b738633bcb
This switches HIP from its currently convoluted macro + pfe based dispatch mechanism to a more natural one partially based on the existing module API. The basic idea is that HCC will always correctly emit __global__ functions: as empty-bodied stubs, on host, and as kernels, on device. It then becomes trivial to obtain the mangled name on host, at dispatch, from the function's address, and then to use the mangled name to retrieve the kernel. This should address all problems stemming from serialisation, dubious mismatches due to the manufactured functor, macro-isms et al. It also immediately enables support for generalised globals as a consequence of that being available in the module API. Finally, it will make debug much easier, since the actual names of the __global__ functions will automatically be used in traces etc. One detail is that due to how dispatch works now (hipLaunchKernel and hipLaunchKernelGGL are themselves variadic function templates which deduce the function type of the callee), in certain cases it may be necesssary to insert explicit casts to ensure that the variadic argument list selects a viable overload - this can be observed in some unit tests. Eventually we may be able to remove this limitation, but for now it does not appear terribly onerous. The code is not extremely HIPpie, nor is it fully optimised, but rather is intended as a starting point for the HIP team to make its own.
...
[ROCm/clr commit: 28f87f7d2e
2017-11-01 15:09:59 +00:00
57bfd56a0d
hipMemcpy-size test: reduce max size to make it work correctly on nvcc path
...
Change-Id: I9ce9f5a9e141ffd8ddf961269010b33358e02771
[ROCm/clr commit: ff8ade59aa
2017-06-07 15:25:54 +05:30
579b8e5050
Add host offset checking
...
[ROCm/clr commit: fbf28a8728
2017-04-24 22:30:54 -05:00
67383ddb5c
Add test for non-page-aligned mem copies.
...
[ROCm/clr commit: d120b2dd12
2017-04-24 22:30:54 -05:00
37fcb3bd13
Add corrected test for offsets
...
[ROCm/clr commit: b44a3eefd1
2017-04-24 22:30:54 -05:00
04082c14a7
Refactor hipMemcpy test to share mem alloc for multiple copies.
...
[ROCm/clr commit: 6b16f56f38
2017-04-24 22:30:54 -05:00
26c65c826b
Fix compilation of some broken tests on nvcc path
...
Change-Id: I92406af00c2de09d728e9b7f661c1f3873470560
[ROCm/clr commit: 40bcf5ed3b
2017-02-27 13:17:51 +05:30
43d07079e9
directed tests: Updated to use new hip include path
...
Change-Id: Iab1aee638b7158eb9674a19625dedf6471947e51
[ROCm/clr commit: 5947878247
2016-10-04 22:20:50 +05:30
bac30c4561
directed tests: Enable remaining tests in HIT infrastructure
...
Change-Id: I800ee00d6f7d339bb5d2ed898a16362a8541ed3a
[ROCm/clr commit: 1e8282327b
2016-09-27 17:24:33 +05:30
b31b23ff1d
Refactor directed test infrastructue.
...
- Add hierarchy. Tests now live in directories, each with its own
CMakeFiles.txt. Reduces merge conflicts.
- Change make_hip_executable -> build_hip_executable.
- Refresh docs.
- Enable some tests that were previously built but not run.
Change-Id: I8c5de3c954400bf233904282b8b42861a2b7c536
[ROCm/clr commit: 3feb13c8f6
2016-06-17 15:18:57 -05:00
Alex Voicu
Maneesh Gupta
Ben Sander