carlushuang d577f27d1a fix __longlong_as_double() problem, return the double value ...

previous version return a long long valus *as* double, hence we may get the wrong result.
this also affect atomicAdd(double * ...), which use long long pointer to mimic double pointer.

Signed-off-by: carlushuang <carlus.huang@amd.com>

2018-09-12 13:25:00 +08:00

..

hcc_detail

fix __longlong_as_double() problem, return the double value

2018-09-12 13:25:00 +08:00

nvcc_detail

Merge pull request #563 from gargrahul/add_gettexrefoffset_nvcc

2018-07-11 15:01:20 +05:30

channel_descriptor.h

Apply .clangformat to all repo source files

2018-03-12 11:29:03 +05:30

device_functions.h

Apply .clangformat to all repo source files

2018-03-12 11:29:03 +05:30

driver_types.h

Apply .clangformat to all repo source files

2018-03-12 11:29:03 +05:30

hip_common.h

Apply .clangformat to all repo source files

2018-03-12 11:29:03 +05:30

hip_complex.h

Apply .clangformat to all repo source files

2018-03-12 11:29:03 +05:30

hip_fp16.h

Apply .clangformat to all repo source files

2018-03-12 11:29:03 +05:30

hip_hcc.h

Apply .clangformat to all repo source files

2018-03-12 11:29:03 +05:30

hip_profile.h

Apply .clangformat to all repo source files

2018-03-12 11:29:03 +05:30

hip_runtime_api.h

[HIPIFY] Support of cudaComputeMode / CUcomputemode

2018-07-14 16:08:19 +03:00

hip_runtime.h

Switch the atomic implementation to use Clang builtins.

2018-06-02 12:27:17 +01:00

hip_texture_types.h

Apply .clangformat to all repo source files

2018-03-12 11:29:03 +05:30

hip_vector_types.h

Apply .clangformat to all repo source files

2018-03-12 11:29:03 +05:30

math_functions.h

Fix __HIP_DEVICE_COMPILE__ not defined when hip/math_functions.h is included

2018-08-07 17:14:39 -04:00

texture_types.h

Apply .clangformat to all repo source files

2018-03-12 11:29:03 +05:30