[X86] Fix a bug when calculating the ldtilecfg insertion points.

[pengfei]

Summary

The BB we initialized the ldtilecfg is special. We don't need to check
if its predecessor BBs need to insert ldtilecfg for calls.

We reused the flag HasCallBeforeAMX, so that the predecessors won't be
added to CfgNeedInsert.

This case happens only when the entry BB is in a loop. We need to hoist
the first tile config point out of the loop in future.

[LuoYuanke]

llvm/lib/Target/X86/X86PreTileConfig.cpp

303

It take the some time to re-understand what HasCallBeforeAMX means. It seems NoPredUpdate is more readable than HasCallBeforeAMX, but it is not related to this patch.

[LuoYuanke]

LGTM, thanks.

[pengfei]

llvm/lib/Target/X86/X86PreTileConfig.cpp

303

Good suggestion. I refactored it bassed on your thought by D99010.

llvm/lib/Target/X86/X86PreTileConfig.cpp

static void reloadTileConfig(MachineInstr *MI, int FI,
                              const TargetRegisterInfo *TRI) {
   SmallSet<MachineInstr *, 8> CfgNeedInsert;
   SmallVector<MachineBasicBlock *, 8> WorkList;
   DenseMap<MachineBasicBlock *, BBInfo> BBVisitedInfo;
 
   MachineBasicBlock *MBB = MI->getParent();
   BBVisitedInfo[MBB] = BBInfo(CfgNeedInsert, MBB, MI);
 
+  // The entry BB is special, since it always has a ldtilecfg before AMX
+  // instruction. We don't need to check if its predecessor BBs have call.
+  // FIXME: This case happens only when the entry BB is in a loop. We need to
+  // hoist the first tile config point out of the loop in future.
+  BBVisitedInfo[MBB].HasCallBeforeAMX = true;
+
   WorkList.push_back(MBB);
   while (!WorkList.empty()) {
     MBB = WorkList.pop_back_val();
     for (auto I = MBB->succ_begin(), E = MBB->succ_end(); I != E; ++I) {
       if (!BBVisitedInfo.count(*I)) {
         BBVisitedInfo[*I] = BBInfo(CfgNeedInsert, *I);
         WorkList.push_back(*I);
       }

llvm/test/CodeGen/X86/AMX/amx-across-func.ll

 ; CHECK-NEXT:    movl %edi, %ebx
 ; CHECK-NEXT:    movl $buf, %r14d
 ; CHECK-NEXT:    movl $32, %r15d
 ; CHECK-NEXT:    movw $8, %bp
 ; CHECK-NEXT:    movl $buf+2048, %r12d
 ; CHECK-NEXT:    .p2align 4, 0x90
 ; CHECK-NEXT:  .LBB3_1: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    callq foo
-; CHECK-NEXT:    movb $1, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    movb $8, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    movw $8, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    ldtilecfg {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    testl %ebx, %ebx
 ; CHECK-NEXT:    jle .LBB3_3
 ; CHECK-NEXT:  # %bb.2: # in Loop: Header=BB3_1 Depth=1
 ; CHECK-NEXT:    vpxord %zmm0, %zmm0, %zmm0
 ; CHECK-NEXT:    vmovdqu64 %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)
 ; CHECK-NEXT:    ldtilecfg {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    tileloadd (%r14,%r15), %tmm0
 ; CHECK-NEXT:    movabsq $64, %rax
 ; CHECK-NEXT:    tilestored %tmm0, 1024(%rsp,%rax) # 1024-byte Folded Spill
 ; CHECK-NEXT:    vzeroupper
 ; CHECK-NEXT:    callq foo
 ; CHECK-NEXT:    ldtilecfg {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movabsq $64, %rax