GlobalISel/IRTranslator resetTargetOptions based on function attributes

[Petar.Avramovic]

Summary

Update TargetMachine.Options with function attributes before we start
to generate MIR instructions. This allows access to correct function
attributes via TargetMachine.Options(it used to access attributes of
function that was translated first).
This affects some existing tests with "no-nans-fp-math" attribute.
Follow-up on D87456.

llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp

bool IRTranslator::runOnMachineFunction(MachineFunction &CurMF) {
   }
   CLI = MF->getSubtarget().getCallLowering();
   CurBuilder->setMF(*MF);
   EntryBuilder->setMF(*MF);
   MRI = &MF->getRegInfo();
   DL = &F.getParent()->getDataLayout();
   ORE = std::make_unique<OptimizationRemarkEmitter>(&F);
   const TargetMachine &TM = MF->getTarget();
+  TM.resetTargetOptions(F);
   EnableOpts = OptLevel != CodeGenOpt::None && !skipFunction(F);
   FuncInfo.MF = MF;
   if (EnableOpts)
     FuncInfo.BPI = &getAnalysis<BranchProbabilityInfoWrapperPass>().getBPI();
   else
     FuncInfo.BPI = nullptr;
 
   const auto &TLI = *MF->getSubtarget().getTargetLowering();

llvm/test/CodeGen/AMDGPU/GlobalISel/fmed3.ll

 ; SI-NEXT:    s_mov_b64 s[8:9], s[2:3]
 ; SI-NEXT:    buffer_load_dword v2, v[0:1], s[8:11], 0 addr64
 ; SI-NEXT:    s_mov_b64 s[8:9], s[4:5]
 ; SI-NEXT:    buffer_load_dword v3, v[0:1], s[8:11], 0 addr64
 ; SI-NEXT:    s_mov_b64 s[8:9], s[6:7]
 ; SI-NEXT:    buffer_load_dword v4, v[0:1], s[8:11], 0 addr64
 ; SI-NEXT:    s_waitcnt vmcnt(2)
 ; SI-NEXT:    v_sub_f32_e32 v2, 0x80000000, v2
+; SI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; SI-NEXT:    s_waitcnt vmcnt(1)
+; SI-NEXT:    v_mul_f32_e32 v3, 1.0, v3
+; SI-NEXT:    v_min_f32_e32 v5, v2, v3
+; SI-NEXT:    v_max_f32_e32 v2, v2, v3
 ; SI-NEXT:    s_waitcnt vmcnt(0)
-; SI-NEXT:    v_med3_f32 v2, v2, v3, v4
+; SI-NEXT:    v_mul_f32_e32 v3, 1.0, v4
+; SI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; SI-NEXT:    v_min_f32_e32 v2, v2, v3
+; SI-NEXT:    v_mul_f32_e32 v3, 1.0, v5
+; SI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; SI-NEXT:    v_max_f32_e32 v2, v3, v2
 ; SI-NEXT:    s_mov_b64 s[2:3], s[10:11]
 ; SI-NEXT:    buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: v_test_no_global_nnans_med3_f32_pat0_srcmod0:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx8 s[0:7], s[0:1], 0x24
-; VI-NEXT:    v_lshlrev_b32_e32 v8, 2, v0
+; VI-NEXT:    v_lshlrev_b32_e32 v6, 2, v0
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v0, s2
 ; VI-NEXT:    v_mov_b32_e32 v1, s3
-; VI-NEXT:    v_add_u32_e32 v0, vcc, v0, v8
+; VI-NEXT:    v_add_u32_e32 v0, vcc, v0, v6
 ; VI-NEXT:    v_mov_b32_e32 v2, s4
 ; VI-NEXT:    v_addc_u32_e32 v1, vcc, 0, v1, vcc
 ; VI-NEXT:    v_mov_b32_e32 v3, s5
-; VI-NEXT:    v_add_u32_e32 v2, vcc, v2, v8
+; VI-NEXT:    v_add_u32_e32 v2, vcc, v2, v6
 ; VI-NEXT:    v_mov_b32_e32 v4, s6
 ; VI-NEXT:    v_addc_u32_e32 v3, vcc, 0, v3, vcc
 ; VI-NEXT:    v_mov_b32_e32 v5, s7
-; VI-NEXT:    v_add_u32_e32 v4, vcc, v4, v8
+; VI-NEXT:    v_add_u32_e32 v4, vcc, v4, v6
 ; VI-NEXT:    v_addc_u32_e32 v5, vcc, 0, v5, vcc
-; VI-NEXT:    flat_load_dword v0, v[0:1]
-; VI-NEXT:    flat_load_dword v1, v[2:3]
-; VI-NEXT:    flat_load_dword v2, v[4:5]
-; VI-NEXT:    v_mov_b32_e32 v7, s1
-; VI-NEXT:    v_mov_b32_e32 v6, s0
-; VI-NEXT:    v_add_u32_e32 v6, vcc, v6, v8
-; VI-NEXT:    v_addc_u32_e32 v7, vcc, 0, v7, vcc
+; VI-NEXT:    flat_load_dword v7, v[0:1]
+; VI-NEXT:    flat_load_dword v2, v[2:3]
+; VI-NEXT:    flat_load_dword v3, v[4:5]
+; VI-NEXT:    v_mov_b32_e32 v0, s0
+; VI-NEXT:    v_mov_b32_e32 v1, s1
+; VI-NEXT:    v_add_u32_e32 v0, vcc, v0, v6
+; VI-NEXT:    v_addc_u32_e32 v1, vcc, 0, v1, vcc
 ; VI-NEXT:    s_waitcnt vmcnt(2) lgkmcnt(2)
-; VI-NEXT:    v_sub_f32_e32 v0, 0x80000000, v0
+; VI-NEXT:    v_sub_f32_e32 v4, 0x80000000, v7
+; VI-NEXT:    s_waitcnt vmcnt(1) lgkmcnt(1)
+; VI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; VI-NEXT:    v_mul_f32_e32 v4, 1.0, v4
+; VI-NEXT:    v_min_f32_e32 v5, v4, v2
+; VI-NEXT:    v_max_f32_e32 v2, v4, v2
 ; VI-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
-; VI-NEXT:    v_med3_f32 v0, v0, v1, v2
-; VI-NEXT:    flat_store_dword v[6:7], v0
+; VI-NEXT:    v_mul_f32_e32 v3, 1.0, v3
+; VI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; VI-NEXT:    v_min_f32_e32 v2, v2, v3
+; VI-NEXT:    v_mul_f32_e32 v3, 1.0, v5
+; VI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; VI-NEXT:    v_max_f32_e32 v2, v3, v2
+; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_no_global_nnans_med3_f32_pat0_srcmod0:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_load_dwordx8 s[0:7], s[0:1], 0x24
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v1, v0, s[2:3]
 ; GFX9-NEXT:    global_load_dword v2, v0, s[4:5]
 ; GFX9-NEXT:    global_load_dword v3, v0, s[6:7]
 ; GFX9-NEXT:    s_waitcnt vmcnt(2)
 ; GFX9-NEXT:    v_sub_f32_e32 v1, 0x80000000, v1
+; GFX9-NEXT:    s_waitcnt vmcnt(1)
+; GFX9-NEXT:    v_max_f32_e32 v2, v2, v2
+; GFX9-NEXT:    v_max_f32_e32 v1, v1, v1
+; GFX9-NEXT:    v_min_f32_e32 v4, v1, v2
+; GFX9-NEXT:    v_max_f32_e32 v1, v1, v2
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    v_med3_f32 v1, v1, v2, v3
+; GFX9-NEXT:    v_max_f32_e32 v3, v3, v3
+; GFX9-NEXT:    v_max_f32_e32 v1, v1, v1
+; GFX9-NEXT:    v_min_f32_e32 v1, v1, v3
+; GFX9-NEXT:    v_max_f32_e32 v2, v4, v4
+; GFX9-NEXT:    v_max_f32_e32 v1, v1, v1
+; GFX9-NEXT:    v_max_f32_e32 v1, v2, v1
 ; GFX9-NEXT:    global_store_dword v0, v1, s[0:1]
 ; GFX9-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep0 = getelementptr float, float addrspace(1)* %aptr, i32 %tid
   %gep1 = getelementptr float, float addrspace(1)* %bptr, i32 %tid
   %gep2 = getelementptr float, float addrspace(1)* %cptr, i32 %tid
   %outgep = getelementptr float, float addrspace(1)* %out, i32 %tid
   %a = load volatile float, float addrspace(1)* %gep0

 ; SI-NEXT:    s_mov_b64 s[8:9], s[6:7]
 ; SI-NEXT:    buffer_load_dword v4, v[0:1], s[8:11], 0 addr64
 ; SI-NEXT:    s_waitcnt vmcnt(2)
 ; SI-NEXT:    v_add_f32_e32 v2, 1.0, v2
 ; SI-NEXT:    s_waitcnt vmcnt(1)
 ; SI-NEXT:    v_add_f32_e32 v3, 2.0, v3
 ; SI-NEXT:    s_waitcnt vmcnt(0)
 ; SI-NEXT:    v_add_f32_e32 v4, 4.0, v4
-; SI-NEXT:    v_med3_f32 v2, v2, v3, v4
+; SI-NEXT:    v_min_f32_e32 v5, v2, v3
+; SI-NEXT:    v_max_f32_e32 v2, v2, v3
+; SI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; SI-NEXT:    v_min_f32_e32 v2, v2, v4
+; SI-NEXT:    v_mul_f32_e32 v3, 1.0, v5
+; SI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; SI-NEXT:    v_max_f32_e32 v2, v3, v2
 ; SI-NEXT:    s_mov_b64 s[2:3], s[10:11]
 ; SI-NEXT:    buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: v_nnan_inputs_med3_f32_pat0:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx8 s[0:7], s[0:1], 0x24
 ; VI-NEXT:    v_lshlrev_b32_e32 v6, 2, v0

 ; VI-NEXT:    v_mov_b32_e32 v0, s0
 ; VI-NEXT:    v_mov_b32_e32 v1, s1
 ; VI-NEXT:    v_add_u32_e32 v0, vcc, v0, v6
 ; VI-NEXT:    v_addc_u32_e32 v1, vcc, 0, v1, vcc
 ; VI-NEXT:    s_waitcnt vmcnt(2) lgkmcnt(2)
 ; VI-NEXT:    v_add_f32_e32 v4, 1.0, v7
 ; VI-NEXT:    s_waitcnt vmcnt(1) lgkmcnt(1)
 ; VI-NEXT:    v_add_f32_e32 v2, 2.0, v2
+; VI-NEXT:    v_min_f32_e32 v5, v4, v2
+; VI-NEXT:    v_max_f32_e32 v2, v4, v2
 ; VI-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; VI-NEXT:    v_add_f32_e32 v3, 4.0, v3
-; VI-NEXT:    v_med3_f32 v2, v4, v2, v3
+; VI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; VI-NEXT:    v_min_f32_e32 v2, v2, v3
+; VI-NEXT:    v_mul_f32_e32 v3, 1.0, v5
+; VI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; VI-NEXT:    v_max_f32_e32 v2, v3, v2
 ; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_nnan_inputs_med3_f32_pat0:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_load_dwordx8 s[0:7], s[0:1], 0x24
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v1, v0, s[2:3]
 ; GFX9-NEXT:    global_load_dword v2, v0, s[4:5]
 ; GFX9-NEXT:    global_load_dword v3, v0, s[6:7]
 ; GFX9-NEXT:    s_waitcnt vmcnt(2)
 ; GFX9-NEXT:    v_add_f32_e32 v1, 1.0, v1
 ; GFX9-NEXT:    s_waitcnt vmcnt(1)
 ; GFX9-NEXT:    v_add_f32_e32 v2, 2.0, v2
+; GFX9-NEXT:    v_min_f32_e32 v4, v1, v2
+; GFX9-NEXT:    v_max_f32_e32 v1, v1, v2
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
 ; GFX9-NEXT:    v_add_f32_e32 v3, 4.0, v3
-; GFX9-NEXT:    v_med3_f32 v1, v1, v2, v3
+; GFX9-NEXT:    v_max_f32_e32 v1, v1, v1
+; GFX9-NEXT:    v_min_f32_e32 v1, v1, v3
+; GFX9-NEXT:    v_max_f32_e32 v2, v4, v4
+; GFX9-NEXT:    v_max_f32_e32 v1, v1, v1
+; GFX9-NEXT:    v_max_f32_e32 v1, v2, v1
 ; GFX9-NEXT:    global_store_dword v0, v1, s[0:1]
 ; GFX9-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep0 = getelementptr float, float addrspace(1)* %aptr, i32 %tid
   %gep1 = getelementptr float, float addrspace(1)* %bptr, i32 %tid
   %gep2 = getelementptr float, float addrspace(1)* %cptr, i32 %tid
   %outgep = getelementptr float, float addrspace(1)* %out, i32 %tid
   %a = load volatile float, float addrspace(1)* %gep0

 ; SI-NEXT:    s_mov_b64 s[8:9], s[2:3]
 ; SI-NEXT:    buffer_load_dword v2, v[0:1], s[8:11], 0 addr64
 ; SI-NEXT:    s_mov_b64 s[8:9], s[4:5]
 ; SI-NEXT:    buffer_load_dword v3, v[0:1], s[8:11], 0 addr64
 ; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    s_mov_b32 s3, s11
 ; SI-NEXT:    s_mov_b64 s[8:9], s[6:7]
 ; SI-NEXT:    buffer_load_dword v4, v[0:1], s[8:11], 0 addr64
+; SI-NEXT:    s_waitcnt vmcnt(2)
+; SI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
 ; SI-NEXT:    s_waitcnt vmcnt(1)
+; SI-NEXT:    v_mul_f32_e32 v3, 1.0, v3
 ; SI-NEXT:    v_min_f32_e32 v5, v2, v3
 ; SI-NEXT:    v_max_f32_e32 v2, v2, v3
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    v_mul_f32_e32 v3, 1.0, v4
 ; SI-NEXT:    buffer_store_dword v5, off, s[0:3], 0
-; SI-NEXT:    s_waitcnt vmcnt(1)
-; SI-NEXT:    v_min_f32_e32 v2, v2, v4
-; SI-NEXT:    v_max_f32_e32 v2, v5, v2
+; SI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; SI-NEXT:    v_min_f32_e32 v2, v2, v3
+; SI-NEXT:    v_mul_f32_e32 v3, 1.0, v5
+; SI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; SI-NEXT:    v_max_f32_e32 v2, v3, v2
 ; SI-NEXT:    s_mov_b64 s[2:3], s[10:11]
 ; SI-NEXT:    buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: v_test_safe_med3_f32_pat0_multi_use0:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx8 s[0:7], s[0:1], 0x24
 ; VI-NEXT:    v_lshlrev_b32_e32 v6, 2, v0

 ; VI-NEXT:    v_addc_u32_e32 v5, vcc, 0, v5, vcc
 ; VI-NEXT:    flat_load_dword v7, v[0:1]
 ; VI-NEXT:    flat_load_dword v2, v[2:3]
 ; VI-NEXT:    flat_load_dword v3, v[4:5]
 ; VI-NEXT:    v_mov_b32_e32 v0, s0
 ; VI-NEXT:    v_mov_b32_e32 v1, s1
 ; VI-NEXT:    v_add_u32_e32 v0, vcc, v0, v6
 ; VI-NEXT:    v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; VI-NEXT:    s_waitcnt vmcnt(2) lgkmcnt(2)
+; VI-NEXT:    v_mul_f32_e32 v4, 1.0, v7
 ; VI-NEXT:    s_waitcnt vmcnt(1) lgkmcnt(1)
-; VI-NEXT:    v_min_f32_e32 v4, v7, v2
-; VI-NEXT:    v_max_f32_e32 v2, v7, v2
+; VI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; VI-NEXT:    v_min_f32_e32 v5, v4, v2
+; VI-NEXT:    v_max_f32_e32 v2, v4, v2
 ; VI-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; VI-NEXT:    v_mul_f32_e32 v3, 1.0, v3
+; VI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
 ; VI-NEXT:    v_min_f32_e32 v2, v2, v3
-; VI-NEXT:    v_max_f32_e32 v2, v4, v2
-; VI-NEXT:    flat_store_dword v[0:1], v4
+; VI-NEXT:    v_mul_f32_e32 v3, 1.0, v5
+; VI-NEXT:    v_mul_f32_e32 v2, 1.0, v2
+; VI-NEXT:    v_max_f32_e32 v2, v3, v2
+; VI-NEXT:    flat_store_dword v[0:1], v5
 ; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_safe_med3_f32_pat0_multi_use0:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_load_dwordx8 s[0:7], s[0:1], 0x24
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v1, v0, s[2:3]
 ; GFX9-NEXT:    global_load_dword v2, v0, s[4:5]
 ; GFX9-NEXT:    global_load_dword v3, v0, s[6:7]
+; GFX9-NEXT:    s_waitcnt vmcnt(2)
+; GFX9-NEXT:    v_max_f32_e32 v1, v1, v1
 ; GFX9-NEXT:    s_waitcnt vmcnt(1)
+; GFX9-NEXT:    v_max_f32_e32 v2, v2, v2
 ; GFX9-NEXT:    v_min_f32_e32 v4, v1, v2
 ; GFX9-NEXT:    v_max_f32_e32 v1, v1, v2
 ; GFX9-NEXT:    global_store_dword v[0:1], v4, off
 ; GFX9-NEXT:    s_waitcnt vmcnt(1)
+; GFX9-NEXT:    v_max_f32_e32 v3, v3, v3
+; GFX9-NEXT:    v_max_f32_e32 v1, v1, v1
 ; GFX9-NEXT:    v_min_f32_e32 v1, v1, v3
-; GFX9-NEXT:    v_max_f32_e32 v1, v4, v1
+; GFX9-NEXT:    v_max_f32_e32 v2, v4, v4
+; GFX9-NEXT:    v_max_f32_e32 v1, v1, v1
+; GFX9-NEXT:    v_max_f32_e32 v1, v2, v1
 ; GFX9-NEXT:    global_store_dword v0, v1, s[0:1]
 ; GFX9-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep0 = getelementptr float, float addrspace(1)* %aptr, i32 %tid
   %gep1 = getelementptr float, float addrspace(1)* %bptr, i32 %tid
   %gep2 = getelementptr float, float addrspace(1)* %cptr, i32 %tid
   %outgep = getelementptr float, float addrspace(1)* %out, i32 %tid
   %a = load volatile float, float addrspace(1)* %gep0

llvm/test/CodeGen/AMDGPU/GlobalISel/frem.ll

 ; CI:       ; %bb.0:
 ; CI-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x9
 ; CI-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0xd
 ; CI-NEXT:    s_mov_b32 s10, -1
 ; CI-NEXT:    s_mov_b32 s11, 0xf000
 ; CI-NEXT:    s_mov_b64 s[2:3], s[10:11]
 ; CI-NEXT:    s_waitcnt lgkmcnt(0)
 ; CI-NEXT:    s_mov_b64 s[8:9], s[6:7]
-; CI-NEXT:    buffer_load_ushort v0, off, s[8:11], 0
 ; CI-NEXT:    buffer_load_ushort v1, off, s[0:3], 0 offset:8
+; CI-NEXT:    buffer_load_ushort v0, off, s[8:11], 0
+; CI-NEXT:    s_mov_b64 s[6:7], s[10:11]
 ; CI-NEXT:    s_waitcnt vmcnt(1)
-; CI-NEXT:    v_cvt_f32_f16_e32 v0, v0
-; CI-NEXT:    s_waitcnt vmcnt(0)
 ; CI-NEXT:    v_cvt_f32_f16_e32 v1, v1
-; CI-NEXT:    v_div_scale_f32 v2, s[0:1], v1, v1, v0
-; CI-NEXT:    v_div_scale_f32 v3, vcc, v0, v1, v0
-; CI-NEXT:    v_rcp_f32_e32 v4, v2
-; CI-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_MODE, 4, 2), 3
-; CI-NEXT:    v_fma_f32 v5, -v2, v4, 1.0
-; CI-NEXT:    v_fma_f32 v4, v5, v4, v4
-; CI-NEXT:    v_mul_f32_e32 v5, v3, v4
-; CI-NEXT:    v_fma_f32 v6, -v2, v5, v3
-; CI-NEXT:    v_fma_f32 v5, v6, v4, v5
-; CI-NEXT:    v_fma_f32 v2, -v2, v5, v3
-; CI-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_MODE, 4, 2), 0
-; CI-NEXT:    v_div_fmas_f32 v2, v2, v4, v5
-; CI-NEXT:    s_mov_b64 s[6:7], s[10:11]
-; CI-NEXT:    v_div_fixup_f32 v2, v2, v1, v0
+; CI-NEXT:    s_waitcnt vmcnt(0)
+; CI-NEXT:    v_cvt_f32_f16_e32 v0, v0
+; CI-NEXT:    v_rcp_f32_e32 v2, v1
+; CI-NEXT:    v_mul_f32_e32 v2, v0, v2
 ; CI-NEXT:    v_trunc_f32_e32 v2, v2
 ; CI-NEXT:    v_fma_f32 v0, -v2, v1, v0
-; CI-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_MODE, 2, 2), 0
 ; CI-NEXT:    v_cvt_f16_f32_e32 v0, v0
 ; CI-NEXT:    buffer_store_short v0, off, s[4:7], 0
 ; CI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: unsafe_frem_f16:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
 ; VI-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0x34
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v0, s6
 ; VI-NEXT:    s_add_u32 s0, s8, 8
 ; VI-NEXT:    v_mov_b32_e32 v1, s7
 ; VI-NEXT:    s_addc_u32 s1, s9, 0
 ; VI-NEXT:    flat_load_ushort v2, v[0:1]
 ; VI-NEXT:    v_mov_b32_e32 v0, s0
 ; VI-NEXT:    v_mov_b32_e32 v1, s1
 ; VI-NEXT:    flat_load_ushort v0, v[0:1]
-; VI-NEXT:    s_waitcnt vmcnt(1) lgkmcnt(1)
-; VI-NEXT:    v_cvt_f32_f16_e32 v1, v2
 ; VI-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
-; VI-NEXT:    v_cvt_f32_f16_e32 v3, v0
-; VI-NEXT:    v_rcp_f32_e32 v3, v3
-; VI-NEXT:    v_mul_f32_e32 v1, v1, v3
-; VI-NEXT:    v_cvt_f16_f32_e32 v1, v1
-; VI-NEXT:    v_div_fixup_f16 v1, v1, v0, v2
+; VI-NEXT:    v_rcp_f16_e32 v1, v0
+; VI-NEXT:    v_mul_f16_e32 v1, v2, v1
 ; VI-NEXT:    v_trunc_f16_e32 v1, v1
 ; VI-NEXT:    v_fma_f16 v2, -v1, v0, v2
 ; VI-NEXT:    v_mov_b32_e32 v0, s4
 ; VI-NEXT:    v_mov_b32_e32 v1, s5
 ; VI-NEXT:    flat_store_short v[0:1], v2
 ; VI-NEXT:    s_endpgm
    %gep2 = getelementptr half, half addrspace(1)* %in2, i32 4
    %r0 = load half, half addrspace(1)* %in1, align 4

 }
 
 define amdgpu_kernel void @unsafe_frem_f32(float addrspace(1)* %out, float addrspace(1)* %in1, float addrspace(1)* %in2) #1 {
 ; CI-LABEL: unsafe_frem_f32:
 ; CI:       ; %bb.0:
 ; CI-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x9
 ; CI-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0xd
 ; CI-NEXT:    s_waitcnt lgkmcnt(0)
-; CI-NEXT:    s_load_dword s2, s[6:7], 0x0
-; CI-NEXT:    s_load_dword s0, s[8:9], 0x4
-; CI-NEXT:    s_waitcnt lgkmcnt(0)
-; CI-NEXT:    v_mov_b32_e32 v0, s0
-; CI-NEXT:    v_div_scale_f32 v1, s[0:1], v0, v0, s2
-; CI-NEXT:    v_div_scale_f32 v2, vcc, s2, v0, s2
-; CI-NEXT:    v_rcp_f32_e32 v3, v1
-; CI-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_MODE, 4, 2), 3
-; CI-NEXT:    v_fma_f32 v4, -v1, v3, 1.0
-; CI-NEXT:    v_fma_f32 v3, v4, v3, v3
-; CI-NEXT:    v_mul_f32_e32 v4, v2, v3
-; CI-NEXT:    v_fma_f32 v5, -v1, v4, v2
-; CI-NEXT:    v_fma_f32 v4, v5, v3, v4
-; CI-NEXT:    v_fma_f32 v1, -v1, v4, v2
-; CI-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_MODE, 4, 2), 0
-; CI-NEXT:    v_div_fmas_f32 v1, v1, v3, v4
+; CI-NEXT:    s_load_dword s0, s[6:7], 0x0
+; CI-NEXT:    s_load_dword s1, s[8:9], 0x4
 ; CI-NEXT:    s_mov_b32 s6, -1
 ; CI-NEXT:    s_mov_b32 s7, 0xf000
-; CI-NEXT:    v_div_fixup_f32 v1, v1, v0, s2
-; CI-NEXT:    v_trunc_f32_e32 v1, v1
-; CI-NEXT:    v_fma_f32 v0, -v1, v0, s2
+; CI-NEXT:    s_waitcnt lgkmcnt(0)
+; CI-NEXT:    v_mov_b32_e32 v1, s0
+; CI-NEXT:    v_rcp_f32_e32 v0, s1
+; CI-NEXT:    v_mul_f32_e32 v0, s0, v0
+; CI-NEXT:    v_trunc_f32_e32 v0, v0
+; CI-NEXT:    v_fma_f32 v0, -v0, s1, v1
 ; CI-NEXT:    buffer_store_dword v0, off, s[4:7], 0
 ; CI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: unsafe_frem_f32:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
 ; VI-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0x34
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    s_load_dword s2, s[6:7], 0x0
-; VI-NEXT:    s_load_dword s0, s[8:9], 0x10
+; VI-NEXT:    s_load_dword s0, s[6:7], 0x0
+; VI-NEXT:    s_load_dword s1, s[8:9], 0x10
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v0, s0
-; VI-NEXT:    v_div_scale_f32 v1, s[0:1], v0, v0, s2
-; VI-NEXT:    v_div_scale_f32 v2, vcc, s2, v0, s2
-; VI-NEXT:    v_rcp_f32_e32 v3, v1
-; VI-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_MODE, 4, 2), 3
-; VI-NEXT:    v_fma_f32 v4, -v1, v3, 1.0
-; VI-NEXT:    v_fma_f32 v3, v4, v3, v3
-; VI-NEXT:    v_mul_f32_e32 v4, v2, v3
-; VI-NEXT:    v_fma_f32 v5, -v1, v4, v2
-; VI-NEXT:    v_fma_f32 v4, v5, v3, v4
-; VI-NEXT:    v_fma_f32 v1, -v1, v4, v2
-; VI-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_MODE, 4, 2), 0
-; VI-NEXT:    v_div_fmas_f32 v1, v1, v3, v4
-; VI-NEXT:    v_div_fixup_f32 v1, v1, v0, s2
-; VI-NEXT:    v_trunc_f32_e32 v1, v1
-; VI-NEXT:    v_fma_f32 v2, -v1, v0, s2
+; VI-NEXT:    v_mov_b32_e32 v1, s0
+; VI-NEXT:    v_rcp_f32_e32 v0, s1
+; VI-NEXT:    v_mul_f32_e32 v0, s0, v0
+; VI-NEXT:    v_trunc_f32_e32 v0, v0
+; VI-NEXT:    v_fma_f32 v2, -v0, s1, v1
 ; VI-NEXT:    v_mov_b32_e32 v0, s4
 ; VI-NEXT:    v_mov_b32_e32 v1, s5
 ; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
    %gep2 = getelementptr float, float addrspace(1)* %in2, i32 4
    %r0 = load float, float addrspace(1)* %in1, align 4
    %r1 = load float, float addrspace(1)* %gep2, align 4
    %r2 = frem float %r0, %r1

 ; CI-LABEL: unsafe_frem_f64:
 ; CI:       ; %bb.0:
 ; CI-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x9
 ; CI-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0xd
 ; CI-NEXT:    s_waitcnt lgkmcnt(0)
 ; CI-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; CI-NEXT:    s_load_dwordx2 s[2:3], s[8:9], 0x0
 ; CI-NEXT:    s_waitcnt lgkmcnt(0)
-; CI-NEXT:    v_mov_b32_e32 v0, s2
-; CI-NEXT:    v_mov_b32_e32 v1, s3
-; CI-NEXT:    v_div_scale_f64 v[2:3], s[2:3], v[0:1], v[0:1], s[0:1]
-; CI-NEXT:    v_div_scale_f64 v[8:9], vcc, s[0:1], v[0:1], s[0:1]
-; CI-NEXT:    v_rcp_f64_e32 v[4:5], v[2:3]
-; CI-NEXT:    v_fma_f64 v[6:7], -v[2:3], v[4:5], 1.0
-; CI-NEXT:    v_fma_f64 v[4:5], v[4:5], v[6:7], v[4:5]
-; CI-NEXT:    v_fma_f64 v[6:7], -v[2:3], v[4:5], 1.0
-; CI-NEXT:    v_fma_f64 v[4:5], v[4:5], v[6:7], v[4:5]
-; CI-NEXT:    v_mul_f64 v[6:7], v[8:9], v[4:5]
-; CI-NEXT:    v_fma_f64 v[2:3], -v[2:3], v[6:7], v[8:9]
-; CI-NEXT:    v_div_fmas_f64 v[2:3], v[2:3], v[4:5], v[6:7]
-; CI-NEXT:    v_div_fixup_f64 v[2:3], v[2:3], v[0:1], s[0:1]
-; CI-NEXT:    v_trunc_f64_e32 v[2:3], v[2:3]
-; CI-NEXT:    v_fma_f64 v[0:1], -v[2:3], v[0:1], s[0:1]
+; CI-NEXT:    v_mov_b32_e32 v3, s1
+; CI-NEXT:    v_rcp_f64_e32 v[0:1], s[2:3]
+; CI-NEXT:    v_mov_b32_e32 v2, s0
+; CI-NEXT:    v_mul_f64 v[0:1], s[0:1], v[0:1]
+; CI-NEXT:    v_trunc_f64_e32 v[0:1], v[0:1]
+; CI-NEXT:    v_fma_f64 v[0:1], -v[0:1], s[2:3], v[2:3]
 ; CI-NEXT:    v_mov_b32_e32 v2, s4
 ; CI-NEXT:    v_mov_b32_e32 v3, s5
 ; CI-NEXT:    flat_store_dwordx2 v[2:3], v[0:1]
 ; CI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: unsafe_frem_f64:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
 ; VI-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0x34
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; VI-NEXT:    s_load_dwordx2 s[2:3], s[8:9], 0x0
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v0, s2
-; VI-NEXT:    v_mov_b32_e32 v1, s3
-; VI-NEXT:    v_div_scale_f64 v[2:3], s[2:3], v[0:1], v[0:1], s[0:1]
-; VI-NEXT:    v_div_scale_f64 v[8:9], vcc, s[0:1], v[0:1], s[0:1]
-; VI-NEXT:    v_rcp_f64_e32 v[4:5], v[2:3]
-; VI-NEXT:    v_fma_f64 v[6:7], -v[2:3], v[4:5], 1.0
-; VI-NEXT:    v_fma_f64 v[4:5], v[4:5], v[6:7], v[4:5]
-; VI-NEXT:    v_fma_f64 v[6:7], -v[2:3], v[4:5], 1.0
-; VI-NEXT:    v_fma_f64 v[4:5], v[4:5], v[6:7], v[4:5]
-; VI-NEXT:    v_mul_f64 v[6:7], v[8:9], v[4:5]
-; VI-NEXT:    v_fma_f64 v[2:3], -v[2:3], v[6:7], v[8:9]
-; VI-NEXT:    v_div_fmas_f64 v[2:3], v[2:3], v[4:5], v[6:7]
-; VI-NEXT:    v_div_fixup_f64 v[2:3], v[2:3], v[0:1], s[0:1]
-; VI-NEXT:    v_trunc_f64_e32 v[2:3], v[2:3]
-; VI-NEXT:    v_fma_f64 v[0:1], -v[2:3], v[0:1], s[0:1]
+; VI-NEXT:    v_mov_b32_e32 v3, s1
+; VI-NEXT:    v_rcp_f64_e32 v[0:1], s[2:3]
+; VI-NEXT:    v_mov_b32_e32 v2, s0
+; VI-NEXT:    v_mul_f64 v[0:1], s[0:1], v[0:1]
+; VI-NEXT:    v_trunc_f64_e32 v[0:1], v[0:1]
+; VI-NEXT:    v_fma_f64 v[0:1], -v[0:1], s[2:3], v[2:3]
 ; VI-NEXT:    v_mov_b32_e32 v2, s4
 ; VI-NEXT:    v_mov_b32_e32 v3, s5
 ; VI-NEXT:    flat_store_dwordx2 v[2:3], v[0:1]
 ; VI-NEXT:    s_endpgm
                              double addrspace(1)* %in2) #1 {
    %r0 = load double, double addrspace(1)* %in1, align 8
    %r1 = load double, double addrspace(1)* %in2, align 8
    %r2 = frem double %r0, %r1