diff --git a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
--- a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
+++ b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
@@ -189,6 +189,8 @@
                                                      "__nv_cos");
   patterns.insert<OpToFuncCallLowering<math::ExpOp>>(converter, "__nv_expf",
                                                      "__nv_exp");
+  patterns.insert<OpToFuncCallLowering<math::ExpM1Op>>(converter, "__nv_expm1f",
+                                                       "__nv_expm1");
   patterns.insert<OpToFuncCallLowering<FloorFOp>>(converter, "__nv_floorf",
                                                   "__nv_floor");
   patterns.insert<OpToFuncCallLowering<math::LogOp>>(converter, "__nv_logf",
diff --git a/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp b/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
--- a/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
+++ b/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
@@ -120,6 +120,8 @@
       converter, "__ocml_cos_f32", "__ocml_cos_f64");
   patterns.insert<OpToFuncCallLowering<math::ExpOp>>(
       converter, "__ocml_exp_f32", "__ocml_exp_f64");
+  patterns.insert<OpToFuncCallLowering<math::ExpM1Op>>(
+      converter, "__ocml_expm1_f32", "__ocml_expm1_f64");
   patterns.insert<OpToFuncCallLowering<FloorFOp>>(converter, "__ocml_floor_f32",
                                                   "__ocml_floor_f64");
   patterns.insert<OpToFuncCallLowering<math::LogOp>>(
diff --git a/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir b/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
--- a/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
+++ b/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
@@ -411,6 +411,21 @@
 
 // -----
 
+gpu.module @test_module {
+  // CHECK: llvm.func @__nv_expm1f(f32) -> f32
+  // CHECK: llvm.func @__nv_expm1(f64) -> f64
+  // CHECK-LABEL: func @gpu_expm1
+  func @gpu_expm1(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
+    %result32 = math.expm1 %arg_f32 : f32
+    // CHECK: llvm.call @__nv_expm1f(%{{.*}}) : (f32) -> f32
+    %result64 = math.expm1 %arg_f64 : f64
+    // CHECK: llvm.call @__nv_expm1(%{{.*}}) : (f64) -> f64
+    std.return %result32, %result64 : f32, f64
+  }
+}
+
+// -----
+
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_powf(f32, f32) -> f32
   // CHECK: llvm.func @__nv_pow(f64, f64) -> f64
diff --git a/mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir b/mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir
--- a/mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir
+++ b/mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir
@@ -143,6 +143,7 @@
 }
 
 // -----
+
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_exp_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_exp_f64(f64) -> f64
@@ -183,6 +184,23 @@
 
 // -----
 
+gpu.module @test_module {
+  // CHECK: llvm.func @__ocml_expm1_f32(f32) -> f32
+  // CHECK: llvm.func @__ocml_expm1_f64(f64) -> f64
+  // CHECK-LABEL: func @gpu_expm1
+  func @gpu_expm1(%arg_f32 : f32, %arg_f64 : f64) -> (f32, f64) {
+    %expm1_f32 = math.expm1 %arg_f32 : f32
+    // CHECK: llvm.call @__ocml_expm1_f32(%{{.*}}) : (f32) -> f32
+    %result32 = math.expm1 %expm1_f32 : f32
+    // CHECK: llvm.call @__ocml_expm1_f32(%{{.*}}) : (f32) -> f32
+    %result64 = math.expm1 %arg_f64 : f64
+    // CHECK: llvm.call @__ocml_expm1_f64(%{{.*}}) : (f64) -> f64
+    std.return %result32, %result64 : f32, f64
+  }
+}
+
+// -----
+
 gpu.module @test_module {
   // CHECK: llvm.func @__ocml_log_f32(f32) -> f32
   // CHECK: llvm.func @__ocml_log_f64(f64) -> f64