Antonio Sanchez 1296abdf82 Fix non-trivial Half constructor for CUDA. ...

Both CUDA and HIP require trivial default constructors for types used
in shared memory. Otherwise failing with
```
error: initialization is not supported for __shared__ variables.
```

2021-03-08 07:32:54 -08:00

..

AltiVec

Make half/bfloat16 constructor take inputs by value, fix powerpc test.

2021-02-27 21:32:06 +00:00

AVX

Fix uninitialized warning on AVX.

2021-02-17 13:13:39 -08:00

AVX512

Updated pfrexp implementation.

2021-02-17 02:23:24 +00:00

CUDA

Specialize std::complex operators for use on GPU device.

2021-01-22 18:19:19 +00:00

Default

Fix non-trivial Half constructor for CUDA.

2021-03-08 07:32:54 -08:00

GPU

Fix some CUDA warnings.

2021-02-24 00:16:31 +00:00

HIP/hcc

moving Half headers from CUDA dir to GPU dir, removing the HIP versions

2018-06-13 12:26:18 -04:00

MSA

Remove unused packet op "palign".

2020-05-07 17:14:26 -07:00

NEON

Fix rint SSE/NEON again, using optimization barrier.

2021-03-05 08:54:12 -08:00

SSE

Fix rint SSE/NEON again, using optimization barrier.

2021-03-05 08:54:12 -08:00

SVE

Updated pfrexp implementation.

2021-02-17 02:23:24 +00:00

SYCL

[SYCL Function pointer Issue]: SYCL does not support function pointer inside the kernel, due to the portability issue of a function pointer and memory address space among host and accelerators. To fix the issue, function pointers have been replaced by function objects.

2020-11-12 01:50:28 +00:00

ZVector

Include <cstdint> in one place, remove custom typedefs

2021-01-26 14:23:05 -08:00