08ed6ab780
Expose support for non-returning atomic FADD
...
Change-Id: If5359488324477315a9bd4f308a75f606c065b39
[ROCm/hip commit: 4a40010ac6
2020-03-05 10:30:52 +05:30
3c66b171e1
Fix HIPRTC headers to export C style symbols ( #1879 )
...
[ROCm/hip commit: 3e1f41c165
2020-02-28 16:47:29 +05:30
c34c9a4b4d
Remove deprecated HIP markers ( #1876 )
...
[ROCm/hip commit: 6c5fa32815
2020-02-28 16:47:15 +05:30
5229ffff99
Add hipDrvOccupancyMaxActiveBlocksPerMultiprocessor[WithFlags] ( #1854 )
...
Equivalent to cuOccupancyMaxActiveBlocksPerMultiprocessor[WithFlags].
[ROCm/hip commit: edc97f3073
2020-02-28 16:46:55 +05:30
2715d1b036
fix long shuffle implementations for windows ( #1895 )
...
Fixes for SWDEV-223694
[ROCm/hip commit: b7dd073d93
2020-02-26 15:53:56 +05:30
f1746197c7
Fix hipMemcpy3D ( #1798 )
...
Fixes #1790 and #1791 . hipMemcpy3D still requires further refactoring for different input and output combinations.
[ROCm/hip commit: 8c5e5e435b
2020-02-17 19:35:35 +05:30
6d661ba6ca
Implement long / long long shuffles ( #1829 )
...
Implement additional data-types for shuffles (long and long long).
Based upon the double implementation.
[ROCm/hip commit: 797a929a65
2020-02-15 09:51:09 +05:30
fb53186682
Reduce GPU copying based on arch it runs on ( #1751 )
...
Implements SWDEV-213230.
[ROCm/hip commit: 8c6934223b
2020-02-13 14:21:51 +05:30
07c3e4f898
fix build error in nvcc path
...
[ROCm/hip commit: 959f1b0f0e
2020-02-11 12:16:51 -05:00
5db60dab96
Fix a typo causing a build error
...
[ROCm/hip commit: 5a29f27455
2020-02-10 11:44:40 -05:00
964a272004
resolve merge conflict
...
[ROCm/hip commit: 874b201ee2
2020-02-10 10:30:55 -05:00
7753b3e827
Revert "Match Occupancy APIs syntax with CUDA ( #1625 )" ( #1857 )
...
Reverting this for now till we figure out how to avoid the build
breakage.
This reverts commit e38db9fb6ff8e1c01900
2020-02-10 10:45:28 +05:30
5d5344eea1
(Maybe) Match alignment between Clang and GCC. ( #1789 )
...
Should fix #1740 and the related internal bug.
[ROCm/hip commit: dd34ea95d6
2020-02-10 10:44:49 +05:30
e5243c1834
Device texture functions should not normalize the sampled pixel ( #1826 )
...
* Device texture functions should not normalize the sampled pixel. This is already done by HW.
* Add support to use h/w capability for normalized float data convertion for driver API's
Co-authored-by: ansurya <50609411+ansurya@users.noreply.github.com >
[ROCm/hip commit: ef514eef71
2020-02-05 20:56:17 +05:30
adc9134318
code clean up
...
[ROCm/hip commit: c8137263d6
2020-01-31 13:08:25 -05:00
78a36b4fb8
[HIP][HIPIFY] Add some missing flags for cooperative launch and occupancy APIs
...
[ROCm/hip commit: 6e867eacb6
2020-01-30 15:05:53 -05:00
e38db9fb6f
Match Occupancy APIs syntax with CUDA ( #1625 )
...
* Match Occupancy APIs syntax with CUDA and fix tests using these APIs
[ROCm/hip commit: fa98798b63
2020-01-29 13:05:53 -08:00
1af35a6044
Add missing texturePitchAlignment member to the hipDeviceProp_t struct. ( #1802 )
...
* Add missing texturePitchAlignment member to the hipDeviceProp_t struct.
* Add missing hipDeviceAttributeTexturePitchAlignment enumerator to the hipDeviceAttribute_t enum.
* Initialize texturePitchAlignment to 256. This works for gfx9+, but is technically overaligned in most cases for pre-gfx9.
* Add the texturePitchAlignment property to the NVCC path.
[ROCm/hip commit: f72a669487
2020-01-27 16:37:00 -08:00
95ee059bbb
Update the HIP_TRSF_* flags to match their Cuda equivalents. ( #1801 )
...
[ROCm/hip commit: 9cfada0f9d
2020-01-24 11:41:15 -08:00
c630cb57b2
SWDEV-220503: this_grid().thread_rank() gives incorrect result ( #1808 )
...
* fix a minor bug while computing this.grid()::thread_rank()
[ROCm/hip commit: bed8f1c1b8
2020-01-24 16:23:28 +05:30
dabbde21c6
Don't use accelerated vector element access for hip-clang. ( #1796 )
...
[ROCm/hip commit: 566adc4594
2020-01-15 18:17:08 -08:00
4c457c2bb5
Add missing constructors for Scalar_accessor class. ( #1792 )
...
[ROCm/hip commit: fae85cf6d2
2020-01-14 11:30:21 -08:00
3d22f829f5
[HIP] Unify hipError_t (Step 3): Sync nvcc path ( #1778 )
...
* [HIP] Unify hipError_t (Step 3): Sync nvcc path
* [HIP][fix] Add CUDA 10.x support to nvcc path
[ROCm/hip commit: a005a8550d
2020-01-10 13:47:18 +05:30
6ebf5ca991
Revert PRs that break ROCm builds ( #1781 )
...
Fixes SWDEV-218626 and SWDEV-218629
Changes:
- Revert "`static inline` in a header, just like excess sugar in a diet, causes bloat (#1692 )"
This reverts commit b7803eb0c6#1777 )"
This reverts commit 9c8c3df29400bd5d1cec
2020-01-08 15:11:58 +05:30
9c8c3df294
Fix rocFFT build failure ( #1777 )
...
Fixes SWDEV-217761
[ROCm/hip commit: 753277422a
2020-01-07 08:12:37 +05:30
327a45b18b
Add hipBindTexture2D on NVCC path ( #1773 )
...
[ROCm/hip commit: a5d7e7d8d3
2020-01-06 12:33:50 +05:30
86dbb13897
Fix hipcc warning related to hipVersion ( #1767 )
...
* Fix hipcc warning related to hipVersion
* Rename hipVersion.h to hip_version.h
* Remove HIP_VERSION splitting
* Update .gitignore
- Ignore generated include/hip/hip_version.h
- Removed some stale entries
- Added executables from samples/1_Utils/*/ for consistency with bin/ entries.
[ROCm/hip commit: f3cafd5855
2020-01-06 12:33:23 +05:30
6ac4d18753
Merge pull request #1759 from emankov/master
...
[HIP] Unify hipError_t (Step 2)
[ROCm/hip commit: 0dadb23327
2019-12-30 19:21:09 +03:00
6d2ec032fe
Change to generate hipVersion.h ( #1726 )
...
HIP_VERSION_MAJOR, HIP_VERSION_MINOR, HIP_VERSION_PATCH and HIP_VERSION pre-processor macros are now defined in hipVersion.h instead of being set by hipcc.
[ROCm/hip commit: aa4aea0754
2019-12-30 12:44:24 +05:30
ffea90f865
[hip] refactoring cooperative kernel launch APIs ( #1737 )
...
This PR is a follow-up on PR# #1698 and it makes two more APIs (hipLaunchCooperativeKernel/hipLaunchCooperativeKernelMultiDevice) inline so that they can work correctly with lazy binding.
[ROCm/hip commit: 6968aeb841
2019-12-30 12:42:17 +05:30
abef353b5b
[HIP] Clean-up deprecated HIP error codes
...
hipErrorMemoryAllocation -> hipErrorOutOfMemory
hipErrorInitializationError -> hipErrorNotInitialized
hipErrorMapBufferObjectFailed -> hipErrorMapFailed
hipErrorInvalidResourceHandle -> hipErrorInvalidHandle
[ROCm/hip commit: 4921678b6c
2019-12-23 17:01:35 +03:00
d10837db9d
Add macro __HIP_ENABLE_CUDA_WRAPPER_FOR_OPENMP__ ( #1761 )
...
This is to allow force enable cuda wrapper for OpenMP for flexibility
[ROCm/hip commit: 3c90d57072
2019-12-23 19:24:54 +05:30
bb7fa73dcc
Fix the return type of demangle function so that its compatible across ABIs ( #1744 )
...
[ROCm/hip commit: 080b0b9a68
2019-12-23 19:11:40 +05:30
1f5ecc0f6a
Fix late-coming issues. ( #1724 )
...
Implementation for hipMemcpyWithStream.
[ROCm/hip commit: 75a11330aa
2019-12-23 19:11:24 +05:30
91f82210fb
replace array designator C99 ( #1694 )
...
* replace array designator C99
* Update texture_functions.h
Highlight valid and invalid values in texFormatToSize
Co-authored-by: Maneesh Gupta <maneesh.gupta@amd.com >
[ROCm/hip commit: 7d6634ce9d
2019-12-23 19:10:24 +05:30
b7803eb0c6
static inline in a header, just like excess sugar in a diet, causes bloat (#1692 )
...
[ROCm/hip commit: be70b9f7e7
2019-12-23 19:09:38 +05:30
97535f3e97
[HIP] Fix typo
...
[ROCm/hip commit: 9544682e2c
2019-12-23 12:06:44 +03:00
30ae3942dc
[HIP] Unify hipError_t (Step 2)
...
Step 2. Make a few hipError codes deprecated
Update hipify-clang, hipify-perl, docs and samples accordingly
[ROCm/hip commit: dbad4d9b7f
2019-12-22 02:05:31 +03:00
ddc169cf4e
Update texture_functions.h
...
Highlight valid and invalid values in texFormatToSize
[ROCm/hip commit: d92169c05a
2019-12-21 12:25:36 +05:30
ef3ee5908f
Fix for windows dtest build failure ( #1742 )
...
[ROCm/hip commit: e2fc00da65
2019-12-19 13:10:43 -08:00
ded857e2b9
[hip] Add macro guarding the enum conversion for scalar accessor. ( #1748 )
...
- That's a high overhead part, which needs enabling ONLY if necessary.
[ROCm/hip commit: 99a3b66110
2019-12-19 10:08:37 -08:00
ca99107c7b
[HIP] Unify hipError_t (Step 1)
...
Step 1. Set the same values for RT error codes as for analogous Driver's
[Reason] RT's and Driver's error codes unification in CUDA 10.2
[ROCm/hip commit: d8737ba50c
2019-12-13 19:40:16 +03:00
e1f55b0cee
Only add hipExtLaunchMultiKernelMultiDevice for non-HCC compilers. ( #1729 )
...
[ROCm/hip commit: 444c931641
2019-12-10 10:32:25 -08:00
65f80f80a1
fix linking of vector types with gcc ( #1690 )
...
* fix linking of vector types when linking hipcc objects with gcc
* use __atribute__((vector_size)) with both clang and gcc
and reinstate nonaligned n=3 vector type
* use implicit conversion to value and ext_vector_type when available
* Alternate formulation for GCC compatibility
* Built-in arrays don't mix well with placement new
* Fix typo
* Add conversions to enum
* Fix Scalar_accessor assignment.
* Update hip_vector_types.h
* stir up the underlying_type hideous mess
This fixes the HIP build issue "error: only enumeration types have underlying types".
[ROCm/hip commit: 00d735cdc9
2019-12-10 09:40:15 +05:30
7703031d33
Fix hipExtLaunchMultiKernelMultiDevice refactoring. ( #1714 )
...
- Use the correct condition for HIP VDI runtime.
[ROCm/hip commit: e9da934ac6
2019-12-06 09:49:17 -08:00
ebdd811632
Revert - Changes related to hipMemcpyWithStream ( #1718 )
...
Reverting #1673 , #1697 and #1707 .
Support for hipMemcpyWithStream and memcpy optimizations, will be brought in again once issues seen with these are resolved independently.
[ROCm/hip commit: e53fc316f1
2019-12-06 09:51:53 +05:30
abe7531676
[hip] refactoring hipExtLaunchMultiKernelMultiDevice API ( #1698 )
...
[Background] it was found that if lazy linking used for a library that calls hipExtLaunchMultiKernelMultiDevice API then this API can get the wrong program_state object for looking up device kernels leading to a "No device code available" error in this API.
To fix this issue, the API was refactored to be inline and get and pass the correct program_state to an internal hip API to request a multi-device kernel launch.
[ROCm/hip commit: 68cc787781
2019-12-04 11:50:51 +05:30
4e564f783e
Revert changes for atomic FADD support when address is in LDS ( #1701 )
...
This reverts PR #1591 and follow-on PR #1695
[ROCm/hip commit: 32442c6506
2019-11-29 11:58:12 +05:30
dc9bc8ee86
Uniform is_shared query. ( #1695 )
...
[ROCm/hip commit: b6514fffb9
2019-11-28 13:39:05 +05:30
023ee64ecf
replace array designator C99
...
[ROCm/hip commit: edf29b8673
2019-11-25 16:51:49 +05:30
Maneesh Gupta
saleelk
Rahul Garg
Nick Curtis
ansurya
Aryan Salmanpour
Alex Voicu
vsytch
satyanveshd
mshivama
kpyzhov
Evgeny Mankov
Sarbojit2019
Yaxun (Sam) Liu
mhbliao
jglaser
Anusha Godavarthy Surya