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
@@ -3,25 +3,16 @@
 
 %struct.__tile_str = type <{ i16, i16, [60 x i8], <256 x i32> }>
 
-@buf = dso_local global [3072 x i8] zeroinitializer, align 16
+@buf = dso_local global [3072 x i8] zeroinitializer, align 64
 
-define dso_local void @test_api(i16 signext %0, i16 signext %1) local_unnamed_addr {
+define dso_local void @test_api(i16 signext %0, i16 signext %1) nounwind {
 ; CHECK-LABEL: test_api:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    pushq %rbp
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    pushq %r15
-; CHECK-NEXT:    .cfi_def_cfa_offset 24
 ; CHECK-NEXT:    pushq %r14
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    pushq %rbx
-; CHECK-NEXT:    .cfi_def_cfa_offset 40
 ; CHECK-NEXT:    subq $4056, %rsp # imm = 0xFD8
-; CHECK-NEXT:    .cfi_def_cfa_offset 4096
-; CHECK-NEXT:    .cfi_offset %rbx, -40
-; CHECK-NEXT:    .cfi_offset %r14, -32
-; CHECK-NEXT:    .cfi_offset %r15, -24
-; CHECK-NEXT:    .cfi_offset %rbp, -16
 ; CHECK-NEXT:    movl %esi, %ebx
 ; CHECK-NEXT:    movl %edi, %ebp
 ; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
@@ -58,15 +49,10 @@
 ; CHECK-NEXT:    tdpbssd %tmm2, %tmm1, %tmm0
 ; CHECK-NEXT:    tilestored %tmm0, (%rax,%r14)
 ; CHECK-NEXT:    addq $4056, %rsp # imm = 0xFD8
-; CHECK-NEXT:    .cfi_def_cfa_offset 40
 ; CHECK-NEXT:    popq %rbx
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    popq %r14
-; CHECK-NEXT:    .cfi_def_cfa_offset 24
 ; CHECK-NEXT:    popq %r15
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    popq %rbp
-; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    tilerelease
 ; CHECK-NEXT:    retq
   %3 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %0, i16 8, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 0), i64 32)
@@ -78,7 +64,7 @@
   ret void
 }
 
-declare dso_local void @foo(...) local_unnamed_addr
+declare dso_local void @foo(...)
 
 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)
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
@@ -1,11 +1,11 @@
 ; 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
 
-@buf = dso_local global [1024 x i8] zeroinitializer, align 16
-@buf2 = dso_local global [1024 x i8] zeroinitializer, align 16
+@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) local_unnamed_addr {
+define dso_local void @test_api(i32 %0, i16 signext %1, i16 signext %2) {
 ; CHECK-LABEL: test_api:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    testl %edi, %edi
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
@@ -1,7 +1,7 @@
 ; 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
 
-define dso_local void @test_chain(i8* %A_mem, i8* %B_mem, i8* %C_mem) local_unnamed_addr {
+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
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
@@ -1,7 +1,7 @@
 ; 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
 
-@buf = dso_local global [3072 x i8] zeroinitializer, align 16
+@buf = dso_local global [3072 x i8] zeroinitializer, align 64
 
 define dso_local void @test_api(i16 signext %0, i16 signext %1) nounwind {
 ; CHECK-LABEL: test_api:
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
@@ -1,14 +1,13 @@
 ; 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
 
-@buf = dso_local global [1024 x i8] zeroinitializer, align 16
-@buf2 = dso_local global [1024 x i8] zeroinitializer, align 16
+@buf = dso_local global [1024 x i8] zeroinitializer, align 64
+@buf2 = dso_local global [1024 x i8] zeroinitializer, align 64
 
-define dso_local void @test_api(i32 %0, i16 signext %1, i16 signext %2) local_unnamed_addr {
+define dso_local void @test_api(i32 %0, i16 signext %1, i16 signext %2) nounwind {
 ; CHECK-LABEL: test_api:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    subq $2936, %rsp # imm = 0xB78
-; CHECK-NEXT:    .cfi_def_cfa_offset 2944
 ; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
 ; CHECK-NEXT:    vmovdqu64 %zmm0, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, {{[0-9]+}}(%rsp)
@@ -63,7 +62,6 @@
 ; CHECK-NEXT:    movl $32, %ecx
 ; CHECK-NEXT:    tilestored %tmm0, (%rax,%rcx)
 ; CHECK-NEXT:    addq $2936, %rsp # imm = 0xB78
-; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    tilerelease
 ; CHECK-NEXT:    vzeroupper
 ; CHECK-NEXT:    retq
diff --git a/llvm/test/CodeGen/X86/AMX/amx-type.ll b/llvm/test/CodeGen/X86/AMX/amx-type.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-type.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-type.ll
@@ -3,8 +3,8 @@
 
 %struct.__tile_str = type { i16, i16, <256 x i32> }
 
-@buf = dso_local global [1024 x i8] zeroinitializer, align 16
-@buf2 = dso_local global [1024 x i8] zeroinitializer, align 16
+@buf = dso_local global [1024 x i8] zeroinitializer, align 64
+@buf2 = dso_local global [1024 x i8] zeroinitializer, align 64
 
 ; test bitcast x86_amx to <256 x i32>
 define dso_local void @test_user_empty(i16 %m, i16 %n, i8 *%buf, i64 %s) {