diff --git a/CHANGELOG.md b/CHANGELOG.md
index ef8b88bc9e3..76dd093fa08 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -21,6 +21,7 @@ This release is compatible with NumPy 2.4.5.
 * Updated tests to align with NumPy 2.4.5 compatibility [gh-2920](https://github.com/IntelPython/dpnp/pull/2920)
 * Replaced `.pxi` includes in `dpnp.tensor` with modular `.pxd`/`.pyx` Cython imports [#2913](https://github.com/IntelPython/dpnp/pull/2913)
 * Reimplemented `dpnp.eye` and `dpnp.tensor.eye` with a branchless kernel [gh-2937](https://github.com/IntelPython/dpnp/pull/2937)
+* Improved performance of `dpnp.fft` functions for complex strided input by avoiding oversized allocations and extra copies [#2939](https://github.com/IntelPython/dpnp/pull/2939)
 
 ### Deprecated
 
diff --git a/dpnp/fft/dpnp_utils_fft.py b/dpnp/fft/dpnp_utils_fft.py
index 733436ab988..dadf8b2fc7f 100644
--- a/dpnp/fft/dpnp_utils_fft.py
+++ b/dpnp/fft/dpnp_utils_fft.py
@@ -408,12 +408,27 @@ def _fft(a, norm, out, forward, in_place, c2c, axes, batch_fft=True):
         a = dpnp.reshape(a, local_shape)
         index = 1
 
+    if not a.flags.c_contiguous:
         # cuFFT requires input arrays to be C-contiguous (row-major)
         # for correct execution
-        if (
-            dpnp.is_cuda_backend(a) and not a.flags.c_contiguous
-        ):  # pragma: no cover
+        if dpnp.is_cuda_backend(a):  # pragma: no cover
             a = dpnp.ascontiguousarray(a)
+        else:
+            # Check if the memory footprint of the strides exceeds
+            # the number of elements.
+            # If so, copy to contiguous to avoid oversized allocation
+            # for the output array and unnecessary copy to contiguous
+            # after oneMKL FFT
+            _strides = dpnp.get_usm_ndarray(a).strides
+            _shape = a.shape
+            # Max element displacement reachable by the strides.
+            # Negative strides are handled by _copy_array, so only
+            # positive strides are possible here
+            max_disp = sum(
+                st * (sh - 1) for st, sh in zip(_strides, _shape) if st > 0
+            )
+            if (max_disp + 1) > a.size:
+                a = dpnp.ascontiguousarray(a)
 
     # w/a for cuFFT to avoid "Invalid strides" error when
     # the last dimension is 1 and there are multiple axes