[AMDGPU][GlobalISel] Save a copy in one case of addrspacecast (#104789)

Refactor legalization of addrspacecast local/private -> flat to avoid
building a copy in the nonnull case.

Author: jayfoad

llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp

@@ -2368,25 +2368,30 @@ bool AMDGPULegalizerInfo::legalizeAddrSpaceCast(
   if (DestAS == AMDGPUAS::FLAT_ADDRESS &&
       (SrcAS == AMDGPUAS::LOCAL_ADDRESS ||
        SrcAS == AMDGPUAS::PRIVATE_ADDRESS)) {
-    Register ApertureReg = getSegmentAperture(SrcAS, MRI, B);
-    if (!ApertureReg.isValid())
-      return false;
+    auto castLocalOrPrivateToFlat = [&](const DstOp &Dst) -> Register {
+      Register ApertureReg = getSegmentAperture(SrcAS, MRI, B);
+      if (!ApertureReg.isValid())
+        return false;
 
-    // Coerce the type of the low half of the result so we can use merge_values.
-    Register SrcAsInt = B.buildPtrToInt(S32, Src).getReg(0);
+      // Coerce the type of the low half of the result so we can use
+      // merge_values.
+      Register SrcAsInt = B.buildPtrToInt(S32, Src).getReg(0);
 
-    // TODO: Should we allow mismatched types but matching sizes in merges to
-    // avoid the ptrtoint?
-    auto BuildPtr = B.buildMergeLikeInstr(DstTy, {SrcAsInt, ApertureReg});
+      // TODO: Should we allow mismatched types but matching sizes in merges to
+      // avoid the ptrtoint?
+      return B.buildMergeLikeInstr(Dst, {SrcAsInt, ApertureReg}).getReg(0);
+    };
 
     // For llvm.amdgcn.addrspacecast.nonnull we can always assume non-null, for
     // G_ADDRSPACE_CAST we need to guess.
     if (isa<GIntrinsic>(MI) || isKnownNonNull(Src, MRI, TM, SrcAS)) {
-      B.buildCopy(Dst, BuildPtr);
+      castLocalOrPrivateToFlat(Dst);
       MI.eraseFromParent();
       return true;
     }
 
+    Register BuildPtr = castLocalOrPrivateToFlat(DstTy);
+
     auto SegmentNull = B.buildConstant(SrcTy, TM.getNullPointerValue(SrcAS));
     auto FlatNull = B.buildConstant(DstTy, TM.getNullPointerValue(DestAS));
 

llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-addrspacecast.mir

@@ -509,16 +509,14 @@ body: |
     ; SIVI-NEXT: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[PTR_ADD]](p4) :: (dereferenceable invariant load (s32), addrspace 4)
     ; SIVI-NEXT: [[PTRTOINT:%[0-9]+]]:_(s32) = G_PTRTOINT [[FRAME_INDEX]](p5)
     ; SIVI-NEXT: [[MV:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[PTRTOINT]](s32), [[LOAD]](s32)
-    ; SIVI-NEXT: [[COPY2:%[0-9]+]]:_(p0) = COPY [[MV]](p0)
-    ; SIVI-NEXT: $vgpr0_vgpr1 = COPY [[COPY2]](p0)
+    ; SIVI-NEXT: $vgpr0_vgpr1 = COPY [[MV]](p0)
     ; GFX9-LABEL: name: test_addrspacecast_p5_fi_to_p0
     ; GFX9: [[FRAME_INDEX:%[0-9]+]]:_(p5) = G_FRAME_INDEX %stack.0
     ; GFX9-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64(s64) = S_MOV_B64 $src_private_base
     ; GFX9-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[S_MOV_B64_]](s64)
     ; GFX9-NEXT: [[PTRTOINT:%[0-9]+]]:_(s32) = G_PTRTOINT [[FRAME_INDEX]](p5)
     ; GFX9-NEXT: [[MV:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[PTRTOINT]](s32), [[UV1]](s32)
-    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY [[MV]](p0)
-    ; GFX9-NEXT: $vgpr0_vgpr1 = COPY [[COPY]](p0)
+    ; GFX9-NEXT: $vgpr0_vgpr1 = COPY [[MV]](p0)
     %0:_(p5) = G_FRAME_INDEX %stack.0
     %1:_(p0) = G_ADDRSPACE_CAST %0
     $vgpr0_vgpr1 = COPY %1