diff --git a/image_analysis/spot_finding/AdaptiveSpotFinderGPU.cu b/image_analysis/spot_finding/AdaptiveSpotFinderGPU.cu
index a20caa01..8ec5328f 100644
--- a/image_analysis/spot_finding/AdaptiveSpotFinderGPU.cu
+++ b/image_analysis/spot_finding/AdaptiveSpotFinderGPU.cu
@@ -191,6 +191,12 @@ AdaptiveSpotFinderGPU::AdaptiveSpotFinderGPU(const AzimuthalIntegrationMapping &
       prof_sum(nbins),
       prof_sum2(nbins),
       prof_count(nbins),
+      host_sum_reg(host_sum),
+      host_sum2_reg(host_sum2),
+      host_count_reg(host_count),
+      prof_sum_reg(prof_sum),
+      prof_sum2_reg(prof_sum2),
+      prof_count_reg(prof_count),
       extractor(static_cast<int32_t>(in_mapping.GetWidth()),
                 static_cast<int32_t>(in_mapping.GetHeight()), std::move(in_stream)),
       last_profile(in_mapping) {
diff --git a/image_analysis/spot_finding/AdaptiveSpotFinderGPU.h b/image_analysis/spot_finding/AdaptiveSpotFinderGPU.h
index 5eecba20..f4beaa5b 100644
--- a/image_analysis/spot_finding/AdaptiveSpotFinderGPU.h
+++ b/image_analysis/spot_finding/AdaptiveSpotFinderGPU.h
@@ -80,6 +80,18 @@ class AdaptiveSpotFinderGPU : public ImageSpotFinder {
     std::vector<float>    prof_sum2;   // plain corrected sum^2 }
     std::vector<uint32_t> prof_count;  // plain pixel count     }
 
+    // Every per-ring array above is a device-to-host copy once per frame. A D2H copy into PAGEABLE
+    // memory blocks the host until it completes, whatever stream it was issued on - which would stall
+    // Detect() between the plain pass and the clip passes, with the device then idle while the host
+    // enqueues them. Pinning the destinations makes the copies genuinely asynchronous, as the
+    // azimuthal-integration engine already does with its own.
+    CudaRegisteredVector<unsigned long long> host_sum_reg;
+    CudaRegisteredVector<unsigned long long> host_sum2_reg;
+    CudaRegisteredVector<uint32_t> host_count_reg;
+    CudaRegisteredVector<float>    prof_sum_reg;
+    CudaRegisteredVector<float>    prof_sum2_reg;
+    CudaRegisteredVector<uint32_t> prof_count_reg;
+
     SpotExtractorGPU extractor;   // builds the spots from gpu_strong without it leaving the device
 
     AzimuthalIntegrationProfile last_profile;   // filled every Run(), retrievable via GetProfile()