diff --git a/devito/operator/xdsl_operator.py b/devito/operator/xdsl_operator.py
index d725dd2715a..67d512d3e79 100644
--- a/devito/operator/xdsl_operator.py
+++ b/devito/operator/xdsl_operator.py
@@ -51,7 +51,7 @@
 MLIR_CPU_PIPELINE = '"builtin.module(canonicalize, cse, loop-invariant-code-motion, canonicalize, cse, loop-invariant-code-motion,cse,canonicalize,fold-memref-alias-ops,expand-strided-metadata, loop-invariant-code-motion,lower-affine,convert-scf-to-cf,convert-math-to-llvm,convert-func-to-llvm{use-bare-ptr-memref-call-conv},finalize-memref-to-llvm,canonicalize,cse)"'
 MLIR_OPENMP_PIPELINE = '"builtin.module(canonicalize, cse, loop-invariant-code-motion, canonicalize, cse, loop-invariant-code-motion,cse,canonicalize,fold-memref-alias-ops,expand-strided-metadata, loop-invariant-code-motion,lower-affine,finalize-memref-to-llvm,loop-invariant-code-motion,canonicalize,cse,convert-scf-to-openmp,finalize-memref-to-llvm,convert-scf-to-cf,convert-func-to-llvm{use-bare-ptr-memref-call-conv},convert-openmp-to-llvm,convert-math-to-llvm,reconcile-unrealized-casts,canonicalize,cse)"'
 # gpu-launch-sink-index-computations seemed to have no impact
-MLIR_GPU_PIPELINE = lambda block_sizes: f'"builtin.module(test-math-algebraic-simplification,scf-parallel-loop-tiling{{parallel-loop-tile-sizes={block_sizes}}},func.func(gpu-map-parallel-loops),convert-parallel-loops-to-gpu,fold-memref-alias-ops,expand-strided-metadata,lower-affine,canonicalize,cse,gpu-kernel-outlining,func.func(gpu-async-region),canonicalize,cse,convert-arith-to-llvm{{index-bitwidth=64}},finalize-memref-to-llvm{{index-bitwidth=64}},convert-scf-to-cf,convert-cf-to-llvm{{index-bitwidth=64}},canonicalize,cse,convert-func-to-llvm{{use-bare-ptr-memref-call-conv}},gpu.module(convert-gpu-to-nvvm,reconcile-unrealized-casts,canonicalize,gpu-to-cubin),gpu-to-llvm,canonicalize,cse)"'
+MLIR_GPU_PIPELINE = lambda block_sizes: f'"builtin.module(test-math-algebraic-simplification,scf-parallel-loop-tiling{{parallel-loop-tile-sizes={block_sizes}}},func.func(gpu-map-parallel-loops),convert-parallel-loops-to-gpu,lower-affine, canonicalize,cse, gpu-launch-sink-index-computations, gpu-kernel-outlining, canonicalize{{region-simplify}},cse,fold-memref-alias-ops,expand-strided-metadata,lower-affine,canonicalize,cse,gpu-kernel-outlining,func.func(gpu-async-region),canonicalize,cse,convert-arith-to-llvm{{index-bitwidth=64}},finalize-memref-to-llvm{{index-bitwidth=64}},convert-scf-to-cf,convert-cf-to-llvm{{index-bitwidth=64}},canonicalize,cse,convert-func-to-llvm{{use-bare-ptr-memref-call-conv}},gpu.module(convert-gpu-to-nvvm,reconcile-unrealized-casts,canonicalize,gpu-to-cubin),gpu-to-llvm,canonicalize,cse)"'
 
 XDSL_CPU_PIPELINE = "stencil-shape-inference,convert-stencil-to-ll-mlir,printf-to-llvm"
 XDSL_GPU_PIPELINE = "stencil-shape-inference,convert-stencil-to-ll-mlir{target=gpu},reconcile-unrealized-casts,printf-to-llvm"