Half-precision functions are generally tested against the
single-precision reference. This causes double rounding: first to single
precision, then from there to half precision. For the most part, it is
good enough, but specifically in the case of fma, a correctly rounded
result is required and is not obtained, for instance for arguments
0x1.eacp+7, 0x1.3f4p+4, 0x1.c04p+14, which produce an exact result of
0x1.065fffp+15 which should be rounded to half-prefcision 0x1.064p+15,
but was previously first rounded to single-precision 0x1.066p+15, and
from there to half-precision 0x1.068p+15. Testing against reference_fmal
gives us sufficient precision that double rounding does not cause
issues.
The f_fma(..., FLUSHED) calls for FTZ testing cannot be updated the same
way but do not need to be: these calls all have at least one constant
operand of zero. If one operand is zero, double rounding cannot be an
issue.
* 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>
* [NFC] Remove duplicate symbol declarations
Those are provided by testHarness.h.
Signed-off-by: Kévin Petit <kpet@free.fr>
* add missing include
---------
Signed-off-by: Kévin Petit <kpet@free.fr>
* grab latest from upstream OpenCL
* Use clEnqueueFillBuffer rather than memset4 in all test files
* Cleanup leftover code from memset_pattern4
* Remove unnecessary map, unmap, writeBuffer from math_brute_force tests
* Remove extraneous build system change
* Appease clang-format
* Add option to perform buffer fills on the host
Co-authored-by: Taeten Prettyman <taeten.j@gmail.com>
Co-authored-by: taetenp <taet@holochip.com>
Co-authored-by: Chip Davis <chip@holochip.com>
Simplify code by relying on RAII to free resources. Reduce code
duplication.
This commit only affects tests that use `BuildKernelInfo`, which are
the multi-threaded tests. Another patch will deal with the
single-threaded tests, i.e., those using `BuildKernelInfo2`.
Original patch by Marco Antognini.
Signed-off-by: Marco Antognini <marco.antognini@arm.com>
Signed-off-by: Sven van Haastregt <sven.vanhaastregt@arm.com>
Signed-off-by: Marco Antognini <marco.antognini@arm.com>
Signed-off-by: Sven van Haastregt <sven.vanhaastregt@arm.com>
* Cleanup usage of static, extern and typedef
Remove static on functions defined headers, as it can result in
duplication in binaries.
Remove unnecessary extern keyword on a function declaration, as it is
the default behavior and can be puzzling when reading the code.
Remove the unused declaration of my_ilogb, which is never defined.
Remove unnecessary usage of typedef, as they are only increasing the
cognitive load of the code for no purpose.
Signed-off-by: Marco Antognini <marco.antognini@arm.com>
* Improve usage of inline and static in harness
Functions declared in header as static can trigger unused warnings when
(indirectly) included in translation units that do not use such
functions. Use inline instead, which also avoids duplicating symbols in
binaries.
Signed-off-by: Marco Antognini <marco.antognini@arm.com>
gWimpyBufferSize is never modified and is actually not used to modify
the number of tests -- gWimpyReductionFactor is used for that purpose by
some tests, but not all.
This patch removes this unnecessary global variable to simplify the
codebase, and reduce differences between tests.
Signed-off-by: Marco Antognini <marco.antognini@arm.com>
* Make variables and functions local to translation unit
Make some global variables local to function, or remove them when
actually dead.
Signed-off-by: Marco Antognini <marco.antognini@arm.com>
* Address comments
Remove unused code.
Reduce scope of gDoubleCapabilities.
Signed-off-by: Marco Antognini <marco.antognini@arm.com>
* Remove code for runtime measurement
The GetTime() and associated functions are not fully implemented on
Linux. This functionality is assumed to be untested, or unused at best.
Reduce differences between tests by removing this unnecessary feature.
It can be (re-)implemented later, if desired, once the math_brute_force
component is in better shape.
Signed-off-by: Marco Antognini <marco.antognini@arm.com>
* Coalesce if-statements
Signed-off-by: Marco Antognini <marco.antognini@arm.com>
* Keep else branch
Address comments.
Signed-off-by: Marco Antognini <marco.antognini@arm.com>
