diff --git a/mlir/include/mlir/Dialect/Affine/Passes.h b/mlir/include/mlir/Dialect/Affine/Passes.h
index bc29d04287ac4..ea5034b60d8bd 100644
--- a/mlir/include/mlir/Dialect/Affine/Passes.h
+++ b/mlir/include/mlir/Dialect/Affine/Passes.h
@@ -14,6 +14,7 @@
 #ifndef MLIR_DIALECT_AFFINE_PASSES_H
 #define MLIR_DIALECT_AFFINE_PASSES_H
 
+#include "mlir/Interfaces/FunctionInterfaces.h"
 #include "mlir/Pass/Pass.h"
 #include <limits>
 
@@ -93,7 +94,7 @@ std::unique_ptr<OperationPass<func::FuncOp>> createLoopTilingPass();
 /// factors supplied through other means. If -1 is passed as the unrollFactor
 /// and no callback is provided, anything passed from the command-line (if at
 /// all) or the default unroll factor is used (LoopUnroll:kDefaultUnrollFactor).
-std::unique_ptr<OperationPass<func::FuncOp>> createLoopUnrollPass(
+std::unique_ptr<InterfacePass<FunctionOpInterface>> createLoopUnrollPass(
     int unrollFactor = -1, bool unrollUpToFactor = false,
     bool unrollFull = false,
     const std::function<unsigned(AffineForOp)> &getUnrollFactor = nullptr);
diff --git a/mlir/include/mlir/Dialect/Affine/Passes.td b/mlir/include/mlir/Dialect/Affine/Passes.td
index d7c7897c65730..5325d3b0a1d69 100644
--- a/mlir/include/mlir/Dialect/Affine/Passes.td
+++ b/mlir/include/mlir/Dialect/Affine/Passes.td
@@ -199,7 +199,7 @@ def AffineLoopTiling : Pass<"affine-loop-tile", "func::FuncOp"> {
   ];
 }
 
-def AffineLoopUnroll : Pass<"affine-loop-unroll", "func::FuncOp"> {
+def AffineLoopUnroll : InterfacePass<"affine-loop-unroll", "FunctionOpInterface"> {
   let summary = "Unroll affine loops";
   let constructor = "mlir::affine::createLoopUnrollPass()";
   let options = [
diff --git a/mlir/lib/Dialect/Affine/Transforms/LoopUnroll.cpp b/mlir/lib/Dialect/Affine/Transforms/LoopUnroll.cpp
index 57df7ada91654..7ff77968c61ad 100644
--- a/mlir/lib/Dialect/Affine/Transforms/LoopUnroll.cpp
+++ b/mlir/lib/Dialect/Affine/Transforms/LoopUnroll.cpp
@@ -82,7 +82,7 @@ static bool isInnermostAffineForOp(AffineForOp op) {
 }
 
 /// Gathers loops that have no affine.for's nested within.
-static void gatherInnermostLoops(func::FuncOp f,
+static void gatherInnermostLoops(FunctionOpInterface f,
                                  SmallVectorImpl<AffineForOp> &loops) {
   f.walk([&](AffineForOp forOp) {
     if (isInnermostAffineForOp(forOp))
@@ -91,7 +91,7 @@ static void gatherInnermostLoops(func::FuncOp f,
 }
 
 void LoopUnroll::runOnOperation() {
-  func::FuncOp func = getOperation();
+  FunctionOpInterface func = getOperation();
   if (func.isExternal())
     return;
 
@@ -100,8 +100,8 @@ void LoopUnroll::runOnOperation() {
     SmallVector<AffineForOp, 4> loops;
 
     // Gathers all loops with trip count <= minTripCount. Do a post order walk
-    // so that loops are gathered from innermost to outermost (or else unrolling
-    // an outer one may delete gathered inner ones).
+    // so that loops are gathered from innermost to outermost (or else
+    // unrolling an outer one may delete gathered inner ones).
     getOperation().walk([&](AffineForOp forOp) {
       std::optional<uint64_t> tripCount = getConstantTripCount(forOp);
       if (tripCount && *tripCount <= unrollFullThreshold)
@@ -145,7 +145,8 @@ LogicalResult LoopUnroll::runOnAffineForOp(AffineForOp forOp) {
                             cleanUpUnroll);
 }
 
-std::unique_ptr<OperationPass<func::FuncOp>> mlir::affine::createLoopUnrollPass(
+std::unique_ptr<InterfacePass<FunctionOpInterface>>
+mlir::affine::createLoopUnrollPass(
     int unrollFactor, bool unrollUpToFactor, bool unrollFull,
     const std::function<unsigned(AffineForOp)> &getUnrollFactor) {
   return std::make_unique<LoopUnroll>(
diff --git a/mlir/test/Dialect/Affine/unroll.mlir b/mlir/test/Dialect/Affine/unroll.mlir
index e398c3fe2011d..574e9f41494af 100644
--- a/mlir/test/Dialect/Affine/unroll.mlir
+++ b/mlir/test/Dialect/Affine/unroll.mlir
@@ -1,8 +1,9 @@
-// RUN: mlir-opt -allow-unregistered-dialect %s -affine-loop-unroll="unroll-full" | FileCheck %s --check-prefix UNROLL-FULL
-// RUN: mlir-opt -allow-unregistered-dialect %s -affine-loop-unroll="unroll-full unroll-full-threshold=2" | FileCheck %s --check-prefix SHORT
-// RUN: mlir-opt -allow-unregistered-dialect %s -affine-loop-unroll="unroll-factor=4" | FileCheck %s --check-prefix UNROLL-BY-4
-// RUN: mlir-opt -allow-unregistered-dialect %s -affine-loop-unroll="unroll-factor=1" | FileCheck %s --check-prefix UNROLL-BY-1
-// RUN: mlir-opt -allow-unregistered-dialect %s -affine-loop-unroll="unroll-factor=5 cleanup-unroll=true" | FileCheck %s --check-prefix UNROLL-CLEANUP-LOOP
+// RUN: mlir-opt -allow-unregistered-dialect %s -pass-pipeline="builtin.module(func.func(affine-loop-unroll{unroll-full=true}))" | FileCheck %s --check-prefix UNROLL-FULL
+// RUN: mlir-opt -allow-unregistered-dialect %s -pass-pipeline="builtin.module(func.func(affine-loop-unroll{unroll-full=true unroll-full-threshold=2}))" | FileCheck %s --check-prefix SHORT
+// RUN: mlir-opt -allow-unregistered-dialect %s -pass-pipeline="builtin.module(func.func(affine-loop-unroll{unroll-factor=4}))" | FileCheck %s --check-prefix UNROLL-BY-4
+// RUN: mlir-opt -allow-unregistered-dialect %s -pass-pipeline="builtin.module(func.func(affine-loop-unroll{unroll-factor=1}))" | FileCheck %s --check-prefix UNROLL-BY-1
+// RUN: mlir-opt -allow-unregistered-dialect %s -pass-pipeline="builtin.module(func.func(affine-loop-unroll{unroll-factor=5 cleanup-unroll=true}))" | FileCheck %s --check-prefix UNROLL-CLEANUP-LOOP
+// RUN: mlir-opt -allow-unregistered-dialect %s -pass-pipeline="builtin.module(gpu.module(gpu.func(affine-loop-unroll{unroll-full=true})))" | FileCheck %s --check-prefix GPU-UNROLL-FULL
 
 // UNROLL-FULL-DAG: [[$MAP0:#map[0-9]*]] = affine_map<(d0) -> (d0 + 1)>
 // UNROLL-FULL-DAG: [[$MAP1:#map[0-9]*]] = affine_map<(d0) -> (d0 + 2)>
@@ -240,6 +241,23 @@ func.func @loop_nest_unroll_full() {
   return
 } // UNROLL-FULL }
 
+gpu.module @unroll_full {
+  // GPU-UNROLL-FULL-LABEL: func @gpu_loop_nest_simplest() {
+  gpu.func @gpu_loop_nest_simplest() {
+    // GPU-UNROLL-FULL: affine.for %arg0 = 0 to 100 step 2 {
+    affine.for %i = 0 to 100 step 2 {
+      // GPU-UNROLL-FULL: %c1_i32 = arith.constant 1 : i32
+      // GPU-UNROLL-FULL-NEXT: %c1_i32_0 = arith.constant 1 : i32
+      // GPU-UNROLL-FULL-NEXT: %c1_i32_1 = arith.constant 1 : i32
+      // GPU-UNROLL-FULL-NEXT: %c1_i32_2 = arith.constant 1 : i32
+      affine.for %j = 0 to 4 {
+        %x = arith.constant 1 : i32
+      }
+    }           // GPU-UNROLL-FULL:  }
+    gpu.return  // GPU-UNROLL-FULL:  return
+  }
+}
+
 // SHORT-LABEL: func @loop_nest_outer_unroll() {
 func.func @loop_nest_outer_unroll() {
   // SHORT:      affine.for %arg0 = 0 to 4 {
diff --git a/mlir/test/Dialect/SCF/loop-unroll.mlir b/mlir/test/Dialect/SCF/loop-unroll.mlir
index 0368505a1b70d..4c72d9e99d049 100644
--- a/mlir/test/Dialect/SCF/loop-unroll.mlir
+++ b/mlir/test/Dialect/SCF/loop-unroll.mlir
@@ -3,9 +3,9 @@
 // RUN: mlir-opt %s -test-loop-unrolling='unroll-factor=2 loop-depth=0' | FileCheck %s --check-prefix UNROLL-OUTER-BY-2
 // RUN: mlir-opt %s -test-loop-unrolling='unroll-factor=2 loop-depth=1' | FileCheck %s --check-prefix UNROLL-INNER-BY-2
 // RUN: mlir-opt %s -test-loop-unrolling='unroll-factor=2 annotate=true' | FileCheck %s --check-prefix UNROLL-BY-2-ANNOTATE
-// RUN: mlir-opt %s --affine-loop-unroll='unroll-factor=6 unroll-up-to-factor=true' | FileCheck %s --check-prefix UNROLL-UP-TO
-// RUN: mlir-opt %s --affine-loop-unroll='unroll-factor=5 cleanup-unroll=true' | FileCheck %s --check-prefix CLEANUP-UNROLL-BY-5
-// RUN: mlir-opt %s --affine-loop-unroll --split-input-file | FileCheck %s
+// RUN: mlir-opt %s -pass-pipeline="builtin.module(func.func(affine-loop-unroll{unroll-factor=6 unroll-up-to-factor=true}))" | FileCheck %s --check-prefix UNROLL-UP-TO
+// RUN: mlir-opt %s -pass-pipeline="builtin.module(func.func(affine-loop-unroll{unroll-factor=5 cleanup-unroll=true}))" | FileCheck %s --check-prefix CLEANUP-UNROLL-BY-5
+// RUN: mlir-opt %s -pass-pipeline="builtin.module(func.func(affine-loop-unroll))" --split-input-file | FileCheck %s
 
 func.func @dynamic_loop_unroll(%arg0 : index, %arg1 : index, %arg2 : index,
                           %arg3: memref<?xf32>) {