COMPMID-1150 : (OCLGrind) Kernel compilation error and assertion
-Multiple definitions of COLS_MTX_B in gemm.cl one for FP32 and one for
FP16.
-GEMMTranspose1xWKernel invalid check fro small window sizes.
Change-Id: I9c7ddd3577aec9afc702731ca27a1e10d6eddb81
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/131023
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
diff --git a/src/core/CL/cl_kernels/gemm.cl b/src/core/CL/cl_kernels/gemm.cl
index 7215f58..69bc09f 100644
--- a/src/core/CL/cl_kernels/gemm.cl
+++ b/src/core/CL/cl_kernels/gemm.cl
@@ -543,6 +543,9 @@
vstore4((float4)(c30, c31, c32, c33), 0, (__global float *)(dst_addr + 3 * dst_stride_y));
}
+// Undefine local defines
+#undef COLS_MTX_B
+
#if defined(ARM_COMPUTE_OPENCL_FP16_ENABLED)
/** This OpenCL kernel computes the matrix multiplication between matrix A (src0) and matrix B (src1)
* Matrix A and matrix B must be reshaped respectively with @ref gemm_interleave4x4_16bit and @ref gemm_transpose1x8 before running the matrix multiplication
@@ -879,6 +882,10 @@
vstore8(c20, 0, (__global half *)(dst_addr + 2 * dst_stride_y));
vstore8(c30, 0, (__global half *)(dst_addr + 3 * dst_stride_y));
}
+
+// Undefine local defines
+#undef COLS_MTX_B
+
#endif // defined(ARM_COMPUTE_OPENCL_FP16_ENABLED)
#if defined(FIXED_POINT_POSITION)