MachineLICM: Merge logic for implicit and explicit definitions.

llvm/lib/CodeGen/MachineLICM.cpp

@@ -553,24 +553,14 @@ void MachineLICMImpl::ProcessMI(MachineInstr *MI, BitVector &RUDefs,
       continue;
     }
 
-    if (MO.isImplicit()) {
-      for (MCRegUnit Unit : TRI->regunits(Reg))
-        RUClobbers.set(Unit);
-      if (!MO.isDead())
-        // Non-dead implicit def? This cannot be hoisted.
+    // FIXME: For now, avoid instructions with multiple defs, unless it's dead.
+    if (!MO.isDead()) {
+      if (Def)
         RuledOut = true;
-      // No need to check if a dead implicit def is also defined by
-      // another instruction.
-      continue;
+      else
+        Def = Reg;
     }
 
-    // FIXME: For now, avoid instructions with multiple defs, unless
-    // it's a dead implicit def.
-    if (Def)
-      RuledOut = true;
-    else
-      Def = Reg;
-
     // If we have already seen another instruction that defines the same
     // register, then this is not safe.  Two defs is indicated by setting a
     // PhysRegClobbers bit.

llvm/test/CodeGen/AArch64/mlicm-implicit-defs.mir

@@ -0,0 +1,103 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=aarch64 -run-pass machinelicm -verify-machineinstrs -o - %s | FileCheck %s
+# RUN: llc -mtriple=aarch64 -passes machinelicm -o - %s | FileCheck %s
+
+---
+name: unsafe_to_move
+tracksRegLiveness: true
+body: |
+  ; CHECK-LABEL: name: unsafe_to_move
+  ; CHECK: bb.0:
+  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
+  ; CHECK-NEXT:   liveins: $x0
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $x16 = COPY killed $x0
+  ; CHECK-NEXT:   B %bb.1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1:
+  ; CHECK-NEXT:   successors: %bb.1(0x40000000), %bb.2(0x40000000)
+  ; CHECK-NEXT:   liveins: $x16
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $x1 = COPY killed $x16
+  ; CHECK-NEXT:   $x2 = MOVi64imm 1024, implicit-def dead $x16
+  ; CHECK-NEXT:   $x16 = LDRXroX killed $x1, killed $x2, 0, 0
+  ; CHECK-NEXT:   $xzr = SUBSXri $x16, 0, 0, implicit-def $nzcv
+  ; CHECK-NEXT:   Bcc 1, %bb.1, implicit $nzcv
+  ; CHECK-NEXT:   B %bb.2
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2:
+  ; CHECK-NEXT:   liveins: $x1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $x0 = COPY killed $x1
+  ; CHECK-NEXT:   RET_ReallyLR
+  bb.0:
+    liveins: $x0
+    $x16 = COPY killed $x0
+    B %bb.1
+
+  bb.1:
+    liveins: $x16
+    $x1 = COPY killed $x16
+    /* MOVi64imm below mimics a pseudo instruction that doesn't have any */
+    /* unmodelled side effects, but uses x16 as a scratch register.      */
+    $x2 = MOVi64imm 1024, implicit-def dead $x16
+    $x16 = LDRXroX killed $x1, killed $x2, 0, 0
+    $xzr = SUBSXri $x16, 0, 0, implicit-def $nzcv
+    Bcc 1, %bb.1, implicit $nzcv
+    B %bb.2
+
+  bb.2:
+    liveins: $x1
+    $x0 = COPY killed $x1
+    RET_ReallyLR
+...
+
+---
+name: dead_implicit_def
+tracksRegLiveness: true
+body: |
+  ; CHECK-LABEL: name: dead_implicit_def
+  ; CHECK: bb.0:
+  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
+  ; CHECK-NEXT:   liveins: $x0
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $x12 = COPY killed $x0
+  ; CHECK-NEXT:   $x2 = MOVi64imm 1024, implicit-def dead $x16
+  ; CHECK-NEXT:   B %bb.1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1:
+  ; CHECK-NEXT:   successors: %bb.1(0x40000000), %bb.2(0x40000000)
+  ; CHECK-NEXT:   liveins: $x12, $x2
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $x1 = COPY killed $x12
+  ; CHECK-NEXT:   $x16 = LDRXroX killed $x1, $x2, 0, 0
+  ; CHECK-NEXT:   $xzr = SUBSXri $x16, 0, 0, implicit-def $nzcv
+  ; CHECK-NEXT:   Bcc 1, %bb.1, implicit $nzcv
+  ; CHECK-NEXT:   B %bb.2
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2:
+  ; CHECK-NEXT:   liveins: $x1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $x0 = COPY killed $x1
+  ; CHECK-NEXT:   RET_ReallyLR
+  bb.0:
+    liveins: $x0
+    $x12 = COPY killed $x0
+    B %bb.1
+
+  bb.1:
+    liveins: $x12
+    $x1 = COPY killed $x12
+    /* MOVi64imm below mimics a pseudo instruction that doesn't have any */
+    /* unmodelled side effects, but uses x16 as a scratch register.      */
+    $x2 = MOVi64imm 1024, implicit-def dead $x16
+    $x16 = LDRXroX killed $x1, killed $x2, 0, 0
+    $xzr = SUBSXri $x16, 0, 0, implicit-def $nzcv
+    Bcc 1, %bb.1, implicit $nzcv
+    B %bb.2
+
+  bb.2:
+    liveins: $x1
+    $x0 = COPY killed $x1
+    RET_ReallyLR
+...

llvm/test/CodeGen/AMDGPU/copy-to-reg-frameindex.ll

@@ -4,10 +4,10 @@
 define amdgpu_kernel void @copy_to_reg_frameindex(ptr addrspace(1) %out, i32 %a, i32 %b, i32 %c) {
 ; CHECK-LABEL: copy_to_reg_frameindex:
 ; CHECK:       ; %bb.0: ; %entry
+; CHECK-NEXT:    s_cmp_lt_u32 0, 16
 ; CHECK-NEXT:    ; implicit-def: $vgpr0
 ; CHECK-NEXT:  .LBB0_1: ; %loop
 ; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    s_cmp_lt_u32 0, 16
 ; CHECK-NEXT:    s_set_gpr_idx_on 0, gpr_idx(DST)
 ; CHECK-NEXT:    v_mov_b32_e32 v0, 0
 ; CHECK-NEXT:    s_set_gpr_idx_off

llvm/test/CodeGen/AMDGPU/mdt-preserving-crash.ll

@@ -16,27 +16,28 @@ define protected amdgpu_kernel void @_RSENC_PRInit______________________________
 ; CHECK-NEXT:    v_lshl_add_u32 v0, v0, 1, v0
 ; CHECK-NEXT:    v_cmp_ne_u32_e32 vcc, s4, v0
 ; CHECK-NEXT:    s_and_saveexec_b64 s[4:5], vcc
-; CHECK-NEXT:    s_cbranch_execz .LBB0_12
+; CHECK-NEXT:    s_cbranch_execz .LBB0_13
 ; CHECK-NEXT:  ; %bb.1: ; %if.end15
 ; CHECK-NEXT:    s_load_dword s4, s[8:9], 0x0
 ; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
 ; CHECK-NEXT:    s_bitcmp1_b32 s4, 0
 ; CHECK-NEXT:    s_cselect_b64 s[4:5], -1, 0
 ; CHECK-NEXT:    s_and_b64 vcc, exec, s[4:5]
-; CHECK-NEXT:    s_cbranch_vccnz .LBB0_12
-; CHECK-NEXT:  .LBB0_2: ; %while.cond.i
-; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    s_cbranch_vccnz .LBB0_13
+; CHECK-NEXT:  ; %bb.2: ; %lor.lhs.false17
 ; CHECK-NEXT:    s_cmp_eq_u32 s4, 0
-; CHECK-NEXT:    s_cbranch_scc1 .LBB0_2
-; CHECK-NEXT:  ; %bb.3: ; %if.end60
-; CHECK-NEXT:    s_cbranch_execz .LBB0_11
-; CHECK-NEXT:  ; %bb.4: ; %if.end5.i
-; CHECK-NEXT:    s_cbranch_scc0 .LBB0_11
-; CHECK-NEXT:  ; %bb.5: ; %if.end5.i314
-; CHECK-NEXT:    s_cbranch_scc0 .LBB0_11
-; CHECK-NEXT:  ; %bb.6: ; %if.end5.i338
-; CHECK-NEXT:    s_cbranch_scc0 .LBB0_11
-; CHECK-NEXT:  ; %bb.7: ; %if.end5.i362
+; CHECK-NEXT:  .LBB0_3: ; %while.cond.i
+; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    s_cbranch_scc1 .LBB0_3
+; CHECK-NEXT:  ; %bb.4: ; %if.end60
+; CHECK-NEXT:    s_cbranch_execz .LBB0_12
+; CHECK-NEXT:  ; %bb.5: ; %if.end5.i
+; CHECK-NEXT:    s_cbranch_scc0 .LBB0_12
+; CHECK-NEXT:  ; %bb.6: ; %if.end5.i314
+; CHECK-NEXT:    s_cbranch_scc0 .LBB0_12
+; CHECK-NEXT:  ; %bb.7: ; %if.end5.i338
+; CHECK-NEXT:    s_cbranch_scc0 .LBB0_12
+; CHECK-NEXT:  ; %bb.8: ; %if.end5.i362
 ; CHECK-NEXT:    v_mov_b32_e32 v0, 0
 ; CHECK-NEXT:    s_getpc_b64 s[4:5]
 ; CHECK-NEXT:    s_add_u32 s4, s4, _RSENC_gDcd_______________________________@rel32@lo+1157
@@ -46,23 +47,23 @@ define protected amdgpu_kernel void @_RSENC_PRInit______________________________
 ; CHECK-NEXT:    buffer_store_byte v0, v0, s[0:3], 0 offen
 ; CHECK-NEXT:    s_waitcnt vmcnt(1)
 ; CHECK-NEXT:    buffer_store_byte v1, off, s[0:3], 0 offset:257
-; CHECK-NEXT:    s_cbranch_scc0 .LBB0_11
-; CHECK-NEXT:  ; %bb.8: ; %if.end5.i400
+; CHECK-NEXT:    s_cbranch_scc0 .LBB0_12
+; CHECK-NEXT:  ; %bb.9: ; %if.end5.i400
 ; CHECK-NEXT:    flat_load_ubyte v0, v[0:1]
 ; CHECK-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; CHECK-NEXT:    v_cmp_eq_u16_e32 vcc, 0, v0
 ; CHECK-NEXT:    s_and_b64 exec, exec, vcc
-; CHECK-NEXT:    s_cbranch_execz .LBB0_11
-; CHECK-NEXT:  ; %bb.9: ; %if.then404
+; CHECK-NEXT:    s_cbranch_execz .LBB0_12
+; CHECK-NEXT:  ; %bb.10: ; %if.then404
 ; CHECK-NEXT:    s_movk_i32 s4, 0x1000
-; CHECK-NEXT:  .LBB0_10: ; %for.body564
+; CHECK-NEXT:  .LBB0_11: ; %for.body564
 ; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    s_sub_i32 s4, s4, 32
 ; CHECK-NEXT:    s_cmp_lg_u32 s4, 0
-; CHECK-NEXT:    s_cbranch_scc1 .LBB0_10
-; CHECK-NEXT:  .LBB0_11: ; %UnifiedUnreachableBlock
+; CHECK-NEXT:    s_cbranch_scc1 .LBB0_11
+; CHECK-NEXT:  .LBB0_12: ; %UnifiedUnreachableBlock
 ; CHECK-NEXT:    ; divergent unreachable
-; CHECK-NEXT:  .LBB0_12: ; %UnifiedReturnBlock
+; CHECK-NEXT:  .LBB0_13: ; %UnifiedReturnBlock
 ; CHECK-NEXT:    s_endpgm
 entry:
   %runtimeVersionCopy = alloca [128 x i8], align 16, addrspace(5)

llvm/test/CodeGen/RISCV/rvv/vxrm-insert-out-of-loop.ll

@@ -71,6 +71,7 @@ define void @test1(ptr nocapture noundef writeonly %dst, i32 noundef signext %i_
 ; RV32-NEXT:    or t1, t1, t3
 ; RV32-NEXT:    andi t1, t1, 1
 ; RV32-NEXT:    slli t2, t2, 1
+; RV32-NEXT:    csrwi vxrm, 0
 ; RV32-NEXT:    j .LBB0_10
 ; RV32-NEXT:  .LBB0_9: # %for.cond1.for.cond.cleanup3_crit_edge.us
 ; RV32-NEXT:    # in Loop: Header=BB0_10 Depth=1
@@ -93,7 +94,6 @@ define void @test1(ptr nocapture noundef writeonly %dst, i32 noundef signext %i_
 ; RV32-NEXT:    li t3, 0
 ; RV32-NEXT:    neg t4, t2
 ; RV32-NEXT:    and t4, t4, a6
-; RV32-NEXT:    csrwi vxrm, 0
 ; RV32-NEXT:    li t6, 0
 ; RV32-NEXT:    li t5, 0
 ; RV32-NEXT:    vsetvli s0, zero, e8, m2, ta, ma
@@ -471,6 +471,7 @@ define void @test1(ptr nocapture noundef writeonly %dst, i32 noundef signext %i_
 ; RV64-NEXT:    or t4, t4, t5
 ; RV64-NEXT:    andi t4, t4, 1
 ; RV64-NEXT:    mv t5, a0
+; RV64-NEXT:    csrwi vxrm, 0
 ; RV64-NEXT:    j .LBB0_6
 ; RV64-NEXT:  .LBB0_5: # %for.cond1.for.cond.cleanup3_crit_edge.us
 ; RV64-NEXT:    # in Loop: Header=BB0_6 Depth=1
@@ -493,7 +494,6 @@ define void @test1(ptr nocapture noundef writeonly %dst, i32 noundef signext %i_
 ; RV64-NEXT:    slli t6, t0, 28
 ; RV64-NEXT:    sub t6, t6, t1
 ; RV64-NEXT:    and t6, t6, a6
-; RV64-NEXT:    csrwi vxrm, 0
 ; RV64-NEXT:    mv s0, a2
 ; RV64-NEXT:    mv s1, a4
 ; RV64-NEXT:    mv s2, t5

llvm/test/CodeGen/X86/ins_subreg_coalesce-3.ll

@@ -22,40 +22,41 @@ define void @FontChange(i1 %foo) nounwind {
 ; CHECK-LABEL: FontChange:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    testb $1, %dil
-; CHECK-NEXT:    je .LBB0_9
+; CHECK-NEXT:    je .LBB0_10
 ; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb366
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb $1, %dil
 ; CHECK-NEXT:    jne .LBB0_1
 ; CHECK-NEXT:  # %bb.2: # %bb428
 ; CHECK-NEXT:    testb $1, %dil
-; CHECK-NEXT:    je .LBB0_9
+; CHECK-NEXT:    je .LBB0_10
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    cmpb $0, 0
 ; CHECK-NEXT:    .p2align 4
-; CHECK-NEXT:  .LBB0_3: # %bb650
+; CHECK-NEXT:  .LBB0_4: # %bb650
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    cmpb $0, 0
-; CHECK-NEXT:    je .LBB0_3
-; CHECK-NEXT:  # %bb.4: # %bb662
+; CHECK-NEXT:    je .LBB0_4
+; CHECK-NEXT:  # %bb.5: # %bb662
 ; CHECK-NEXT:    movl 0, %eax
 ; CHECK-NEXT:    movl %eax, %ecx
 ; CHECK-NEXT:    andl $57344, %ecx # imm = 0xE000
 ; CHECK-NEXT:    cmpl $8192, %ecx # imm = 0x2000
-; CHECK-NEXT:    jne .LBB0_9
-; CHECK-NEXT:  # %bb.5: # %bb4884
+; CHECK-NEXT:    jne .LBB0_10
+; CHECK-NEXT:  # %bb.6: # %bb4884
 ; CHECK-NEXT:    andl $7168, %eax # imm = 0x1C00
 ; CHECK-NEXT:    cmpl $1024, %eax # imm = 0x400
-; CHECK-NEXT:    jne .LBB0_9
-; CHECK-NEXT:  # %bb.6: # %bb4932
+; CHECK-NEXT:    jne .LBB0_10
+; CHECK-NEXT:  # %bb.7: # %bb4932
 ; CHECK-NEXT:    testb $1, %dil
-; CHECK-NEXT:    jne .LBB0_9
-; CHECK-NEXT:  # %bb.7: # %bb4940
+; CHECK-NEXT:    jne .LBB0_10
+; CHECK-NEXT:  # %bb.8: # %bb4940
 ; CHECK-NEXT:    movl 0, %eax
 ; CHECK-NEXT:    cmpl $160, %eax
-; CHECK-NEXT:    je .LBB0_9
-; CHECK-NEXT:  # %bb.8: # %bb4940
+; CHECK-NEXT:    je .LBB0_10
+; CHECK-NEXT:  # %bb.9: # %bb4940
 ; CHECK-NEXT:    cmpl $159, %eax
-; CHECK-NEXT:  .LBB0_9: # %bb4897
+; CHECK-NEXT:  .LBB0_10: # %bb4897
 ; CHECK-NEXT:    retq
 entry:
 	br i1 %foo, label %bb298, label %bb49