Reuse math_brute_force ulp threshold in spir test

Spir test compares floating-point kernel results bit-by-bit with
correct results. However, for math_brute_force kernels, specification
does not ask for SPIR and OpenCL C path to match bit-to-bit. This patch
reuses ulps threshold from math_brute_force folder for math_brute_force
kernels in spir test.

Signed-off-by: Wenju He <wenju.he@intel.com>
This commit is contained in:
Wenju He
2019-03-27 16:54:45 +08:00
committed by Alastair Murray
parent a82e620b98
commit 00f716b0f8
7 changed files with 130 additions and 16 deletions

View File

@@ -217,6 +217,6 @@ void generate_kernel_data(cl_context context, cl_kernel kernel,
WorkSizeInfo &ws, TestResult& res);
void run_kernel(cl_kernel kernel, cl_command_queue queue, WorkSizeInfo &ws, TestResult& result);
bool compare_results(const TestResult& lhs, const TestResult& rhs);
bool compare_results(const TestResult& lhs, const TestResult& rhs, float ulps);
#endif