COMPMID-2117 : Use FFT convolution if output feature map depth is less than input

Change-Id: I588f467258aaa86a9fab8eb96603e02f24362d05
Signed-off-by: Vidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1010
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/core/Types.h b/arm_compute/core/Types.h
index 5a469a6..24e91bd 100644
--- a/arm_compute/core/Types.h
+++ b/arm_compute/core/Types.h
@@ -128,9 +128,10 @@
 /** Available ConvolutionMethod*/
 enum class ConvolutionMethod
 {
-    GEMM,    /**< Convolution using GEMM */
-    DIRECT,  /**< Direct convolution */
-    WINOGRAD /**< Convolution using Winograd */
+    GEMM,     /**< Convolution using GEMM */
+    DIRECT,   /**< Direct convolution */
+    WINOGRAD, /**< Convolution using Winograd */
+    FFT       /**< Convolution using FFT */
 };
 
 /** Padding mode to use for PadLayer */