mirror of
https://github.com/KhronosGroup/OpenCL-CTS.git
synced 2026-03-19 14:09:03 +00:00
b4c3bf2af2
Basic explicit_s2v: The verification step was always using round to even when converting a float to half even for round to zero cores. Commonfns degrees: The verification step was only taking into account infinities and not values that over/underflow. This resulted in an incorrect error calculation. E.g: double cpu_result = 175668.85998711039; cl_half gpu_result = 31743; // this is 65504 when converting to float, we overflowed. float error = (cpu_result - gpu_result) * some_factor; The fix adds the check if( (cl_half) reference == test ) before calculating the error.