Aditya Atluri 5ef8ef3bd7 added packed math fp16 native device functions ...

1. Added SDWA implementation inside IR file
2. Added device functions to header + used them in test

Change-Id: Ib4e059a58eee201cc82438689e3e9bc5f9d26653

2017-01-12 14:10:51 -06:00

..

cuda

Move include/* to include/hip/*

2016-10-04 22:17:18 +05:30

device_functions.h

Added proper device data types

2017-01-11 15:06:25 -06:00

hcc_acc.h

include headers: Update copyright header and fix line endings

2016-10-15 22:52:10 +05:30

hip_complex.h

changed data type used for complex

2017-01-11 18:23:37 -06:00

hip_fp16.h

added packed math fp16 native device functions

2017-01-12 14:10:51 -06:00

hip_ldg.h

Added proper device data types

2017-01-11 15:06:25 -06:00

hip_runtime_api.h

Add name for function

2016-12-17 08:54:09 -06:00

hip_runtime.h

Added proper device data types

2017-01-11 15:06:25 -06:00

hip_texture.h

fixed compilation bugs

2016-11-21 08:56:30 -06:00

hip_vector_types.h

fixed compilation issues with operator overloading device data types

2017-01-11 17:53:32 -06:00

host_defines.h

Added support for constant memory

2016-10-20 09:57:53 -05:00