bdc67ac1b4
Merge pull request #490 from ROCm-Developer-Tools/feature_decouple_atomics_from_hc
...
Switch the atomic implementation to use Clang builtins.
[ROCm/clr commit: d27991e1c8
2018-06-20 14:16:43 +05:30
c1cd1513aa
Revert "Switch over to using native vector types, for better codegen. Remove noise."
...
[ROCm/clr commit: d137271083
2018-06-08 16:48:22 -04:00
43a5f04e9c
Switch the atomic implementation to use Clang builtins.
...
[ROCm/clr commit: 513ba4eb8a
2018-06-02 12:27:17 +01:00
130e9d409e
Re-sync with upstream.
...
[ROCm/clr commit: f2d7f112ab
2018-06-01 15:49:05 +01:00
2a9a7b9aa3
Merge pull request #447 from ROCm-Developer-Tools/feature_native_vector_types
...
Switch over to using native vector types, for better codegen. Remove noise.
[ROCm/clr commit: 3fec282097
2018-06-01 13:58:07 +05:30
a9cabfc8df
Re-sync with upstream. Add integer abs.
...
[ROCm/clr commit: e03ca1a72e
2018-05-31 16:38:00 +01:00
840d5c5fe0
Add missing interop with volatile. Fix unit tests.
...
[ROCm/clr commit: 208f5a41c6
2018-05-31 15:27:12 +01:00
2924783ee4
Switch to using ROCDL directly, as opposed to via HC. Add missing bits.
...
[ROCm/clr commit: 14e6a04387
2018-05-31 03:17:26 +01:00
7a480af716
Move converting constructor from _Float16 under macro guard. Refactor.
...
[ROCm/clr commit: 40dad93426
2018-05-25 19:46:41 +01:00
bfbc4f6587
Update hipTestHalf to actually test behaviour. Add missing hipHostfree.
...
[ROCm/clr commit: 59a046dd2d
2018-05-24 13:55:30 +01:00
2b16b4e31b
Missing commit.
...
[ROCm/clr commit: ecefdd6541
2018-05-23 17:57:47 +01:00
47f3529ccf
Disable incomplete unit tests that don't work on nvcc path
...
Change-Id: If5823ec96a3b2497a08c46ab802c5a0158271053
[ROCm/clr commit: 92d8e05aa0
2018-05-21 11:35:03 +05:30
0d0992b868
Merge pull request #444 from aaronenyeshi/vg20-initial
...
initial gfx906 support
[ROCm/clr commit: 3638bb5b1c
2018-05-18 13:18:07 +05:30
3dd565a6d7
Switch over to using native vector types, for better codegen. Remove noise.
...
[ROCm/clr commit: fcce9f5337
2018-05-12 00:14:17 +01:00
3d3356a2ed
Fix hipMathFunction for gfx906
...
[ROCm/clr commit: 4488f9f7a7
2018-05-11 10:53:07 -04:00
04bf6c5109
initial gfx906 support
...
[ROCm/clr commit: 368affcea4
2018-05-10 19:28:00 +00:00
16d8a56909
add intrinsics mbcnt_lo, mbcnt_hi, lane_id
...
[ROCm/clr commit: 4f12ddea8f
2018-05-08 13:43:53 -04:00
24c4daedc4
Fixing a copy/paste error in my previous checkin
...
[ROCm/clr commit: 30f0c19cf1
2018-04-27 12:59:51 +00:00
9946827d1b
Checkin to add unit tests for fixes in my previous commit
...
This change adds unit tests for
1. __hisinf
2. __hisnan
2. abs(long long)
3. lgamma(double)
[ROCm/clr commit: 76e808304c
2018-04-25 17:53:21 +00:00
46ddefedee
Apply .clangformat to all repo source files
...
Change-Id: I7e79c6058f0303f9a98911e3b7dd2e8596079344
[ROCm/clr commit: 9e47fccc89
2018-03-12 11:29:03 +05:30
bab8090dfc
[nvccWarnings] Fix -Wno-deprecated-declarations in hip_anyall and hip_ballot
...
[ROCm/clr commit: f69762b300
2017-12-20 12:05:21 +05:30
033e2cde33
[nvccWarnings] Fix warnings seen with dtests on nvcc path
...
[ROCm/clr commit: 0ac125e3db
2017-12-14 14:10:37 +05:30
c9f031bc72
Temporarily disable a couple tests pending some HCC work
...
[ROCm/clr commit: 721d862089
2017-12-01 21:46:28 +00:00
a27fa25d76
Revert "Revert adoption of CUDA indexing in general - this can only work with later versions of the compiler, just like module based dispatch, and thus must be guarded against usage in earlier (e.g. 1.6) versions."
...
This reverts commit 1cd64164966518846
2017-11-29 21:49:10 +00:00
a1d5f0ab0c
Revert "Revert adoption of CUDA indexing in general - this can only work with later versions of the compiler, just like module based dispatch, and thus must be guarded against usage in earlier (e.g. 1.6) versions."
...
This reverts commit d2fd1f52557000b56
2017-11-29 21:36:29 +00:00
f9b177c0b3
Modify the set component of the memcpy test (unclear why there is a memset component to begin with).
...
[ROCm/clr commit: 0755f1fc26
2017-11-21 17:52:01 +00:00
9cf73ef515
Re-sync with upstream.
...
[ROCm/clr commit: 30d90dab38
2017-11-20 15:34:50 +00:00
02cbb93ec1
Merge pull request #266 from gargrahul/fix_half2_gfx900
...
Fixed half2 issue on gfx900
[ROCm/clr commit: 4477d3d314
2017-11-20 07:28:41 +05:30
af0ae5421c
This implements the trivial change needed to move back from the hip{Something}_{x, y, z} macros to the natural CUDA syntax of Something.{x, y, z}. This is contained in lines 384-404 in hip_runtime.h. All of the other changes have to do with changing unit tests to use this syntax. The macros are retained for backwards compatibility.
...
[ROCm/clr commit: 0cc921f103
2017-11-19 01:54:12 +00:00
b0461a2176
Fixed test case for GFX900
...
[ROCm/clr commit: cfc9f87465
2017-11-16 09:34:52 +05:30
c3ba309562
Fixed half2 issue on gfx900
...
[ROCm/clr commit: 20947f80fb
2017-11-15 18:52:59 +05:30
41045dd24d
This corrects some interesting choices that were present in the HIP
...
unit tests such as e.g. de-allocating memory allocated with new[] using
free. All of these were identified via cppcheck.
[ROCm/clr commit: 58a18eaf0c
2017-11-01 22:51:22 +00:00
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
bf29705489
[dtests] Fix hip_threadfence_system test's BUILD command
...
Change-Id: I037c523369e4bddd7a386ffe117fe97a178900fd
[ROCm/clr commit: 88ff8d9da4
2017-08-11 14:49:17 +05:30
a69503394d
add C++11 compilation flags and minor bug fixes
...
[ROCm/clr commit: 8c2cda8f9e
2017-08-10 17:58:36 +00:00
a8dc5dc11b
[dtests] Disable hip_threadfence_system.tst on nvcc
...
The test needs some more modifications before it is ready for building
on nvcc path. Disabling it for now so that the pull request can be
merged.
Change-Id: I19a894fcda7b2159f86a4e4e95a409c5655d3760
[ROCm/clr commit: 0d537f9966
2017-08-10 12:05:58 +05:30
6598eabd24
implement __threadfence_system
...
[ROCm/clr commit: b6e22b5c93
2017-08-02 08:50:18 +00:00
f29245a846
Renable frexp(f) device math function
...
Change-Id: I53c022b8ddf38cd17ddb42eba457b9020db66395
[ROCm/clr commit: 1bd1c6bea8
2017-07-20 14:41:30 +05:30
f3b112716e
Enable memcpytosymbol family functions test
...
[ROCm/clr commit: f2d6da3e34
2017-07-18 12:37:37 +05:30
4ce97c30e9
Remove explicit address spaces declarations
...
[ROCm/clr commit: 0237aeab06
2017-07-07 12:46:29 -05:00
949fbad6e2
hipDeviceMemcpy test: make it functional on nvcc path
...
Change-Id: Id10c79b48747ed701adbd0a233c53cd60cfa743b
[ROCm/clr commit: a50f5ca0ac
2017-06-07 15:24:44 +05:30
2985fa3814
Disable rcbrtf, scalblnf, scalbnf in single precision device test
...
Change-Id: I8a250a64a0cb05132d022a11d9766ced9cdf11a7
[ROCm/clr commit: 2145e94049
2017-05-31 10:16:19 +05:30
13896d6fb9
Disable rcbrt, scalbln and scalbn double precision device test
...
Change-Id: I46bd895701c46d3592b553090cafba99e41a2e2d
[ROCm/clr commit: da19087ae2
2017-05-31 10:15:41 +05:30
d1c334df66
added __host__ for complex functions and corrected memset and memcpy test
...
Change-Id: I9ffefb7a0025aa111a54d20d2766982df15532e7
[ROCm/clr commit: 42739c37ef
2017-04-06 09:29:44 -05:00
06684daac1
fix hipVectorTypesDevice direct test with GGL enabled
...
Change-Id: I7a63b87348f08f094cd709e87397d9e0fc24e4c2
[ROCm/clr commit: 38c4331861
2017-03-30 17:14:55 -05:00
a9a6b5e8a6
Update hipTestDeviceSymbol sample
...
Change-Id: If5ba99c60cd30c4491ca3a4856764224163d3ddf
[ROCm/clr commit: c33c58d687
2017-03-24 10:39:11 +05:30
572be5449d
Add USE_PROMOTE_FREE_HCC for smooth transition to new HCC caps.
...
ADDRESS_SPACE_1 defines
[ROCm/clr commit: f4256cb57c
2017-03-17 11:04:39 -05:00
c81fb24611
Add simple device-side assert macro
...
Currently swallows asserts but will compile.
[ROCm/clr commit: c9f64bbd2d
2017-03-17 10:25:56 -05:00
da5548303e
Disable broken tests on hcc path
...
Change-Id: Id6234da576566faa32d5fdf42dca6d6267596823
[ROCm/clr commit: 8536af7b71
2017-03-15 12:03:44 +05:30
54f40acc7a
Revert "Changes to HIP to cope with Promote-free HCC"
...
This reverts commit 9591c5a44717af837120
2017-03-14 22:59:27 +08:00
Maneesh Gupta
Siu Chi Chan
Alex Voicu
Aaron Enye Shi
Deven Desai
Phaneendr-kumar Lanka
Phaneendr-kumar Lanka
Ben Sander
Rahul Garg
Wen-Heng (Jack) Chung
Aditya Atluri
Sun, Peng
Wen-Heng (Jack) Chung