diff --git a/mlir/include/mlir/Dialect/Tosa/IR/TosaOps.td b/mlir/include/mlir/Dialect/Tosa/IR/TosaOps.td
--- a/mlir/include/mlir/Dialect/Tosa/IR/TosaOps.td
+++ b/mlir/include/mlir/Dialect/Tosa/IR/TosaOps.td
@@ -340,30 +340,6 @@
   let hasCanonicalizer = 1;
 }
 
-//===----------------------------------------------------------------------===//
-// Operator: reluN
-//===----------------------------------------------------------------------===//
-def Tosa_ReluNOp : Tosa_Op<"reluN", [
-    DeclareOpInterfaceMethods<InferShapedTypeOpInterface,
-                              ["inferReturnTypeComponents"]>,
-    NoSideEffect]> {
-  let summary = "Computes rectified linear: `max(features, N)`.";
-
-  let description = [{
-     ReLU with a scalar maximum value.
-  }];
-
-  let arguments = (ins
-    Tosa_Tensor:$input,
-    I64Attr:$max_int,
-    F32Attr:$max_fp
-  );
-
-  let results = (outs
-    Tosa_Tensor:$output
-  );
-}
-
 //===----------------------------------------------------------------------===//
 // Operator: sigmoid
 //===----------------------------------------------------------------------===//
diff --git a/mlir/lib/Conversion/TosaToLinalg/TosaToLinalg.cpp b/mlir/lib/Conversion/TosaToLinalg/TosaToLinalg.cpp
--- a/mlir/lib/Conversion/TosaToLinalg/TosaToLinalg.cpp
+++ b/mlir/lib/Conversion/TosaToLinalg/TosaToLinalg.cpp
@@ -406,25 +406,6 @@
                                       arith::CmpIPredicate::slt, rewriter);
   }
 
-  // tosa::ReluNOp
-  if (isa<tosa::ReluNOp>(op) && elementTy.isa<FloatType>()) {
-    auto zero =
-        rewriter.create<arith::ConstantOp>(loc, FloatAttr::get(elementTy, 0));
-    auto n = rewriter.create<arith::ConstantOp>(loc, elementTy,
-                                                op->getAttr("max_fp"));
-    return clampHelper<arith::CmpFOp>(loc, args[0], zero, n,
-                                      arith::CmpFPredicate::OLT, rewriter);
-  }
-
-  if (isa<tosa::ReluNOp>(op) && elementTy.isa<IntegerType>()) {
-    auto zero =
-        rewriter.create<arith::ConstantOp>(loc, IntegerAttr::get(elementTy, 0));
-    auto n = createConstFromIntAttribute<int32_t>(op, "max_int", elementTy,
-                                                  rewriter);
-    return clampHelper<arith::CmpIOp>(loc, args[0], zero, n,
-                                      arith::CmpIPredicate::slt, rewriter);
-  }
-
   // tosa::SigmoidOp
   if (isa<tosa::SigmoidOp>(op) && elementTy.isa<FloatType>()) {
     auto one =
@@ -2246,7 +2227,6 @@
       PointwiseConverter<tosa::CeilOp>,
       PointwiseConverter<tosa::FloorOp>,
       PointwiseConverter<tosa::ClampOp>,
-      PointwiseConverter<tosa::ReluNOp>,
       PointwiseConverter<tosa::SigmoidOp>,
       IdentityNConverter<tosa::IdentityOp>,
       ReduceConverter<tosa::ReduceAllOp>,
diff --git a/mlir/lib/Dialect/Tosa/IR/TosaOps.cpp b/mlir/lib/Dialect/Tosa/IR/TosaOps.cpp
--- a/mlir/lib/Dialect/Tosa/IR/TosaOps.cpp
+++ b/mlir/lib/Dialect/Tosa/IR/TosaOps.cpp
@@ -1485,7 +1485,6 @@
 NARY_SHAPE_INFER(tosa::NegateOp)
 NARY_SHAPE_INFER(tosa::PowOp)
 NARY_SHAPE_INFER(tosa::ReciprocalOp)
-NARY_SHAPE_INFER(tosa::ReluNOp)
 NARY_SHAPE_INFER(tosa::RescaleOp)
 NARY_SHAPE_INFER(tosa::ReverseOp)
 NARY_SHAPE_INFER(tosa::RsqrtOp)
diff --git a/mlir/test/Conversion/TosaToLinalg/tosa-to-linalg.mlir b/mlir/test/Conversion/TosaToLinalg/tosa-to-linalg.mlir
--- a/mlir/test/Conversion/TosaToLinalg/tosa-to-linalg.mlir
+++ b/mlir/test/Conversion/TosaToLinalg/tosa-to-linalg.mlir
@@ -220,17 +220,12 @@
   // CHECK: select
   %18 = "tosa.clamp"(%0) {min_int = 1 : i64, max_int = 5 : i64, min_fp = 1.0 : f32, max_fp = 5.0 : f32} : (tensor<1xf32>) -> tensor<1xf32>
 
-  // CHECK: linalg.generic
-  // CHECK: arith.cmpf
-  // CHECK: select
-  %19 = "tosa.reluN"(%0) {max_int = 5 : i64, max_fp = 5.0 : f32} : (tensor<1xf32>) -> tensor<1xf32>
-
   // CHECK: linalg.generic
   // CHECK: arith.negf
   // CHECK: exp
   // CHECK: arith.addf
   // CHECK: arith.divf
-  %20 = "tosa.sigmoid"(%0) : (tensor<1xf32>) -> tensor<1xf32>
+  %19 = "tosa.sigmoid"(%0) : (tensor<1xf32>) -> tensor<1xf32>
 
   // CHECK: linalg.generic
   // CHECK: arith.constant 0.000000e+00
@@ -246,20 +241,20 @@
   // CHECK: arith.cmpf olt
   // CHECK: select
   // CHECK: arith.fptosi
-  %21 = "tosa.cast"(%0) : (tensor<1xf32>) -> tensor<1xi32>
+  %20 = "tosa.cast"(%0) : (tensor<1xf32>) -> tensor<1xi32>
 
   // CHECK: linalg.generic
   // CHECK: arith.constant 0
   // CHECK: arith.cmpf
-  %22 = "tosa.cast"(%0) : (tensor<1xf32>) -> tensor<1xi1>
+  %21 = "tosa.cast"(%0) : (tensor<1xf32>) -> tensor<1xi1>
 
   // CHECK: linalg.generic
   // CHECK: arith.truncf
-  %23 = "tosa.cast"(%0) : (tensor<1xf32>) -> tensor<1xf16>
+  %22 = "tosa.cast"(%0) : (tensor<1xf32>) -> tensor<1xf16>
 
   // CHECK: linalg.generic
   // CHECK: arith.divf
-  %24 = "tosa.reciprocal"(%0) : (tensor<1xf32>) -> tensor<1xf32>
+  %23 = "tosa.reciprocal"(%0) : (tensor<1xf32>) -> tensor<1xf32>
 
   return
 }
@@ -396,11 +391,6 @@
   // CHECK: select
   %19 = "tosa.clamp"(%0) {min_int = 1 : i64, max_int = 5 : i64, min_fp = 1.0 : f32, max_fp = 5.0 : f32} : (tensor<1xi32>) -> tensor<1xi32>
 
-  // CHECK: linalg.generic
-  // CHECK: arith.cmpi
-  // CHECK: select
-  %20 = "tosa.reluN"(%0) {max_int = 5 : i64, max_fp = 5.0 : f32} : (tensor<1xi32>) -> tensor<1xi32>
-
   // CHECK: linalg.generic
   // CHECK: arith.constant -32768
   // CHECK: arith.constant 32767
@@ -409,27 +399,27 @@
   // CHECK: arith.cmpi slt
   // CHECK: select
   // CHECK: arith.trunci
-  %21 = "tosa.cast"(%0) : (tensor<1xi32>) -> tensor<1xi16>
+  %20 = "tosa.cast"(%0) : (tensor<1xi32>) -> tensor<1xi16>
 
   // CHECK: linalg.generic
   // CHECK: arith.extsi
-  %22 = "tosa.cast"(%0) : (tensor<1xi32>) -> tensor<1xi64>
+  %21 = "tosa.cast"(%0) : (tensor<1xi32>) -> tensor<1xi64>
 
   // CHECK: linalg.generic
   // CHECK: arith.constant 0
   // CHECK: arith.cmpi
-  %23 = "tosa.cast"(%0) : (tensor<1xi32>) -> tensor<1xi1>
+  %22 = "tosa.cast"(%0) : (tensor<1xi32>) -> tensor<1xi1>
 
   // CHECK: linalg.generic
   // CHECK: arith.sitofp
-  %24 = "tosa.cast"(%0) : (tensor<1xi32>) -> tensor<1xf32>
+  %23 = "tosa.cast"(%0) : (tensor<1xi32>) -> tensor<1xf32>
 
   // CHECK: linalg.generic
   // CHECK: arith.constant 0
   // CHECK: arith.cmpi sgt
   // CHECK: arith.subi
   // CHECK: select
-  %25 = "tosa.abs"(%arg0) : (tensor<1xi32>) -> tensor<1xi32>
+  %24 = "tosa.abs"(%arg0) : (tensor<1xi32>) -> tensor<1xi32>
 
   return
 }
@@ -1236,7 +1226,7 @@
   // CHECK-DAG: [[INDEX4:%.+]] = arith.constant 4 : index
   // CHECK-DAG: [[CST:%.+]] = arith.constant 0.000000e+00 : f32
   // CHECK: tensor.pad %arg0 low{{\[}}%{{.*}}, [[INDEX3]]] high{{\[}}[[INDEX2]], [[INDEX4]]]  {
-  // CHECK: ^bb0(%arg1: index, %arg2: index):  
+  // CHECK: ^bb0(%arg1: index, %arg2: index):
   // CHECK:   tensor.yield [[CST]]
   // CHECK: } : tensor<1x2xf32> to tensor<4x9xf32>
   %1 = "tosa.pad"(%arg0, %0)  : (tensor<1x2xf32>, tensor<2x2xi32>)  -> (tensor<4x9xf32>)
@@ -1272,7 +1262,7 @@
   // CHECK-DAG: [[INDEX4:%.+]] = arith.constant 4 : index
   // CHECK-DAG: [[CST:%.+]] = arith.constant 4.200000e+01 : f32
   // CHECK: tensor.pad %arg0 low{{\[}}%{{.*}}, [[INDEX3]]] high{{\[}}[[INDEX2]], [[INDEX4]]]  {
-  // CHECK: ^bb0(%arg1: index, %arg2: index):  
+  // CHECK: ^bb0(%arg1: index, %arg2: index):
   // CHECK:   tensor.yield [[CST]]
   // CHECK: } : tensor<1x2xf32> to tensor<4x9xf32>
   %1 = arith.constant dense<42.0> : tensor<f32>
diff --git a/mlir/test/Dialect/Tosa/ops.mlir b/mlir/test/Dialect/Tosa/ops.mlir
--- a/mlir/test/Dialect/Tosa/ops.mlir
+++ b/mlir/test/Dialect/Tosa/ops.mlir
@@ -86,14 +86,6 @@
   return %0 : tensor<13x21x3xf32>
 }
 
-// -----
-// CHECK-LABEL: relu
-func.func @test_relu(%arg0: tensor<13x21x3xf32>) -> tensor<13x21x3xf32> {
-  %0 = "tosa.reluN"(%arg0) {max_fp = 3.40282347E+38 : f32, max_int = 0 : i64} : (tensor<13x21x3xf32>) -> tensor<13x21x3xf32>
-  return %0 : tensor<13x21x3xf32>
-}
-
-
 // -----
 // CHECK-LABEL: sigmoid
 func.func @test_sigmoid(%arg0: tensor<13x21x3xf32>) -> tensor<13x21x3xf32> {
@@ -506,11 +498,11 @@
 // CHECK-LABEL: cond_if
 func.func @test_cond_if(%arg0: tensor<f32>, %arg1: tensor<f32>, %arg2: tensor<i1>) -> tensor<f32> {
   %0 = "tosa.cond_if"(%arg2, %arg0, %arg1) ({
-  ^bb0(%arg3: tensor<f32>, %arg4: tensor<f32>):  
+  ^bb0(%arg3: tensor<f32>, %arg4: tensor<f32>):
     %1 = "tosa.add"(%arg3, %arg4) : (tensor<f32>, tensor<f32>) -> tensor<f32>
     "tosa.yield"(%1) : (tensor<f32>) -> ()
   },  {
-  ^bb0(%arg3: tensor<f32>, %arg4: tensor<f32>):  
+  ^bb0(%arg3: tensor<f32>, %arg4: tensor<f32>):
     %1 = "tosa.sub"(%arg3, %arg4) : (tensor<f32>, tensor<f32>) -> tensor<f32>
     "tosa.yield"(%1) : (tensor<f32>) -> ()
   }) : (tensor<i1>, tensor<f32>, tensor<f32>) -> tensor<f32>
@@ -522,12 +514,12 @@
 func.func @test_while_loop(%arg0: tensor<10xi32>, %arg1: tensor<i32>) {
   %0 = "tosa.const"() {value = dense<0> : tensor<i32>} : () -> tensor<i32>
   %1:3 = "tosa.while_loop"(%0, %0, %arg0) ({
-  ^bb0(%arg2: tensor<i32>, %arg3: tensor<i32>, %arg4: tensor<10xi32>):  
+  ^bb0(%arg2: tensor<i32>, %arg3: tensor<i32>, %arg4: tensor<10xi32>):
     %2 = "tosa.greater_equal"(%arg3, %arg1) : (tensor<i32>, tensor<i32>) -> tensor<i1>
     %3 = "tosa.logical_not"(%2) : (tensor<i1>) -> tensor<i1>
     "tosa.yield"(%3) : (tensor<i1>) -> ()
   },  {
-  ^bb0(%arg2: tensor<i32>, %arg3: tensor<i32>, %arg4: tensor<10xi32>):  
+  ^bb0(%arg2: tensor<i32>, %arg3: tensor<i32>, %arg4: tensor<10xi32>):
     %2 = "tosa.const"() {value = dense<1> : tensor<i32>} : () -> tensor<i32>
     %3 = "tosa.add"(%arg3, %2) : (tensor<i32>, tensor<i32>) -> tensor<i32>
     %4 = "tosa.reshape"(%2) {new_shape = [1]} : (tensor<i32>) -> tensor<1xi32>
diff --git a/mlir/test/Dialect/Tosa/tosa-infer-shapes.mlir b/mlir/test/Dialect/Tosa/tosa-infer-shapes.mlir
--- a/mlir/test/Dialect/Tosa/tosa-infer-shapes.mlir
+++ b/mlir/test/Dialect/Tosa/tosa-infer-shapes.mlir
@@ -51,23 +51,20 @@
   // CHECK: "tosa.reciprocal"(%arg0) : (tensor<4xf32>) -> tensor<4xf32>
   %7 = "tosa.reciprocal"(%arg0) : (tensor<4xf32>) -> tensor<*xf32>
 
-  // CHECK: "tosa.reluN"(%arg0) {{.+}} : (tensor<4xf32>) -> tensor<4xf32>
-  %8 = "tosa.reluN"(%arg0) { max_int = 10 : i64, min_int = 0 : i64, min_fp = 0.0 : f32, max_fp = 10.0 : f32 } : (tensor<4xf32>) -> tensor<*xf32>
-
   // CHECK: "tosa.reverse"(%arg0) {axis = 0 : i64} : (tensor<4xf32>) -> tensor<4xf32>
-  %9 = "tosa.reverse"(%arg0) { axis = 0 : i64 } : (tensor<4xf32>) -> tensor<?xf32>
+  %8 = "tosa.reverse"(%arg0) { axis = 0 : i64 } : (tensor<4xf32>) -> tensor<?xf32>
 
   // CHECK: "tosa.rsqrt"(%arg0) : (tensor<4xf32>) -> tensor<4xf32>
-  %10 = "tosa.rsqrt"(%arg0) : (tensor<4xf32>) -> tensor<*xf32>
+  %9 = "tosa.rsqrt"(%arg0) : (tensor<4xf32>) -> tensor<*xf32>
 
   // CHECK: "tosa.tanh"(%arg0) : (tensor<4xf32>) -> tensor<4xf32>
-  %11 = "tosa.tanh"(%arg0) : (tensor<4xf32>) -> tensor<*xf32>
+  %10 = "tosa.tanh"(%arg0) : (tensor<4xf32>) -> tensor<*xf32>
 
   // CHECK: "tosa.sigmoid"(%arg0) : (tensor<4xf32>) -> tensor<4xf32>
-  %12 = "tosa.sigmoid"(%arg0) : (tensor<4xf32>) -> tensor<*xf32>
+  %11 = "tosa.sigmoid"(%arg0) : (tensor<4xf32>) -> tensor<*xf32>
 
   // CHECK: "tosa.cast"(%arg0) : (tensor<4xf32>) -> tensor<4xi32>
-  %13 = "tosa.cast"(%arg0) : (tensor<4xf32>) -> tensor<*xi32>
+  %12 = "tosa.cast"(%arg0) : (tensor<4xf32>) -> tensor<*xi32>
   return
 }
 
@@ -90,17 +87,14 @@
   // CHECK: "tosa.negate"(%arg0) : (tensor<4xi32>) -> tensor<4xi32>
   %4 = "tosa.negate"(%arg0) : (tensor<4xi32>) -> tensor<*xi32>
 
-  // CHECK: "tosa.reluN"(%arg0) {{.+}} : (tensor<4xi32>) -> tensor<4xi32>
-  %5 = "tosa.reluN"(%arg0) { max_int = 10 : i64, min_int = 0 : i64, min_fp = 0.0 : f32, max_fp = 10.0 : f32 } : (tensor<4xi32>) -> tensor<*xi32>
-
   // CHECK: "tosa.reverse"(%arg0) {axis = 0 : i64} : (tensor<4xi32>) -> tensor<4xi32>
-  %6 = "tosa.reverse"(%arg0) { axis = 0 : i64 } : (tensor<4xi32>) -> tensor<?xi32>
+  %5 = "tosa.reverse"(%arg0) { axis = 0 : i64 } : (tensor<4xi32>) -> tensor<?xi32>
 
   // CHECK: "tosa.rescale"(%arg0) {{.+}} : (tensor<4xi32>) -> tensor<4xi16>
-  %7 = "tosa.rescale"(%arg0) {input_zp = 243 : i32, output_zp = 252 : i32, multiplier = [42 : i32, 43 : i32], shift = [14 : i32, 15 : i32], scale32 = false, double_round = false, per_channel = false} : (tensor<4xi32>)  -> (tensor<*xi16>)
+  %6 = "tosa.rescale"(%arg0) {input_zp = 243 : i32, output_zp = 252 : i32, multiplier = [42 : i32, 43 : i32], shift = [14 : i32, 15 : i32], scale32 = false, double_round = false, per_channel = false} : (tensor<4xi32>)  -> (tensor<*xi16>)
 
   // CHECK: "tosa.identity"(%arg0) : (tensor<4xi32>) -> tensor<4xi32>
-  %8 = "tosa.identity"(%arg0) : (tensor<4xi32>) -> tensor<?xi32>
+  %7 = "tosa.identity"(%arg0) : (tensor<4xi32>) -> tensor<?xi32>
   return
 }
 
@@ -1125,7 +1119,7 @@
 
 // CHECK-LABEL: @while_test
 func.func @while_test(%arg0 : tensor<i32>) -> (tensor<*xi32>) {
-  // CHECK:      "tosa.add" 
+  // CHECK:      "tosa.add"
   // CHECK-SAME: (tensor<i32>, tensor<i32>) -> tensor<i32>
   %0 = "tosa.add"(%arg0, %arg0) : (tensor<i32>, tensor<i32>) -> tensor<*xi32>