diff --git a/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h b/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h
--- a/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h
+++ b/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h
@@ -353,6 +353,7 @@
   LegalizeResult lowerBswap(MachineInstr &MI);
   LegalizeResult lowerBitreverse(MachineInstr &MI);
   LegalizeResult lowerReadWriteRegister(MachineInstr &MI);
+  LegalizeResult lowerSMULH_UMULH(MachineInstr &MI);
 };
 
 /// Helper function that creates a libcall to the given \p Name using the given
diff --git a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
--- a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
@@ -2709,6 +2709,9 @@
   case TargetOpcode::G_SADDO:
   case TargetOpcode::G_SSUBO:
     return lowerSADDO_SSUBO(MI);
+  case TargetOpcode::G_UMULH:
+  case TargetOpcode::G_SMULH:
+    return lowerSMULH_UMULH(MI);
   case TargetOpcode::G_SMULO:
   case TargetOpcode::G_UMULO: {
     // Generate G_UMULH/G_SMULH to check for overflow and a normal G_MUL for the
@@ -6000,3 +6003,24 @@
   MI.eraseFromParent();
   return Legalized;
 }
+
+LegalizerHelper::LegalizeResult
+LegalizerHelper::lowerSMULH_UMULH(MachineInstr &MI) {
+  bool IsSigned = MI.getOpcode() == TargetOpcode::G_SMULH;
+  unsigned ExtOp = IsSigned ? TargetOpcode::G_SEXT : TargetOpcode::G_ZEXT;
+  Register Result = MI.getOperand(0).getReg();
+  auto SizeInBits = MRI.getType(Result).getScalarSizeInBits();
+  LLT WideTy = LLT::scalar(SizeInBits * 2);
+
+  auto LHS = MIRBuilder.buildInstr(ExtOp, {WideTy}, {MI.getOperand(1)});
+  auto RHS = MIRBuilder.buildInstr(ExtOp, {WideTy}, {MI.getOperand(2)});
+  auto Mul = MIRBuilder.buildMul(WideTy, LHS, RHS);
+  unsigned ShiftOp = IsSigned ? TargetOpcode::G_ASHR : TargetOpcode::G_LSHR;
+
+  auto ShiftAmt = MIRBuilder.buildConstant(WideTy, SizeInBits - IsSigned);
+  auto Shifted = MIRBuilder.buildInstr(ShiftOp, {WideTy}, {Mul, ShiftAmt});
+  MIRBuilder.buildTrunc(Result, Shifted);
+
+  MI.eraseFromParent();
+  return Legalized;
+}
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
@@ -536,9 +536,10 @@
     .scalarize(0);
 
   getActionDefinitionsBuilder({G_UMULH, G_SMULH})
-    .legalFor({S32})
-    .clampScalar(0, S32, S32)
-    .scalarize(0);
+      .legalFor({S32})
+      .maxScalar(0, S32)
+      .scalarize(0)
+      .lower();
 
   // Report legal for any types we can handle anywhere. For the cases only legal
   // on the SALU, RegBankSelect will be able to re-legalize.
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-smulh.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-smulh.mir
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-smulh.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-smulh.mir
@@ -38,3 +38,62 @@
     %2:_(<2 x s32>) = G_SMULH %0, %1
     $vgpr0_vgpr1 = COPY %2
 ...
+
+---
+name: test_smulh_s16
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; CHECK-LABEL: name: test_smulh_s16
+    ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; CHECK: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 16
+    ; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; CHECK: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 16
+    ; CHECK: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 15
+    ; CHECK: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
+    ; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY [[ASHR]](s32)
+    ; CHECK: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 16
+    ; CHECK: $vgpr0 = COPY [[SEXT_INREG2]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s16) = G_TRUNC %0
+    %3:_(s16) = G_TRUNC %1
+    %4:_(s16) = G_SMULH %2, %3
+    %5:_(s32) = G_SEXT %4
+    $vgpr0 = COPY %5
+...
+
+---
+name: test_smulh_s8
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; CHECK-LABEL: name: test_smulh_s8
+    ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+    ; CHECK: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; CHECK: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC]], [[C]](s16)
+    ; CHECK: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[C]](s16)
+    ; CHECK: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
+    ; CHECK: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[TRUNC1]], [[C]](s16)
+    ; CHECK: [[ASHR1:%[0-9]+]]:_(s16) = G_ASHR [[SHL1]], [[C]](s16)
+    ; CHECK: [[MUL:%[0-9]+]]:_(s16) = G_MUL [[ASHR]], [[ASHR1]]
+    ; CHECK: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 7
+    ; CHECK: [[ASHR2:%[0-9]+]]:_(s16) = G_ASHR [[MUL]], [[C1]](s16)
+    ; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ASHR2]](s16)
+    ; CHECK: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT]], 8
+    ; CHECK: $vgpr0 = COPY [[SEXT_INREG]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s8) = G_TRUNC %0
+    %3:_(s8) = G_TRUNC %1
+    %4:_(s8) = G_SMULH %2, %3
+    %5:_(s32) = G_SEXT %4
+    $vgpr0 = COPY %5
+...
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulh.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulh.mir
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulh.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulh.mir
@@ -78,3 +78,62 @@
     %2:_(s64) = G_UMULH %0, %1
     $vgpr0_vgpr1 = COPY %2
 ...
+
+---
+name: test_umulh_s16
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; CHECK-LABEL: name: test_umulh_s16
+    ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+    ; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
+    ; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
+    ; CHECK: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
+    ; CHECK: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[MUL]], [[C1]](s32)
+    ; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
+    ; CHECK: [[AND2:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
+    ; CHECK: $vgpr0 = COPY [[AND2]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s16) = G_TRUNC %0
+    %3:_(s16) = G_TRUNC %1
+    %4:_(s16) = G_UMULH %2, %3
+    %5:_(s32) = G_ZEXT %4
+    $vgpr0 = COPY %5
+...
+
+---
+name: test_umulh_s8
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; CHECK-LABEL: name: test_umulh_s8
+    ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; CHECK: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 255
+    ; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+    ; CHECK: [[AND:%[0-9]+]]:_(s16) = G_AND [[TRUNC]], [[C]]
+    ; CHECK: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
+    ; CHECK: [[AND1:%[0-9]+]]:_(s16) = G_AND [[TRUNC1]], [[C]]
+    ; CHECK: [[MUL:%[0-9]+]]:_(s16) = G_MUL [[AND]], [[AND1]]
+    ; CHECK: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; CHECK: [[LSHR:%[0-9]+]]:_(s16) = G_LSHR [[MUL]], [[C1]](s16)
+    ; CHECK: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
+    ; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[LSHR]](s16)
+    ; CHECK: [[AND2:%[0-9]+]]:_(s32) = G_AND [[ANYEXT]], [[C2]]
+    ; CHECK: $vgpr0 = COPY [[AND2]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s8) = G_TRUNC %0
+    %3:_(s8) = G_TRUNC %1
+    %4:_(s8) = G_UMULH %2, %3
+    %5:_(s32) = G_ZEXT %4
+    $vgpr0 = COPY %5
+...