0d16565061
Change Device->Ctx
...
Change ihipDevice_t -> ihipCtx_t (new)
Change ihipGetTlsDefaultDevice->ihipGetTlsDefaultCtx
Some other changes from device->ctx where appropriate.
Change-Id: I5c4ae93b2fd42c6303aa23d748eb166b7431925d
2016-08-07 21:47:12 -05:00
3c604b6430
Remove ihipStream_r::_device_index
...
Replace with direct pointer to device. Cleaner, and prep
for transition to contexts.
Change-Id: I0e550f34412923d46c541c0a14bb7d29c3fd4b11
2016-08-07 20:47:06 -05:00
b7ac63e202
clang-hipify: Transformation of declarations with external linkage and shared attribute for IncompleteArrayType (aka C array[]) only.
...
Example:
extern __shared__ uint sRadix1[]; => HIP_DYNAMIC_SHARED(unsigned int, sRadix1);
2016-08-05 21:35:58 +03:00
52712e2134
Region based apis to pool based api changes
...
Change-Id: If53019eebafe051ab4e811863995f78315297080
2016-08-05 15:05:57 +05:30
6a2e92f7c8
.hipconfig now lives in lib
...
Also moved reading .hipconfig to begining of hipcc
Change-Id: Ibb9d32bef64a79f189aa037c36814759c8cc8052
2016-08-03 12:01:48 +05:30
992195b395
compile all hip objects with -fPIC so that they work in a shared library
...
Change-Id: I1f8355d4a81dbd5f408062c317c16a5efc668876
2016-08-03 11:48:46 +05:30
1381681335
hipcc reads .hipconfig
...
hipcc dies if HCC_VERSION is not same as the one used to build HIP
Change-Id: I180c0108812fe5cb6c5304477557c524a4a61f75
2016-08-03 11:32:08 +05:30
b732fd74b4
Only create .hipconfig on install
...
Change-Id: I9c20440023401f5794b33a0165e0918372783a68
2016-08-03 11:25:59 +05:30
25c65c5fc4
Merge branch 'release_0.92.00' into amd-develop
2016-08-03 09:10:44 +05:30
58097bb717
Fix hipcc to work correctly when HIP_ATP_MARKER is not defined
...
Change-Id: I7cc525daccf896704e6ccf6d04ed395fda622031
2016-08-03 09:08:40 +05:30
8b272278f5
hip_hcc rpm package does not depend on rocm-profiler
...
Change-Id: I291c046371e704ce395781d5de3f6430c0dcba7b
2016-08-03 09:07:58 +05:30
5971c64a7b
Added configuration file to be used by hipcc
...
1. CMake will create .hip-config file in bin directory
Future Work: Need to make changes to hipcc to read the file
Change-Id: Ia7dc48d43787921d5af4ab07d7a5befbcf904465
2016-08-02 15:45:46 -05:00
bb005d1755
Remove faulty assert for kernelCnt==0
...
Change-Id: I8a925c95f48e857c0a31f44561499e90dc6df552
2016-08-01 13:38:47 -05:00
2d6eb727e9
Merge branch 'release_0.92.00' into amd-develop
...
Conflicts:
RELEASE.md
docs/markdown/hip_faq.md
Change-Id: Ifae1b64b6255a7872dfdc885bb8fb52f622464b7
2016-08-01 10:47:25 +05:30
9c7ee12822
Signal Fix: The signals in a stream are re-used
...
1. Before, the signal pool is increased depending on the usage
2. After, a static number of signals are allocated to the pool
Only these are used by hip in a stream
3. If the signals required are more than the pool size, the
stream has to wait to make sure all the signals are available
4. Once they are available, the stream can use them
5. Removed HIP_NUM_SIGNALS_PER_STREAM because of redundancy with HIP_STREAM_SIGNALS
6. Increased signal count from 2 to 32.
Future Work: Dynamically increase the pool size depending on the number of
streams allocated by the application. And, null stream should have more signals
Change-Id: I6be36e084f26bb04766fabf776c7210aee0f9e91
2016-07-28 23:01:35 -05:00
f7ab82cb39
Remove dead enqueueBarrier function.
...
Change-Id: Ib18fe6bd96ce24dbeb342961ddb5721f7d03f2b2
2016-07-28 22:48:22 -05:00
ef61aae878
Cleanup sync code.
...
Remove dead depFutures, enqueueBarrier call.
Rename some parms to reflect usage.
Add comments to better explain tricky parts of sync code.
Change-Id: I763296421d9c2b3b58fc8cef5f010b12ab49553c
2016-07-27 18:31:11 -05:00
f5118ce3cd
Fix API string message for hipDeviceGetAttribute
...
Change-Id: I30f54627630c8ee835506be8c9921742bb68a43a
2016-07-27 16:18:14 -05:00
1b2a24d0b8
Signal Fix: Added signal limit to allocSignal
...
1. Did not change the logic in allocSignal
2. Added guard to wait on signal limit
Change-Id: I78f29097e6a584b3c3d78319dac19869067bd1fe
2016-07-27 13:48:49 -05:00
de7c9769a4
Update release notes for 0.92.00 release
...
Change-Id: I9ca588cd0d5d752dc6521e76ba943500eb55525f
2016-07-27 20:30:04 +05:30
7be196de48
Signal Fix: Moved kernel count to critical stream
...
1. Added environment variable HIP_NUM_KERNELS_INFLIGHT
2. Moved kernelcount variable inside stream critical section
Change-Id: I51d24d0a2a109467209170de117a6d02ba4e308e
2016-07-26 17:09:27 -05:00
2e754d27dc
Signal Fix: Changed global signal count to per stream signal count
...
1. The number of kernels that can use signals are increased to 128
2. The kernel count is now specific to the stream
Change-Id: Ie6d1aa3f437aad8f08c3333fe48bd3f46e551e60
2016-07-26 14:03:51 -05:00
524127b4a4
removed redundant signal destroy
...
Change-Id: Icf0cd76b2620d34c87cfb6c7a83049087c0a0bc4
2016-07-26 13:35:35 -05:00
77be00e8d3
Doc update for FAQ and future RELEASE notes
...
Change-Id: I7e7c32d9a19fdaea0a0e41f1d4fa4652e53640f2
2016-07-26 12:14:15 -05:00
75d1f8c297
Doc update for README.md - add more intro text, example
...
Change-Id: I99b8eaacd6460dfdbdbc8ddba3fe589647d877e7
2016-07-26 12:14:02 -05:00
b9e48d6066
Make HCC ignore register keyword
...
- (previously would emit a warning)
- Also tweak documentation.
Change-Id: I0f4f00f82f8cc53d420112570f2d7675535e6aea
2016-07-26 12:13:48 -05:00
0232e6bbb4
Added re-fix for memcpy kernel sync
...
1. The patch uses HIP signal pools to sync between copy and kernel commands
2. The hsa_signal_create is removed
3. Left the redundant enqueueBarrier method just in case
Change-Id: I3dff3e8ee57fff3cd49bec802ff735ed128e5ca1
2016-07-26 09:22:59 -05:00
b29ed98f9a
Documentation updates
...
Change-Id: Ia624d86915c4c96da0ac0242f767135f30ff73c6
2016-07-25 14:53:15 +05:30
d11d65d401
D2H and H2D unpinned memory transfer support
...
Change-Id: If6d6c970f435e5d917d5cc6cddc2ee2918cd1c37
Conflicts:
src/hip_hcc.cpp
2016-07-25 14:36:07 +05:30
1704006bed
Partial fix async after kernel launch signal issue
...
Change-Id: Ib48d6564379160035bded9493b93663fba361710
2016-07-23 14:54:20 -05:00
6db08e5135
Add empty stubs for threadfence family routines, changes include:
...
- stubs and documentation in include/hcc_details/hip_runtime.h
- stubs with "no-op" in src/hip_memory.cpp
- document update in hip_kernel_language.md, add suggestions to
disable L1 and L2 caches when using the threadfence routines.
Change-Id: Ic0753170f802003055bca9d7476d7f48817b98b7
2016-07-22 10:40:58 -05:00
b485470819
Replace calls to ihipInit with use of HIP_INIT_API macro
...
Change-Id: Iabf7df79f0238a8ddffea4607fe945df36642850
2016-07-22 15:46:55 +05:30
5c18187741
hip_hcc package now depends on rocm-profiler
...
Change-Id: I80d1c6048cc18c47c2024efb90368b17139a09ad
2016-07-22 15:45:32 +05:30
dffed956fb
Fix using ATP markers
...
Change-Id: If2d04f80b580237426c569737551e2001a8cd35a
2016-07-21 16:02:51 +05:30
7d5cffdc17
Merge branch 'hiparray' into amd-develop
...
Change-Id: I63ca7b1db7b593ac5cfb3fd7cd5d08d6e4075a4c
2016-07-21 12:29:56 +05:30
8c4cd59903
Bump HIP version to 0.92.00
...
Change-Id: I4d653213dcf3ddf7d09d36433afe31e21d17a7ee
2016-07-21 09:52:08 +05:30
300ec2af1e
added kernel launch stress test
...
Change-Id: Ib50d47e55079839ba31aabb524b70b704d7a46fe
2016-07-19 13:57:56 -05:00
77d7134619
added fix for signal overflow in kernels
...
Change-Id: Ie0b1f97f69b7d7b34e445f6f120472819be03a0e
2016-07-19 13:51:44 -05:00
538eeb7cc0
Add markdown documentation to hip_docs package
...
Change-Id: I4075e6baaf287356ac8b485cccc231bfb729f078
2016-07-19 14:30:03 +05:30
89cbfadf86
Set cmake policy CMP0037 to old behavior for newer cmake versions
...
Change-Id: Ib2a7da53a238a489e73d6c006c50f12f07f866a1
2016-07-19 06:52:38 +05:30
4b3102b578
Update documentation.
...
- Add more detailed feature comparison HIP vs specific CUDA SDK revs.
- Remove reference to old codenames.
- Fix TOC in some md files.
Change-Id: If0f6a05dc61237c4710c4d4bf2d933d556dcaeae
2016-07-18 13:56:22 -05:00
a181262ae5
README.md: Fix link to clang-hipify documentation
...
Change-Id: I4c668c0e3c5ee2b16dfc213b48ccd1dbaac7b2a2
2016-07-15 14:18:59 +05:30
0eb4f5e108
Handle linker warning correctly
...
Change-Id: Ifca5886e31b4551603944c2b90a8e532442e889f
2016-07-15 10:40:56 +05:30
1be2dbb150
Add specifying ROCm target support to HIP
...
Change-Id: I42930d8ccf0dafe408ce5bebe2d95f99e544ee8d
2016-07-15 10:08:27 +05:30
2410d285a2
Merge branch 'release_0.90.00' into amd-develop
...
Conflicts:
bin/hipcc
Change-Id: Iced6290fe205551f5d30f656088530b0ea813193
2016-07-15 10:04:03 +05:30
b0dc9d208a
Whitespace cleanup in hipcc
...
Change-Id: I36d32808e9e393df44ffd80b49d09ccf68b5751e
2016-07-13 11:26:03 +05:30
b4b9ab1d28
Cleanup hip_hcc packaging script
...
Change-Id: I41168b3135b36263369b97974a2d2646516e8401
2016-07-12 13:08:21 +05:30
7d3217a3e3
Fix whitespace in cmakefile
...
Change-Id: Ide671e19ea15d57cc8619ec57ad10bca615b3858
2016-07-12 13:00:42 +05:30
22941235e1
cmake queries hip version from hipconfig
...
Change-Id: I8c65ca508ddc288111eaa1d818213c72ef27ac1b
2016-07-12 12:40:35 +05:30
1b184c8527
Move hip version information to hipconfig
...
Change-Id: I2892a9eb9356ac5310b89a433d858c1c3eb986ee
2016-07-11 16:38:41 +05:30
Ben Sander
Evgeny Mankov
Rahul Garg
Maneesh Gupta
scchan
Aditya Atluri
pensun