Use float<->half conversion routines from the OpenCL headers (#884)

* Use float<->half conversion routines from the OpenCL headers

Fixes #870

Signed-off-by: Kevin Petit <kevin.petit@arm.com>

* Use cl_half_from_double

* Fix windows build errors

* Fix more build errors

* Code formatting

* Remove TEST class
This commit is contained in:
Kévin Petit
2020-08-14 13:50:14 +01:00
committed by GitHub
parent 655d83db80
commit ed50fcad2d
15 changed files with 64 additions and 941 deletions

View File

@@ -368,7 +368,7 @@ char * convert_to_expected( void * inputBuffer, size_t numPixels, ExplicitType i
cl_float *outData = new cl_float[ numPixels * channelNum ];
for( size_t i = 0; i < numPixels * channelNum; i++ )
{
outData[ i ] = convert_half_to_float(src[ i ]);
outData[i] = cl_half_to_float(src[i]);
}
return (char *)outData;
}