51dbf4f5ca
Null checks added for hipmallocpitch and hipmemcpy apis
...
[ROCm/hip commit: 6411ca1f6d
2018-05-03 09:27:50 +05:30
ab1dabe61b
Fix texture 3D for HIP/NVCC
...
[ROCm/hip commit: 9de5f23d54
2018-05-02 11:56:37 +05:30
701de3092b
SWDEV-141024
...
[ROCm/hip commit: 1c2509dc04
2018-04-20 17:40:00 +05:30
e1e88f3bff
Added hipMemset2DAsync support
...
[ROCm/hip commit: 3cfb9c0d40
2018-04-17 18:27:27 +05:30
89511823f0
Correct missed ihipMemsetCopyDataType change
...
[ROCm/hip commit: 16c89d101a
2018-04-12 10:27:19 +05:30
abe14442a5
Changed ihipMemsetCopyDataType to ihipMemsetDataType
...
[ROCm/hip commit: 3d6eb75828
2018-04-12 09:29:22 +05:30
6c4236dfb6
Fix hipMemset stream resolution
...
[ROCm/hip commit: 294bf50f68
2018-04-11 19:01:53 +05:30
36c6e0019d
hipMemset refactoring
...
[ROCm/hip commit: 412a35be20
2018-04-11 15:58:48 +05:30
4077c681c9
hipMemcpyAsync returns success when trying to copy 0 bytes
...
Change-Id: I4c0ee7ccc7563e2df657b50356cdd7fec9a1ef15
[ROCm/hip commit: 03eca1c57e
2018-04-09 12:39:44 +05:30
4f42ee762d
Apply .clangformat to all repo source files
...
Change-Id: I7e79c6058f0303f9a98911e3b7dd2e8596079344
[ROCm/hip commit: 1ba06f63c4
2018-03-12 11:29:03 +05:30
717a01660a
Change directory name to match HIP lowercase style.
...
[ROCm/hip commit: dc7560ef22
2018-02-22 13:15:10 +00:00
d4a4a8a1c1
Merge pull request #321 from gargrahul/hipMemcpyArray_Functions
...
Added support for hipMemcpy Array functions-
[ROCm/hip commit: 4b8ae78891
2018-02-12 10:36:38 +05:30
e2ade308cf
Fixed host allocated globals address lookup for host usage
...
Fixed texture driver APIs failure
[ROCm/hip commit: 24ab820a11
2018-01-30 18:06:31 +05:30
5da7dcbd3b
Added support for -
...
- hipMemcpyFromArray
- hipMemcpyAtoH
- hipMemcpyHtoA
[ROCm/hip commit: 487a430b5a
2018-01-16 11:44:19 +05:30
299c873e1a
Added support for
...
- 3D texture driver APIs
- hipMalloc3D
- hipMemcpy3D for destination other than array
[ROCm/hip commit: 115c7f2b79
2017-12-05 14:11:13 +05:30
905389741c
Fix some cppcheck style issues.
...
[ROCm/hip commit: 9bba97fdcc
2017-12-01 20:45:34 +00:00
419a80db24
Fix warning from default cppchek.
...
[ROCm/hip commit: 4313686d6e
2017-12-01 20:45:33 +00:00
08a0d96448
Fix legacy mode detection of the address of an agent allocated variable. In this mode, there exist two executables per each code object, one created by HCC and one created by HIP. Since we dispatch through HCC in legacy mode, we should obtain the address for an agent allocated variable from the latter's executable. Also add two omitted validity checks, whose absence could lead to segfaults when the current process had no .kernel section and / or when an invalid or empty blob was extracted from the latter.
...
[ROCm/hip commit: 7c0b9a005b
2017-11-30 03:29:04 +00:00
8d51eaafb6
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 1c5096832e11e7dc6
2017-11-29 21:49:10 +00:00
fcc42f035e
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 d2fd1f5fbaf729f88
2017-11-29 21:36:29 +00:00
9668003fe3
Change memset kernel to use memcpy instead of placement new. Simplify indexers.
...
[ROCm/hip commit: 6e4ca3fbb4
2017-11-28 19:45:47 +00:00
11f7d895f4
Merge remote-tracking branch 'origin/master' into feature_use_module_based_dispatch_instead_of_pfe
...
# Conflicts:
# src/hip_module.cpp
[ROCm/hip commit: dc67ca3feb
2017-11-28 17:29:11 +00:00
13879387e5
Fixed review comments
...
[ROCm/hip commit: 56862b1c35
2017-11-21 21:19:06 +05:30
03552f2e94
Changed function hipMemcpy_2D to hipMemcpyParam2D
...
[ROCm/hip commit: 9866fa250d
2017-11-21 12:36:24 +05:30
45ff3c31c4
Refactor the __device__ versions of memset and memcpy to be less awkward i.e. not return nullptr as opposed to the destination pointer (it can only be assumed it was done for maximum confusion) and actually unroll as they claim to. Change all of the {to, from}Symbol functions to use hipModuleGetGlobal, as opposed to hc::accelerator::get_symbol_address which is no longer valid with module based dispatch.
...
[ROCm/hip commit: 9d088d2283
2017-11-21 02:40:34 +00:00
49a2c6468e
Texture driver APIs support
...
[ROCm/hip commit: ef09c4918d
2017-11-09 22:10:55 +05:30
35d8af2001
Clean up trailing whitespace so as to reduce noise in #246 .
...
[ROCm/hip commit: d8e323d4b5
2017-11-08 00:08:55 +00:00
1f911cd23a
Merge remote-tracking branch 'origin/master' into feature_use_module_based_dispatch_instead_of_pfe
...
# Conflicts:
# src/hip_module.cpp
[ROCm/hip commit: bb1176001f
2017-11-03 10:53:39 +00:00
dab971370e
Correctly deal with functions from shared objects, wherein the program visible VA == so_base_va + st_value(function_symbol). Remove quaint usage of pfe for hipMemset (which is actually fill_n).
...
[ROCm/hip commit: 2cacda91bb
2017-11-01 22:33:13 +00:00
70a41e7dac
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/hip commit: c2482d1255
2017-11-01 15:09:59 +00:00
d7153f792d
Fix bug with peer-to-peer combined with context API
...
- Store context inside the tracker rather than using int deviceID that
was always mapped to primary context
- IsPeerWatcher now based on device IDs rather than specific peers.
[ROCm/hip commit: 7d30f32332
2017-10-26 19:44:22 +00:00
ab4128a53f
Merge pull request #179 from gargrahul/fix_hipmallocarray
...
Fixed hipMallocArray for 1D cases
[ROCm/hip commit: 3ed5f42dad
2017-09-14 12:59:33 -05:00
5418e3de45
Add HIP_INIT_ALLOC to init allocated memory.
...
[ROCm/hip commit: cea80cd8b3
2017-09-13 23:31:48 +00:00
3178dc04cd
Fixed hipMallocArray for 1D cases
...
[ROCm/hip commit: 2a915b2790
2017-09-12 21:52:11 +05:30
870228006e
Null check on input pointer arguments
...
[ROCm/hip commit: 38c9febe21
2017-08-25 08:46:34 +05:30
c036a1b25c
[texture] guard new HCC APIs under workweek
...
Change-Id: I4f60a64fb0b0496ca1eb01ffe6ddda121c25d976
[ROCm/hip commit: e40047f2bf
2017-08-15 15:51:38 +05:30
5bf177340a
[HIP Texture] The GPU virtual address for texture memory needs to be
...
aligned.
In hcc_am, a bigger buffer will be allocated for alignment purpose
and _unalignedDevicePointer is added in struct AmPointerInfo for
original allocated address.
[ROCm/hip commit: 4264a4ce56
2017-08-08 11:18:00 -04:00
7e9c13f8de
fix hipMemcpy2DAsync
...
[ROCm/hip commit: 0053e4db03
2017-07-29 06:50:56 +05:30
da4042554f
Merge pull request #116 from bensander/enable_coh_host
...
Make host memory allocations coherent by default.
[ROCm/hip commit: 526fcb1223
2017-07-27 10:45:32 +05:30
6834270f15
Make host memory allocations coherent by default.
...
Associated change is to optimize event recording so it uses
agent-scope releaes (since it was only using system-scope release
to support non-coherent host mem).
Flags and environment variables exist to obtain previous behavior
if desired. Options are documented in new performance guide.
[ROCm/hip commit: 8b8e97ff28
2017-07-26 19:20:34 -05:00
65bec11393
HIP Texture Support
...
[ROCm/hip commit: e671cec367
2017-07-17 15:16:12 -04:00
84fbc3dfaa
Add support of HIP_HIDDEN_FREE_MEM, to deduct the returned available
...
memory from hipMemGetInfo API, measured in MB.
Change-Id: I7a8260c12e032e04e26611db4c38c893a29f2653
[ROCm/hip commit: 1df08626c8
2017-06-26 15:29:38 -05:00
a8a8b2c888
Validity check of input arguments in Ipc Mem APIs
...
Change-Id: Ia48e949d19f354f10c7e44cc2457fd4154bf6d76
[ROCm/hip commit: ba51d7f676
2017-06-14 15:18:57 +05:30
ef7c9be9c6
Use amHostCoherentFlag. Requires new HCC version.
...
[ROCm/hip commit: 99e9c7cca5
2017-06-07 09:06:40 -05:00
5b9ce41633
Add hipHostMallocCoherent, hipHostMallocNonCoherent
...
Provide per-allocation control over coherent/non-coherent mem.
These overrid the default HIP_COHERENT_HOST_ALLOC setting.
[ROCm/hip commit: 75f691ec2f
2017-05-24 00:48:10 -05:00
07865c3a02
Remove HIP_MAX_QUEUES (replaced with HCC_MAX_QUEUES)
...
[ROCm/hip commit: d0ef9d8462
2017-05-23 23:48:01 -05:00
1e0046f737
Fix trace category for hipHostMalloc
...
[ROCm/hip commit: 7cfe07cff4
2017-05-23 23:15:45 -05:00
324dfb870f
Return precise address for hipHostGetDevicePointer.
...
[ROCm/hip commit: 46030bb2d2
2017-05-17 07:36:06 -05:00
a55ce5bee4
Add initial HIP_SYNC_NULL_STREAM=0 mode.
...
This eliminates host-synchronization for null stream. Instead, the
null-stream uses GPU-side events to wait for other streams.
Default is OFF pending additional testing.
Add enhanced null-stream test.
Also refine HIP_TRACE_API.
[ROCm/hip commit: 27877f8854
2017-05-16 19:04:25 -05:00
2cf05ad54b
Add HIP_TRACE_API=4. Only display memory allocation/free apis.
...
[ROCm/hip commit: 0edab14139
2017-05-16 19:04:25 -05:00
Lakhan Singh
Rahul Garg
Maneesh Gupta
Alex Voicu
Ben Sander
Weixing Zhang
Sun, Peng