diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst
index deb87365ae8d7..59496ebb93cd7 100644
--- a/llvm/docs/LangRef.rst
+++ b/llvm/docs/LangRef.rst
@@ -20295,6 +20295,9 @@ More update operation types may be added in the future.
 
     declare void @llvm.experimental.vector.histogram.add.v8p0.i32(<8 x ptr> %ptrs, i32 %inc, <8 x i1> %mask)
     declare void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %ptrs, i64 %inc, <vscale x 2 x i1> %mask)
+    declare void @llvm.experimental.vector.histogram.uadd.sat.v8p0.i32(<8 x ptr> %ptrs, i32 %inc, <8 x i1> %mask)
+    declare void @llvm.experimental.vector.histogram.umax.v8p0.i32(<8 x ptr> %ptrs, i32 %val, <8 x i1> %mask)
+    declare void @llvm.experimental.vector.histogram.umin.v8p0.i32(<8 x ptr> %ptrs, i32 %val, <8 x i1> %mask)
 
 Arguments:
 """"""""""
diff --git a/llvm/include/llvm/IR/Intrinsics.td b/llvm/include/llvm/IR/Intrinsics.td
index 14ecae41ff08f..31a0ba2e6500d 100644
--- a/llvm/include/llvm/IR/Intrinsics.td
+++ b/llvm/include/llvm/IR/Intrinsics.td
@@ -1947,6 +1947,24 @@ def int_experimental_vector_histogram_add : DefaultAttrsIntrinsic<[],
                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>], // Mask
                              [ IntrArgMemOnly ]>;
 
+def int_experimental_vector_histogram_uadd_sat : DefaultAttrsIntrinsic<[],
+                             [ llvm_anyvector_ty, // Vector of pointers
+                               llvm_anyint_ty,    // Increment
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>], // Mask
+                             [ IntrArgMemOnly ]>;
+
+def int_experimental_vector_histogram_umin : DefaultAttrsIntrinsic<[],
+                             [ llvm_anyvector_ty, // Vector of pointers
+                               llvm_anyint_ty,    // Update value
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>], // Mask
+                             [ IntrArgMemOnly ]>;
+
+def int_experimental_vector_histogram_umax : DefaultAttrsIntrinsic<[],
+                             [ llvm_anyvector_ty, // Vector of pointers
+                               llvm_anyint_ty,    // Update value
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>], // Mask
+                             [ IntrArgMemOnly ]>;
+
 // Experimental match
 def int_experimental_vector_match : DefaultAttrsIntrinsic<
                              [ LLVMScalarOrSameVectorWidth<0, llvm_i1_ty> ],
diff --git a/llvm/lib/Transforms/Scalar/ScalarizeMaskedMemIntrin.cpp b/llvm/lib/Transforms/Scalar/ScalarizeMaskedMemIntrin.cpp
index 63fcc1760ccaf..9506747bf464d 100644
--- a/llvm/lib/Transforms/Scalar/ScalarizeMaskedMemIntrin.cpp
+++ b/llvm/lib/Transforms/Scalar/ScalarizeMaskedMemIntrin.cpp
@@ -968,6 +968,29 @@ static void scalarizeMaskedVectorHistogram(const DataLayout &DL, CallInst *CI,
 
   // FIXME: Do we need to add an alignment parameter to the intrinsic?
   unsigned VectorWidth = AddrType->getNumElements();
+  auto CreateHistogramUpdateValue = [&](IntrinsicInst *CI, Value *Load,
+                                        Value *Inc) -> Value * {
+    Value *UpdateOp;
+    switch (CI->getIntrinsicID()) {
+    case Intrinsic::experimental_vector_histogram_add:
+      UpdateOp = Builder.CreateAdd(Load, Inc);
+      break;
+    case Intrinsic::experimental_vector_histogram_uadd_sat:
+      UpdateOp =
+          Builder.CreateIntrinsic(Intrinsic::uadd_sat, {EltTy}, {Load, Inc});
+      break;
+    case Intrinsic::experimental_vector_histogram_umin:
+      UpdateOp = Builder.CreateIntrinsic(Intrinsic::umin, {EltTy}, {Load, Inc});
+      break;
+    case Intrinsic::experimental_vector_histogram_umax:
+      UpdateOp = Builder.CreateIntrinsic(Intrinsic::umax, {EltTy}, {Load, Inc});
+      break;
+
+    default:
+      llvm_unreachable("Unexpected histogram intrinsic");
+    }
+    return UpdateOp;
+  };
 
   // Shorten the way if the mask is a vector of constants.
   if (isConstantIntVector(Mask)) {
@@ -976,8 +999,9 @@ static void scalarizeMaskedVectorHistogram(const DataLayout &DL, CallInst *CI,
         continue;
       Value *Ptr = Builder.CreateExtractElement(Ptrs, Idx, "Ptr" + Twine(Idx));
       LoadInst *Load = Builder.CreateLoad(EltTy, Ptr, "Load" + Twine(Idx));
-      Value *Add = Builder.CreateAdd(Load, Inc);
-      Builder.CreateStore(Add, Ptr);
+      Value *Update =
+          CreateHistogramUpdateValue(cast<IntrinsicInst>(CI), Load, Inc);
+      Builder.CreateStore(Update, Ptr);
     }
     CI->eraseFromParent();
     return;
@@ -997,8 +1021,9 @@ static void scalarizeMaskedVectorHistogram(const DataLayout &DL, CallInst *CI,
     Builder.SetInsertPoint(CondBlock->getTerminator());
     Value *Ptr = Builder.CreateExtractElement(Ptrs, Idx, "Ptr" + Twine(Idx));
     LoadInst *Load = Builder.CreateLoad(EltTy, Ptr, "Load" + Twine(Idx));
-    Value *Add = Builder.CreateAdd(Load, Inc);
-    Builder.CreateStore(Add, Ptr);
+    Value *UpdateOp =
+        CreateHistogramUpdateValue(cast<IntrinsicInst>(CI), Load, Inc);
+    Builder.CreateStore(UpdateOp, Ptr);
 
     // Create "else" block, fill it in the next iteration
     BasicBlock *NewIfBlock = ThenTerm->getSuccessor(0);
@@ -1089,6 +1114,9 @@ static bool optimizeCallInst(CallInst *CI, bool &ModifiedDT,
     default:
       break;
     case Intrinsic::experimental_vector_histogram_add:
+    case Intrinsic::experimental_vector_histogram_uadd_sat:
+    case Intrinsic::experimental_vector_histogram_umin:
+    case Intrinsic::experimental_vector_histogram_umax:
       if (TTI.isLegalMaskedVectorHistogram(CI->getArgOperand(0)->getType(),
                                            CI->getArgOperand(1)->getType()))
         return false;
diff --git a/llvm/test/CodeGen/AArch64/neon-scalarize-histogram.ll b/llvm/test/CodeGen/AArch64/neon-scalarize-histogram.ll
index e59d9098a30d6..ca74b4e95b0ae 100644
--- a/llvm/test/CodeGen/AArch64/neon-scalarize-histogram.ll
+++ b/llvm/test/CodeGen/AArch64/neon-scalarize-histogram.ll
@@ -112,3 +112,357 @@ define void @histogram_i32_literal_alltruemask(ptr %base, <4 x i32> %indices) {
   call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
   ret void
 }
+
+define void @histogram_uadd_sat_i64(<2 x ptr> %buckets, i64 %inc, <2 x i1> %mask) {
+; CHECK-LABEL: histogram_uadd_sat_i64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    fmov w8, s1
+; CHECK-NEXT:    tbnz w8, #0, .LBB3_3
+; CHECK-NEXT:  // %bb.1: // %else
+; CHECK-NEXT:    mov w8, v1.s[1]
+; CHECK-NEXT:    tbnz w8, #0, .LBB3_4
+; CHECK-NEXT:  .LBB3_2: // %else2
+; CHECK-NEXT:    ret
+; CHECK-NEXT:  .LBB3_3: // %cond.histogram.update
+; CHECK-NEXT:    fmov x8, d0
+; CHECK-NEXT:    ldr x9, [x8]
+; CHECK-NEXT:    adds x9, x9, x0
+; CHECK-NEXT:    csinv x9, x9, xzr, lo
+; CHECK-NEXT:    str x9, [x8]
+; CHECK-NEXT:    mov w8, v1.s[1]
+; CHECK-NEXT:    tbz w8, #0, .LBB3_2
+; CHECK-NEXT:  .LBB3_4: // %cond.histogram.update1
+; CHECK-NEXT:    mov x8, v0.d[1]
+; CHECK-NEXT:    ldr x9, [x8]
+; CHECK-NEXT:    adds x9, x9, x0
+; CHECK-NEXT:    csinv x9, x9, xzr, lo
+; CHECK-NEXT:    str x9, [x8]
+; CHECK-NEXT:    ret
+  call void @llvm.experimental.vector.histogram.uadd.sat.nxv2p0.i64(<2 x ptr> %buckets, i64 %inc, <2 x i1> %mask)
+  ret void
+}
+
+define void @histogram_uadd_sat_i32_literal(ptr %base, <4 x i32> %indices, <4 x i1> %mask) {
+; CHECK-LABEL: histogram_uadd_sat_i32_literal:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup v2.2d, x0
+; CHECK-NEXT:    sshll v3.2d, v0.2s, #2
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    umov w8, v1.h[0]
+; CHECK-NEXT:    add v3.2d, v2.2d, v3.2d
+; CHECK-NEXT:    tbz w8, #0, .LBB4_2
+; CHECK-NEXT:  // %bb.1: // %cond.histogram.update
+; CHECK-NEXT:    fmov x8, d3
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    adds w9, w9, #1
+; CHECK-NEXT:    csinv w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:  .LBB4_2: // %else
+; CHECK-NEXT:    umov w8, v1.h[1]
+; CHECK-NEXT:    sshll2 v0.2d, v0.4s, #2
+; CHECK-NEXT:    tbz w8, #0, .LBB4_4
+; CHECK-NEXT:  // %bb.3: // %cond.histogram.update1
+; CHECK-NEXT:    mov x8, v3.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    adds w9, w9, #1
+; CHECK-NEXT:    csinv w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:  .LBB4_4: // %else2
+; CHECK-NEXT:    umov w8, v1.h[2]
+; CHECK-NEXT:    add v0.2d, v2.2d, v0.2d
+; CHECK-NEXT:    tbnz w8, #0, .LBB4_7
+; CHECK-NEXT:  // %bb.5: // %else4
+; CHECK-NEXT:    umov w8, v1.h[3]
+; CHECK-NEXT:    tbnz w8, #0, .LBB4_8
+; CHECK-NEXT:  .LBB4_6: // %else6
+; CHECK-NEXT:    ret
+; CHECK-NEXT:  .LBB4_7: // %cond.histogram.update3
+; CHECK-NEXT:    fmov x8, d0
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    adds w9, w9, #1
+; CHECK-NEXT:    csinv w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    umov w8, v1.h[3]
+; CHECK-NEXT:    tbz w8, #0, .LBB4_6
+; CHECK-NEXT:  .LBB4_8: // %cond.histogram.update5
+; CHECK-NEXT:    mov x8, v0.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    adds w9, w9, #1
+; CHECK-NEXT:    csinv w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    ret
+  %buckets = getelementptr i32, ptr %base, <4 x i32> %indices
+  call void @llvm.experimental.vector.histogram.uadd.sat.nxv4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
+  ret void
+}
+
+define void @histogram_uadd_sat_i32_literal_alltruemask(ptr %base, <4 x i32> %indices) {
+; CHECK-LABEL: histogram_uadd_sat_i32_literal_alltruemask:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup v1.2d, x0
+; CHECK-NEXT:    sshll v2.2d, v0.2s, #2
+; CHECK-NEXT:    sshll2 v0.2d, v0.4s, #2
+; CHECK-NEXT:    add v2.2d, v1.2d, v2.2d
+; CHECK-NEXT:    add v0.2d, v1.2d, v0.2d
+; CHECK-NEXT:    fmov x8, d2
+; CHECK-NEXT:    mov x10, v2.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    adds w9, w9, #1
+; CHECK-NEXT:    csinv w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    ldr w8, [x10]
+; CHECK-NEXT:    adds w8, w8, #1
+; CHECK-NEXT:    csinv w8, w8, wzr, lo
+; CHECK-NEXT:    str w8, [x10]
+; CHECK-NEXT:    fmov x8, d0
+; CHECK-NEXT:    mov x10, v0.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    adds w9, w9, #1
+; CHECK-NEXT:    csinv w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    ldr w8, [x10]
+; CHECK-NEXT:    adds w8, w8, #1
+; CHECK-NEXT:    csinv w8, w8, wzr, lo
+; CHECK-NEXT:    str w8, [x10]
+; CHECK-NEXT:    ret
+  %buckets = getelementptr i32, ptr %base, <4 x i32> %indices
+  call void @llvm.experimental.vector.histogram.uadd.sat.nxv4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
+  ret void
+}
+
+define void @histogram_umax_i64(<2 x ptr> %buckets, i64 %inc, <2 x i1> %mask) {
+; CHECK-LABEL: histogram_umax_i64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    fmov w8, s1
+; CHECK-NEXT:    tbnz w8, #0, .LBB6_3
+; CHECK-NEXT:  // %bb.1: // %else
+; CHECK-NEXT:    mov w8, v1.s[1]
+; CHECK-NEXT:    tbnz w8, #0, .LBB6_4
+; CHECK-NEXT:  .LBB6_2: // %else2
+; CHECK-NEXT:    ret
+; CHECK-NEXT:  .LBB6_3: // %cond.histogram.update
+; CHECK-NEXT:    fmov x8, d0
+; CHECK-NEXT:    ldr x9, [x8]
+; CHECK-NEXT:    cmp x9, x0
+; CHECK-NEXT:    csel x9, x9, x0, hi
+; CHECK-NEXT:    str x9, [x8]
+; CHECK-NEXT:    mov w8, v1.s[1]
+; CHECK-NEXT:    tbz w8, #0, .LBB6_2
+; CHECK-NEXT:  .LBB6_4: // %cond.histogram.update1
+; CHECK-NEXT:    mov x8, v0.d[1]
+; CHECK-NEXT:    ldr x9, [x8]
+; CHECK-NEXT:    cmp x9, x0
+; CHECK-NEXT:    csel x9, x9, x0, hi
+; CHECK-NEXT:    str x9, [x8]
+; CHECK-NEXT:    ret
+  call void @llvm.experimental.vector.histogram.umax.nxv2p0.i64(<2 x ptr> %buckets, i64 %inc, <2 x i1> %mask)
+  ret void
+}
+
+define void @histogram_umax_i32_literal(ptr %base, <4 x i32> %indices, <4 x i1> %mask) {
+; CHECK-LABEL: histogram_umax_i32_literal:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup v2.2d, x0
+; CHECK-NEXT:    sshll v3.2d, v0.2s, #2
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    umov w8, v1.h[0]
+; CHECK-NEXT:    add v3.2d, v2.2d, v3.2d
+; CHECK-NEXT:    tbz w8, #0, .LBB7_2
+; CHECK-NEXT:  // %bb.1: // %cond.histogram.update
+; CHECK-NEXT:    fmov x8, d3
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, hi
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:  .LBB7_2: // %else
+; CHECK-NEXT:    umov w8, v1.h[1]
+; CHECK-NEXT:    sshll2 v0.2d, v0.4s, #2
+; CHECK-NEXT:    tbz w8, #0, .LBB7_4
+; CHECK-NEXT:  // %bb.3: // %cond.histogram.update1
+; CHECK-NEXT:    mov x8, v3.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, hi
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:  .LBB7_4: // %else2
+; CHECK-NEXT:    umov w8, v1.h[2]
+; CHECK-NEXT:    add v0.2d, v2.2d, v0.2d
+; CHECK-NEXT:    tbnz w8, #0, .LBB7_7
+; CHECK-NEXT:  // %bb.5: // %else4
+; CHECK-NEXT:    umov w8, v1.h[3]
+; CHECK-NEXT:    tbnz w8, #0, .LBB7_8
+; CHECK-NEXT:  .LBB7_6: // %else6
+; CHECK-NEXT:    ret
+; CHECK-NEXT:  .LBB7_7: // %cond.histogram.update3
+; CHECK-NEXT:    fmov x8, d0
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, hi
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    umov w8, v1.h[3]
+; CHECK-NEXT:    tbz w8, #0, .LBB7_6
+; CHECK-NEXT:  .LBB7_8: // %cond.histogram.update5
+; CHECK-NEXT:    mov x8, v0.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, hi
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    ret
+  %buckets = getelementptr i32, ptr %base, <4 x i32> %indices
+  call void @llvm.experimental.vector.histogram.umax.nxv4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
+  ret void
+}
+
+define void @histogram_umax_i32_literal_alltruemask(ptr %base, <4 x i32> %indices) {
+; CHECK-LABEL: histogram_umax_i32_literal_alltruemask:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup v1.2d, x0
+; CHECK-NEXT:    sshll v2.2d, v0.2s, #2
+; CHECK-NEXT:    sshll2 v0.2d, v0.4s, #2
+; CHECK-NEXT:    add v2.2d, v1.2d, v2.2d
+; CHECK-NEXT:    add v0.2d, v1.2d, v0.2d
+; CHECK-NEXT:    fmov x8, d2
+; CHECK-NEXT:    mov x10, v2.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, hi
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    ldr w8, [x10]
+; CHECK-NEXT:    cmp w8, #1
+; CHECK-NEXT:    csinc w8, w8, wzr, hi
+; CHECK-NEXT:    str w8, [x10]
+; CHECK-NEXT:    fmov x8, d0
+; CHECK-NEXT:    mov x10, v0.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, hi
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    ldr w8, [x10]
+; CHECK-NEXT:    cmp w8, #1
+; CHECK-NEXT:    csinc w8, w8, wzr, hi
+; CHECK-NEXT:    str w8, [x10]
+; CHECK-NEXT:    ret
+  %buckets = getelementptr i32, ptr %base, <4 x i32> %indices
+  call void @llvm.experimental.vector.histogram.umax.nxv4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
+  ret void
+}
+
+define void @histogram_umin_i64(<2 x ptr> %buckets, i64 %inc, <2 x i1> %mask) {
+; CHECK-LABEL: histogram_umin_i64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    fmov w8, s1
+; CHECK-NEXT:    tbnz w8, #0, .LBB9_3
+; CHECK-NEXT:  // %bb.1: // %else
+; CHECK-NEXT:    mov w8, v1.s[1]
+; CHECK-NEXT:    tbnz w8, #0, .LBB9_4
+; CHECK-NEXT:  .LBB9_2: // %else2
+; CHECK-NEXT:    ret
+; CHECK-NEXT:  .LBB9_3: // %cond.histogram.update
+; CHECK-NEXT:    fmov x8, d0
+; CHECK-NEXT:    ldr x9, [x8]
+; CHECK-NEXT:    cmp x9, x0
+; CHECK-NEXT:    csel x9, x9, x0, lo
+; CHECK-NEXT:    str x9, [x8]
+; CHECK-NEXT:    mov w8, v1.s[1]
+; CHECK-NEXT:    tbz w8, #0, .LBB9_2
+; CHECK-NEXT:  .LBB9_4: // %cond.histogram.update1
+; CHECK-NEXT:    mov x8, v0.d[1]
+; CHECK-NEXT:    ldr x9, [x8]
+; CHECK-NEXT:    cmp x9, x0
+; CHECK-NEXT:    csel x9, x9, x0, lo
+; CHECK-NEXT:    str x9, [x8]
+; CHECK-NEXT:    ret
+  call void @llvm.experimental.vector.histogram.umin.nxv2p0.i64(<2 x ptr> %buckets, i64 %inc, <2 x i1> %mask)
+  ret void
+}
+
+define void @histogram_umin_i32_literal(ptr %base, <4 x i32> %indices, <4 x i1> %mask) {
+; CHECK-LABEL: histogram_umin_i32_literal:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup v2.2d, x0
+; CHECK-NEXT:    sshll v3.2d, v0.2s, #2
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    umov w8, v1.h[0]
+; CHECK-NEXT:    add v3.2d, v2.2d, v3.2d
+; CHECK-NEXT:    tbz w8, #0, .LBB10_2
+; CHECK-NEXT:  // %bb.1: // %cond.histogram.update
+; CHECK-NEXT:    fmov x8, d3
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:  .LBB10_2: // %else
+; CHECK-NEXT:    umov w8, v1.h[1]
+; CHECK-NEXT:    sshll2 v0.2d, v0.4s, #2
+; CHECK-NEXT:    tbz w8, #0, .LBB10_4
+; CHECK-NEXT:  // %bb.3: // %cond.histogram.update1
+; CHECK-NEXT:    mov x8, v3.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:  .LBB10_4: // %else2
+; CHECK-NEXT:    umov w8, v1.h[2]
+; CHECK-NEXT:    add v0.2d, v2.2d, v0.2d
+; CHECK-NEXT:    tbnz w8, #0, .LBB10_7
+; CHECK-NEXT:  // %bb.5: // %else4
+; CHECK-NEXT:    umov w8, v1.h[3]
+; CHECK-NEXT:    tbnz w8, #0, .LBB10_8
+; CHECK-NEXT:  .LBB10_6: // %else6
+; CHECK-NEXT:    ret
+; CHECK-NEXT:  .LBB10_7: // %cond.histogram.update3
+; CHECK-NEXT:    fmov x8, d0
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    umov w8, v1.h[3]
+; CHECK-NEXT:    tbz w8, #0, .LBB10_6
+; CHECK-NEXT:  .LBB10_8: // %cond.histogram.update5
+; CHECK-NEXT:    mov x8, v0.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    ret
+  %buckets = getelementptr i32, ptr %base, <4 x i32> %indices
+  call void @llvm.experimental.vector.histogram.umin.nxv4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
+  ret void
+}
+
+define void @histogram_umin_i32_literal_alltruemask(ptr %base, <4 x i32> %indices) {
+; CHECK-LABEL: histogram_umin_i32_literal_alltruemask:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup v1.2d, x0
+; CHECK-NEXT:    sshll v2.2d, v0.2s, #2
+; CHECK-NEXT:    sshll2 v0.2d, v0.4s, #2
+; CHECK-NEXT:    add v2.2d, v1.2d, v2.2d
+; CHECK-NEXT:    add v0.2d, v1.2d, v0.2d
+; CHECK-NEXT:    fmov x8, d2
+; CHECK-NEXT:    mov x10, v2.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    ldr w8, [x10]
+; CHECK-NEXT:    cmp w8, #1
+; CHECK-NEXT:    csinc w8, w8, wzr, lo
+; CHECK-NEXT:    str w8, [x10]
+; CHECK-NEXT:    fmov x8, d0
+; CHECK-NEXT:    mov x10, v0.d[1]
+; CHECK-NEXT:    ldr w9, [x8]
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    csinc w9, w9, wzr, lo
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    ldr w8, [x10]
+; CHECK-NEXT:    cmp w8, #1
+; CHECK-NEXT:    csinc w8, w8, wzr, lo
+; CHECK-NEXT:    str w8, [x10]
+; CHECK-NEXT:    ret
+  %buckets = getelementptr i32, ptr %base, <4 x i32> %indices
+  call void @llvm.experimental.vector.histogram.umin.nxv4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
+  ret void
+}