[llvm] 146c782 - [GlobalISel][Legalizer] Support reducing load/store width in big endian order

[Matt Arsenault via llvm-commits]

Author: Sheng
Date: 2022-02-07T20:06:17-05:00
New Revision: 146c7820d9b67eea4577b59d7dce9601d774cf66

URL: https://github.com/llvm/llvm-project/commit/146c7820d9b67eea4577b59d7dce9601d774cf66
DIFF: https://github.com/llvm/llvm-project/commit/146c7820d9b67eea4577b59d7dce9601d774cf66.diff

LOG: [GlobalISel][Legalizer] Support reducing load/store width in big endian order

Added: 
    

Modified: 
    llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
    llvm/test/CodeGen/M68k/GlobalISel/legalize-load-store.mir

Removed: 
    


################################################################################
diff  --git a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
index 37bc8a65dc7c3..0c16eae34d46b 100644
--- a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
@@ -4096,13 +4096,14 @@ LegalizerHelper::reduceLoadStoreWidth(GLoadStore &LdStMI, unsigned TypeIdx,
   // is a load, return the new registers in ValRegs. For a store, each elements
   // of ValRegs should be PartTy. Returns the next offset that needs to be
   // handled.
+  bool isBigEndian = MIRBuilder.getDataLayout().isBigEndian();
   auto MMO = LdStMI.getMMO();
   auto splitTypePieces = [=](LLT PartTy, SmallVectorImpl<Register> &ValRegs,
-                             unsigned Offset) -> unsigned {
+                             unsigned NumParts, unsigned Offset) -> unsigned {
     MachineFunction &MF = MIRBuilder.getMF();
     unsigned PartSize = PartTy.getSizeInBits();
     for (unsigned Idx = 0, E = NumParts; Idx != E && Offset < TotalSize;
-         Offset += PartSize, ++Idx) {
+         ++Idx) {
       unsigned ByteOffset = Offset / 8;
       Register NewAddrReg;
 
@@ -4118,16 +4119,19 @@ LegalizerHelper::reduceLoadStoreWidth(GLoadStore &LdStMI, unsigned TypeIdx,
       } else {
         MIRBuilder.buildStore(ValRegs[Idx], NewAddrReg, *NewMMO);
       }
+      Offset = isBigEndian ? Offset - PartSize : Offset + PartSize;
     }
 
     return Offset;
   };
 
-  unsigned HandledOffset = splitTypePieces(NarrowTy, NarrowRegs, 0);
+  unsigned Offset = isBigEndian ? TotalSize - NarrowTy.getSizeInBits() : 0;
+  unsigned HandledOffset =
+      splitTypePieces(NarrowTy, NarrowRegs, NumParts, Offset);
 
   // Handle the rest of the register if this isn't an even type breakdown.
   if (LeftoverTy.isValid())
-    splitTypePieces(LeftoverTy, NarrowLeftoverRegs, HandledOffset);
+    splitTypePieces(LeftoverTy, NarrowLeftoverRegs, NumLeftover, HandledOffset);
 
   if (IsLoad) {
     insertParts(ValReg, ValTy, NarrowTy, NarrowRegs,

diff  --git a/llvm/test/CodeGen/M68k/GlobalISel/legalize-load-store.mir b/llvm/test/CodeGen/M68k/GlobalISel/legalize-load-store.mir
index fb3d0f9ae566b..9a38e1ea320a3 100644
--- a/llvm/test/CodeGen/M68k/GlobalISel/legalize-load-store.mir
+++ b/llvm/test/CodeGen/M68k/GlobalISel/legalize-load-store.mir
@@ -78,16 +78,16 @@ body:             |
     ; CHECK-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 2
     ; CHECK-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 3
     ; CHECK-NEXT: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 4
-    ; CHECK-NEXT: G_STORE [[C]](s32), [[LOAD]](p0) :: (store (s32), align 16)
-    ; CHECK-NEXT: [[C4:%[0-9]+]]:_(s32) = G_CONSTANT i32 4
+    ; CHECK-NEXT: [[C4:%[0-9]+]]:_(s32) = G_CONSTANT i32 12
     ; CHECK-NEXT: [[PTR_ADD:%[0-9]+]]:_(p0) = G_PTR_ADD [[LOAD]], [[C4]](s32)
-    ; CHECK-NEXT: G_STORE [[C1]](s32), [[PTR_ADD]](p0) :: (store (s32) into unknown-address + 4)
+    ; CHECK-NEXT: G_STORE [[C]](s32), [[PTR_ADD]](p0) :: (store (s32) into unknown-address + 12)
     ; CHECK-NEXT: [[C5:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
     ; CHECK-NEXT: [[PTR_ADD1:%[0-9]+]]:_(p0) = G_PTR_ADD [[LOAD]], [[C5]](s32)
-    ; CHECK-NEXT: G_STORE [[C2]](s32), [[PTR_ADD1]](p0) :: (store (s32) into unknown-address + 8, align 8)
-    ; CHECK-NEXT: [[C6:%[0-9]+]]:_(s32) = G_CONSTANT i32 12
+    ; CHECK-NEXT: G_STORE [[C1]](s32), [[PTR_ADD1]](p0) :: (store (s32) into unknown-address + 8, align 8)
+    ; CHECK-NEXT: [[C6:%[0-9]+]]:_(s32) = G_CONSTANT i32 4
     ; CHECK-NEXT: [[PTR_ADD2:%[0-9]+]]:_(p0) = G_PTR_ADD [[LOAD]], [[C6]](s32)
-    ; CHECK-NEXT: G_STORE [[C3]](s32), [[PTR_ADD2]](p0) :: (store (s32) into unknown-address + 12)
+    ; CHECK-NEXT: G_STORE [[C2]](s32), [[PTR_ADD2]](p0) :: (store (s32) into unknown-address + 4)
+    ; CHECK-NEXT: G_STORE [[C3]](s32), [[LOAD]](p0) :: (store (s32), align 16)
     ; CHECK-NEXT: RTS
     %1:_(p0) = G_FRAME_INDEX %fixed-stack.0
     %0:_(p0) = G_LOAD %1(p0) :: (load (p0) from %fixed-stack.0, align 8)