; CHECK-NEXT:    movb $8, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw $8, {{[0-9]+}}(%rsp)
@@ -179,8 +179,8 @@
 ; IPRA:       # %bb.0:
 ; IPRA-NEXT:    subq $72, %rsp
 ; IPRA-NEXT:    movl %edi, %eax
-; IPRA-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; IPRA-NEXT:    vmovdqu64 %zmm0, {{[0-9]+}}(%rsp)
+; IPRA-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; IPRA-NEXT:    vmovups %zmm0, {{[0-9]+}}(%rsp)
 ; IPRA-NEXT:    movb $1, {{[0-9]+}}(%rsp)
 ; IPRA-NEXT:    movb $8, {{[0-9]+}}(%rsp)
 ; IPRA-NEXT:    movw $8, {{[0-9]+}}(%rsp)
@@ -272,8 +272,8 @@
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    subq $1088, %rsp # imm = 0x440
 ; CHECK-NEXT:    movl %edi, %ebx
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, (%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, (%rsp)
 ; CHECK-NEXT:    movb $1, (%rsp)
 ; CHECK-NEXT:    movb $8, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw $8, {{[0-9]+}}(%rsp)
@@ -312,8 +312,8 @@
 ; IPRA-LABEL: test_loop2:
 ; IPRA:       # %bb.0:
 ; IPRA-NEXT:    subq $72, %rsp
-; IPRA-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; IPRA-NEXT:    vmovdqu64 %zmm0, {{[0-9]+}}(%rsp)
+; IPRA-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; IPRA-NEXT:    vmovups %zmm0, {{[0-9]+}}(%rsp)
 ; IPRA-NEXT:    movb $1, {{[0-9]+}}(%rsp)
 ; IPRA-NEXT:    movb $8, {{[0-9]+}}(%rsp)
 ; IPRA-NEXT:    movw $8, {{[0-9]+}}(%rsp)
diff --git a/llvm/test/CodeGen/X86/AMX/amx-config.ll b/llvm/test/CodeGen/X86/AMX/amx-config.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-config.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-config.ll
@@ -1,17 +1,18 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -verify-machineinstrs | FileCheck %s --check-prefix=AVX512
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx2 -verify-machineinstrs | FileCheck %s --check-prefix=AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8,+avx512f -verify-machineinstrs | FileCheck %s --check-prefix=AVX512
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8,+avx2 -verify-machineinstrs | FileCheck %s --check-prefix=AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8,+avx -verify-machineinstrs | FileCheck %s --check-prefix=AVX1
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -verify-machineinstrs | FileCheck %s --check-prefix=SSE2
 
 @buf = dso_local global [1024 x i8] zeroinitializer, align 64
 @buf2 = dso_local global [1024 x i8] zeroinitializer, align 64
 
 ; Function Attrs: nounwind uwtable
-define dso_local void @test_api(i32 %0, i16 signext %1, i16 signext %2) {
+define <4 x i32> @test_api(i32 %0, i16 signext %1, i16 signext %2, <4 x i32> %xmm0) {
 ; AVX512-LABEL: test_api:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; AVX512-NEXT:    vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
+; AVX512-NEXT:    vxorps %xmm1, %xmm1, %xmm1
+; AVX512-NEXT:    vmovups %zmm1, -{{[0-9]+}}(%rsp)
 ; AVX512-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; AVX512-NEXT:    movw %dx, -{{[0-9]+}}(%rsp)
 ; AVX512-NEXT:    movw %dx, -{{[0-9]+}}(%rsp)
@@ -43,9 +44,9 @@
 ;
 ; AVX2-LABEL: test_api:
 ; AVX2:       # %bb.0:
-; AVX2-NEXT:    vxorps %ymm0, %ymm0, %ymm0
-; AVX2-NEXT:    vmovups %ymm0, -{{[0-9]+}}(%rsp)
-; AVX2-NEXT:    vmovups %ymm0, -{{[0-9]+}}(%rsp)
+; AVX2-NEXT:    vxorps %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vmovups %ymm1, -{{[0-9]+}}(%rsp)
+; AVX2-NEXT:    vmovups %ymm1, -{{[0-9]+}}(%rsp)
 ; AVX2-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; AVX2-NEXT:    movw %dx, -{{[0-9]+}}(%rsp)
 ; AVX2-NEXT:    movw %dx, -{{[0-9]+}}(%rsp)
@@ -75,13 +76,48 @@
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
+; AVX1-LABEL: test_api:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vxorps %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    movups %xmm1, -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    movups %xmm1, -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    movups %xmm1, -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    movups %xmm1, -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    movw %dx, -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    movw %dx, -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    movw %si, -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    testl %edi, %edi
+; AVX1-NEXT:    movsbl %sil, %eax
+; AVX1-NEXT:    movb %al, -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    movb %al, -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    movb %al, -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    ldtilecfg -{{[0-9]+}}(%rsp)
+; AVX1-NEXT:    je .LBB0_2
+; AVX1-NEXT:  # %bb.1:
+; AVX1-NEXT:    movl $buf, %ecx
+; AVX1-NEXT:    jmp .LBB0_3
+; AVX1-NEXT:  .LBB0_2:
+; AVX1-NEXT:    movl $buf2, %ecx
+; AVX1-NEXT:  .LBB0_3:
+; AVX1-NEXT:    movl $32, %edi
+; AVX1-NEXT:    tileloadd (%rcx,%rdi), %tmm0
+; AVX1-NEXT:    tileloadd (%rcx,%rdi), %tmm2
+; AVX1-NEXT:    tileloadd (%rcx,%rdi), %tmm1
+; AVX1-NEXT:    tdpbssd %tmm2, %tmm0, %tmm1
+; AVX1-NEXT:    movl $buf, %ecx
+; AVX1-NEXT:    movl $32, %esi
+; AVX1-NEXT:    tilestored %tmm1, (%rcx,%rsi)
+; AVX1-NEXT:    tilerelease
+; AVX1-NEXT:    retq
+;
 ; SSE2-LABEL: test_api:
 ; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorps %xmm0, %xmm0
-; SSE2-NEXT:    movups %xmm0, -{{[0-9]+}}(%rsp)
-; SSE2-NEXT:    movups %xmm0, -{{[0-9]+}}(%rsp)
-; SSE2-NEXT:    movups %xmm0, -{{[0-9]+}}(%rsp)
-; SSE2-NEXT:    movups %xmm0, -{{[0-9]+}}(%rsp)
+; SSE2-NEXT:    xorps %xmm1, %xmm1
+; SSE2-NEXT:    movups %xmm1, -{{[0-9]+}}(%rsp)
+; SSE2-NEXT:    movups %xmm1, -{{[0-9]+}}(%rsp)
+; SSE2-NEXT:    movups %xmm1, -{{[0-9]+}}(%rsp)
+; SSE2-NEXT:    movups %xmm1, -{{[0-9]+}}(%rsp)
 ; SSE2-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; SSE2-NEXT:    movw %dx, -{{[0-9]+}}(%rsp)
 ; SSE2-NEXT:    movw %dx, -{{[0-9]+}}(%rsp)
@@ -132,11 +168,9 @@
   %18 = phi x86_amx [ %14, %11 ], [ %10, %7 ]
   %19 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %6, i16 %2, i16 %1, x86_amx %18, x86_amx %16, x86_amx %17)
   tail call void @llvm.x86.tilestored64.internal(i16 %6, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32, x86_amx %19)
-  ret void
+  ret <4 x i32> %xmm0
 }
 
 declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64)
-
 declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)
-
 declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx)
diff --git a/llvm/test/CodeGen/X86/AMX/amx-intrinsic-chain.ll b/llvm/test/CodeGen/X86/AMX/amx-intrinsic-chain.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-intrinsic-chain.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-intrinsic-chain.ll
@@ -4,8 +4,8 @@
 define dso_local void @test_chain(i8* %A_mem, i8* %B_mem, i8* %C_mem) {
 ; CHECK-LABEL: test_chain:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $16, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw $64, -{{[0-9]+}}(%rsp)
diff --git a/llvm/test/CodeGen/X86/AMX/amx-ldtilecfg-insert.ll b/llvm/test/CodeGen/X86/AMX/amx-ldtilecfg-insert.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-ldtilecfg-insert.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-ldtilecfg-insert.ll
@@ -5,8 +5,8 @@
 define dso_local void @test1(i16 signext %0, i16 signext %1) nounwind {
 ; CHECK-LABEL: test1:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw $8, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $8, -{{[0-9]+}}(%rsp)
@@ -46,8 +46,8 @@
 ; CHECK-NEXT:    subq $72, %rsp
 ; CHECK-NEXT:    movl %esi, %ebx
 ; CHECK-NEXT:    movl %edi, %ebp
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw $8, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $8, {{[0-9]+}}(%rsp)
@@ -119,8 +119,8 @@
 define dso_local void @test3(i16 signext %0, i16 signext %1) nounwind {
 ; CHECK-LABEL: test3:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw %si, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
@@ -162,8 +162,8 @@
 define dso_local void @test4(i16 signext %0, i16 signext %1) nounwind {
 ; CHECK-LABEL: test4:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw %si, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
@@ -231,8 +231,8 @@
 ; CHECK-LABEL: test5:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    # kill: def $esi killed $esi def $rsi
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw %si, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
@@ -292,8 +292,8 @@
 ; CHECK-LABEL: test6:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    # kill: def $edi killed $edi def $rdi
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb %dil, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    xorl %r8d, %r8d
diff --git a/llvm/test/CodeGen/X86/AMX/amx-lower-tile-copy.ll b/llvm/test/CodeGen/X86/AMX/amx-lower-tile-copy.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-lower-tile-copy.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-lower-tile-copy.ll
@@ -9,8 +9,8 @@
 ; CHECK-NEXT:    pushq %r14
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    subq $4056, %rsp # imm = 0xFD8
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $8, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw $8, {{[0-9]+}}(%rsp)
@@ -96,8 +96,8 @@
 ; CHECK-NEXT:    pushq %r14
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    subq $72, %rsp
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $8, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw $8, {{[0-9]+}}(%rsp)
diff --git a/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll b/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll
@@ -13,8 +13,8 @@
 ; CHECK-NEXT:    subq $2120, %rsp # imm = 0x848
 ; CHECK-NEXT:    movl %esi, %ebx
 ; CHECK-NEXT:    movl %edi, %ebp
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, (%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, (%rsp)
 ; CHECK-NEXT:    movb $1, (%rsp)
 ; CHECK-NEXT:    movw $8, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $8, {{[0-9]+}}(%rsp)
@@ -121,8 +121,8 @@
 ; CHECK-NEXT:    pushq %r14
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    subq $72, %rsp
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $8, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw $8, {{[0-9]+}}(%rsp)
diff --git a/llvm/test/CodeGen/X86/AMX/amx-spill.ll b/llvm/test/CodeGen/X86/AMX/amx-spill.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-spill.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-spill.ll
@@ -8,8 +8,8 @@
 ; CHECK-LABEL: test_api:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    subq $968, %rsp # imm = 0x3C8
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw %dx, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb %sil, -{{[0-9]+}}(%rsp)
diff --git a/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll b/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll
@@ -4,8 +4,8 @@
 define void @test_amx(i8* %pointer, i8* %base, i64 %stride) {
 ; CHECK-LABEL: test_amx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
-; CHECK-NEXT:    vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vmovups %zmm0, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $8, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw $8, -{{[0-9]+}}(%rsp)