Index: mlir/include/mlir/Dialect/Linalg/Passes.h
===================================================================
--- mlir/include/mlir/Dialect/Linalg/Passes.h
+++ mlir/include/mlir/Dialect/Linalg/Passes.h
@@ -31,7 +31,6 @@
 std::unique_ptr<Pass> createLinalgFoldUnitExtentDimsPass();
 
 std::unique_ptr<Pass> createLinalgElementwiseOpFusionPass();
-std::unique_ptr<Pass> createFoldReshapeOpsByLinearizationPass();
 
 std::unique_ptr<Pass> createLinalgNamedOpConversionPass();
 
Index: mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
===================================================================
--- mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
+++ mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
@@ -254,6 +254,10 @@
       StringAttr::get(&converter.getContext(),
                       NVVM::NVVMDialect::getKernelFuncAttrName()));
 
+  patterns.add<OpToFuncCallLowering<arith::MaxFOp>>(converter, "__nv_fmaxf",
+                                                    "__nv_fmax");
+  patterns.add<OpToFuncCallLowering<arith::MinFOp>>(converter, "__nv_fminf",
+                                                    "__nv_fmin");
   patterns.add<OpToFuncCallLowering<math::AbsOp>>(converter, "__nv_fabsf",
                                                   "__nv_fabs");
   patterns.add<OpToFuncCallLowering<math::AtanOp>>(converter, "__nv_atanf",
Index: mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
===================================================================
--- mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
+++ mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
@@ -166,6 +166,36 @@
 // -----
 
 gpu.module @test_module {
+  // CHECK: llvm.func @__nv_fmaxf(f32, f32) -> f32
+  // CHECK: llvm.func @__nv_fmax(f64, f64) -> f64
+  // CHECK-LABEL: func @gpu_fmax
+  func.func @gpu_fmax(%arg0_f32 : f32, %arg1_f32 : f32, %arg0_f64 : f64, %arg1_f64 : f64) -> (f32, f64) {
+    %result32 = arith.maxf %arg0_f32, %arg1_f32 : f32
+    // CHECK: llvm.call @__nv_fmaxf(%{{.*}}) : (f32, f32) -> f32
+    %result64 = arith.maxf %arg0_f64, %arg1_f64 : f64
+    // CHECK: llvm.call @__nv_fmax(%{{.*}}) : (f64, f64) -> f64
+    func.return %result32, %result64 : f32, f64
+  }
+}
+
+// -----
+
+gpu.module @test_module {
+  // CHECK: llvm.func @__nv_fminf(f32, f32) -> f32
+  // CHECK: llvm.func @__nv_fmin(f64, f64) -> f64
+  // CHECK-LABEL: func @gpu_fmin
+  func.func @gpu_fmin(%arg0_f32 : f32, %arg1_f32 : f32, %arg0_f64 : f64, %arg1_f64 : f64) -> (f32, f64) {
+    %result32 = arith.minf %arg0_f32, %arg1_f32 : f32
+    // CHECK: llvm.call @__nv_fminf(%{{.*}}) : (f32, f32) -> f32
+    %result64 = arith.minf %arg0_f64, %arg1_f64 : f64
+    // CHECK: llvm.call @__nv_fmin(%{{.*}}) : (f64, f64) -> f64
+    func.return %result32, %result64 : f32, f64
+  }
+}
+
+// -----
+
+gpu.module @test_module {
   // CHECK: llvm.func @__nv_fabsf(f32) -> f32
   // CHECK: llvm.func @__nv_fabs(f64) -> f64
   // CHECK-LABEL: func @gpu_fabs