Fp16 math bruteforce staging (#1863)

* Enable fp16 in math bruteforce

* Added modernization of remaining half tests for consistency (issue #142, bruteforce)

* Added kernel types related corrections

* Added more fixes and general cleanup

* Corrected ULP values for half tests (issue #142, bruteforce)

* Corrected presubmit check for clang format

* Added support for ternary, unary_two_result and unary_two_result_i tests for cl_half (issue #142, bruteforce)

* Added missing condition due to vendor's review

* code format correction

* Added check for lack of support for denormals in binary_half scenario

* Corrected procedure to compute nextafter cl_half for flush-to-zero mode

* Added correction for external check of reference value for nextafter test

* Added correction due to code review request

* Changed quantity of tests performed for half in unary and macro_unary procedures from basic

* Added corrections related to code review:

-added binary_operator_half.cpp and binary_two_results_i_half.cpp
-address sanitizer errors fixed
-extending list of special half values
-removed unnecessary relaxed math references in half tests
-corrected conditions to verify ulp narrowing of computation results
-several refactoring and cosmetics corrections

* Print format correction due to failed CI check

* Corrected bug found in code review (fp16 bruteforce)

* Corrections related to code review (cl_khr_fp16 support according to #142)

-gHostFill missing support added
-special half values array extended
-cosmetics and unifying

* clang format applied

* consistency correction

* more consistency corrections for cl_fp16_khr supported tests

* Corrections related to code review (bureforce #142)

* Correction for i_unary_half test capacity

* Corrections related to capacity of cl_khr_fp16 tests in bruteforce (#142)

---------

Co-authored-by: Wawiorko, Grzegorz <grzegorz.wawiorko@intel.com>

test_conformance/math_brute_force/utility.h

@@ -22,6 +22,7 @@
 #include "harness/testHarness.h"
 #include "harness/ThreadPool.h"
 #include "harness/conversions.h"
+#include "CL/cl_half.h"
 
 #define BUFFER_SIZE (1024 * 1024 * 2)
 #define EMBEDDED_REDUCTION_FACTOR (64)
@@ -61,10 +62,20 @@ extern int gFastRelaxedDerived;
 extern int gWimpyMode;
 extern int gHostFill;
 extern int gIsInRTZMode;
+extern int gHasHalf;
+extern int gInfNanSupport;
+extern int gIsEmbedded;
 extern int gVerboseBruteForce;
 extern uint32_t gMaxVectorSizeIndex;
 extern uint32_t gMinVectorSizeIndex;
 extern cl_device_fp_config gFloatCapabilities;
+extern cl_device_fp_config gHalfCapabilities;
+extern RoundingMode gFloatToHalfRoundingMode;
+
+extern cl_half_rounding_mode gHalfRoundingMode;
+
+#define HFF(num) cl_half_from_float(num, gHalfRoundingMode)
+#define HTF(num) cl_half_to_float(num)
 
 #define LOWER_IS_BETTER 0
 #define HIGHER_IS_BETTER 1
@@ -115,6 +126,12 @@ inline int IsFloatResultSubnormal(double x, float ulps)
     return x < MAKE_HEX_DOUBLE(0x1.0p-126, 0x1, -126);
 }
 
+inline int IsHalfResultSubnormal(float x, float ulps)
+{
+    x = fabs(x) - MAKE_HEX_FLOAT(0x1.0p-24, 0x1, -24) * ulps;
+    return x < MAKE_HEX_FLOAT(0x1.0p-14, 0x1, -14);
+}
+
 inline int IsFloatResultSubnormalAbsError(double x, float abs_err)
 {
     x = x - abs_err;
@@ -157,6 +174,26 @@ inline int IsFloatNaN(double x)
     return ((u.u & 0x7fffffffU) > 0x7F800000U);
 }
 
+inline bool IsHalfNaN(const cl_half v)
+{
+    // Extract FP16 exponent and mantissa
+    uint16_t h_exp = (((cl_half)v) >> (CL_HALF_MANT_DIG - 1)) & 0x1F;
+    uint16_t h_mant = ((cl_half)v) & 0x3FF;
+
+    // NaN test
+    return (h_exp == 0x1F && h_mant != 0);
+}
+
+inline bool IsHalfInfinity(const cl_half v)
+{
+    // Extract FP16 exponent and mantissa
+    uint16_t h_exp = (((cl_half)v) >> (CL_HALF_MANT_DIG - 1)) & 0x1F;
+    uint16_t h_mant = ((cl_half)v) & 0x3FF;
+
+    // Inf test
+    return (h_exp == 0x1F && h_mant == 0);
+}
+
 cl_uint RoundUpToNextPowerOfTwo(cl_uint x);
 
 // Windows (since long double got deprecated) sets the x87 to 53-bit precision