[llvm] 1a276d1 - GlobalISel: Implement widenScalar for G_INSERT_VECTOR_ELT

[Matt Arsenault via llvm-commits]

Author: Matt Arsenault
Date: 2019-10-25T13:55:07-07:00
New Revision: 1a276d1e8c5da57a0c83d1b1d1a02ec0bcdb77d7

URL: https://github.com/llvm/llvm-project/commit/1a276d1e8c5da57a0c83d1b1d1a02ec0bcdb77d7
DIFF: https://github.com/llvm/llvm-project/commit/1a276d1e8c5da57a0c83d1b1d1a02ec0bcdb77d7.diff

LOG: GlobalISel: Implement widenScalar for G_INSERT_VECTOR_ELT

Added: 
    

Modified: 
    llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
    llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-insert-vector-elt.mir

Removed: 
    


################################################################################
diff  --git a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
index 21512e543878..68c8304d79f8 100644
--- a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
@@ -1789,10 +1789,35 @@ LegalizerHelper::widenScalar(MachineInstr &MI, unsigned TypeIdx, LLT WideTy) {
     if (TypeIdx != 2)
       return UnableToLegalize;
     Observer.changingInstr(MI);
+    // TODO: Probably should be zext
     widenScalarSrc(MI, WideTy, 2, TargetOpcode::G_SEXT);
     Observer.changedInstr(MI);
     return Legalized;
   }
+  case TargetOpcode::G_INSERT_VECTOR_ELT: {
+    if (TypeIdx == 1) {
+      Observer.changingInstr(MI);
+
+      Register VecReg = MI.getOperand(1).getReg();
+      LLT VecTy = MRI.getType(VecReg);
+      LLT WideVecTy = LLT::vector(VecTy.getNumElements(), WideTy);
+
+      widenScalarSrc(MI, WideVecTy, 1, TargetOpcode::G_ANYEXT);
+      widenScalarSrc(MI, WideTy, 2, TargetOpcode::G_ANYEXT);
+      widenScalarDst(MI, WideVecTy, 0);
+      Observer.changedInstr(MI);
+      return Legalized;
+    }
+
+    if (TypeIdx == 2) {
+      Observer.changingInstr(MI);
+      // TODO: Probably should be zext
+      widenScalarSrc(MI, WideTy, 3, TargetOpcode::G_SEXT);
+      Observer.changedInstr(MI);
+    }
+
+    return Legalized;
+  }
   case TargetOpcode::G_FADD:
   case TargetOpcode::G_FMUL:
   case TargetOpcode::G_FSUB:

diff  --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-insert-vector-elt.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-insert-vector-elt.mir
index df1cef761d27..0d35ec8c5032 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-insert-vector-elt.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-insert-vector-elt.mir
@@ -115,3 +115,51 @@ body: |
     %3:_(<16 x s64>) = G_INSERT_VECTOR_ELT %1, %0, %2
     S_ENDPGM 0, implicit %3
 ...
+
+---
+name: insert_vector_elt_0_v2s32_s8
+
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2
+
+    ; CHECK-LABEL: name: insert_vector_elt_0_v2s32_s8
+    ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr2
+    ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+    ; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[C]](s32)
+    ; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 24
+    ; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[COPY2]], [[C1]](s32)
+    ; CHECK: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SHL]], [[C1]](s32)
+    ; CHECK: [[IVEC:%[0-9]+]]:_(<2 x s32>) = G_INSERT_VECTOR_ELT [[COPY]], [[COPY1]](s32), [[ASHR]](s32)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[IVEC]](<2 x s32>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(s32) = COPY $vgpr2
+    %2:_(s8) = G_CONSTANT i8 0
+    %3:_(<2 x s32>) = G_INSERT_VECTOR_ELT %0, %1, %2
+    $vgpr0_vgpr1 = COPY %3
+...
+
+---
+name: insert_vector_elt_0_v2i8_i32
+
+body: |
+  bb.0:
+    liveins: $vgpr0
+
+    ; CHECK-LABEL: name: insert_vector_elt_0_v2i8_i32
+    ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; CHECK: [[DEF:%[0-9]+]]:_(<2 x s32>) = G_IMPLICIT_DEF
+    ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY [[DEF]](<2 x s32>)
+    ; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; CHECK: [[INSERT:%[0-9]+]]:_(<2 x s32>) = G_INSERT [[COPY1]], [[COPY2]](s32), 0
+    ; CHECK: [[COPY3:%[0-9]+]]:_(<2 x s32>) = COPY [[INSERT]](<2 x s32>)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[COPY3]](<2 x s32>)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s8) = G_TRUNC %0
+    %2:_(<2 x s8>) = G_IMPLICIT_DEF
+    %3:_(s32) = G_CONSTANT i32 0
+    %4:_(<2 x s8>) = G_INSERT_VECTOR_ELT %2, %1, %3
+    %5:_(<2 x s32>) = G_ANYEXT %4
+    $vgpr0_vgpr1 = COPY %5
+...