diff --git a/PerfectNumbers.Core/ULongExtensions.Gpu.cs b/PerfectNumbers.Core/ULongExtensions.Gpu.cs
index 4c6c2a5..67eb9ef 100644
--- a/PerfectNumbers.Core/ULongExtensions.Gpu.cs
+++ b/PerfectNumbers.Core/ULongExtensions.Gpu.cs
@@ -19,7 +19,7 @@ public static partial class ULongExtensions
 	}
 
 	[MethodImpl(MethodImplOptions.AggressiveInlining)]
-	[Obsolete("Deprecated: use ULongExtensions.MulMod64 for CPU code and GpuUInt128.MulMod inside GPU kernels.")]
+	[Obsolete("Use ULongExtensions.GpuCompatibleMulModSimplifiedExtension for GPU-compatible host code or GpuUInt128.MulMod inside kernels.")]
 	public static ulong MulMod64Gpu(this ulong a, ulong b, ulong modulus)
 	{
 		// TODO: Remove this GPU-compatible shim from production once callers migrate to MulMod64,
@@ -29,6 +29,7 @@ public static partial class ULongExtensions
 	}
 
 	[MethodImpl(MethodImplOptions.AggressiveInlining)]
+	[Obsolete("Use ULongExtensions.GpuCompatibleMulModSimplifiedExtension for GPU-compatible host code or GpuUInt128.MulMod inside kernels.")]
 	public static ulong MulMod64GpuDeferred(this ulong a, ulong b, ulong modulus)
 	{
 		// TODO: Move this deferred helper to the benchmark suite; the baseline MulMod64 avoids the
@@ -37,6 +38,13 @@ public static partial class ULongExtensions
 		return state.MulModWithNativeModulo(b, modulus);
 	}
 
+	[MethodImpl(MethodImplOptions.AggressiveInlining)]
+	public static ulong GpuCompatibleMulModSimplifiedExtension(this ulong left, ulong right, ulong modulus)
+	{
+		GpuUInt128 state = new(left);
+		return state.MulModSimplified(right, modulus);
+	}
+
 	[MethodImpl(MethodImplOptions.AggressiveInlining)]
 	public static ulong Pow2ModWindowedGpu(this ulong exponent, ulong modulus)
 	{
diff --git a/docs/gpu-bydivisor-mulmod-audit.md b/docs/gpu-bydivisor-mulmod-audit.md
index c47b503..cdbf42f 100644
--- a/docs/gpu-bydivisor-mulmod-audit.md
+++ b/docs/gpu-bydivisor-mulmod-audit.md
@@ -6,7 +6,8 @@ This note tracks every `MulMod` call site in the GPU-only `--mersenne=bydivisor`
 
 | Location | Notes |
 | --- | --- |
-| `ULongExtensions.MulMod64Gpu` | Marked as deprecated to steer new code toward `MulMod64` on the CPU and `GpuUInt128.MulMod` inside GPU kernels. The shim remains only for legacy callers that require the GPU-compatible arithmetic façade.【F:PerfectNumbers.Core/ULongExtensions.Gpu.cs†L1-L33】 |
+| `ULongExtensions.GpuCompatibleMulModSimplifiedExtension` | Wraps `GpuUInt128.MulModSimplified` so host code mirrors the benchmark winner without reimplementing GPU logic.【F:PerfectNumbers.Core/ULongExtensions.Gpu.cs†L23-L31】 |
+| `ULongExtensions.MulMod64Gpu` | Marked obsolete; migrate to `ULongExtensions.GpuCompatibleMulModSimplifiedExtension` for GPU-compatible host code or `GpuUInt128.MulMod` when running inside kernels.【F:PerfectNumbers.Core/ULongExtensions.Gpu.cs†L17-L24】 |
 | `ULongExtensions.Pow2ModWindowedGpu` | Migrated to call `MulMod64` for every square and multiply, eliminating the 6–18× slowdown that the shim introduced while executing on the host.【F:PerfectNumbers.Core/ULongExtensions.Gpu.cs†L39-L109】 |
 | `ULongExtensions.InitializeStandardOddPowers` | Populates the odd-power table through `MulMod64`, so the host setup costs now match the CPU benchmark baseline.【F:PerfectNumbers.Core/ULongExtensions.Gpu.cs†L286-L309】 |