diff --git a/image_analysis/bragg_integration/BraggIntegrationEngineGPU.cu b/image_analysis/bragg_integration/BraggIntegrationEngineGPU.cu
index b0a3d6a5..2de35c7d 100644
--- a/image_analysis/bragg_integration/BraggIntegrationEngineGPU.cu
+++ b/image_analysis/bragg_integration/BraggIntegrationEngineGPU.cu
@@ -434,25 +434,29 @@ BraggIntegrationEngineGPU::BraggIntegrationEngineGPU(const DiffractionExperiment
 void BraggIntegrationEngineGPU::EnsureCapacity(size_t n) {
     if (n <= capacity)
         return;
-    d_px_x = CudaDevicePtr<float>(n);
-    d_px_y = CudaDevicePtr<float>(n);
-    d_d = CudaDevicePtr<float>(n);
-    d_cx = CudaDevicePtr<int>(n);
-    d_cy = CudaDevicePtr<int>(n);
-    d_I = CudaDevicePtr<float>(n);
-    d_sigma = CudaDevicePtr<float>(n);
-    d_bkg = CudaDevicePtr<float>(n);
-    d_obs_x = CudaDevicePtr<float>(n);
-    d_obs_y = CudaDevicePtr<float>(n);
-    d_ok = CudaDevicePtr<uint8_t>(n);
-    d_strong = CudaDevicePtr<uint8_t>(n);
-    d_has_obs = CudaDevicePtr<uint8_t>(n);
+    // Grow with slack. cudaMalloc/cudaFree take a device-wide lock in the driver, so growing to
+    // exactly n makes every image that sets a new reflection-count record stall all other workers.
+    const size_t new_capacity = std::max(n, capacity + capacity / 2);
 
-    h_px_x.resize(n); h_px_y.resize(n); h_d.resize(n);
-    h_I.resize(n); h_sigma.resize(n); h_bkg.resize(n);
-    h_obs_x.resize(n); h_obs_y.resize(n);
-    h_ok.resize(n); h_has_obs.resize(n);
-    capacity = n;
+    d_px_x = CudaDevicePtr<float>(new_capacity);
+    d_px_y = CudaDevicePtr<float>(new_capacity);
+    d_d = CudaDevicePtr<float>(new_capacity);
+    d_cx = CudaDevicePtr<int>(new_capacity);
+    d_cy = CudaDevicePtr<int>(new_capacity);
+    d_I = CudaDevicePtr<float>(new_capacity);
+    d_sigma = CudaDevicePtr<float>(new_capacity);
+    d_bkg = CudaDevicePtr<float>(new_capacity);
+    d_obs_x = CudaDevicePtr<float>(new_capacity);
+    d_obs_y = CudaDevicePtr<float>(new_capacity);
+    d_ok = CudaDevicePtr<uint8_t>(new_capacity);
+    d_strong = CudaDevicePtr<uint8_t>(new_capacity);
+    d_has_obs = CudaDevicePtr<uint8_t>(new_capacity);
+
+    h_px_x.resize(new_capacity); h_px_y.resize(new_capacity); h_d.resize(new_capacity);
+    h_I.resize(new_capacity); h_sigma.resize(new_capacity); h_bkg.resize(new_capacity);
+    h_obs_x.resize(new_capacity); h_obs_y.resize(new_capacity);
+    h_ok.resize(new_capacity); h_has_obs.resize(new_capacity);
+    capacity = new_capacity;
 }
 
 std::vector<Reflection> BraggIntegrationEngineGPU::Run(const ImagePreprocessorBuffer &image,