5fa1029861
Update release notes for 0.92.00 release
...
Change-Id: I9ca588cd0d5d752dc6521e76ba943500eb55525f
[ROCm/clr commit: de7c9769a4
2016-07-27 20:30:04 +05:30
b99410bd07
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
[ROCm/clr commit: 7be196de48
2016-07-26 17:09:27 -05:00
d8ea207f61
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
[ROCm/clr commit: 2e754d27dc
2016-07-26 14:03:51 -05:00
bb363f9d63
removed redundant signal destroy
...
Change-Id: Icf0cd76b2620d34c87cfb6c7a83049087c0a0bc4
[ROCm/clr commit: 524127b4a4
2016-07-26 13:35:35 -05:00
0ed0ad30da
Doc update for FAQ and future RELEASE notes
...
Change-Id: I7e7c32d9a19fdaea0a0e41f1d4fa4652e53640f2
[ROCm/clr commit: 77be00e8d3
2016-07-26 12:14:15 -05:00
542948ad75
Doc update for README.md - add more intro text, example
...
Change-Id: I99b8eaacd6460dfdbdbc8ddba3fe589647d877e7
[ROCm/clr commit: 75d1f8c297
2016-07-26 12:14:02 -05:00
4094170fd7
Make HCC ignore register keyword
...
- (previously would emit a warning)
- Also tweak documentation.
Change-Id: I0f4f00f82f8cc53d420112570f2d7675535e6aea
[ROCm/clr commit: b9e48d6066
2016-07-26 12:13:48 -05:00
e207805f81
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
[ROCm/clr commit: 0232e6bbb4
2016-07-26 09:22:59 -05:00
cc9a901498
Documentation updates
...
Change-Id: Ia624d86915c4c96da0ac0242f767135f30ff73c6
[ROCm/clr commit: b29ed98f9a
2016-07-25 14:53:15 +05:30
7a70966cb1
D2H and H2D unpinned memory transfer support
...
Change-Id: If6d6c970f435e5d917d5cc6cddc2ee2918cd1c37
Conflicts:
src/hip_hcc.cpp
[ROCm/clr commit: d11d65d401
2016-07-25 14:36:07 +05:30
776ea7a1f0
Partial fix async after kernel launch signal issue
...
Change-Id: Ib48d6564379160035bded9493b93663fba361710
[ROCm/clr commit: 1704006bed
2016-07-23 14:54:20 -05:00
2c945dba23
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
[ROCm/clr commit: 6db08e5135
2016-07-22 10:40:58 -05:00
64d0ffb404
Replace calls to ihipInit with use of HIP_INIT_API macro
...
Change-Id: Iabf7df79f0238a8ddffea4607fe945df36642850
[ROCm/clr commit: b485470819
2016-07-22 15:46:55 +05:30
21ae09859d
hip_hcc package now depends on rocm-profiler
...
Change-Id: I80d1c6048cc18c47c2024efb90368b17139a09ad
[ROCm/clr commit: 5c18187741
2016-07-22 15:45:32 +05:30
68b1a199c4
Fix using ATP markers
...
Change-Id: If2d04f80b580237426c569737551e2001a8cd35a
[ROCm/clr commit: dffed956fb
2016-07-21 16:02:51 +05:30
997cb27be8
Merge branch 'hiparray' into amd-develop
...
Change-Id: I63ca7b1db7b593ac5cfb3fd7cd5d08d6e4075a4c
[ROCm/clr commit: 7d5cffdc17
2016-07-21 12:29:56 +05:30
0b97390948
Bump HIP version to 0.92.00
...
Change-Id: I4d653213dcf3ddf7d09d36433afe31e21d17a7ee
[ROCm/clr commit: 8c4cd59903
2016-07-21 09:52:08 +05:30
794d6bfda8
added kernel launch stress test
...
Change-Id: Ib50d47e55079839ba31aabb524b70b704d7a46fe
[ROCm/clr commit: 300ec2af1e
2016-07-19 13:57:56 -05:00
2098afc04d
added fix for signal overflow in kernels
...
Change-Id: Ie0b1f97f69b7d7b34e445f6f120472819be03a0e
[ROCm/clr commit: 77d7134619
2016-07-19 13:51:44 -05:00
1d3164ac80
Add markdown documentation to hip_docs package
...
Change-Id: I4075e6baaf287356ac8b485cccc231bfb729f078
[ROCm/clr commit: 538eeb7cc0
2016-07-19 14:30:03 +05:30
bb2296d48b
Set cmake policy CMP0037 to old behavior for newer cmake versions
...
Change-Id: Ib2a7da53a238a489e73d6c006c50f12f07f866a1
[ROCm/clr commit: 89cbfadf86
2016-07-19 06:52:38 +05:30
5586cc02b4
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
[ROCm/clr commit: 4b3102b578
2016-07-18 13:56:22 -05:00
f58a6b4dd5
README.md: Fix link to clang-hipify documentation
...
Change-Id: I4c668c0e3c5ee2b16dfc213b48ccd1dbaac7b2a2
[ROCm/clr commit: a181262ae5
2016-07-15 14:18:59 +05:30
87003ac6c5
Handle linker warning correctly
...
Change-Id: Ifca5886e31b4551603944c2b90a8e532442e889f
[ROCm/clr commit: 0eb4f5e108
2016-07-15 10:40:56 +05:30
ad1f67604c
Add specifying ROCm target support to HIP
...
Change-Id: I42930d8ccf0dafe408ce5bebe2d95f99e544ee8d
[ROCm/clr commit: 1be2dbb150
2016-07-15 10:08:27 +05:30
9e414f242c
Merge branch 'release_0.90.00' into amd-develop
...
Conflicts:
bin/hipcc
Change-Id: Iced6290fe205551f5d30f656088530b0ea813193
[ROCm/clr commit: 2410d285a2
2016-07-15 10:04:03 +05:30
f75691db73
Whitespace cleanup in hipcc
...
Change-Id: I36d32808e9e393df44ffd80b49d09ccf68b5751e
[ROCm/clr commit: b0dc9d208a
2016-07-13 11:26:03 +05:30
4a0c601995
Cleanup hip_hcc packaging script
...
Change-Id: I41168b3135b36263369b97974a2d2646516e8401
[ROCm/clr commit: b4b9ab1d28
2016-07-12 13:08:21 +05:30
7bfc1de762
Fix whitespace in cmakefile
...
Change-Id: Ide671e19ea15d57cc8619ec57ad10bca615b3858
[ROCm/clr commit: 7d3217a3e3
2016-07-12 13:00:42 +05:30
f0b61dce8d
cmake queries hip version from hipconfig
...
Change-Id: I8c65ca508ddc288111eaa1d818213c72ef27ac1b
[ROCm/clr commit: 22941235e1
2016-07-12 12:40:35 +05:30
ab99447c73
Move hip version information to hipconfig
...
Change-Id: I2892a9eb9356ac5310b89a433d858c1c3eb986ee
[ROCm/clr commit: 1b184c8527
2016-07-11 16:38:41 +05:30
11b143ae2d
clang-hipify: Populate replacement rules and fix typos.
...
+ fix typo in hipStreamWaitEvent.
+ hipHostAlloc -> hipHostMalloc.
+ Memory Types, Pointer Attributes are added.
+ Event, Host Malloc and Register, Device and Stream Flags are added.
+ exclude cudacommon.h.prehip from includes' replacement rules.
[ROCm/clr commit: 9f77666802
2016-07-07 18:01:41 +03:00
d03904578c
Merge branch 'amd-master' into amd-develop
...
[ROCm/clr commit: 5947731054
2016-07-05 21:40:22 +05:30
d087ddbaf0
Merge remote-tracking branch 'hipblas' into hipblas
...
[ROCm/clr commit: e936f584f7
2016-07-05 10:04:10 +05:30
8a2cb5bdcb
don't bundle source in rocm packages
...
Change-Id: I36bd93e2bff9db1310724dd79c6c736ee17aa806
[ROCm/clr commit: 5bb51a3150
2016-07-05 08:18:30 +05:30
7d19c11a56
clang-hipify: add Replacement Excludes
...
Excludes are not replaced, for instance, CHECK_CUDA_ERROR and CUDA_SAFE_CALL.
Add check for excludes in MacroExpands and CallExpr routines.
[ROCm/clr commit: 5d04a17a44
2016-07-01 19:58:14 +03:00
c17209f530
added more nvcc event functions
...
Change-Id: I79ee20ef444d4c1ab6ada3c0d56730ce754ab6b6
[ROCm/clr commit: adad6ef71f
2016-06-30 21:03:19 -05:00
4e84678f27
Merge branch 'amd-develop' into amd-master
...
Change-Id: I04f85b207e15e66c1a546675dc0937726ee08362
[ROCm/clr commit: 2577b6158f
2016-06-30 18:36:07 +05:30
eb0db4e549
Replace GPU agent with CPU agent properly for memory async copy API
...
ihipStream_t::copySync use GPU agent in memory async copy API, even
if the src/dst memory does not belong to GPU, which cause the hsa
runtime to choose a slower copy engine.
SWDEV-95191
Change-Id: If3cab3d493c0c96ed63721cdcf28247a1193887c
[ROCm/clr commit: dc0a787984
2016-06-30 18:23:29 +05:30
cf3186cd63
moved half support to a source file
...
Change-Id: I7c09b41877e22c1b743dea25a585e5307427dafd
[ROCm/clr commit: 38720f8a4e
2016-06-30 18:23:29 +05:30
29c5bf181a
added fp16 software support
...
Change-Id: Ic0fdd9f8248a66911169fc00d3af71f50b36e233
[ROCm/clr commit: 4a6ebce880
2016-06-30 18:23:29 +05:30
80026f4019
clang-hipify: fix typos and populate replacement rules
...
+ typos in cudaDeviceAttr and cudaDeviceAttr
+ Device Attribules are added
+ More error codes are added
[ROCm/clr commit: 53401727a8
2016-06-29 20:32:05 +03:00
c9b2c560c2
Update release notes
...
Change-Id: I6ae7e5c44b1f7d084abb7cedd353276b81531f82
[ROCm/clr commit: 88ca6f7312
2016-06-29 20:50:14 +05:30
138148a788
Update markdown documentation
...
Change-Id: I92cf4411d601e5bbd62ce6c3346cdac0ea2945a8
[ROCm/clr commit: 4138461080
2016-06-29 20:49:40 +05:30
ee53c355d1
clang-hipify: Array of elements of typedef type translation support.
...
Example: cudaStream_t streams[2]
[ROCm/clr commit: f19992760e
2016-06-28 19:57:08 +03:00
96dd64f05b
cublas to hipblas translation support in clang-hipify
...
+ CUBLAS V2 functions support
+ annotating, formatting
[ROCm/clr commit: ab2a7f436d
2016-06-28 15:33:38 +03:00
308a0f7c31
NVCC_COMPAT
...
add support for both cuda compatible implementation and hcc(faster)
implementation with test
Change-Id: I79a22344f458391d7dffac5f147619a542e97e4e
[ROCm/clr commit: 54034e5048
2016-06-28 09:36:06 +05:30
8ddf1af785
hip_samples package now contains uncompressed samples
...
Change-Id: I69e773ebeff59733e016abd5a90bd1637798b1f5
[ROCm/clr commit: 058cdf2a8c
2016-06-24 21:17:52 +05:30
4ae1b48c66
Included code to calculate value of maxThreadsPerMultiprocessor property
...
Change-Id: Ie7cad7442f36a7163e715048de5a309febc28664
[ROCm/clr commit: dc5ca03143
2016-06-24 21:17:30 +05:30
28915dd491
Merge branch 'amd-master' into amd-develop
...
[ROCm/clr commit: dca8fca8eb
2016-06-24 21:13:11 +05:30
Maneesh Gupta
Aditya Atluri
Ben Sander
Rahul Garg
pensun
Evgeny Mankov
Evgeny Mankov
Fan Cao
7SK