Grafico dei commit

4403 Commit

Autore SHA1 Messaggio Data
Christophe Paquot d4df8f2042 Default HostMalloc to uncached memory
Change-Id: I72e19c7f7820a77fd5afc09f09cfea9acd0b8e84


[ROCm/hip commit: fa5a9b3810]
2020-04-03 19:19:33 -04:00
Saleel Kudchadker 5f95e68b90 Merge "Wake up commandQueue before returning" into amd-master-next
[ROCm/hip commit: f1a9a4f22a]
2020-04-03 18:27:03 -04:00
Michael LIAO 5bdf843642 [vdi] Add hipFreeHost
Change-Id: I8a5b7ff3f0ab4f5674efd6723c18808ad6ef33f5


[ROCm/hip commit: 9e619430f4]
2020-04-03 16:34:28 -04:00
German Andryeyev 73c507c3c6 Merge "SWDEV-184709 - support hipLaunchCooperativeKernel()" into amd-master-next
[ROCm/hip commit: 6f19e77f69]
2020-04-03 16:23:05 -04:00
Vladislav Sytchenko 0d6c4fe470 Take into an account the number of channels...
when querying the element size of an array.

Change-Id: Id57d3374b14d80a59230ec8286704f2fbabb0fae


[ROCm/hip commit: 5f14ae1161]
2020-04-03 15:43:18 -04:00
German Andryeyev e55b231bb1 SWDEV-184709 - support hipLaunchCooperativeKernel()
- Add validation checks for cooperative launch to pass Cuda test

Change-Id: Ie296f0c3f113909d9a357879db3b2a833ab314c5


[ROCm/hip commit: 7820018037]
2020-04-03 15:18:21 -04:00
Michael Hong Bin Liao 8c63e2536d Merge "Fix size type in __hipRegisterVar" into amd-master-next
[ROCm/hip commit: fad9e39597]
2020-04-03 15:12:21 -04:00
Saleel Kudchadker f3bdfe2baa Wake up commandQueue before returning
Change-Id: I87eb5a22c81a9cb807474a960b5987d5fb6c2b86


[ROCm/hip commit: bc8d6ac97c]
2020-04-03 10:23:36 -07:00
Aaron En Ye Shi 1ed78d9869 Merge "Fix path for hip-clang when using hipcc (#1961)" into amd-master-next
[ROCm/hip commit: a2104f6c94]
2020-04-03 12:28:50 -04:00
Michael LIAO 9759e31dac Fix size type in __hipRegisterVar
Change-Id: I6b667600ae8f133583b768ab963318882b84179f


[ROCm/hip commit: 00bb2ce04a]
2020-04-03 10:51:58 -04:00
Michael Hong Bin Liao 7083af4690 Merge "[hip] Clean up unnecessary casting." into amd-master-next
[ROCm/hip commit: dbedce9e54]
2020-04-03 10:50:40 -04:00
Michael LIAO 4b28e810f9 [hip] Clean up unnecessary casting.
Change-Id: I64b08aaef5c67ffb49330c9c605611f1fbd3f5a2


[ROCm/hip commit: 79d8f7e47e]
2020-04-02 12:46:15 -04:00
Paul Fultz II 17f9e2358b Fix path for hip-clang when using hipcc (#1961)
* Fix path for hip-clang when using hipcc

* Fix typo

* Update regex

Change-Id: I31bbee2e70d58b89191f970f5c6ae7e1c8b40900


[ROCm/hip commit: c8bcf28320]
2020-04-02 12:09:31 -04:00
Paul Fultz II 8aff07fe80 Add missing flags for hip::device target on hip-clang (#1230)
This adds the missing compilation flags to hip::device so it can compile with hip-clang compiler.

Change-Id: Ie2b30ea606bfca385a0e84ae03ee0a8d828ad16a


[ROCm/hip commit: 2c246dabfe]
2020-04-02 12:09:03 -04:00
Saleel Kudchadker 124e126d85 Merge "OpenCL2.2 Header changes" into amd-master-next
[ROCm/hip commit: 68d013d030]
2020-04-02 02:46:49 -04:00
Vladislav Sytchenko 1ce5ee07d2 Add entry points for hipTexObject*() API
Even though the runtime and driver texture object API is one to one, the structs used by these APIs are not. See hipResourceDesc vs HIP_RESOURCE_DESC differences.

These differences are not trivial and most likely won't be able to handled by hipify, so we need new API entry points.

Change-Id: Id4bcb1ad0ae15378dbdb5a2ed07e5ea30f320082


[ROCm/hip commit: aea688b79c]
2020-04-01 14:51:51 -04:00
Saleel Kudchadker 1bd55da10a Merge "Cleanup stream from hip:Event class." into amd-master-next
[ROCm/hip commit: 34a3ed9c1b]
2020-03-31 20:14:48 -04:00
Vladislav Sytchenko deacfcd063 (SWDEV-229354)
This patch is a workaround to support user pitch for hipMemcpy{2D/3D}.

Historically OpenCL didn't support pitch with clEnqueueFillBuffer(), so neither did we in VDI. Adding it now will be slightly nontrivial, since the fill kernel and runtime in many places will need to be modified.

As a temporary workaround for cases when pitch > width, we can just enqueue a fill for each row separately. This implementation is slow, but it satisfies the correctness criteria.

Change-Id: Idfeca349288b51d6ff84a7cf001fb63c6a66818a


[ROCm/hip commit: 77223a8eca]
2020-03-31 18:12:56 -04:00
Reshabh Sharma 264082869c Output file name should not change flags picked for compiler (#1938)
Fixes SWDEV-207362,

The output file name should not contribute to picking up the right flags for the compiler. This fix solves issues when the output has conflicting extensions which confuses hipcc to treat them as the source files and add the required flags for them.

PS: Output file refers to the file followed by -o

Change-Id: I1095966c11143ad73e81fabc35b4e9de5d3afada
Example: hipcc test.o -o test.hip will add the flags for .hip compilation ignoring the fact that it is an output file


[ROCm/hip commit: bb62f8553f]
2020-03-31 16:13:43 -04:00
Saleel Kudchadker 2f1617e21a Cleanup stream from hip:Event class.
Change-Id: I98de07d33bb7fea8f5e2d32b288c15f10ce58902


[ROCm/hip commit: e4ea1f60bb]
2020-03-31 11:22:00 -07:00
Michael Hong Bin Liao e89abbb63b Merge "[hipcc] Remove the previous workaround." into amd-master-next
[ROCm/hip commit: 5b96f38c1e]
2020-03-31 10:05:56 -04:00
Michael LIAO 5e5f4e23d5 [vdi] Fix hipGetSymbol{Address|Size}
- Use symbol value as the qeury key. Compared to the symbol name, the
  symbol value is more robust as developers may use unqualified or
  qualified identifiers. It also removes the mangling and/or demangling
  requirement for the runtime API.

Change-Id: I9d4259f3842612c7cc98551269fc2092d8b5c19e


[ROCm/hip commit: b72196613a]
2020-03-31 00:26:53 -04:00
Christophe Paquot 24cd888b3a Do not retry to allocate when OOM. Shouldn't be needed since we idle on Free.
SWDEV-229214

Change-Id: I183006f409388e3c7981f2569649d01d6378be46


[ROCm/hip commit: 94a7ef6ed1]
2020-03-30 12:49:48 -07:00
kjayapra-amd ce461331d3 SWDEV-216213 - Use different static & dynamic module maps for faster lookup.
Change-Id: Ia605e76a411ad5be04046b9d61f1ac111d49bb4a


[ROCm/hip commit: b081912962]
2020-03-30 14:28:07 -04:00
Anusha Godavarthy Surya 03a8b95eb4 Merge "Update Enable/Disable peers to match cuda behaviour" into amd-master-next
[ROCm/hip commit: caa083357a]
2020-03-30 13:46:42 -04:00
agodavar d7db609b92 Update Enable/Disable peers to match cuda behaviour
Change-Id: I67194ccf77a0019368579ff7d95b7790fcf228f3


[ROCm/hip commit: bdb3a4b393]
2020-03-30 12:49:16 -04:00
Tao Sang 1254e84b7b Merge "enable HCC printf when using hip-clang" into amd-master-next
[ROCm/hip commit: 1697cfc790]
2020-03-30 11:37:23 -04:00
Michael LIAO 9a2e585762 [hipcc] Remove the previous workaround.
Change-Id: Ie1c2aa21689bc343c10fd4b699546cf500ced5b2


[ROCm/hip commit: f1566f6dc5]
2020-03-30 10:18:47 -04:00
Michael LIAO cbac75a003 [vdi] Fix calculation of MaxWaves
- Consider the case where `usedVGPRs` is zero.
- This fixes [SWDEV-228537](http://ontrack-internal.amd.com/browse/SWDEV-228537)

Change-Id: I8675311f5fe24fb59c5d45bada122afefb55b128


[ROCm/hip commit: 3a690e960f]
2020-03-30 09:10:16 -04:00
Sameer Sahasrabuddhe 3e7d08f5ee enable HCC printf when using hip-clang
This is cherry-picked from PR#1947 that was committed to the
github repo. It allows printf to work with hip-clang and HCC
runtime.

Change-Id: I754753250ea1e694cf3441722e2d4c9d25fa75bc


[ROCm/hip commit: 9a0c5d0653]
2020-03-28 00:18:21 -04:00
Saleel Kudchadker 35e9fa08be Merge "Check event status before notify" into amd-master-next
[ROCm/hip commit: 5a8add03a5]
2020-03-27 20:19:40 -04:00
Vladislav Sytchenko 511f2d03a2 (SWDEV-228794)
Adjust the origin of the copy if the user passes a pointer that wasn't allocated by the runtime.

Change-Id: I0aeb20195ed730857a461a53f537626ec2573fd1


[ROCm/hip commit: 6ed73f50f7]
2020-03-27 16:33:16 -04:00
Vladislav Sytchenko d3b9203359 (SWDEV-228794)
Add hipMallocHost()

Change-Id: Ia3c7c5ca94b39fe30f3a51d1b60782d3472259ff


[ROCm/hip commit: fd7a8f0367]
2020-03-27 15:57:48 -04:00
Vladislav Sytchenko 7a867cd98f (SWDEV-228782)
The only requirment from hipMallocPitch() is that the returned pitch is aligned to the HW image pitch alignment. There is no restriction on the size of the allocation, since the memory might not be used for images.

Change-Id: I97438e5fe4012ca4721b14b85f514dbac803c17c


[ROCm/hip commit: a91b82f00e]
2020-03-27 15:52:17 -04:00
Tao Sang aa94d9c654 Merge "Support hipFuncGetAttributes with hip-clang+Hcc RT" into amd-master-next
[ROCm/hip commit: af7d131749]
2020-03-27 14:36:41 -04:00
Saleel Kudchadker 573d676ef0 Check event status before notify
Change-Id: I68f6bbbf236e49b859be2d5afbe0c8282fe15dd3


[ROCm/hip commit: 178fc17846]
2020-03-27 11:32:46 -07:00
Tao Sang c20e13d1f0 Support hipFuncGetAttributes with hip-clang+Hcc RT
Fix issues of missing kernel function symbols and missing argument list via
using __hipRegister* functions.
Then the following tests can pass,
directed_tests/runtimeApi/module/hipFuncGetAttributes
directed_tests/runtimeApi/module/hipExtLaunchMultiKernelMultiDevice
directed_tests/gcc/LaunchKernel

Change-Id: I52135b61e8283eb4f9f10f77895151e4e55418d9


[ROCm/hip commit: d967be8eeb]
2020-03-26 23:28:35 -04:00
Saleel Kudchadker 89295ceafa OpenCL2.2 Header changes
Change-Id: I3285a8ffc7e34333feb68e925ebd460831c8e3d4


[ROCm/hip commit: a5fb06f4db]
2020-03-26 17:35:09 -07:00
Vladislav Sytchenko ec09381120 Add support for formating hipExtent objects
Change-Id: Iea54a510e81a856c0c450305b3e5a7179ee48295


[ROCm/hip commit: 2a2b9e47a0]
2020-03-26 14:45:20 -04:00
Vladislav Sytchenko 99b2084641 Enable initial sRGB support
Instead of using the sampler field force_degamma to perform sRGB->linear conversion during pixel sampling, we use an appropriate image format instead. The overhead of this is having to create an image view when creating a texture object from an array.

Change-Id: I1ca368c312c1fd4b6f784a3a1b35b5eeb28070ff


[ROCm/hip commit: 8ddeeb4551]
2020-03-26 14:45:20 -04:00
Vladislav Sytchenko c1b7b2276e Add initial entry points for mipmapped array API
Change-Id: Icd59cc7323ddcb6773da6105260415a1e6f4cdcb


[ROCm/hip commit: e0187ba405]
2020-03-26 14:45:20 -04:00
Vladislav Sytchenko b48bf1dc8c Handle offsets for dptr <-> image copies
Change-Id: I7a4a56ee07a26a741d2aac35502446d248f720ad


[ROCm/hip commit: faf3b83594]
2020-03-26 14:45:20 -04:00
Vladislav Sytchenko e149397f73 Replace hip::TextureObject with __hip_texture
This avoids the use of extra casts when obtaining a texture object handle.

Change-Id: I42df22bdad0ab9ac6c33cb8b282dee65fe7cfd6e


[ROCm/hip commit: c1475f948e]
2020-03-26 14:45:20 -04:00
Vladislav Sytchenko cbeaeeb249 Correctly format hipResourceDesc objects
The struct consists of a union - only the active object should be read.

Change-Id: I1c40965b61518acd91a2dcbae92a015ac9be346a


[ROCm/hip commit: fbe30090a2]
2020-03-26 14:45:20 -04:00
Vladislav Sytchenko 1ff602f312 Headers need to export C symbols for texture API
This also adds declarations of all the missing texture APIs.

hipTexRefSet*() functions need to take a textureReference as a ptr for type erasure to work. Runtime has been modified to accomodate this.

This change only applies to VDI.

Change-Id: Icf43cc5bd44dfc2c39084b7fe56d5a793bf7319f


[ROCm/hip commit: 2028b6eb29]
2020-03-26 14:45:20 -04:00
Vladislav Sytchenko ab94b954f9 Set textureObject to nullptr
This avoids dangling pointers for newly initiazlied textures

Change-Id: Ia444b91fe17fd756ed583ec595ae1febbdfbd034


[ROCm/hip commit: ced0582a52]
2020-03-26 14:45:20 -04:00
Vladislav Sytchenko fca3ce3008 Modify formatting for textureReferences
We don't program the numChannels and format members (these are HCC specific), so printing these will only display garbage.

Change-Id: I83dc8be9a3cae2659c64f4594d07c05330d2dd14


[ROCm/hip commit: 39558dc1b9]
2020-03-26 14:45:20 -04:00
Vladislav Sytchenko 462dcfe244 Correct typos in texture function declarations
Change-Id: I492995e984eda2e8a5e806c5d4c9c78da09ac483


[ROCm/hip commit: b09fe1280e]
2020-03-26 12:43:17 -04:00
Vladislav Sytchenko f8d11f2f30 Allow creating texture from unaligned user ptr
All we have to do is align the ptr to HW requirments an if it's not zero, then return the offset to the user.

We currently don't have anywhere to store this offset, so hipGetTextureAlignmentOffset() will still always return 0.

Change-Id: If31998127d99a2a3222a026d88249519d6102505


[ROCm/hip commit: ea701777d8]
2020-03-26 12:43:17 -04:00
Payam Ghafari 3a9576f1e2 Merge "updated cmake to create libamdhip64 static file as well" into amd-master-next
[ROCm/hip commit: 8e8b372726]
2020-03-26 01:10:12 -04:00