GlobalISel: Implement widenScalar for saturating add/sub

Add a placeholder legality rule for AMDGPU until the rest of the
actions are handled.

diff --git a/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h b/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h
index 0fe1d60..058aacf 100644 (file)
--- a/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h
+++ b/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h
@@ -163,6 +163,8 @@ private:
   widenScalarExtract(MachineInstr &MI, unsigned TypeIdx, LLT WideTy);
   LegalizeResult
   widenScalarInsert(MachineInstr &MI, unsigned TypeIdx, LLT WideTy);
+  LegalizeResult widenScalarAddSubSat(MachineInstr &MI, unsigned TypeIdx,
+                                      LLT WideTy);
 
   /// Helper function to split a wide generic register into bitwise blocks with
   /// the given Type (which implies the number of blocks needed). The generic

diff --git a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
index 3859065..7cd52df 100644 (file)
--- a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
@@ -1639,6 +1639,44 @@ LegalizerHelper::widenScalarInsert(MachineInstr &MI, unsigned TypeIdx,
 }
 
 LegalizerHelper::LegalizeResult
+LegalizerHelper::widenScalarAddSubSat(MachineInstr &MI, unsigned TypeIdx,
+                                      LLT WideTy) {
+  bool IsSigned = MI.getOpcode() == TargetOpcode::G_SADDSAT ||
+                  MI.getOpcode() == TargetOpcode::G_SSUBSAT;
+  // We can convert this to:
+  //   1. Any extend iN to iM
+  //   2. SHL by M-N
+  //   3. [US][ADD|SUB]SAT
+  //   4. L/ASHR by M-N
+  //
+  // It may be more efficient to lower this to a min and a max operation in
+  // the higher precision arithmetic if the promoted operation isn't legal,
+  // but this decision is up to the target's lowering request.
+  Register DstReg = MI.getOperand(0).getReg();
+
+  unsigned NewBits = WideTy.getScalarSizeInBits();
+  unsigned SHLAmount = NewBits - MRI.getType(DstReg).getScalarSizeInBits();
+
+  auto LHS = MIRBuilder.buildAnyExt(WideTy, MI.getOperand(1));
+  auto RHS = MIRBuilder.buildAnyExt(WideTy, MI.getOperand(2));
+  auto ShiftK = MIRBuilder.buildConstant(WideTy, SHLAmount);
+  auto ShiftL = MIRBuilder.buildShl(WideTy, LHS, ShiftK);
+  auto ShiftR = MIRBuilder.buildShl(WideTy, RHS, ShiftK);
+
+  auto WideInst = MIRBuilder.buildInstr(MI.getOpcode(), {WideTy},
+                                        {ShiftL, ShiftR}, MI.getFlags());
+
+  // Use a shift that will preserve the number of sign bits when the trunc is
+  // folded away.
+  auto Result = IsSigned ? MIRBuilder.buildAShr(WideTy, WideInst, ShiftK)
+                         : MIRBuilder.buildLShr(WideTy, WideInst, ShiftK);
+
+  MIRBuilder.buildTrunc(DstReg, Result);
+  MI.eraseFromParent();
+  return Legalized;
+}
+
+LegalizerHelper::LegalizeResult
 LegalizerHelper::widenScalar(MachineInstr &MI, unsigned TypeIdx, LLT WideTy) {
   switch (MI.getOpcode()) {
   default:
@@ -1674,6 +1712,11 @@ LegalizerHelper::widenScalar(MachineInstr &MI, unsigned TypeIdx, LLT WideTy) {
     MI.eraseFromParent();
     return Legalized;
   }
+  case TargetOpcode::G_SADDSAT:
+  case TargetOpcode::G_SSUBSAT:
+  case TargetOpcode::G_UADDSAT:
+  case TargetOpcode::G_USUBSAT:
+    return widenScalarAddSubSat(MI, TypeIdx, WideTy);
   case TargetOpcode::G_CTTZ:
   case TargetOpcode::G_CTTZ_ZERO_UNDEF:
   case TargetOpcode::G_CTLZ:

diff --git a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
index 0802f2a..2976794 100644 (file)
--- a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
@@ -1427,6 +1427,12 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST_,
     SextInReg.lowerFor({{S32}, {S64}});
   }
 
+  // FIXME: Placeholder rule. Really depends on whether the clamp modifier is
+  // available, and is selectively legal for s16, s32, v2s16.
+  getActionDefinitionsBuilder({G_SADDSAT, G_SSUBSAT, G_UADDSAT, G_USUBSAT})
+    .scalarize(0)
+    .clampScalar(0, S16, S32);
+
   SextInReg
     .scalarize(0)
     .clampScalar(0, S32, S64)

diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-saddsat.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-saddsat.mir
index 2506452..50b6392 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-saddsat.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-saddsat.mir
@@ -14,25 +14,49 @@ body: |
     ; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX6: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX6: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX6: [[SADDSAT:%[0-9]+]]:_(s7) = G_SADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SADDSAT]](s7)
-    ; GFX6: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX6: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX6: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX6: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX6: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX6: [[SADDSAT:%[0-9]+]]:_(s16) = G_SADDSAT [[SHL]], [[SHL1]]
+    ; GFX6: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[C]](s16)
+    ; GFX6: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[SADDSAT]](s16)
+    ; GFX6: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SEXT]], [[ZEXT]](s32)
+    ; GFX6: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[ASHR]](s32)
+    ; GFX6: [[TRUNC3:%[0-9]+]]:_(s7) = G_TRUNC [[TRUNC2]](s16)
+    ; GFX6: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC3]](s7)
+    ; GFX6: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX8-LABEL: name: saddsat_s7
     ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX8: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX8: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX8: [[SADDSAT:%[0-9]+]]:_(s7) = G_SADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SADDSAT]](s7)
-    ; GFX8: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX8: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX8: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX8: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX8: [[SADDSAT:%[0-9]+]]:_(s16) = G_SADDSAT [[SHL]], [[SHL1]]
+    ; GFX8: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SADDSAT]], [[C]](s16)
+    ; GFX8: [[TRUNC2:%[0-9]+]]:_(s7) = G_TRUNC [[ASHR]](s16)
+    ; GFX8: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s7)
+    ; GFX8: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX9-LABEL: name: saddsat_s7
     ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX9: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX9: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX9: [[SADDSAT:%[0-9]+]]:_(s7) = G_SADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SADDSAT]](s7)
-    ; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX9: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX9: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX9: [[SADDSAT:%[0-9]+]]:_(s16) = G_SADDSAT [[SHL]], [[SHL1]]
+    ; GFX9: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SADDSAT]], [[C]](s16)
+    ; GFX9: [[TRUNC2:%[0-9]+]]:_(s7) = G_TRUNC [[ASHR]](s16)
+    ; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s7)
+    ; GFX9: $vgpr0 = COPY [[ANYEXT2]](s32)
     %0:_(s32) = COPY $vgpr0
     %1:_(s32) = COPY $vgpr1
     %2:_(s7) = G_TRUNC %0
@@ -53,25 +77,49 @@ body: |
     ; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX6: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX6: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX6: [[SADDSAT:%[0-9]+]]:_(s8) = G_SADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SADDSAT]](s8)
-    ; GFX6: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX6: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX6: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX6: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX6: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX6: [[SADDSAT:%[0-9]+]]:_(s16) = G_SADDSAT [[SHL]], [[SHL1]]
+    ; GFX6: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[C]](s16)
+    ; GFX6: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[SADDSAT]](s16)
+    ; GFX6: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SEXT]], [[ZEXT]](s32)
+    ; GFX6: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[ASHR]](s32)
+    ; GFX6: [[TRUNC3:%[0-9]+]]:_(s8) = G_TRUNC [[TRUNC2]](s16)
+    ; GFX6: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC3]](s8)
+    ; GFX6: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX8-LABEL: name: saddsat_s8
     ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX8: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX8: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX8: [[SADDSAT:%[0-9]+]]:_(s8) = G_SADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SADDSAT]](s8)
-    ; GFX8: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX8: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX8: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX8: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX8: [[SADDSAT:%[0-9]+]]:_(s16) = G_SADDSAT [[SHL]], [[SHL1]]
+    ; GFX8: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SADDSAT]], [[C]](s16)
+    ; GFX8: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[ASHR]](s16)
+    ; GFX8: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s8)
+    ; GFX8: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX9-LABEL: name: saddsat_s8
     ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX9: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX9: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX9: [[SADDSAT:%[0-9]+]]:_(s8) = G_SADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SADDSAT]](s8)
-    ; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX9: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX9: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX9: [[SADDSAT:%[0-9]+]]:_(s16) = G_SADDSAT [[SHL]], [[SHL1]]
+    ; GFX9: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SADDSAT]], [[C]](s16)
+    ; GFX9: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[ASHR]](s16)
+    ; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s8)
+    ; GFX9: $vgpr0 = COPY [[ANYEXT2]](s32)
     %0:_(s32) = COPY $vgpr0
     %1:_(s32) = COPY $vgpr1
     %2:_(s8) = G_TRUNC %0

diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ssubsat.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ssubsat.mir
index 53c9ba8..3a4cbb1 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ssubsat.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ssubsat.mir
@@ -14,25 +14,49 @@ body: |
     ; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX6: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX6: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX6: [[SSUBSAT:%[0-9]+]]:_(s7) = G_SSUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SSUBSAT]](s7)
-    ; GFX6: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX6: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX6: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX6: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX6: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX6: [[SSUBSAT:%[0-9]+]]:_(s16) = G_SSUBSAT [[SHL]], [[SHL1]]
+    ; GFX6: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[C]](s16)
+    ; GFX6: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[SSUBSAT]](s16)
+    ; GFX6: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SEXT]], [[ZEXT]](s32)
+    ; GFX6: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[ASHR]](s32)
+    ; GFX6: [[TRUNC3:%[0-9]+]]:_(s7) = G_TRUNC [[TRUNC2]](s16)
+    ; GFX6: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC3]](s7)
+    ; GFX6: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX8-LABEL: name: ssubsat_s7
     ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX8: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX8: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX8: [[SSUBSAT:%[0-9]+]]:_(s7) = G_SSUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SSUBSAT]](s7)
-    ; GFX8: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX8: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX8: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX8: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX8: [[SSUBSAT:%[0-9]+]]:_(s16) = G_SSUBSAT [[SHL]], [[SHL1]]
+    ; GFX8: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SSUBSAT]], [[C]](s16)
+    ; GFX8: [[TRUNC2:%[0-9]+]]:_(s7) = G_TRUNC [[ASHR]](s16)
+    ; GFX8: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s7)
+    ; GFX8: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX9-LABEL: name: ssubsat_s7
     ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX9: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX9: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX9: [[SSUBSAT:%[0-9]+]]:_(s7) = G_SSUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SSUBSAT]](s7)
-    ; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX9: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX9: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX9: [[SSUBSAT:%[0-9]+]]:_(s16) = G_SSUBSAT [[SHL]], [[SHL1]]
+    ; GFX9: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SSUBSAT]], [[C]](s16)
+    ; GFX9: [[TRUNC2:%[0-9]+]]:_(s7) = G_TRUNC [[ASHR]](s16)
+    ; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s7)
+    ; GFX9: $vgpr0 = COPY [[ANYEXT2]](s32)
     %0:_(s32) = COPY $vgpr0
     %1:_(s32) = COPY $vgpr1
     %2:_(s7) = G_TRUNC %0
@@ -53,25 +77,49 @@ body: |
     ; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX6: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX6: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX6: [[SSUBSAT:%[0-9]+]]:_(s8) = G_SSUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SSUBSAT]](s8)
-    ; GFX6: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX6: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX6: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX6: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX6: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX6: [[SSUBSAT:%[0-9]+]]:_(s16) = G_SSUBSAT [[SHL]], [[SHL1]]
+    ; GFX6: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[C]](s16)
+    ; GFX6: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[SSUBSAT]](s16)
+    ; GFX6: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SEXT]], [[ZEXT]](s32)
+    ; GFX6: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[ASHR]](s32)
+    ; GFX6: [[TRUNC3:%[0-9]+]]:_(s8) = G_TRUNC [[TRUNC2]](s16)
+    ; GFX6: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC3]](s8)
+    ; GFX6: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX8-LABEL: name: ssubsat_s8
     ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX8: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX8: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX8: [[SSUBSAT:%[0-9]+]]:_(s8) = G_SSUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SSUBSAT]](s8)
-    ; GFX8: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX8: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX8: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX8: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX8: [[SSUBSAT:%[0-9]+]]:_(s16) = G_SSUBSAT [[SHL]], [[SHL1]]
+    ; GFX8: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SSUBSAT]], [[C]](s16)
+    ; GFX8: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[ASHR]](s16)
+    ; GFX8: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s8)
+    ; GFX8: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX9-LABEL: name: ssubsat_s8
     ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX9: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX9: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX9: [[SSUBSAT:%[0-9]+]]:_(s8) = G_SSUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SSUBSAT]](s8)
-    ; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX9: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX9: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX9: [[SSUBSAT:%[0-9]+]]:_(s16) = G_SSUBSAT [[SHL]], [[SHL1]]
+    ; GFX9: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SSUBSAT]], [[C]](s16)
+    ; GFX9: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[ASHR]](s16)
+    ; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s8)
+    ; GFX9: $vgpr0 = COPY [[ANYEXT2]](s32)
     %0:_(s32) = COPY $vgpr0
     %1:_(s32) = COPY $vgpr1
     %2:_(s8) = G_TRUNC %0

diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-uaddsat.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-uaddsat.mir
index 79d6712..ac229cd 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-uaddsat.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-uaddsat.mir
@@ -14,25 +14,49 @@ body: |
     ; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX6: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX6: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX6: [[UADDSAT:%[0-9]+]]:_(s7) = G_UADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UADDSAT]](s7)
-    ; GFX6: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX6: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX6: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX6: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX6: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX6: [[UADDSAT:%[0-9]+]]:_(s16) = G_UADDSAT [[SHL]], [[SHL1]]
+    ; GFX6: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[C]](s16)
+    ; GFX6: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[UADDSAT]](s16)
+    ; GFX6: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[ZEXT1]], [[ZEXT]](s32)
+    ; GFX6: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
+    ; GFX6: [[TRUNC3:%[0-9]+]]:_(s7) = G_TRUNC [[TRUNC2]](s16)
+    ; GFX6: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC3]](s7)
+    ; GFX6: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX8-LABEL: name: uaddsat_s7
     ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX8: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX8: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX8: [[UADDSAT:%[0-9]+]]:_(s7) = G_UADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UADDSAT]](s7)
-    ; GFX8: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX8: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX8: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX8: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX8: [[UADDSAT:%[0-9]+]]:_(s16) = G_UADDSAT [[SHL]], [[SHL1]]
+    ; GFX8: [[LSHR:%[0-9]+]]:_(s16) = G_LSHR [[UADDSAT]], [[C]](s16)
+    ; GFX8: [[TRUNC2:%[0-9]+]]:_(s7) = G_TRUNC [[LSHR]](s16)
+    ; GFX8: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s7)
+    ; GFX8: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX9-LABEL: name: uaddsat_s7
     ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX9: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX9: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX9: [[UADDSAT:%[0-9]+]]:_(s7) = G_UADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UADDSAT]](s7)
-    ; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX9: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX9: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX9: [[UADDSAT:%[0-9]+]]:_(s16) = G_UADDSAT [[SHL]], [[SHL1]]
+    ; GFX9: [[LSHR:%[0-9]+]]:_(s16) = G_LSHR [[UADDSAT]], [[C]](s16)
+    ; GFX9: [[TRUNC2:%[0-9]+]]:_(s7) = G_TRUNC [[LSHR]](s16)
+    ; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s7)
+    ; GFX9: $vgpr0 = COPY [[ANYEXT2]](s32)
     %0:_(s32) = COPY $vgpr0
     %1:_(s32) = COPY $vgpr1
     %2:_(s7) = G_TRUNC %0
@@ -53,25 +77,49 @@ body: |
     ; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX6: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX6: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX6: [[UADDSAT:%[0-9]+]]:_(s8) = G_UADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UADDSAT]](s8)
-    ; GFX6: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX6: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX6: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX6: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX6: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX6: [[UADDSAT:%[0-9]+]]:_(s16) = G_UADDSAT [[SHL]], [[SHL1]]
+    ; GFX6: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[C]](s16)
+    ; GFX6: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[UADDSAT]](s16)
+    ; GFX6: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[ZEXT1]], [[ZEXT]](s32)
+    ; GFX6: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
+    ; GFX6: [[TRUNC3:%[0-9]+]]:_(s8) = G_TRUNC [[TRUNC2]](s16)
+    ; GFX6: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC3]](s8)
+    ; GFX6: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX8-LABEL: name: uaddsat_s8
     ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX8: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX8: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX8: [[UADDSAT:%[0-9]+]]:_(s8) = G_UADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UADDSAT]](s8)
-    ; GFX8: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX8: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX8: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX8: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX8: [[UADDSAT:%[0-9]+]]:_(s16) = G_UADDSAT [[SHL]], [[SHL1]]
+    ; GFX8: [[LSHR:%[0-9]+]]:_(s16) = G_LSHR [[UADDSAT]], [[C]](s16)
+    ; GFX8: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[LSHR]](s16)
+    ; GFX8: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s8)
+    ; GFX8: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX9-LABEL: name: uaddsat_s8
     ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX9: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX9: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX9: [[UADDSAT:%[0-9]+]]:_(s8) = G_UADDSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UADDSAT]](s8)
-    ; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX9: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX9: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX9: [[UADDSAT:%[0-9]+]]:_(s16) = G_UADDSAT [[SHL]], [[SHL1]]
+    ; GFX9: [[LSHR:%[0-9]+]]:_(s16) = G_LSHR [[UADDSAT]], [[C]](s16)
+    ; GFX9: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[LSHR]](s16)
+    ; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s8)
+    ; GFX9: $vgpr0 = COPY [[ANYEXT2]](s32)
     %0:_(s32) = COPY $vgpr0
     %1:_(s32) = COPY $vgpr1
     %2:_(s8) = G_TRUNC %0

diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-usubsat.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-usubsat.mir
index caf44cd..f0ea03d 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-usubsat.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-usubsat.mir
@@ -14,25 +14,49 @@ body: |
     ; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX6: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX6: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX6: [[USUBSAT:%[0-9]+]]:_(s7) = G_USUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[USUBSAT]](s7)
-    ; GFX6: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX6: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX6: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX6: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX6: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX6: [[USUBSAT:%[0-9]+]]:_(s16) = G_USUBSAT [[SHL]], [[SHL1]]
+    ; GFX6: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[C]](s16)
+    ; GFX6: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[USUBSAT]](s16)
+    ; GFX6: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[ZEXT1]], [[ZEXT]](s32)
+    ; GFX6: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
+    ; GFX6: [[TRUNC3:%[0-9]+]]:_(s7) = G_TRUNC [[TRUNC2]](s16)
+    ; GFX6: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC3]](s7)
+    ; GFX6: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX8-LABEL: name: usubsat_s7
     ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX8: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX8: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX8: [[USUBSAT:%[0-9]+]]:_(s7) = G_USUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[USUBSAT]](s7)
-    ; GFX8: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX8: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX8: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX8: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX8: [[USUBSAT:%[0-9]+]]:_(s16) = G_USUBSAT [[SHL]], [[SHL1]]
+    ; GFX8: [[LSHR:%[0-9]+]]:_(s16) = G_LSHR [[USUBSAT]], [[C]](s16)
+    ; GFX8: [[TRUNC2:%[0-9]+]]:_(s7) = G_TRUNC [[LSHR]](s16)
+    ; GFX8: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s7)
+    ; GFX8: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX9-LABEL: name: usubsat_s7
     ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX9: [[TRUNC:%[0-9]+]]:_(s7) = G_TRUNC [[COPY]](s32)
     ; GFX9: [[TRUNC1:%[0-9]+]]:_(s7) = G_TRUNC [[COPY1]](s32)
-    ; GFX9: [[USUBSAT:%[0-9]+]]:_(s7) = G_USUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[USUBSAT]](s7)
-    ; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s7)
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s7)
+    ; GFX9: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
+    ; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX9: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX9: [[USUBSAT:%[0-9]+]]:_(s16) = G_USUBSAT [[SHL]], [[SHL1]]
+    ; GFX9: [[LSHR:%[0-9]+]]:_(s16) = G_LSHR [[USUBSAT]], [[C]](s16)
+    ; GFX9: [[TRUNC2:%[0-9]+]]:_(s7) = G_TRUNC [[LSHR]](s16)
+    ; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s7)
+    ; GFX9: $vgpr0 = COPY [[ANYEXT2]](s32)
     %0:_(s32) = COPY $vgpr0
     %1:_(s32) = COPY $vgpr1
     %2:_(s7) = G_TRUNC %0
@@ -53,25 +77,49 @@ body: |
     ; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX6: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX6: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX6: [[USUBSAT:%[0-9]+]]:_(s8) = G_USUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[USUBSAT]](s8)
-    ; GFX6: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX6: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX6: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX6: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX6: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX6: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX6: [[USUBSAT:%[0-9]+]]:_(s16) = G_USUBSAT [[SHL]], [[SHL1]]
+    ; GFX6: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[C]](s16)
+    ; GFX6: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[USUBSAT]](s16)
+    ; GFX6: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[ZEXT1]], [[ZEXT]](s32)
+    ; GFX6: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
+    ; GFX6: [[TRUNC3:%[0-9]+]]:_(s8) = G_TRUNC [[TRUNC2]](s16)
+    ; GFX6: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC3]](s8)
+    ; GFX6: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX8-LABEL: name: usubsat_s8
     ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX8: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX8: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX8: [[USUBSAT:%[0-9]+]]:_(s8) = G_USUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[USUBSAT]](s8)
-    ; GFX8: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX8: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX8: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX8: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX8: [[USUBSAT:%[0-9]+]]:_(s16) = G_USUBSAT [[SHL]], [[SHL1]]
+    ; GFX8: [[LSHR:%[0-9]+]]:_(s16) = G_LSHR [[USUBSAT]], [[C]](s16)
+    ; GFX8: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[LSHR]](s16)
+    ; GFX8: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s8)
+    ; GFX8: $vgpr0 = COPY [[ANYEXT2]](s32)
     ; GFX9-LABEL: name: usubsat_s8
     ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
     ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
     ; GFX9: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
     ; GFX9: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
-    ; GFX9: [[USUBSAT:%[0-9]+]]:_(s8) = G_USUBSAT [[TRUNC]], [[TRUNC1]]
-    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[USUBSAT]](s8)
-    ; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC]](s8)
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s16) = G_ANYEXT [[TRUNC1]](s8)
+    ; GFX9: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT]], [[C]](s16)
+    ; GFX9: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[ANYEXT1]], [[C]](s16)
+    ; GFX9: [[USUBSAT:%[0-9]+]]:_(s16) = G_USUBSAT [[SHL]], [[SHL1]]
+    ; GFX9: [[LSHR:%[0-9]+]]:_(s16) = G_LSHR [[USUBSAT]], [[C]](s16)
+    ; GFX9: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[LSHR]](s16)
+    ; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s8)
+    ; GFX9: $vgpr0 = COPY [[ANYEXT2]](s32)
     %0:_(s32) = COPY $vgpr0
     %1:_(s32) = COPY $vgpr1
     %2:_(s8) = G_TRUNC %0