diff --git a/llvm/lib/Target/X86/X86InstrInfo.cpp b/llvm/lib/Target/X86/X86InstrInfo.cpp
--- a/llvm/lib/Target/X86/X86InstrInfo.cpp
+++ b/llvm/lib/Target/X86/X86InstrInfo.cpp
@@ -6788,7 +6788,8 @@
 
   // ENDBR instructions should not be scheduled around.
   unsigned Opcode = MI.getOpcode();
-  if (Opcode == X86::ENDBR64 || Opcode == X86::ENDBR32)
+  if (Opcode == X86::ENDBR64 || Opcode == X86::ENDBR32 ||
+      Opcode == X86::PLDTILECFG)
     return true;
 
   return TargetInstrInfo::isSchedulingBoundary(MI, MBB, MF);
diff --git a/llvm/test/CodeGen/X86/AMX/amx-sched.ll b/llvm/test/CodeGen/X86/AMX/amx-sched.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/X86/AMX/amx-sched.ll
@@ -0,0 +1,16 @@
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -mcpu=skx -verify-machineinstrs | FileCheck %s
+
+define <256 x i32> @test_shape_sched(i16 %m, i16 %n, i16 %k, <256 x i32> %c, <256 x i32> %a, <256 x i32> %b) nounwind {
+; Just to make sure shape def is not scheduled across ldtilecfg.
+; CHECK:    ldtilecfg
+; CHECK-NOT: movw
+  %c1 = bitcast <256 x i32> %c to x86_amx
+  %a1 = bitcast <256 x i32> %a to x86_amx
+  %b1 = bitcast <256 x i32> %b to x86_amx
+  %t = call x86_amx @llvm.x86.tdpbssd.internal(i16 %m, i16 %n, i16 %k, x86_amx %c1, x86_amx %a1, x86_amx %b1)
+  %res = bitcast x86_amx %t to <256 x i32>
+  ret <256 x i32> %res
+}
+
+
+declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)