[AMDGPU][RegBankInfo] Promote scalar i16 and/or/xor to i32 (#131306)

See #64591

Author: Pierre-vh

llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp

@@ -2416,9 +2416,10 @@ void AMDGPURegisterBankInfo::applyMappingImpl(
     Register DstReg = MI.getOperand(0).getReg();
     LLT DstTy = MRI.getType(DstReg);
 
-    if (DstTy.getSizeInBits() == 1) {
-      const RegisterBank *DstBank =
+    const RegisterBank *DstBank =
         OpdMapper.getInstrMapping().getOperandMapping(0).BreakDown[0].RegBank;
+
+    if (DstTy.getSizeInBits() == 1) {
       if (DstBank == &AMDGPU::VCCRegBank)
         break;
 
@@ -2432,6 +2433,27 @@ void AMDGPURegisterBankInfo::applyMappingImpl(
       return;
     }
 
+    if (DstTy.getSizeInBits() == 16 && DstBank == &AMDGPU::SGPRRegBank) {
+      const LLT S32 = LLT::scalar(32);
+      MachineBasicBlock *MBB = MI.getParent();
+      MachineFunction *MF = MBB->getParent();
+      ApplyRegBankMapping ApplySALU(B, *this, MRI, &AMDGPU::SGPRRegBank);
+      LegalizerHelper Helper(*MF, ApplySALU, B);
+      // Widen to S32, but handle `G_XOR x, -1` differently. Legalizer widening
+      // will use a G_ANYEXT to extend the -1 which prevents matching G_XOR -1
+      // as "not".
+      if (MI.getOpcode() == AMDGPU::G_XOR &&
+          mi_match(MI.getOperand(2).getReg(), MRI, m_SpecificICstOrSplat(-1))) {
+        Helper.widenScalarSrc(MI, S32, 1, AMDGPU::G_ANYEXT);
+        Helper.widenScalarSrc(MI, S32, 2, AMDGPU::G_SEXT);
+        Helper.widenScalarDst(MI, S32);
+      } else {
+        if (Helper.widenScalar(MI, 0, S32) != LegalizerHelper::Legalized)
+          llvm_unreachable("widen scalar should have succeeded");
+      }
+      return;
+    }
+
     if (DstTy.getSizeInBits() != 64)
       break;
 

llvm/test/CodeGen/AMDGPU/GlobalISel/andn2.ll

@@ -391,20 +391,20 @@ define amdgpu_ps i16 @s_andn2_i16_commute(i16 inreg %src0, i16 inreg %src1) {
 define amdgpu_ps { i16, i16 } @s_andn2_i16_multi_use(i16 inreg %src0, i16 inreg %src1) {
 ; GCN-LABEL: s_andn2_i16_multi_use:
 ; GCN:       ; %bb.0:
-; GCN-NEXT:    s_xor_b32 s1, s3, -1
+; GCN-NEXT:    s_not_b32 s1, s3
 ; GCN-NEXT:    s_andn2_b32 s0, s2, s3
 ; GCN-NEXT:    ; return to shader part epilog
 ;
 ; GFX10-LABEL: s_andn2_i16_multi_use:
 ; GFX10:       ; %bb.0:
 ; GFX10-NEXT:    s_andn2_b32 s0, s2, s3
-; GFX10-NEXT:    s_xor_b32 s1, s3, -1
+; GFX10-NEXT:    s_not_b32 s1, s3
 ; GFX10-NEXT:    ; return to shader part epilog
 ;
 ; GFX11-LABEL: s_andn2_i16_multi_use:
 ; GFX11:       ; %bb.0:
 ; GFX11-NEXT:    s_and_not1_b32 s0, s2, s3
-; GFX11-NEXT:    s_xor_b32 s1, s3, -1
+; GFX11-NEXT:    s_not_b32 s1, s3
 ; GFX11-NEXT:    ; return to shader part epilog
   %not.src1 = xor i16 %src1, -1
   %and = and i16 %src0, %not.src1
@@ -482,14 +482,14 @@ define amdgpu_ps float @v_andn2_i16_sv(i16 inreg %src0, i16 %src1) {
 define amdgpu_ps float @v_andn2_i16_vs(i16 %src0, i16 inreg %src1) {
 ; GCN-LABEL: v_andn2_i16_vs:
 ; GCN:       ; %bb.0:
-; GCN-NEXT:    s_xor_b32 s0, s2, -1
+; GCN-NEXT:    s_not_b32 s0, s2
 ; GCN-NEXT:    v_and_b32_e32 v0, s0, v0
 ; GCN-NEXT:    v_and_b32_e32 v0, 0xffff, v0
 ; GCN-NEXT:    ; return to shader part epilog
 ;
 ; GFX10PLUS-LABEL: v_andn2_i16_vs:
 ; GFX10PLUS:       ; %bb.0:
-; GFX10PLUS-NEXT:    s_xor_b32 s0, s2, -1
+; GFX10PLUS-NEXT:    s_not_b32 s0, s2
 ; GFX10PLUS-NEXT:    v_and_b32_e32 v0, s0, v0
 ; GFX10PLUS-NEXT:    v_and_b32_e32 v0, 0xffff, v0
 ; GFX10PLUS-NEXT:    ; return to shader part epilog