Added cl_half support for test_printf (#1622)

* Added support to test half floats with printf calls (issue #142, printf)

* Added corrections related to rounding and casting halfs (issue #142, printf)

* Reusing similar function (issue #142, printf)

* Corrected path without cl_khr_fp16 support (issue #142, printf)

* Cosmetic fix for order of vector tests (issue #142, printf)

* Added correction related to vendor test review (issue #142, printf)
This commit is contained in:
Marcin Hajder
2023-03-28 17:57:03 +02:00
committed by GitHub
parent f537c40abc
commit 20ab003053
5 changed files with 396 additions and 60 deletions

View File

@@ -159,7 +159,9 @@ size_t get_min_alignment(cl_context context);
/* Helper to obtain the default rounding mode for single precision computation.
* (Double is always CL_FP_ROUND_TO_NEAREST.) Returns 0 on error. */
cl_device_fp_config get_default_rounding_mode(cl_device_id device);
cl_device_fp_config
get_default_rounding_mode(cl_device_id device,
const cl_uint &param = CL_DEVICE_SINGLE_FP_CONFIG);
#define PASSIVE_REQUIRE_IMAGE_SUPPORT(device) \
if (checkForImageSupport(device)) \