[X86] Zero AMX config buffer for non AVX512 cases.

Zero AMX config buffer for non AVX512 cases.

Differential Revision: https://reviews.llvm.org/D96927

Author: phoebewang

llvm/lib/Target/X86/X86PreTileConfig.cpp

@@ -103,16 +103,44 @@ static void buildConfigMI(MachineBasicBlock::iterator MI, int FrameIdx,
                           const X86Subtarget *ST) {
   auto *MBB = MI->getParent();
 
-  // FIXME: AMX should assume AVX512 enabled.
+  // Zero stack slot.
   if (ST->hasAVX512()) {
-    // Zero stack slot.
     Register Zmm = MRI->createVirtualRegister(&X86::VR512RegClass);
     BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::VPXORDZrr), Zmm)
         .addReg(Zmm, RegState::Undef)
         .addReg(Zmm, RegState::Undef);
     addFrameReference(BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::VMOVUPSZmr)),
                       FrameIdx)
         .addReg(Zmm);
+  } else if (ST->hasAVX2()) {
+    Register Ymm = MRI->createVirtualRegister(&X86::VR256RegClass);
+    BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::VPXORYrr), Ymm)
+        .addReg(Ymm, RegState::Undef)
+        .addReg(Ymm, RegState::Undef);
+    addFrameReference(BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::VMOVUPSYmr)),
+                      FrameIdx)
+        .addReg(Ymm);
+    addFrameReference(BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::VMOVUPSYmr)),
+                      FrameIdx, 32)
+        .addReg(Ymm);
+  } else {
+    assert(ST->hasSSE2() && "AMX should assume SSE2 enabled");
+    Register Xmm = MRI->createVirtualRegister(&X86::VR128RegClass);
+    BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::PXORrr), Xmm)
+        .addReg(Xmm, RegState::Undef)
+        .addReg(Xmm, RegState::Undef);
+    addFrameReference(BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::MOVUPSmr)),
+                      FrameIdx)
+        .addReg(Xmm);
+    addFrameReference(BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::MOVUPSmr)),
+                      FrameIdx, 16)
+        .addReg(Xmm);
+    addFrameReference(BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::MOVUPSmr)),
+                      FrameIdx, 32)
+        .addReg(Xmm);
+    addFrameReference(BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::MOVUPSmr)),
+                      FrameIdx, 48)
+        .addReg(Xmm);
   }
 
   // build psuedo ldtilecfg

llvm/test/CodeGen/X86/AMX/amx-config.ll

@@ -45,6 +45,9 @@ define dso_local void @test_api(i32 %0, i16 signext %1, i16 signext %2) {
 ; AVX2:       # %bb.0:
 ; AVX2-NEXT:    testl %edi, %edi
 ; AVX2-NEXT:    movsbl %sil, %eax
+; AVX2-NEXT:    vxorps %ymm0, %ymm0, %ymm0
+; AVX2-NEXT:    vmovups %ymm0, -{{[0-9]+}}(%rsp)
+; AVX2-NEXT:    vmovups %ymm0, -{{[0-9]+}}(%rsp)
 ; AVX2-NEXT:    movb $1, -{{[0-9]+}}(%rsp)
 ; AVX2-NEXT:    movb %al, -{{[0-9]+}}(%rsp)
 ; AVX2-NEXT:    movw %si, -{{[0-9]+}}(%rsp)
@@ -69,12 +72,18 @@ define dso_local void @test_api(i32 %0, i16 signext %1, i16 signext %2) {
 ; AVX2-NEXT:    movl $32, %esi
 ; AVX2-NEXT:    tilestored %tmm1, (%rcx,%rsi)
 ; AVX2-NEXT:    tilerelease
+; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; SSE2-LABEL: test_api:
 ; SSE2:       # %bb.0:
 ; SSE2-NEXT:    testl %edi, %edi
 ; SSE2-NEXT:    movsbl %sil, %eax
+; 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:    movb $1, -{{[0-9]+}}(%rsp)
 ; SSE2-NEXT:    movb %al, -{{[0-9]+}}(%rsp)
 ; SSE2-NEXT:    movw %si, -{{[0-9]+}}(%rsp)