COMPMID-1736: Fixed out-of-bound write in CLIm2Col

The issue was related to CLIm2Col when the number of input channels was less than
the number of elements processed by each thread.
The bug has been fixed in the validate_and_configure_window() function setting the correct number of elements accessed
in the output tensor.

Also fixed an issue GEMM3D when we have a single output channel

Change-Id: I094292d0c7662599c4a4c3916ec5f5821df5faef

1 files changed, 2 insertions, 2 deletions

diff --git a/tests/validation/fixtures/GEMMFixture.h b/tests/validation/fixtures/GEMMFixture.h
index 255b12c0ed..74205e25d4 100644
--- a/tests/validation/fixtures/GEMMFixture.h
+++ b/tests/validation/fixtures/GEMMFixture.h
@@ -85,9 +85,9 @@ protected:
         // Create and configure function
         FunctionType gemm;
         // The GEMMinfo includes the values of the depth in case of reinterpreted 3d output.
-        // If the output shape has the same number of dimensions of the input the method called is a 2D matrix multiplication (depth_output_reinterpreted_as_3D = 1),
+        // If the output shape has the same number of dimensions of the input the method called is a 2D matrix multiplication (depth_output_reinterpreted_as_3D = 0),
         // in the other case we have to use the reinterpreted version of GEMM (depth_output_reinterpreted_as_3D = depth of the 3D output).
-        gemm.configure(&a, &b, &c, &dst, alpha, beta, GEMMInfo(false, false, false, (reinterpret_ouput_as_3d ? output_shape[2] : 1), reinterpret_input_as_3d));
+        gemm.configure(&a, &b, &c, &dst, alpha, beta, GEMMInfo(false, false, false, (reinterpret_ouput_as_3d ? output_shape[2] : 0), reinterpret_input_as_3d));
         ARM_COMPUTE_EXPECT(a.info()->is_resizable(), framework::LogLevel::ERRORS);
         ARM_COMPUTE_EXPECT(b.info()->is_resizable(), framework::LogLevel::ERRORS);
         ARM_COMPUTE_EXPECT(c.info()->is_resizable(), framework::LogLevel::ERRORS);