Commit Graph

13677 Commits

Author SHA1 Message Date
Ben Sander a03c51dc9e Clean up old work-week and USE_* refs
Change-Id: I929c979fa085f8e5205194cbccca46e9b5516aa9


[ROCm/clr commit: 44d117ba63]
2016-06-17 15:18:57 -05:00
Ben Sander b31b23ff1d Refactor directed test infrastructue.
- Add hierarchy.  Tests now live in directories, each with its own
  CMakeFiles.txt.  Reduces merge conflicts.
- Change make_hip_executable -> build_hip_executable.
- Refresh docs.
- Enable some tests that were previously built but not run.

Change-Id: I8c5de3c954400bf233904282b8b42861a2b7c536


[ROCm/clr commit: 3feb13c8f6]
2016-06-17 15:18:57 -05:00
Ben Sander d2d921f7be Fix hierchical tests. Set compiler before project to avoid loop
Change-Id: Icede4e76cb47820b39403a7f1ba3f4bd3f47ed03


[ROCm/clr commit: 883d733174]
2016-06-17 15:18:57 -05:00
Aditya Atluri 1e390cd4af added tests for host math functions
Change-Id: I66a5c574a27190e32054586f07ecf20e1ff71292


[ROCm/clr commit: ba262ea855]
2016-06-17 15:05:33 -05:00
foreman cc0179fb13 P4 to Git Change 1281192 by jatang@jatang-opencl-hsa-stg2 on 2016/06/17 15:19:04
SWDEV-1 - Back out changelist 1281189.

	Made a mistake. Was trying to shelve the CL.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/computeCmdBuffer.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/computeCmdBuffer.h#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/gfx6/gfx6ComputeCmdBuffer.cpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/gfx6/gfx6ComputeCmdBuffer.h#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/gfx6/gfx6PerfCounter.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/gfx6/gfx6PerfTrace.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcounters.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcounters.hpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#13 edit


[ROCm/clr commit: 2a8a6888a9]
2016-06-17 15:05:12 -05:00
foreman 284ae9f6db P4 to Git Change 1281189 by jatang@jatang-opencl-hsa-stg2 on 2016/06/17 15:16:29
SWDEV-1 - OCL PerfCounter on PAL.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/computeCmdBuffer.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/computeCmdBuffer.h#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/gfx6/gfx6ComputeCmdBuffer.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/gfx6/gfx6ComputeCmdBuffer.h#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/gfx6/gfx6PerfCounter.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palbe/src/core/hw/gfxip/gfx6/gfx6PerfTrace.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcounters.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcounters.hpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#12 edit


[ROCm/clr commit: 6e099aabfb]
2016-06-17 15:58:45 -04:00
foreman 242fba8eb6 P4 to Git Change 1281101 by smekhano@stas-rampitec-hsa on 2016/06/17 13:42:09
SWDEV-95698 - Complib: set data layout string from the subtarget in codegen
	This logic was broken since llvm 3.6 merge and datalayout was not set as supposed.
	This results in a different compilation results with complib and llc.
	In addition that leads to the suboptimal codegen.

	Testing: smoke, precheckin, llc_opt, ocl_features, vec_ldst, ocl_sdk_aoc2_compare_main
	Reviewed by Evgeny Mankov

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/codegen.cpp#71 edit
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/ocl/regression/95698/calcweight-nounroll-min.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/tlst/ocl_regression.tlst#37 edit


[ROCm/clr commit: 2300414425]
2016-06-17 13:49:36 -04:00
Aditya Atluri f13c55fb2a added copyright
Change-Id: Ic77c09ff11e031836f4c3d66c9b8ba1894d2e374


[ROCm/clr commit: c07646fddd]
2016-06-17 11:51:36 -05:00
Maneesh Gupta 75ecf38bb7 hipLaunchKernel supports empty kernel with no arguments
Change-Id: Iaa46ced7fe0e3d72734d02250dfb48b98bef615d


[ROCm/clr commit: 275c5516b6]
2016-06-17 14:11:46 +05:30
foreman f1f7c700b6 P4 to Git Change 1280856 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/06/17 03:00:11
SWDEV-2 - Change OpenCL version number from 2147 to 2148.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1894 edit


[ROCm/clr commit: 90d81a61cc]
2016-06-17 03:11:45 -04:00
Aditya Atluri 6837ae644c added bessel nth order function
Change-Id: I18a64d894dda9330b39638535dfafd7ce31bb968


[ROCm/clr commit: 75fc024308]
2016-06-17 09:22:23 +05:30
Ben Sander ac73c9331c Resolve cmake infinite loop issue
Change-Id: I8af4eb8dee754c97b72c108d4613071b0de023bd


[ROCm/clr commit: debddd9b45]
2016-06-16 19:43:07 -05:00
Ben Sander e317f07cb3 Add NVCC implementation for hipPeeakAtLastError
[ROCm/clr commit: 7492351a3c]
2016-06-16 09:38:34 -05:00
Ben Sander 62c5658e93 remove old KERNELBEGIN/KERNELEND macros
[ROCm/clr commit: dbffc7bba2]
2016-06-16 09:38:07 -05:00
Ben Sander 4679da2c45 Add include guards for HIP_PLATFORM_NVCC
[ROCm/clr commit: c2f9fb32a1]
2016-06-16 09:37:10 -05:00
Ben Sander a8cba75ce4 Update launch_bounds test
[ROCm/clr commit: 46e27c7568]
2016-06-16 09:29:03 -05:00
Ben Sander c6ace6f647 Add first steps for CMake test hierarchy + initial launch_bounds.
[ROCm/clr commit: 71b9369256]
2016-06-16 08:41:32 -05:00
Maneesh Gupta 475fd56684 Add compiler annotations to make_ functions
Change-Id: Ic16cfe402dc5cb387b1b63ad311ce8b57ea07361


[ROCm/clr commit: bdfd943b4a]
2016-06-16 16:18:35 +05:30
foreman eec25c6145 P4 to Git Change 1280472 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/06/16 03:00:10
SWDEV-2 - Change OpenCL version number from 2146 to 2147.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1893 edit


[ROCm/clr commit: 32e6cea52f]
2016-06-16 03:06:48 -04:00
Ben Sander c46b2e7450 NVCC improvements.
- Complete translation tables for cudaError <-> hipError_t.
- Remove some odd errors that were not correctly translated or not used.
- Add HIPCHECK_API to test infrastructure.  Used for negative testing
  an API ; if a mismatch occurs it shows the expected return error
  code.  Can also print a warning rather than error.
- Enable hipMemoryAllocate on NV system, and review error coded.
- Add hipErrorName to nvcc.

Change-Id: I680427dcf32a5796d5913cf9e7f3b4c6f6b91599

Conflicts:
	tests/src/CMakeLists.txt

Bug fixes and improved docs for hipFree and hipHostFree.

    - Passing NULL pointer initialized runtime and return hipSuccess
      (not an error like before).
    - add negative test for this. (hipMemoryAllocate, improved)
    - Match NVCC errors for invalid pointers, add to test.
    - Update hipFree and hipHostFree docs.
    - hipGetDevicePointer always set *devicePointer=NULL, even for
      invalid flags.
    - Gate shared memory usage on specific HCC work-week.

Change-Id: I533b4fd3280a3d6cdbf05eb768976f0c7506c012


[ROCm/clr commit: 6a2a140f34]
2016-06-16 06:13:51 +05:30
foreman b5e4d50c08 P4 to Git Change 1280222 by gandryey@gera-w8 on 2016/06/15 13:17:28
SWDEV-95908 - OpenCL on PAL - cl_amd_offline_devices platform extension
	- Add support for offline devices

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#11 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#8 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#5 edit


[ROCm/clr commit: 67d9bc5d63]
2016-06-15 13:23:18 -04:00
Aditya Atluri d01b51eab9 added more host functions and tests
Change-Id: I9904e65e14c5479ba33d836c5c0b763cb5af71e3


[ROCm/clr commit: c4e667cf90]
2016-06-15 11:45:19 -05:00
foreman 38b5667a92 P4 to Git Change 1280009 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/06/15 03:00:14
SWDEV-2 - Change OpenCL version number from 2145 to 2146.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1892 edit


[ROCm/clr commit: ac02a393c2]
2016-06-15 03:14:39 -04:00
Maneesh Gupta cf468b9a7b Merge "added host device functions" into amd-master
[ROCm/clr commit: 8755f2f1bc]
2016-06-15 02:45:55 -04:00
Maneesh Gupta 8b9f354f60 Merge "cmake picks HIP version from hipcc" into amd-master
[ROCm/clr commit: 065b2f532f]
2016-06-15 01:47:18 -04:00
Maneesh Gupta e003279b6e Merge "hipcc supports printing HIP version" into amd-master
[ROCm/clr commit: 35624f33f9]
2016-06-15 01:46:11 -04:00
Aditya Atluri f56bda32bf added host device functions
Change-Id: I8f299752fb8dd8e8947da62e4ad88842c1c19f62


[ROCm/clr commit: bb02880a12]
2016-06-14 18:14:44 -05:00
foreman 6a712e8c60 P4 to Git Change 1279733 by gandryey@gera-w8 on 2016/06/14 15:36:09
SWDEV-95917 - OpenCL on PAL - add device info query to get the number of aysnc queues
	- Correct the number of normal compute queues
	- Fix concurrency test workloads

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/perf/OCLPerfConcurrency.cpp#19 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/perf/OCLPerfConcurrency.h#5 edit


[ROCm/clr commit: c7522d11c4]
2016-06-14 16:10:52 -04:00
foreman a0f0cc1977 P4 to Git Change 1279712 by smekhano@stas-rampitec-hsa on 2016/06/14 15:07:52
SWDEV-94189 - HSA Finalizer: do not use temp files
	New memfile interface is used to emulate files in memory inside perforce build.

	Testing: smoke, precheckin, test_compiler, vp9 in chrome sandbox

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/utils/libelf/_libelf_config.h#4 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/utils/libelf/elf_begin.c#5 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/utils/libelf/memfile.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/utils/libelf/memfile.h#2 edit


[ROCm/clr commit: 133f24578e]
2016-06-14 15:53:29 -04:00
Maneesh Gupta 862ee762cd cmake picks HIP version from hipcc
Change-Id: I334d9573bb6d60fe907a13083486f06504a621e4


[ROCm/clr commit: ea953cb76a]
2016-06-14 14:57:56 +05:30
Maneesh Gupta 4009b60b44 hipcc supports printing HIP version
Change-Id: I9f1cd9a29ded9d354b9ebe265dcd91b060e8fc08


[ROCm/clr commit: 29ca733be2]
2016-06-14 14:51:03 +05:30
foreman 70cb0d32d8 P4 to Git Change 1279406 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/06/14 03:00:13
SWDEV-2 - Change OpenCL version number from 2144 to 2145.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1891 edit


[ROCm/clr commit: 5f184d7a8a]
2016-06-14 03:14:13 -04:00
Aditya Atluri 4d16bb272e added bessel zero and one order functions
Change-Id: I57039d54eae7207db00415bc7ba09bbf9cb6425a


[ROCm/clr commit: ce52a8f70c]
2016-06-14 11:50:48 +05:30
Maneesh Gupta bdfa974253 Merge "added erfinv software implementation" into amd-master
[ROCm/clr commit: 1dbb2f5205]
2016-06-14 02:13:01 -04:00
Maneesh Gupta 46e60b1bd1 Merge "hipDispatchLatency: reduce iterations to 5120" into amd-master
[ROCm/clr commit: 37257dda35]
2016-06-14 00:28:12 -04:00
Aditya Atluri 657a1222d7 added erfinv software implementation
Change-Id: Ib1a5584f6c81ab3afa70f7bcbfd7780e156454e3


[ROCm/clr commit: 720fa16355]
2016-06-14 00:09:41 -04:00
foreman 900222d6bc P4 to Git Change 1279251 by gandryey@gera-w8 on 2016/06/13 17:47:42
SWDEV-86035 - Add PAL backend to OpenCL
	- Remove ciPlus_, since OCL on PAL supports CI+ only
	- Remove singleHeap_
	- Update WaveLimiter

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusettings.cpp#346 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusettings.hpp#97 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.hpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.hpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#11 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palwavelimiter.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palwavelimiter.hpp#3 edit


[ROCm/clr commit: bc84416db0]
2016-06-13 17:53:13 -04:00
foreman f3a24ccf8b P4 to Git Change 1279201 by gandryey@gera-w8 on 2016/06/13 15:49:49
SWDEV-95914 - OpenCL on PAL - Liquid Flash
	- Add liquid flash extension

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#5 edit


[ROCm/clr commit: c2aa3ca6f8]
2016-06-13 15:58:22 -04:00
foreman afa976ec52 P4 to Git Change 1279182 by asalmanp@asalmanp-ocl-stg-pal on 2016/06/13 15:10:34
SWDEV-79278 - [OpenCL][PAL][GFXIP9 Bring up] OCL GFXIP9 general development.Adding support for ASIC detection based on gfxLevel on PAL.  For GFXIP9+, the Asic revision on PAL is Unknown and gfxLevel should be used for ASIC detection.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/10616/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#4 edit


[ROCm/clr commit: 2d5f1bc48d]
2016-06-13 15:20:52 -04:00
Aditya Atluri 570eba42ae added more device functions
Change-Id: I191919060b393772ee442cc19d83479217c5a4ce


[ROCm/clr commit: ae96fe4d12]
2016-06-13 11:55:12 -05:00
Maneesh Gupta c59f486109 hipDispatchLatency: reduce iterations to 5120
Change-Id: I94ae4993ff5058cf15f9487a5a528fc24c1ad5fa


[ROCm/clr commit: 3d4bbc4224]
2016-06-13 14:23:51 +05:30
foreman a23a729a03 P4 to Git Change 1278958 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/06/13 03:00:10
SWDEV-2 - Change OpenCL version number from 2143 to 2144.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1890 edit


[ROCm/clr commit: 0a6f25b703]
2016-06-13 03:22:30 -04:00
Aditya Atluri 4e46d95dac added normcdf support
Change-Id: I4887bc588589ed067eaa339d5eccd988c1c5d649


[ROCm/clr commit: 20b991e99a]
2016-06-13 10:09:37 +05:30
Maneesh Gupta 449f868019 Merge "Added more device functions" into amd-master
[ROCm/clr commit: 102b424ca9]
2016-06-12 23:51:02 -04:00
Maneesh Gupta ef0fdcc0a0 Merge "added test for float device functions c6dfb0" into amd-master
[ROCm/clr commit: fc4b55f516]
2016-06-12 23:50:57 -04:00
foreman d50c516d10 P4 to Git Change 1278842 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/06/12 03:00:16
SWDEV-2 - Change OpenCL version number from 2142 to 2143.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1889 edit


[ROCm/clr commit: 01540fd78f]
2016-06-12 03:09:03 -04:00
foreman ae8a2f0e51 P4 to Git Change 1278792 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/06/11 03:00:11
SWDEV-2 - Change OpenCL version number from 2141 to 2142.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1888 edit


[ROCm/clr commit: e985f8ac99]
2016-06-11 03:11:11 -04:00
foreman fe2efaf603 P4 to Git Change 1278607 by smekhano@stas-rampitec-hsa on 2016/06/10 13:18:54
SWDEV-94189 - ORCA RT: do not use temp files

	This is memfile implementation, an interface to plug into libelf and emulate files in memory w/o any IO.
	If passed filename to open() is empty it will use in memory file, otherwise proxy it to the real file IO routine.

	This allows RT not to use temp files. Next this interface will be plugged to the finalizer.

	Testing: smoke, precheckin, conformance 2.0 reallyquick, test_compiler 1.2 with -legacy, test_compiler with -save-temps-all and -g -O0 -mem2reg=0
	Reviewed by Evgeny Mankov

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/elf.cpp#34 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/elf.hpp#23 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/elf_utils.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/utils/libelf/_libelf_config.h#3 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/utils/libelf/build/Makefile.libelf#5 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/utils/libelf/elf_update.c#12 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/utils/libelf/memfile.cpp#1 add
... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/utils/libelf/memfile.h#1 add


[ROCm/clr commit: 43e8a3bd3d]
2016-06-10 13:23:51 -04:00
Maneesh Gupta 87f1880cfe Merge "fix_testcase" into amd-master
[ROCm/clr commit: 79cb250265]
2016-06-10 12:44:05 -04:00
Aditya Atluri d94fa903bf Added more device functions
1. Added copyright for device float test
2. Added device double functions support
3. Added device double functions test
4. Corrected device function signatures in headers

Change-Id: I13c8829682c925992f5cad84062bc9f702fe4048


[ROCm/clr commit: c7462bd524]
2016-06-10 09:46:31 -05:00