diff --git a/mlir/lib/Conversion/LoopsToGPU/LoopsToGPU.cpp b/mlir/lib/Conversion/LoopsToGPU/LoopsToGPU.cpp
--- a/mlir/lib/Conversion/LoopsToGPU/LoopsToGPU.cpp
+++ b/mlir/lib/Conversion/LoopsToGPU/LoopsToGPU.cpp
@@ -403,10 +403,10 @@
   Value constOne = (numBlockDims < 3 || numThreadDims < 3)
                        ? builder.create<ConstantIndexOp>(rootForOp.getLoc(), 1)
                        : nullptr;
-  Value gridSizeX = dims[0];
+  Value gridSizeX = numBlockDims > 0 ? dims[0] : constOne;
   Value gridSizeY = numBlockDims > 1 ? dims[1] : constOne;
   Value gridSizeZ = numBlockDims > 2 ? dims[2] : constOne;
-  Value blockSizeX = dims[numBlockDims];
+  Value blockSizeX = numThreadDims > 0 ? dims[numBlockDims] : constOne;
   Value blockSizeY = numThreadDims > 1 ? dims[numBlockDims + 1] : constOne;
   Value blockSizeZ = numThreadDims > 2 ? dims[numBlockDims + 2] : constOne;
 
diff --git a/mlir/test/Conversion/LoopsToGPU/no_blocks_no_threads.mlir b/mlir/test/Conversion/LoopsToGPU/no_blocks_no_threads.mlir
new file mode 100644
--- /dev/null
+++ b/mlir/test/Conversion/LoopsToGPU/no_blocks_no_threads.mlir
@@ -0,0 +1,34 @@
+// RUN: mlir-opt -convert-loops-to-gpu -gpu-block-dims=0 -gpu-thread-dims=1 %s | FileCheck --check-prefix=CHECK-THREADS %s --dump-input-on-failure
+// RUN: mlir-opt -convert-loops-to-gpu -gpu-block-dims=1 -gpu-thread-dims=0 %s | FileCheck --check-prefix=CHECK-BLOCKS %s --dump-input-on-failure
+
+// CHECK-THREADS-LABEL: @one_d_loop
+// CHECK-BLOCKS-LABEL: @one_d_loop
+func @one_d_loop(%A : memref<?xf32>, %B : memref<?xf32>) {
+  // Bounds of the loop, its range and step.
+  // CHECK-THREADS-NEXT: %{{.*}} = constant 0 : index
+  // CHECK-THREADS-NEXT: %{{.*}} = constant 42 : index
+  // CHECK-THREADS-NEXT: %[[BOUND:.*]] = subi %{{.*}}, %{{.*}} : index
+  // CHECK-THREADS-NEXT: %{{.*}} = constant 1 : index
+  // CHECK-THREADS-NEXT: %[[ONE:.*]] = constant 1 : index
+  //
+  // CHECK-BLOCKS-NEXT: %{{.*}} = constant 0 : index
+  // CHECK-BLOCKS-NEXT: %{{.*}} = constant 42 : index
+  // CHECK-BLOCKS-NEXT: %[[BOUND:.*]] = subi %{{.*}}, %{{.*}} : index
+  // CHECK-BLOCKS-NEXT: %{{.*}} = constant 1 : index
+  // CHECK-BLOCKS-NEXT: %[[ONE:.*]] = constant 1 : index
+
+  // CHECK-THREADS-NEXT: gpu.launch blocks(%[[B0:.*]], %[[B1:.*]], %[[B2:.*]]) in (%{{.*}} = %[[ONE]], %{{.*}} = %[[ONE]], %{{.*}}0 = %[[ONE]]) threads(%[[T0:.*]], %[[T1:.*]], %[[T2:.*]]) in (%{{.*}} = %[[BOUND]], %{{.*}} = %[[ONE]], %{{.*}} = %[[ONE]])
+  // CHECK-BLOCKS-NEXT: gpu.launch blocks(%[[B0:.*]], %[[B1:.*]], %[[B2:.*]]) in (%{{.*}} = %[[BOUND]], %{{.*}} = %[[ONE]], %{{.*}}0 = %[[ONE]]) threads(%[[T0:.*]], %[[T1:.*]], %[[T2:.*]]) in (%{{.*}} = %[[ONE]], %{{.*}} = %[[ONE]], %{{.*}} = %[[ONE]])
+  affine.for %i = 0 to 42 {
+  // CHECK-THREADS-NEXT: %[[INDEX:.*]] = addi %{{.*}}, %[[T0]]
+  // CHECK-THREADS-NEXT: load %{{.*}}[%[[INDEX]]]
+  // CHECK-BLOCKS-NEXT: %[[INDEX:.*]] = addi %{{.*}}, %[[B0]]
+  // CHECK-BLOCKS-NEXT: load %{{.*}}[%[[INDEX]]]
+    %0 = load %A[%i] : memref<?xf32>
+    store %0, %B[%i] : memref<?xf32>
+    // CHECK-THREADS: gpu.terminator
+    // CHECK-BLOCKS: gpu.terminator
+  }
+  return
+}
+